CN105095347A - Method and device for associating named entities - Google Patents
Method and device for associating named entities Download PDFInfo
- Publication number
- CN105095347A CN105095347A CN201510310542.3A CN201510310542A CN105095347A CN 105095347 A CN105095347 A CN 105095347A CN 201510310542 A CN201510310542 A CN 201510310542A CN 105095347 A CN105095347 A CN 105095347A
- Authority
- CN
- China
- Prior art keywords
- named entity
- history
- user
- information
- association
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/954—Navigation, e.g. using categorised browsing
Abstract
The invention provides a method for associating named entities in computer equipment. The method comprises the following steps of obtaining the named entities for access information according to the access information of a user; and determining at least one associated named entity associated with the named entities according to a history access record of the user. According to the scheme of the embodiment, at least one associated named entity associated with the named entities is determined based on the history access record of the user, so that when associating the named entities, omission of some named entities which are dissimilar in meaning can be avoided, and thus more website traffic can be covered, and user-oriented recommendation or promotion service can be better provided.
Description
Technical field
The present invention relates to field of computer technology, particularly relate to a kind of in computer equipment to the method and apparatus that named entity associates.
Background technology
In prior art, named entity, as an important composition composition of natural language understanding, is widely used in various field, as commercial field, service field etc.At present, usual employing associates named entity based on the method for similarity of character string, such as, for named entity " rainbow like a chain of pearls or a string of beads ", computer equipment based on similarity of character string method obtain with the implication of this named entity similar associate named entity, as " seven coloured silks like a chain of pearls or a string of beads ", " five sons like a chain of pearls or a string of beads " etc.; Also namely, other only similar or close to named entity implication named entities, can be associated to this named entity.
Summary of the invention
The object of this invention is to provide a kind of in computer equipment to the method and apparatus that named entity associates.
According to an aspect of the present invention, provide a kind of in computer equipment to the method that named entity associates, wherein, the method comprises:
According to the visit information of user, obtain described visit information for named entity;
According to the history access record of described user, determine that at least one being associated with described named entity associates named entity.
According to another aspect of the present invention, additionally provide a kind of in computer equipment to the device that named entity associates, wherein, this device comprises:
First obtaining means, for the visit information according to user, obtain described visit information for named entity;
Determining device, for the history access record according to described user, determines that at least one being associated with described named entity associates named entity.
Compared with prior art, the present invention has the following advantages: 1) can based on the history access record of user, determine that at least one being associated with named entity associates named entity, also be, and not only consider current to user for close or similar in implication of named entity, but from user perspective, determine at least one association named entity, thus avoid when carrying out the association of named entity, omit in implication and more dissimilar named entities, thus more website traffic can be covered, can better provide user oriented recommendation or extension service, 2) can by obtain for multiple user, visit information for the relevant named entity of named entity be polymerized, obtain the associated entity set of described named entity, thus carry out more extensively, more fully associating, 3) by determining or upgrade the weight information of association named entity, and the content association information corresponding with associating named entity can be provided according to weight information to user, thus realize more effective recommendation or extension service.
Accompanying drawing explanation
By reading the detailed description done non-limiting example done with reference to the following drawings, other features, objects and advantages of the present invention will become more obvious:
Fig. 1 be one embodiment of the invention in computer equipment to the schematic flow sheet of the method that named entity associates;
Fig. 2 be one embodiment of the invention in computer equipment to the structural representation of the device that named entity associates;
Fig. 3 is the schematic diagram being obtained the associated entity set of named entity by polymerization of the present invention's example.
In accompanying drawing, same or analogous Reference numeral represents same or analogous parts.
Embodiment
Below in conjunction with accompanying drawing, the present invention is described in further detail.
Fig. 1 be one embodiment of the invention in computer equipment to the schematic flow sheet of the method that named entity associates.
Wherein, the method for the present embodiment realizes mainly through computer equipment; Described computer equipment comprises the network equipment and subscriber equipment; The described network equipment includes but not limited to the server group that single network server, multiple webserver form or the cloud be made up of a large amount of computing machine or the webserver based on cloud computing (CloudComputing), wherein, cloud computing is the one of Distributed Calculation, the super virtual machine be made up of a group loosely-coupled computing machine collection; Network residing for the described network equipment includes but not limited to internet, wide area network, Metropolitan Area Network (MAN), LAN (Local Area Network), VPN etc.Described subscriber equipment includes but not limited to PC, panel computer, smart mobile phone, PDA, IPTV etc.
