CN110399548A - A kind of search processing method, device, electronic equipment and storage medium - Google Patents

Abstract

The embodiment of the invention provides a kind of search processing method, device, electronic equipment and storage mediums, to improve the accuracy of search.The method includes: to be in advance based on search engine to obtain the corresponding description information of entity word；Semantic analysis is carried out to the description information, generates the corresponding label data of the entity word, wherein the label data includes: mood label；The searching request to the entity word is received, search result is determined according to the corresponding label data of the entity word and feeds back.More accurate search result and recommending data more abundant can be provided, the accuracy of search result is improved by tag extension entity word.

Description

A kind of search processing method, device, electronic equipment and storage medium

Technical field

The present invention relates to search technique fields, more particularly to a kind of search processing method, a kind of search process device, one Kind electronic equipment and a kind of storage medium.

Background technique

With the development of computer technology, user can search for required various information in a network, such as be searched by browser The various information such as rope webpage, news, music, video, for another example search for corresponding information etc. in Vertical Website.

The keyword that search is often based on user's offer scans for, and then generates corresponding search result and carries out instead Feedback.But search is all based on keyword and scans at present, such as search star usually feeds back is all encyclopaedia, discussion bar, micro- The roundup contents such as rich, video, followed by contents such as some news web pages, and search for star+event will priority feedback it is corresponding The news web page of star's event, it is seen that the accuracy of search result depends on the fine degree of keyword.

Summary of the invention

The embodiment of the present invention is the technical problem to be solved is that a kind of search processing method is provided, to improve the accurate of search Property.

Correspondingly, the embodiment of the invention also provides a kind of search process device, a kind of electronic equipment and a kind of storage Jie Matter, to guarantee the implementation and application of the above method.

To solve the above-mentioned problems, the embodiment of the invention discloses a kind of search processing methods, comprising: is in advance based on search Engine obtains the corresponding description information of entity word；Semantic analysis is carried out to the description information, it is corresponding to generate the entity word Label data, wherein the label data includes: mood label；The searching request to the entity word is received, according to the reality The corresponding label data of pronouns, general term for nouns, numerals and measure words determines search result and feeds back.

Optionally, the search engine that is in advance based on obtains the corresponding description information of entity word, comprising: search engine is preparatory It is matched according to entity search template, obtains the corresponding description information of entity word.

Optionally, described search engine is matched according to entity search template in advance, obtains the corresponding description of entity word Information comprises at least one of the following step: search engine in advance matches search information according to entity search template, general The search information matched is as the corresponding description information of entity word；Search engine crawls entity word pair according to entity search template in advance The network data answered determines the corresponding description information of the entity word according to the network data, wherein the network packet Include: user comment data, news data, entity introduce data.

Optionally, described that semantic analysis is carried out to the description information, the corresponding label data of the entity word is generated, is wrapped It includes: semantic analysis being carried out to the description information, extracts corresponding semantic key words；The semantic key words are screened, Generate the corresponding label data of the entity word.

Optionally, the search engine that is in advance based on obtains the corresponding description information of entity word, comprising: search engine pair with The temperature of the relevant information of entity word is monitored, and temperature is met to the information to impose a condition and is believed as the corresponding hot spot of entity word It ceases and obtains；It is described that semantic analysis is carried out to the description information, generate the corresponding label data of the entity word, comprising: right The corresponding hot information of the entity word carries out semantic analysis, excavates the corresponding mood word of entity word, raw according to the mood word At mood label.

Optionally, described to determine search result according to the corresponding label data of entity word, comprising: to described search request pair The search information answered scans for, and determines corresponding search result；Corresponding search information is requested according to described search, matching is real The label data of pronouns, general term for nouns, numerals and measure words and the entity word；Described search result is adjusted according to the label data.

Optionally, described to determine search result according to the corresponding label data of entity word, comprising: to be requested according to described search Corresponding search information, matching entities word and the corresponding label data of the entity word；By the corresponding label of the entity word Data are added in search result.

Optionally, further includes: when entity word corresponds to multiple label datas, determine that the entity word corresponds to each label respectively Weight information of the data at least one dimension；Determine that the entity word corresponds to the sequence of each label data according to weight information Value, corresponds to each label data to the entity word according to the ranking value and is ranked up.

Optionally, further includes: the corresponding label data of the entity word is screened according to ranking value.

Optionally, further includes: if the entry that label data described in search result corresponds to result data exceeds amount threshold, It polymerize the label data to carry out concentration displaying.

The embodiment of the invention also discloses a kind of search process devices, comprising: obtains module, draws for being in advance based on search It holds up and obtains the corresponding description information of entity word；Tag generation module generates institute for carrying out semantic analysis to the description information State the corresponding label data of entity word, wherein the label data includes: mood label；Search process module, for reception pair The searching request of the entity word determines search result according to the corresponding label data of the entity word and feeds back.

Optionally, the acquisition module is matched in advance according to entity search template for search engine, obtains entity The corresponding description information of word.

Optionally, the acquisition module, for search engine in advance according to entity search template to search information progress Match, using matched search information as the corresponding description information of entity word；And/or search engine is in advance according to entity search mould Plate crawls the corresponding network data of entity word, determines the corresponding description information of the entity word according to the network data, wherein The network data includes: user comment data, news data, entity introduce data.

Optionally, the tag generation module, comprising: extracting sub-module, for carrying out semantic point to the description information Analysis, extracts corresponding semantic key words；It generates submodule and generates the entity for screening to the semantic key words The corresponding label data of word.

Optionally, the acquisition module, the temperature for search engine pair information relevant to entity word are monitored, will Temperature meets the information to impose a condition and as the corresponding hot information of entity word and obtains；The tag generation module, for pair The corresponding hot information of the entity word carries out semantic analysis, excavates the corresponding mood word of entity word, raw according to the mood word At mood label.

Optionally, described search processing module is determined for requesting corresponding search information to scan for described search Corresponding search result；Corresponding search information, the label of matching entities word and the entity word are requested according to described search Data；Described search result is adjusted according to the label data.

Optionally, described search processing module, for requesting corresponding search information, matching entities word according to described search And the corresponding label data of the entity word；The corresponding label data of the entity word is added in search result.

Optionally, the tag generation module is also used to when entity word corresponds to multiple label datas, respectively determine described in Entity word corresponds to each label data in the weight information of at least one dimension；Determine that the entity word is corresponding each according to weight information The ranking value of label data corresponds to each label data to the entity word according to the ranking value and is ranked up.

Optionally, the tag generation module, be also used to according to ranking value to the corresponding label data of the entity word into Row screening.

Optionally, described search processing module, if being also used to label data described in search result corresponds to result data Entry exceeds amount threshold, polymerize the label data to carry out concentration displaying.

It include memory and one or more than one the embodiment of the invention also discloses a kind of electronic equipment Program, perhaps more than one program is stored in memory and is configured to by one or more than one processing for one of them It includes the instruction for performing the following operation that device, which executes the one or more programs: being in advance based on search engine acquisition The corresponding description information of entity word；Semantic analysis is carried out to the description information, generates the corresponding label data of the entity word, Wherein, the label data includes: mood label；The searching request to the entity word is received, it is corresponding according to the entity word Label data determine search result and feed back.

Optionally, the search engine that is in advance based on obtains the corresponding description information of entity word, comprising: search engine is preparatory It is matched according to entity search template, obtains the corresponding description information of entity word.

Optionally, described search engine is matched according to entity search template in advance, obtains the corresponding description of entity word Information, comprise at least one of the following the instruction of operation: search engine is in advance according to entity search template to search information progress Match, using matched search information as the corresponding description information of entity word；Search engine is crawled according to entity search template in advance The corresponding network data of entity word determines the corresponding description information of the entity word according to the network data, wherein the net Network data include: that user comment data, news data, entity introduce data.

Optionally, described that semantic analysis is carried out to the description information, the corresponding label data of the entity word is generated, is wrapped It includes: semantic analysis being carried out to the description information, extracts corresponding semantic key words；The semantic key words are screened, Generate the corresponding label data of the entity word.

Optionally, the search engine that is in advance based on obtains the corresponding description information of entity word, comprising: search engine pair with The temperature of the relevant information of entity word is monitored, and temperature is met to the information to impose a condition and is believed as the corresponding hot spot of entity word It ceases and obtains；It is described that semantic analysis is carried out to the description information, generate the corresponding label data of the entity word, comprising: right The corresponding hot information of the entity word carries out semantic analysis, excavates the corresponding mood word of entity word, raw according to the mood word At mood label.

Optionally, described to determine search result according to the corresponding label data of entity word, comprising: to described search request pair The search information answered scans for, and determines corresponding search result；Corresponding search information is requested according to described search, matching is real The label data of pronouns, general term for nouns, numerals and measure words and the entity word；Described search result is adjusted according to the label data.

Optionally, described to determine search result according to the corresponding label data of entity word, comprising: to be requested according to described search Corresponding search information, matching entities word and the corresponding label data of the entity word；By the corresponding label of the entity word Data are added in search result.

Optionally, also comprising the instruction for performing the following operation: true respectively when entity word corresponds to multiple label datas The fixed entity word corresponds to each label data in the weight information of at least one dimension；The entity word is determined according to weight information The ranking value of corresponding each label data, corresponds to each label data to the entity word according to the ranking value and is ranked up.

Optionally, also comprising the instruction for performing the following operation: according to ranking value to the corresponding label of the entity word Data are screened.

Optionally, also comprising the instruction for performing the following operation: if label data described in search result corresponds to result The entry of data exceeds amount threshold, polymerize the label data to carry out concentration displaying.

The embodiment of the invention also discloses a kind of readable storage medium storing program for executing, when the instruction in the storage medium is by electronic equipment Processor execute when so that electronic equipment is able to carry out the search processing method as described in any in the embodiment of the present invention.

The embodiment of the present invention includes following advantages:

In the embodiment of the present invention, search engine the description information to entity word can carry out semantic analysis in advance, to obtain The label data of entity word, the label data include mood label, can be provided more accurately by tag extension entity word Search result and recommending data more abundant can foundations so as to after the searching request of subsequently received entity word The corresponding label data of entity word determines search result and is fed back, and improves the accuracy of search result.

Detailed description of the invention

Fig. 1 is a kind of step flow chart of search processing method embodiment of the invention；

Fig. 2 is the step flow chart of another search processing method embodiment of the invention；

Fig. 3 is a kind of structural block diagram of search process device embodiment of the invention；

Fig. 4 is the structural block diagram of another search process device embodiment of the invention；

Fig. 5 is a kind of structural block diagram of electronic equipment for search process shown according to an exemplary embodiment；

Fig. 6 is the structural schematic diagram of server in the embodiment of the present invention.

Specific embodiment

In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, with reference to the accompanying drawing and specific real Applying mode, the present invention is described in further detail.

The things that entity refers to objective reality and can be mutually distinguishable can be specific people, thing, object, can pass through one Series attribute come describe an entity and with other entities distinguish.For example, a certain position star, some film, some electricity Depending on play, certain Mobile phone etc..Entity word refers to the title of entity, such as name, the TV play name of star.

Corresponding description information can be obtained based on search engine for entity word, such as search for information, news web page, Yong Hu The comment data of social network sites etc. and it is some introduce data such as encyclopaedia etc., then description information is analyzed and extracts entity The corresponding label data of word, such as use the popular keyword of some entity words, mood word as label data.Wherein, label Data include the correlation tag of entity word, and the correlation tag and entity word have incidence relation, can additional notes reality by label Pronouns, general term for nouns, numerals and measure words, the feature based on label can expand description entity word, such as the number of tags obtained based on hot information under different scenes According to the hot spot of extendible description entity word searches for information, can expand it based on label data for the entity word of electronic product Relevant parameter search information.The search information of subjective emotion is corresponded to based on the extendible entity word of mood label.Specifically, can be with base Mood label is generated in mood word, consequently facilitating the matching of search result.Mood word is referred to for expressing user's subjective emotion Vocabulary, such as general, sunlight, make laughs, be self-conceit.