It should be noted that, described computer equipment is only citing, and other computer equipments that are existing or that may occur from now on, as being applicable to the present invention, within also should being included in scope, and are contained in this with way of reference.
Step S1 and step S2 is comprised according to the method for the present embodiment.
In step sl, computer equipment according to the visit information of user, obtain described visit information for named entity.
Wherein, described visit information comprises any to user's information that the page of current accessed is relevant in computer equipment; Preferably, described visit information includes but not limited to: the address information, access time information, the information relevant to the content in current page (if the content in current page is a document, described content information includes but not limited to the name information, identification information, recommended information etc. of the document) etc. of current page.
Wherein, described named entity comprises any entity that can be called mark with name; Preferably, described named entity includes but not limited to: name, place name, organization names, description of goods etc.
Particularly, computer equipment according to the visit information of user, obtain described visit information for the implementation of named entity include but not limited to:
1) computer equipment directly extract from the visit information of user this visit information for named entity.
Such as, the content in current page is a document, and the visit information of user comprises the title of the document " Hainan Scenic spot introduction ", then computer equipment extract from this title this visit information for named entity " Hainan ".
2) be previously stored with the corresponding relation between visit information and named entity in computer equipment, computer equipment according to the visit information of user, and in conjunction with described corresponding relation, reads the named entity corresponding with this visit information from this locality.
Such as, the corresponding relation between the address information of the page and named entity is previously stored with in computer equipment.In step sl, computer equipment obtains address information that comprise in the visit information of user, current page, and reads the named entity corresponding with this address information according to this corresponding relation from this locality.
Again such as, the corresponding relation between the name information of document and named entity is previously stored with in computer equipment.In step sl, computer equipment obtains name information that comprise in the visit information of user, document, and reads the named entity corresponding with this name information according to this corresponding relation from this locality.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any visit information according to user, obtain described visit information for the implementation of named entity, all should be within the scope of the present invention.
It should be noted that, in step sl, the named entity that computer equipment obtains can be multiple; Such as, the content in current page is a document, and the visit information of user comprises the title of the document " Mount Taishan and Song Shan culture ", computer equipment obtain this visit information for named entity comprise: " Mount Taishan " and " Song Shan ".
In step s 2, computer equipment, according to the history access record of user, determines that at least one being associated with described named entity associates named entity.
Wherein, described association named entity mark and user current for relevant other named entities of named entity.
Wherein, described history access record comprises any record relevant to the history accessing operation of user; Preferably, described history access record includes but not limited to:
1) user's history for named entity.
Wherein, user's history for named entity represent the named entity obtained for this user institute history.
Such as, computer equipment is according to the visit information of user at current time " 2015-04-2809:30 ", the named entity obtained is " Mount Taishan ", then computer equipment is in this prior before the time, the named entity " Song Shan " obtained for this user institute history, " Qingdao ", as user's history for named entity.
2) user's history for named entity corresponding history access time.
Such as, based on 1) in user's history for the citing of named entity, wherein, the history access time corresponding with the named entity " Song Shan " that user institute history obtains is " 2015-04-2809:28 ", and the named entity " Qingdao " that user institute history obtains corresponding history access time is " 2015-04-2809:25 ".
It should be noted that, if named entity repeatedly by history institute for, then the described history access time comprise this named entity at every turn by history for time.
3) user's history for named entity between incidence relation.
Wherein, described incidence relation be used to indicate user's history for named entity between association.
Such as, user's history for named entity as follows: " Mount Taishan ", " Song Shan ", " Need For Speed ", " zillionaire ", " Qingdao ".Between the instruction of described incidence relation " Mount Taishan ", " Song Shan ", " Qingdao ", there is association, and " Need For Speed ", there is association between " zillionaire ".
It should be noted that, above-mentioned history access record is only citing, and those skilled in the art will be understood that any record relevant to the history accessing operation of user, all should be included in the scope of history access record of the present invention.
Particularly, computer equipment, according to the history access record of user, determines that the implementation that at least one being associated with described named entity associates named entity includes but not limited to:
1) described history access record comprise described history for named entity and the described history access time, described step S2 comprises step S21 further.
In described step S21, the named entity that computer equipment was accessed according to described history and described access time, by user's history at least one named entity of accessing near the time point of the described visit information of access, as with described visit information for named entity be associated at least one associate named entity.