To determine corresponding search result based on label data when scanning for entity word, it is based on label Data optimize the corresponding search result of entity word, improve the accuracy of search.

Referring to Fig.1, a kind of step flow chart of search processing method embodiment of the invention is shown, can specifically include Following steps:

Step 102, it is in advance based on search engine and obtains the corresponding description information of entity word.

Step 104, semantic analysis is carried out to the description information, generates the corresponding label data of the entity word.

For each entity word, search engine can be in advance based on and obtain the corresponding description information of the entity word, wherein description letter Breath refers to the information of description entity.The description information can be obtained by multiple channel, as the corresponding news web page of entity word, Social information etc..Search engine can record the description information for determining the entity word based on historical user to the search of entity word, The description information that corresponding webpage of entity word etc. obtains the entity word can be crawled.Then language can be carried out to the description information of entity word Justice analysis, such as the keyword that description information includes is determined by participle processing progress semantics recognition, it is raw to be then based on keyword At the label data of the entity word.Such as entity word is " deer break ", and the description information of " the deer break " of acquisition is analyzed and can be obtained It, can be using these keywords as the label data of " deer break " to keyword " general ", " sunlight ", " girl friend " etc., wherein can incite somebody to action " general ", " sunlight " etc. can express the keyword of user's subjective emotion as the corresponding mood label of entity word " deer break ".

Step 106, the searching request to the entity word is received, is searched according to the corresponding label data determination of the entity word Hitch fruit simultaneously feeds back.

Label data can be used for optimizing search result, when user scans for entity relevant information, can be transmitted Corresponding searching request, the searching request can carry search information, which may include the letter such as entity word, keyword Breath, such as " girlfriend of deer break ".After search engine receives the searching request for entity word, the search information can be used and searched Rope obtains search result, according to the corresponding label data of the entity word, can optimize to search result, such as according to number of tags Associative information etc. is provided according to label data according to label data adjustment search information according to the sequence of adjustment search result.To After the search result optimized, user can be fed back to.

To sum up, search engine the description information to entity word can carry out semantic analysis in advance, to obtain the mark of entity word Sign data, which includes mood label, can by tag extension entity word, provide more accurate search result and Recommending data more abundant, so as to be corresponded to according to entity word after the searching request of subsequently received entity word Label data determine search result and fed back, improve the accuracy of search result.

In the embodiment of the present invention, the corresponding various description informations of the available entity word of search engine are based on, such as will contain There is description information of the search information of entity word as the entity word, the relevant data of some entity words are for another example crawled from network As description information, wherein the acquisition of information can be described based on entity word, template can also be constructed to obtain entity word Description information.

By taking template acquisition modes query specification information as an example, can preset entity search template, wrap in the entity search template Include abstracted information and description label information.Wherein, the abstracted information correspondent entity word, the abstracted information and description label information phase It closes.For example, abstracted information is name, then describing label information can be used for that appearance, personality etc. is described；For another example abstracted information For TV play, then describing label can be used for that plot, type etc. is described.To using " abstracted information+description label letter The mode of breath " constitutes entity search template, such as " viewing of XX is felt ", wherein XX is abstracted information, such as " deer break ", the " the 6th Sense " etc.；" viewing impression " etc. is description label information；Search engine can carry out climbing for information using " viewing of XX is felt " It takes, so that the description informations such as the film review about all kinds of films, viewing information are obtained, so as to quick based on entity search template Extraction description information, convenient for being subsequently generated the label data of correspondent entity word.

The step 102 is in advance based on search engine and obtains the corresponding description information of entity, comprising: search engine in advance according to Factually body search pattern is matched, and obtains the corresponding description information of entity word.Wherein, entity search mould can be used in search engine Plate matches data, such as is matched using entity search template to search information, network data, obtains matched number According to, and corresponding entity word is determined according to entity search template and matched data, using the matched data as entity word pair The description information answered.

The embodiment of the present invention can be applied in various scenes, such as periodically collect the description information of entity word, consequently facilitating Search of the user to entity word.Hot information can also be detected in real time, handled and be recommended, to search for heat in user Recommended and fed back in time when point information.

In one alternative embodiment, the step 102 is in advance based on search engine and obtains the corresponding description information of entity word, Include: that the temperature of search engine pair information relevant to entity word is monitored, temperature is met the information that imposes a condition as The corresponding hot information of entity word simultaneously obtains；The step 104 carries out semantic analysis to the description information, generates the entity The corresponding label data of word, comprising: semantic analysis is carried out to the corresponding hot information of the entity word, it is corresponding to excavate entity word Mood word, the hot information are monitored by search engine and are obtained, and generate mood label according to the mood word.

The setting condition of the temperature of detection and entity word relevant information can be set, so as to collect the letter of hot spot in time Cease and sort out the recommendation label of corresponding entity word, such as star's scandal, the political situation of the time information, episode information of hot spot, detection heat The setting condition of degree can be set according to actual demand, as condition be within the scope of setting time information content be more than threshold value, such as The amount of reading of news is more than 100,000 etc. in 10 minutes, so that search engine can in real time detect the temperature of information, hair Now information relevant to entity word, and the volumes of searches of the information, topic amount, amount of reading etc. detect and determine temperature, in heat Degree can obtain after meeting setting condition using the information as hot information, can be using the hot information retouching as entity word Information is stated, which can also be matched with entity search template, to extract description information.It then can be to hot information Or the description information extracted from hot information carries out semantic analysis, excavates corresponding keyword, which includes mood Word and other kinds of keyword, such as descriptor, word is introduced, corresponding label data then is generated according to keyword, wherein Mood label is produced according to mood word.