As an example, user's history for named entity comprise: " Song Shan ", " Qingdao ", " Need For Speed ", " zillionaire ", and the history access time of " Song Shan " correspondence is " 2015-04-2809:28 ", the history access time of " Qingdao " correspondence is " 2015-04-2809:25 ", the history access time that " Need For Speed " is corresponding is " 2015-04-2808:10 ", and the history access time that " zillionaire " is corresponding is " 2015-04-2808:50 ".Computer equipment is according to the visit information of user at current time " 2015-04-2809:30 ", and the named entity obtained is " Mount Taishan "; " Song Shan " that distance current time nearest institute history was accessed by computer equipment, associates named entity as what be associated with named entity " Mount Taishan ".
As another example, user's history for named entity comprise: " Song Shan ", " Qingdao ", " Need For Speed ", " zillionaire ", and the history access time of " Song Shan " correspondence is " 2015-04-2809:28 ", the history access time of " Qingdao " correspondence is " 2015-04-2809:25 ", the history access time that " Need For Speed " is corresponding is " 2015-04-2809:21 ", and the history access time that " zillionaire " is corresponding is " 2015-04-2808:50 ".Computer equipment is according to the visit information of user at current time " 2015-04-2809:30 ", and the named entity obtained is " Mount Taishan "; First computer equipment determines the time range (2015-04-2809:20 near the time point of this visit information of access, 2015-04-2809:30), then, computer equipment history in this time range was accessed named entity " Song Shan ", " Qingdao ", " Need For Speed ", associate named entity as what be associated with named entity " Mount Taishan ".
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any named entity of accessing according to described history and described access time, by user's at least one named entity that history was accessed near the time point of the described visit information of access, as with described visit information for named entity be associated at least one associate the implementation of named entity, all should be within the scope of the present invention.
2) described history access record comprise user's history for named entity between incidence relation, described step S2 comprises step S22 further.
In described step S22, computer equipment according to described incidence relation, determine with described visit information for named entity be associated at least one associate named entity.
Such as, user's history for named entity as follows: " Mount Taishan ", " Song Shan ", " Need For Speed ", " zillionaire ", " Qingdao ".Between the instruction of described incidence relation " Mount Taishan ", " Song Shan ", " Qingdao ", there is association, and " Need For Speed ", there is association between " zillionaire ".In step sl, computer equipment obtain current for named entity " Mount Taishan ", then in step s 2, computer equipment, based on above-mentioned incidence relation, determines that the named entity that associates be associated with " Mount Taishan " comprises: " Song Shan ", " Qingdao ".
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any according to described incidence relation, determine with described visit information for named entity be associated at least one associate the implementation of named entity, all should be within the scope of the present invention.
3) described history access record comprise user's history for named entity, described step S2 comprises step S23 further.
In described step S23, computer equipment named entity that described history was accessed and described visit information for named entity mate, determine with described visit information for named entity be associated at least one associate named entity.
Wherein, described coupling is included in the coupling that multiple aspect is carried out, as semantic matches, type matching etc.
As an example of this implementation, user's history for named entity as follows: " Eastern Mountain ", " Song Shan ", " Need For Speed ", " zillionaire ", " Qingdao "; Obtaining named entity is in step sl " Mount Taishan ", then computer equipment by these history for named entity and " Mount Taishan " carry out semantic matches, determine that the semantic matching degree between " Eastern Mountain " and " Mount Taishan " is the highest, then determine that the named entity that associates be associated with " Mount Taishan " is " Eastern Mountain ".
As another example of this implementation, user's history for named entity as follows: " Mount Taishan ", " Song Shan ", " Need For Speed ", " zillionaire ", " Qingdao "; Obtaining named entity is in step sl " Eastern Mountain ", then computer equipment by these history for named entity and " Eastern Mountain " carry out type matching, determine " Mount Taishan ", " Song Shan ", " Qingdao " and " Eastern Mountain " be place name, then determine associate relevant to " Eastern Mountain " named entity is " Mount Taishan ", " Song Shan ", " Qingdao ".
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any named entity that described history was accessed and described visit information for named entity mate, determine with described visit information for named entity be associated at least one associate the implementation of named entity, all should be within the scope of the present invention.
It should be noted that, above-mentioned implementation 1), 2), 3) between can be combined with each other.Such as, implementation 1) and 2) combine, the named entity that computer equipment was accessed according to described history and described access time, obtain the named entity that history was accessed near the time point of the described visit information of access, and according to the incidence relation waited corresponding to named entity that this history was accessed, determine with described visit information for named entity be associated at least one associate named entity.Again such as, implementation 2) and 3) combine, computer equipment by obtained named entity in step sl and user's history for named entity mate, and the named entity obtained according to coupling and the incidence relation corresponding with mating the named entity that obtains, determine with described visit information for named entity be associated at least one associate named entity.Again such as, the named entity that computer equipment was accessed according to described history and described access time, obtain the named entity that history was accessed near the time point of the described visit information of access, afterwards, the named entity that these history obtained were accessed mates with the named entity obtained in step S1 by computer equipment, and the named entity that at least one history matched was accessed as with obtain in step S1 that named entity is associated associate named entity.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any history access record according to described user, determine that at least one being associated with described named entity associates the implementation of named entity, all should be within the scope of the present invention.
As a kind of preferred version of step S2, described step S2 also comprises step S2 '.
In described step S2 ', the weight information of at least one association named entity described determined by computer equipment.
Wherein, described weight information is used to indicate the weight of association named entity.
Particularly, computer equipment determines that the implementation of the weight information of at least one association named entity includes but not limited to:
1) computer equipment according to this at least one association named entity and visit information institute for named entity between matching degree, determine this at least one associate the weight information of named entity.
Wherein, association named entity and visit information for named entity between matching degree higher, the weight of this association named entity is larger.
2) computer equipment is according to described history access record, determines the weight information of at least one association named entity.
Such as, the time point of the history access time distance access described visit information of association corresponding to named entity is nearer, and the weight of this association named entity is larger.
Again such as, association named entity by history for number of times more, the weight of this association named entity is larger.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any implementation determining the weight information of at least one association named entity described, all should be within the scope of the present invention.
As a kind of preferred version of the present embodiment, the method for the present embodiment also comprises step S3.
In described step S3, computer equipment by that obtain for multiple user, described visit information for the relevant named entity of named entity be polymerized, obtain the associated entity set of described named entity.
Such as, Fig. 3 is the schematic diagram being obtained the associated entity set of named entity by polymerization of the present invention's example; Visit information for named entity be " Mount Taishan ", it is " Confucian temple ", " Song Shan ", " Thailand " that computer equipment obtains for user A the named entity that associates be associated with " Mount Taishan ", obtaining for user B the named entity that associates be associated with " Mount Taishan " is " Eastern Mountain " and " Mount Huang ", " Confucian temple ", and obtaining for user C the named entity that associates be associated with " Mount Taishan " is " Confucian temple ", " park, South Mountain "; Then the relevant named entity in " Mount Taishan " that obtains for user A, B, C is polymerized by computer equipment, obtains the associated entity set in " Mount Taishan ": " Song Shan ", " Mount Huang ", " Eastern Mountain ", " Confucian temple ", " park, South Mountain ", " Thailand ".
Preferably, the method for this preferred version also comprises step S4.
In described step S4, the weight information of at least one the association named entity in described associated entity set is determined or upgraded to computer equipment, according to following at least one item:
The appearance situation information of-one association named entity in described relevant named entity;
-one association named entity and described visit information for named entity between matching degree.
Wherein, described occur situation information comprise any to associate named entity the relevant information of appearance situation in relevant named entity; Preferably, describedly occur that situation information includes but not limited to: the number of times that association named entity occurs in the relevant named entity of institute, associate named entity the time sequencing etc. that occurs in relevant named entity.
As an example of this preferred version, based on Fig. 3, computer equipment obtain visit information for the associated entity set of named entity " Mount Taishan " comprising: " Song Shan ", " Mount Huang ", " Eastern Mountain ", " Confucian temple ", " park, South Mountain ", " Thailand ", computer equipment is according to the matching degree between above-mentioned 6 association named entities and " Mount Taishan ", determine the weight information of these 6 association named entities, the weight of this weight information instruction " Eastern Mountain " is the highest (" Eastern Mountain " and " Mount Taishan " refer to same entity), " Confucian temple ", the weight in " park, South Mountain " is taken second place (" Confucian temple ", " park, South Mountain " and " Mount Taishan " are the place name being positioned at Shandong), " Song Shan ", the weight in " Mount Huang " third (" Song Shan ", " Mount Huang " and " Mount Taishan " are place name within Chinese territory), the weight of " Thailand " is minimum (" Thailand " is external place name).