To which the embodiment of the present invention can be applied to the data mining of the scene for hot news etc., to hot news event Real-time monitoring and rapidly processing are carried out, excavates the keywords such as the corresponding mood word of entity word for obtaining that hot news includes as mark Data are signed, it is subsequent when user searches for the entity word relevant information, it can be added in search result including respective labels data Hot news, or recommend the label datas such as the corresponding mood word of the entity word, it allows users to understand hot spot dynamic in time, User can also be guided to pay close attention to the news from the emotional.

For example, the news such as sportsman AA triumph, can also excavate rapidly the marks such as the corresponding related race of the sportsman AA, gold medal Data are signed, so that the label datas such as relevant news or race, gold medal can be pushed when user searches for sportsman name " AA ", Associated dynamic is understood in time convenient for user.

For another example, the news of star BB, the news meet the setting condition of temperature detection, can be excavated based on news data Mood label to the corresponding mood word of star name " BB ", as " BB ".When user searches in " BB " or its search result items When search result related including the star BB, it can show that label data etc. should to user, or displaying in search results pages The data such as the news web page of star " BB ", so that user be attracted to go deep search, read to check more relevant informations.

Referring to Fig. 2, a kind of step flow chart of search processing method embodiment of the invention is shown, can specifically include Following steps:

Step 202, search engine is matched according to entity search template in advance, obtains the corresponding description letter of entity word Breath.

The embodiment of the present invention can carry out the extraction that entity word corresponds to description information based on entity search template, can be quick Information needed for obtaining.Wherein, step 202 comprises at least one of the following sub-step: search engine is in advance according to entity search mould Plate matches search information, using matched search information as the corresponding description information of entity word；Search engine in advance according to Factually body search pattern crawls the corresponding network data of entity word, determines that the entity word is corresponding according to the network data and retouches State information.

For searching for information, search engine can collect the search information of user in advance, then use entity search template Search information is matched, the search information with entity search template matching is obtained, it can be true from the matched search information The corresponding entity word of abstracted information is determined, then using matched search information as the description information of the entity word, so as to logical Cross the description information that entity search template quickly extracts entity word.

For network data, search engine can crawl data in a network, and search engine can also be according to entity during this Search pattern crawls the corresponding network data of entity word, wherein the network data includes: user comment data, news data, Entity introduces data, user comment data refer to user in the comment data of website, such as shopping website, social network sites, newly It hears data and refers to the data obtained from various news websites, entity introduces data and refers to that the entity obtained from various websites is situated between Continue data, such as encyclopaedia class website, shopping website, official website.It can be crawled in a network by entity search template and real Then the relevant network data of pronouns, general term for nouns, numerals and measure words determines the corresponding description information of entity word according to the network data, such as by network data As the description information of entity word, for another example extraction section data are as the corresponding description information of entity word from network data, such as Using entire chapter news as network data, then information relevant to entity word can be extracted from the news as description information.

Step 204, semantic analysis is carried out to the description information, extracts corresponding semantic key words.

Step 206, the semantic key words are screened, generates the corresponding label data of the entity word.

Semantic analysis can be carried out to description information, wherein cutting can be carried out to description information, obtain each segment data, so The semanteme of description information is determined based on segment data afterwards, then one or more semantemes are extracted from the description information based on semanteme Keyword produces the label data of entity word based on the semantic key words.Wherein, due to search engine may get it is more Description information, to obtain the corresponding various semantic key words of entity word, therefore can pass through that entity word is corresponding semantic to close Keyword is screened, and the semantic key words that screening is obtained are as label data.It, can including foundation frequency screening semantic key words To be trained using semantic key words and entity word, such as search information, network data that search engine is obtained etc. are made For training sample, it is then based on training sample and determines corresponding relationship between semantic key words and entity word, such as obtain " deer break -- General ", " deer break -- Quadratic Finite Element " etc., to filter out description information of the corresponding semantic key words as the entity word.Wherein, one A entity word can be used as the label data of another entity word, such as " C and D are in love ", then " C " and " D " can other side each other Label data.

For the label data of entity word, tag database can be constructed, each entity word pair is stored in the tag database The label data answered, consequently facilitating being used during subsequent searches.

In an alternative embodiment of the invention, when entity word corresponds to multiple label datas, the entity word is determined respectively Weight information of the corresponding each label data at least one dimension；Determine that the entity word corresponds to each number of tags according to weight information According to ranking value, each label data is corresponded to the entity word according to the ranking value and is ranked up.

The label data of entity word also has dimensional information, it may be determined that weight letter of the label data at least one dimension Breath, wherein dimension can be arranged according to demand, such as time dimension, source dimension, can be existed based on label data on time dimension The number occurred in preset time period determines weight information, and source dimension can be based on label data from search information, network Data etc. determine, the ranking value of label data then can be determined based on weight information, such as based on weighted data to label data into Row weighted calculation obtains ranking value.Such as abovementioned steps obtain the degree of correlation of keyword and entity word based on training, are based on the phase Guan Du can determine the keyword for belonging to label data, can also calculate the label based on the weight information of the degree of correlation and label data The ranking value of data.It is ranked up to correspond to each label data to the entity word according to the ranking value, it will according to sequence Label data is stored into tag database.Wherein, can also according to ranking value to the corresponding label data of the entity word into Row screening such as obtains the label data that ranking value is more than sequence threshold value, to filter out the mark on the low side such as some data volumes, temperature Sign data.

Step 208, the searching request to the entity word is received.

Step 210, search result is determined according to the corresponding label data of the entity word and feed back.

The searching request for being directed to entity word is received, search information is carried in the searching request, searches in information and usually contains Entity word, so as to the entity word to be searched for of determination.It then can be with the corresponding label data of matching entities word, based on search letter Breath, label data of entity word etc. scan for, and obtain search result.Wherein, label data can be adjusted search result, Such as search result is screened, or adjustment search results ranking etc., to provide the user with accurate search result.Number of tags User is recommended according to also can be used as the related informations such as associative information and be added in search result, thus based on label data to user Data that are comprehensive, meeting demand are provided, user experience is improved.

In one alternative embodiment, step 208 determines search result according to the corresponding label data of entity word, comprising: right Described search requests corresponding search information to scan for, and determines corresponding search result；It is requested according to described search corresponding Search for information, the label data of matching entities word and the entity word；According to the label data to described search result into Row adjustment.It can be based on label data Optimizing Search and be scanned for as a result, search information wherein can be used, get corresponding search As a result, being then adjusted according to the label data of entity word to search result, such as determine each number of results in search result Whether there is correlation according to label data, the weight of this result data is set according to correlation, thus to result data weight It is newly ranked up, or filters out one or more result datas for each label data and be added in the search result of feedback. It is shown in addition, multiple result datas of the same label data can be aggregated in an entry, if described in search result Label data corresponds to the quantity of result data beyond amount threshold, polymerize the label data to carry out concentration displaying.Such as setting Amount threshold such as 5, then the entry that a label data corresponds to result data is more than the amount threshold, then the label data is corresponding Result data can be aggregated to together, be shown on the subscriber terminal, concentrated and checked convenient for user.

In another alternative embodiment, step 208 determines search result according to the corresponding label data of entity word, comprising: Corresponding search information, matching entities word and the corresponding label data of the entity word are requested according to described search；It will be described The corresponding label data of entity word is added in search result as associative information.It can be recommended based on label data to user popular Information, wherein search information can be used and scan for, get corresponding search result, and determine in fact according to search information Pronouns, general term for nouns, numerals and measure words, then the corresponding one or more label datas of entity word are searched, then recommend label data as associative information, search Information etc. is added in search result, clicks search convenient for user.

Wherein, above-mentioned two example, can also be according to sequence after matching entities word and the label data of the entity word Value screens the corresponding label data of the entity word.The label data such as obtained to matching determines its corresponding sequence Value, then screens label data according to ranking value, label data of the ranking value at preceding 5,10 is obtained, to filter out Part labels data improve the treatment effeciency of subsequent calculating.

It should be noted that for simple description, therefore, it is stated as a series of action groups for embodiment of the method It closes, but those skilled in the art should understand that, embodiment of that present invention are not limited by the describe sequence of actions, because according to According to the embodiment of the present invention, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art also should Know, the embodiments described in the specification are all preferred embodiments, and the related movement not necessarily present invention is implemented Necessary to example.

Referring to Fig. 3, show a kind of structural block diagram of search process device embodiment of the invention, can specifically include as Lower module:

Module 302 is obtained, obtains the corresponding description information of entity word for being in advance based on search engine.

Tag generation module 304 generates the corresponding mark of the entity word for carrying out semantic analysis to the description information Sign data, wherein the label data includes: mood label.

Search process module 306, for receiving the searching request to the entity word, according to the corresponding mark of the entity word Label data determine search result and feed back.

To sum up, search engine can carry out semantic analysis to the description information of entity word, to obtain the number of tags of entity word According to the label data includes mood label, so as to by tag extension entity word, provide search more abundant, recommendation Data can determine search result simultaneously after receiving the searching request of entity word according to the corresponding label data of entity word It is fed back, so that abundant search result, improves the accuracy of search result.

Referring to Fig. 4, the structural block diagram of another search process device embodiment of the invention is shown, can specifically include Following module:

Module 302 is obtained, obtains the corresponding description information of entity word for being in advance based on search engine.

Tag generation module 304 generates the corresponding mark of the entity word for carrying out semantic analysis to the description information Sign data, wherein the label data includes: mood label.

Search process module 306, for receiving the searching request to the entity word, according to the corresponding mark of the entity word Label data determine search result and feed back.

Wherein, the acquisition module 302 is matched in advance according to entity search template for search engine, is obtained real The corresponding description information of pronouns, general term for nouns, numerals and measure words.

The acquisition module 302 in advance matches search information according to entity search template for search engine, will Matched search information is as the corresponding description information of entity word；And/or search engine is crawled according to entity search template in advance The corresponding network data of entity word determines the corresponding description information of the entity word according to the network data, wherein the net Network data include: that user comment data, news data, entity introduce data.

In the embodiment of the present invention, the tag generation module, be also used to correspond to entity word each label data be ranked up, Screening.Wherein: the tag generation module 304, comprising: extracting sub-module 3042 generates submodule 3044, sorting sub-module 3046 and screening submodule 3048.

The extracting sub-module 3042 is extracted corresponding semantic crucial for carrying out semantic analysis to the description information Word.

It is corresponding to generate the entity word for screening to the semantic key words for the generation submodule 3044 Label data.

The sorting sub-module 3046, for determining the entity word respectively when entity word corresponds to multiple label datas Weight information of the corresponding each label data at least one dimension；Determine that the entity word corresponds to each number of tags according to weight information According to ranking value, each label data is corresponded to the entity word according to the ranking value and is ranked up.

The screening submodule 3048, for being screened according to ranking value to the corresponding label data of the entity word.

In one alternative embodiment, the acquisition module 302, the heat for search engine pair information relevant to entity word Degree is monitored, and temperature is met the information to impose a condition and as hot information and is obtained；The tag generation module 304 is used In carrying out semantic analysis to the hot information, the corresponding mood word of entity word is excavated, generates mood mark according to the mood word Label.

Described search processing module 306 is determined and is corresponded to for requesting corresponding search information to scan for described search Search result；Corresponding search information, the label data of matching entities word and the entity word are requested according to described search； Described search result is adjusted according to the label data.

Described search processing module 306, for requesting corresponding search information according to described search, matching entities word and The corresponding label data of the entity word；The corresponding label data of the entity word is added in search result.

Wherein, label data can be adjusted search result, such as screen to search, or adjustment search information etc., To provide the user with accurate search result.Label data also can be used as the related informations such as associative information and be added to search result In recommend user, thus based on label data provide the user with comprehensively, meet the data of demand, improve user experience.

Described search processing module 306 is also used to the entry that the label data described in search result corresponds to result data After amount threshold, it polymerize the label data to carry out concentration displaying.

To determine corresponding search result based on label data when scanning for entity, it is based on number of tags It is optimized according to the corresponding search result of entity word, improves the accuracy of search.The embodiment of the present invention can be applied to various fields Jing Zhong, such as the description information of entity word is periodically collected, consequently facilitating search of the user to entity word.It can also be to hot information It detected, handled and is recommended in real time, even if to recommend and feed back when user searches for hot information.

The embodiment of the present invention can be applied to the data mining of the scene for hot news etc., carry out to hot news event Real-time monitoring and rapidly processing excavate the keywords such as the corresponding mood word of entity word for obtaining that hot news includes as number of tags According to, it is subsequent when user searches for the entity word relevant information, the hot spot including respective labels data can be added in search result News, or recommend the label datas such as the corresponding mood word of the entity word, it allows users to understand hot spot dynamic in time, may be used also To guide user to pay close attention to the news from the emotional.

For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple Place illustrates referring to the part of embodiment of the method.

Fig. 5 is shown according to an exemplary embodiment a kind of for showing the structure of the electronic equipment 500 of search process Block diagram.For example, electronic equipment 500 can be mobile phone, computer, digital broadcasting terminal, messaging device, game control Platform, tablet device, Medical Devices, body-building equipment, personal digital assistant etc..

Referring to Fig. 5, electronic equipment 500 may include following one or more components: processing component 502, memory 504, Power supply module 506, multimedia component 508, audio component 510, the interface 512 of input/output (I/O), sensor module 514, And communication component 516.

The integrated operation of the usual controlling electronic devices 500 of processing component 502, such as with display, call, data are logical Letter, camera operation and record operate associated operation.Processing element 502 may include one or more processors 520 to hold Row instruction, to perform all or part of the steps of the methods described above.In addition, processing component 502 may include one or more moulds Block, convenient for the interaction between processing component 502 and other assemblies.For example, processing component 502 may include multi-media module, with Facilitate the interaction between multimedia component 508 and processing component 502.

Memory 504 is configured as storing various types of data to support the operation in equipment 500.These data are shown Example includes the instruction of any application or method for operating on electronic equipment 500, contact data, telephone directory number According to, message, picture, video etc..Memory 504 can by any kind of volatibility or non-volatile memory device or they Combination realize, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable Programmable read only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, quick flashing Memory, disk or CD.

Power supply module 506 provides electric power for the various assemblies of electronic equipment 500.Power supply module 506 may include power supply pipe Reason system, one or more power supplys and other with for electronic equipment 500 generate, manage, and distribute the associated component of electric power.

Multimedia component 508 includes the screen of one output interface of offer between the electronic equipment 500 and user. In some embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch surface Plate, screen may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touches Sensor is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding The boundary of movement, but also detect duration and pressure associated with the touch or slide operation.In some embodiments, Multimedia component 508 includes a front camera and/or rear camera.When equipment 500 is in operation mode, as shot When mode or video mode, front camera and/or rear camera can receive external multi-medium data.It is each preposition to take the photograph As head and rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.

Audio component 510 is configured as output and/or input audio signal.For example, audio component 510 includes a wheat Gram wind (MIC), when electronic equipment 500 is in operation mode, when such as call mode, recording mode, and voice recognition mode, Mike Wind is configured as receiving external audio signal.The received audio signal can be further stored in memory 504 or via Communication component 516 is sent.In some embodiments, audio component 510 further includes a loudspeaker, is used for output audio signal.

I/O interface 512 provides interface between processing component 502 and peripheral interface module, and above-mentioned peripheral interface module can To be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and lock Determine button.

Sensor module 514 includes one or more sensors, for providing the state of various aspects for electronic equipment 500 Assessment.For example, sensor module 514 can detecte the state that opens/closes of equipment 500, the relative positioning of component, such as institute The display and keypad that component is electronic equipment 500 are stated, sensor module 514 can also detect electronic equipment 500 or electronics The position change of 500 1 components of equipment, the existence or non-existence that user contacts with electronic equipment 500,500 orientation of electronic equipment Or the temperature change of acceleration/deceleration and electronic equipment 500.Sensor module 514 may include proximity sensor, be configured to use To detect the presence of nearby objects without any physical contact.Sensor module 514 can also include optical sensor, such as CMOS or ccd image sensor, for being used in imaging applications.In some embodiments, which can be with Including acceleration transducer, gyro sensor, Magnetic Sensor, pressure sensor or temperature sensor.

Communication component 516 is configured to facilitate the communication of wired or wireless way between electronic equipment 500 and other equipment. Electronic equipment 500 can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.At one In exemplary embodiment, broadcast singal or wide of the communication component 516 via broadcast channel reception from external broadcasting management system Broadcast relevant information.In one exemplary embodiment, the communication component 516 further includes near-field communication (NFC) module, to promote Short range communication.For example, radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wide can be based in NFC module Band (UWB) technology, bluetooth (BT) technology and other technologies are realized.

In the exemplary embodiment, electronic equipment 500 can by one or more application specific integrated circuit (ASIC), Digital signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field-programmable gate array It arranges (FPGA), controller, microcontroller, microprocessor or other electronic components to realize, for executing the above method.

In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided It such as include the memory 504 of instruction, above-metioned instruction can be executed by the processor 520 of electronic equipment 500 to complete the above method. For example, the non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, magnetic Band, floppy disk and optical data storage devices etc..

A kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by the processing of electronic equipment When device executes, so that electronic equipment is able to carry out a kind of search processing method, which comprises be in advance based on search engine and obtain Take the corresponding description information of entity word；Semantic analysis is carried out to the description information, generates the corresponding number of tags of the entity word According to, wherein the label data includes: mood label；The searching request to the entity word is received, according to the entity word pair The label data answered determines search result and feeds back.

Optionally, the search engine that is in advance based on obtains the corresponding description information of entity word, comprising: search engine is preparatory It is matched according to entity search template, obtains the corresponding description information of entity word.

Optionally, described search engine is matched according to entity search template in advance, obtains the corresponding description of entity word Information comprises at least one of the following step: search engine in advance matches search information according to entity search template, general The search information matched is as the corresponding description information of entity word；Search engine crawls entity word pair according to entity search template in advance The network data answered determines the corresponding description information of the entity word according to the network data, wherein the network packet Include: user comment data, news data, entity introduce data.

Optionally, described that semantic analysis is carried out to the description information, the corresponding label data of the entity word is generated, is wrapped It includes: semantic analysis being carried out to the description information, extracts corresponding semantic key words；The semantic key words are screened, Generate the corresponding label data of the entity word.

Optionally, the search engine that is in advance based on obtains the corresponding description information of entity word, comprising: search engine pair with The temperature of the relevant information of entity word is monitored, and temperature is met to the information to impose a condition and is believed as the corresponding hot spot of entity word It ceases and obtains；It is described that semantic analysis is carried out to the description information, generate the corresponding label data of the entity word, comprising: right The corresponding hot information of the entity word carries out semantic analysis, excavates the corresponding mood word of entity word, raw according to the mood word At mood label.

Optionally, described to determine search result according to the corresponding label data of entity word, comprising: to described search request pair The search information answered scans for, and determines corresponding search result；Corresponding search information is requested according to described search, matching is real The label data of pronouns, general term for nouns, numerals and measure words and the entity word；Described search result is adjusted according to the label data.

Optionally, described to determine search result according to the corresponding label data of entity word, comprising: to be requested according to described search Corresponding search information, matching entities word and the corresponding label data of the entity word；By the corresponding label of the entity word Data are added in search result.

Optionally, further includes: when entity word corresponds to multiple label datas, determine that the entity word corresponds to each label respectively Weight information of the data at least one dimension；Determine that the entity word corresponds to the sequence of each label data according to weight information Value, corresponds to each label data to the entity word according to the ranking value and is ranked up.

Optionally, further includes: the corresponding label data of the entity word is screened according to ranking value.

Optionally, further includes: if the entry that label data described in search result corresponds to result data exceeds amount threshold, It polymerize the label data to carry out concentration displaying.

Fig. 6 is the structural schematic diagram of server in the embodiment of the present invention.The server 600 can be due to configuration or performance be different Generate bigger difference, may include one or more central processing units (central processing units, CPU) 622 (for example, one or more processors) and memory 632, one or more storage application programs 642 or The storage medium 630 (such as one or more mass memory units) of data 644.Wherein, memory 632 and storage medium 630 can be of short duration storage or persistent storage.The program for being stored in storage medium 630 may include one or more modules (diagram does not mark), each module may include to the series of instructions operation in server.Further, central processing unit 622 can be set to communicate with storage medium 630, and the series of instructions behaviour in storage medium 630 is executed on server 800 Make.

Server 600 can also include one or more power supplys 626, one or more wired or wireless networks Interface 650, one or more input/output interfaces 658, one or more keyboards 656, and/or, one or one The above operating system 641, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM etc..

The embodiment of the invention also discloses a kind of electronic equipment, such as server, user equipment etc. includes memory, with And one perhaps more than one program one of them or more than one program be stored in memory, and be configured to by It includes the instruction for performing the following operation that one or more than one processor, which execute the one or more programs: It is in advance based on search engine and obtains the corresponding description information of entity word；Semantic analysis is carried out to the description information, described in generation The corresponding label data of entity word, wherein the label data includes: mood label；The search of the entity word is asked in reception It asks, determine search result according to the corresponding label data of the entity word and feeds back.

Optionally, the search engine that is in advance based on obtains the corresponding description information of entity word, comprising: search engine is preparatory It is matched according to entity search template, obtains the corresponding description information of entity word.

Optionally, described search engine is matched according to entity search template in advance, obtains the corresponding description of entity word Information, comprise at least one of the following the instruction of operation: search engine is in advance according to entity search template to search information progress Match, using matched search information as the corresponding description information of entity word；Search engine is crawled according to entity search template in advance The corresponding network data of entity word determines the corresponding description information of the entity word according to the network data, wherein the net Network data include: that user comment data, news data, entity introduce data.

Optionally, described that semantic analysis is carried out to the description information, the corresponding label data of the entity word is generated, is wrapped It includes: semantic analysis being carried out to the description information, extracts corresponding semantic key words；The semantic key words are screened, Generate the corresponding label data of the entity word.

Optionally, the search engine that is in advance based on obtains the corresponding description information of entity word, comprising: search engine pair with The temperature of the relevant information of entity word is monitored, and temperature is met to the information to impose a condition and is believed as the corresponding hot spot of entity word It ceases and obtains；It is described that semantic analysis is carried out to the description information, generate the corresponding label data of the entity word, comprising: right The corresponding hot information of the entity word carries out semantic analysis, excavates the corresponding mood word of entity word, raw according to the mood word At mood label.

Optionally, described to determine search result according to the corresponding label data of entity word, comprising: to described search request pair The search information answered scans for, and determines corresponding search result；Corresponding search information is requested according to described search, matching is real The label data of pronouns, general term for nouns, numerals and measure words and the entity word；Described search result is adjusted according to the label data.

Optionally, described to determine search result according to the corresponding label data of entity word, comprising: to be requested according to described search Corresponding search information, matching entities word and the corresponding label data of the entity word；By the corresponding label of the entity word Data are added in search result.

Optionally, also comprising the instruction for performing the following operation: true respectively when entity word corresponds to multiple label datas The fixed entity word corresponds to each label data in the weight information of at least one dimension；The entity word is determined according to weight information The ranking value of corresponding each label data, corresponds to each label data to the entity word according to the ranking value and is ranked up.

Optionally, also comprising the instruction for performing the following operation: according to ranking value to the corresponding label of the entity word Data are screened.

Optionally, also comprising the instruction for performing the following operation: if label data described in search result corresponds to result The entry of data exceeds amount threshold, polymerize the label data to carry out concentration displaying.

All the embodiments in this specification are described in a progressive manner, the highlights of each of the examples are with The difference of other embodiments, the same or similar parts between the embodiments can be referred to each other.

It should be understood by those skilled in the art that, the embodiment of the embodiment of the present invention can provide as method, apparatus or calculate Machine program product.Therefore, the embodiment of the present invention can be used complete hardware embodiment, complete software embodiment or combine software and The form of the embodiment of hardware aspect.Moreover, the embodiment of the present invention can be used one or more wherein include computer can With in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code The form of the computer program product of implementation.

The embodiment of the present invention be referring to according to the method for the embodiment of the present invention, terminal device (system) and computer program The flowchart and/or the block diagram of product describes.It should be understood that flowchart and/or the block diagram can be realized by computer program instructions In each flow and/or block and flowchart and/or the block diagram in process and/or box combination.It can provide these Computer program instructions are set to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminals Standby processor is to generate a machine, so that being held by the processor of computer or other programmable data processing terminal devices Capable instruction generates for realizing in one or more flows of the flowchart and/or one or more blocks of the block diagram The device of specified function.

These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing terminal devices In computer-readable memory operate in a specific manner, so that instruction stored in the computer readable memory generates packet The manufacture of command device is included, which realizes in one side of one or more flows of the flowchart and/or block diagram The function of being specified in frame or multiple boxes.

These computer program instructions can also be loaded into computer or other programmable data processing terminal devices, so that Series of operation steps are executed on computer or other programmable terminal equipments to generate computer implemented processing, thus The instruction executed on computer or other programmable terminal equipments is provided for realizing in one or more flows of the flowchart And/or in one or more blocks of the block diagram specify function the step of.

Although the preferred embodiment of the embodiment of the present invention has been described, once a person skilled in the art knows bases This creative concept, then additional changes and modifications can be made to these embodiments.So the following claims are intended to be interpreted as Including preferred embodiment and fall into all change and modification of range of embodiment of the invention.

Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements not only wrap Those elements are included, but also including other elements that are not explicitly listed, or further includes for this process, method, article Or the element that terminal device is intrinsic.In the absence of more restrictions, being wanted by what sentence "including a ..." limited Element, it is not excluded that there is also other identical elements in process, method, article or the terminal device for including the element.

It is situated between above to a kind of search processing method provided by the present invention and device, a kind of electronic equipment and a kind of storage Matter is described in detail, and used herein a specific example illustrates the principle and implementation of the invention, above The explanation of embodiment is merely used to help understand method and its core concept of the invention；Meanwhile for the general skill of this field Art personnel, according to the thought of the present invention, there will be changes in the specific implementation manner and application range, in conclusion this Description should not be construed as limiting the invention.

Claims (10)

1. a kind of search processing method characterized by comprising

It is in advance based on search engine and obtains the corresponding description information of entity word；

Semantic analysis is carried out to the description information, generates the corresponding label data of the entity word, wherein the label data It include: mood label；

It receives to the searching request of the entity word, determines search result and anti-according to the corresponding label data of the entity word Feedback.

2. the method according to claim 1, wherein it is described be in advance based on search engine obtain entity word it is corresponding Description information, comprising:

Search engine is matched according to entity search template in advance, obtains the corresponding description information of entity word.

3. according to the method described in claim 2, it is characterized in that, described search engine is carried out according to entity search template in advance Matching obtains the corresponding description information of entity word, comprises at least one of the following step:

Search engine in advance matches search information according to entity search template, using matched search information as entity word Corresponding description information；

Search engine crawls the corresponding network data of entity word according to entity search template in advance, determines according to the network data The corresponding description information of the entity word, wherein the network data includes: user comment data, news data, entity introduction Data.

4. being generated the method according to claim 1, wherein described carry out semantic analysis to the description information The corresponding label data of the entity word, comprising:

Semantic analysis is carried out to the description information, extracts corresponding semantic key words；

The semantic key words are screened, the corresponding label data of the entity word is generated.

5. the method according to claim 1, wherein it is described be in advance based on search engine obtain entity word it is corresponding Description information, comprising:

The temperature of search engine pair information relevant to entity word is monitored, and temperature is met to the information to impose a condition as real The corresponding hot information of pronouns, general term for nouns, numerals and measure words simultaneously obtains；

It is described that semantic analysis is carried out to the description information, generate the corresponding label data of the entity word, comprising:

Semantic analysis is carried out to the corresponding hot information of the entity word, the corresponding mood word of entity word is excavated, according to the feelings Thread word generates mood label.

6. the method according to claim 1, wherein described determine search according to the corresponding label data of entity word As a result, comprising:

It requests corresponding search information to scan for described search, determines corresponding search result；

Corresponding search information, the label data of matching entities word and the entity word are requested according to described search；

Described search result is adjusted according to the label data.

7. the method according to claim 1, wherein described determine search according to the corresponding label data of entity word As a result, comprising:

Corresponding search information, matching entities word and the corresponding label data of the entity word are requested according to described search；

The corresponding label data of the entity word is added in search result.

8. a kind of search process device characterized by comprising

Module is obtained, obtains the corresponding description information of entity word for being in advance based on search engine；

Tag generation module, for generating the corresponding label data of the entity word to description information progress semantic analysis, Wherein, the label data includes: mood label；

Search process module, for receiving the searching request to the entity word, according to the corresponding label data of the entity word It determines search result and feeds back.

9. a kind of electronic equipment, which is characterized in that include memory and one or more than one program, wherein one A perhaps more than one program is stored in memory and is configured to execute described one by one or more than one processor A or more than one program includes the instruction for performing the following operation:

It is in advance based on search engine and obtains the corresponding description information of entity word；

Semantic analysis is carried out to the description information, generates the corresponding label data of the entity word, wherein the label data It include: mood label；

It receives to the searching request of the entity word, determines search result and anti-according to the corresponding label data of the entity word Feedback.

10. a kind of readable storage medium storing program for executing, which is characterized in that when the instruction in the storage medium is held by the processor of electronic equipment When row, so that electronic equipment is able to carry out the search processing method as described in claim to a method 1-7 is any.