As another example of this preferred version, based on Fig. 3, computer equipment obtain visit information for the associated entity set of named entity " Mount Taishan " comprising: " Song Shan ", " Mount Huang ", " Eastern Mountain ", " Confucian temple ", " park, South Mountain ", " Thailand "; Computer equipment according to above-mentioned 6 association named entities shown in Fig. 3 the appearance situation information in relevant named entity determine the weight of " Confucian temple " the highest (" Confucian temple " has occurred three times in this relevant named entity of institute).
Preferably, in step S2 ', computer equipment for a user, determine this user current for named entity at least one association named entity weight information; Then in step s 4 which, computer equipment upgrades the weight information of this at least one association named entity.Such as, in step sl, computer equipment, according to the visit information of user C, obtains named entity " Mount Taishan "; In step S2 ', the association named entity that computer equipment is determined " Mount Taishan " is " Confucian temple " and " park, South Mountain ", and determines that the weight information of " Confucian temple " is 0.8, and the weight information in " park, South Mountain " is 0.7; In step s 4 which, computer equipment based on Fig. 3, according to " Confucian temple " and " park, South Mountain " obtain for user A, B, C the number of times that occurs in relevant named entity, will, the weight information of " Confucian temple " increases to 0.9.
It should be noted that, the weight information of the whole association named entities in associated entity set can be determined or upgrade to computer equipment, or, only determine or upgrade the weight information of the partial association named entity in associated entity set.Wherein, computer equipment can adopt various ways to select partial association named entity from associated entity set; Such as, computer equipment Stochastic choice partial association named entity from associated entity set; Again such as, computer equipment select from associated entity set access described visit information time point near for partial association named entity.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any implementation determining the weight information of at least one association named entity described, all should be within the scope of the present invention.
As the another kind of preferred version of the present embodiment, the method for the present embodiment also comprises the step S5 performed upon step s 2.
In step s 5, computer equipment is supplied to described user by with at least one content association information associating named entity corresponding described.
Wherein, corresponding to associating named entity described content association information comprises the relevant information of any content association associating named entity with this; Preferably, described content association information includes but not limited to: the address information, identification information, recommended information etc. of the content association of association named entity.
Particularly, computer equipment directly can perform step S5 upon step s 2, user is supplied to by with at least one the content association information associating named entity corresponding determined in step s 2, or, perform step S5 after step s 3, be supplied to user by with the content association information that at least one in associated entity set associates named entity corresponding.
As a kind of preferred version of step S5, computer equipment, according to the weight information of at least one association named entity described, is supplied to described user by with at least one content association information associating named entity corresponding described.
Such as, computer equipment is according to the weight information of at least one association named entity described, and to this, at least one association named entity sorts, and is supplied to user based on this sequence content association information that at least one association named entity is corresponding by this.
Again such as, the weight information of computer equipment at least one association named entity according to this, selects the predetermined quantity association named entity that weight is higher, and is supplied to user by with the content association information that this predetermined quantity associates named entity corresponding.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any by with described at least one associate the implementation that the corresponding content association information of named entity is supplied to described user, all should be within the scope of the present invention.
In prior art, named entity, as an important composition composition of natural language understanding, is widely used in various field, as commercial field, service field etc.At present, usual employing associates named entity based on the method for similarity of character string, such as, for named entity " rainbow like a chain of pearls or a string of beads ", computer equipment based on similarity of character string method obtain with the implication of this named entity similar associate named entity, as " seven coloured silks like a chain of pearls or a string of beads ", " five sons like a chain of pearls or a string of beads " etc.; Also namely, other only similar or close to named entity implication named entities, can be associated to this named entity.
According to the scheme of the present embodiment, can based on the history access record of user, determine that at least one being associated with named entity associates named entity, also be, and not only consider current to user for close or similar in implication of named entity, but from user perspective, determine at least one association named entity, thus avoid when carrying out the association of named entity, omit in implication and more dissimilar named entities, thus more website traffic can be covered, can better provide user oriented recommendation or extension service; In addition, can by obtain for multiple user, visit information for the relevant named entity of named entity be polymerized, obtain the associated entity set of described named entity, thus carry out more extensively, more fully associating; Further, by determining or upgrade the weight information of association named entity, and the content association information corresponding with associating named entity can be provided according to weight information to user, thus realize more effective recommendation or extension service.
Fig. 2 be one embodiment of the invention in computer equipment to the structural representation of the device that named entity associates.This device (hereinafter referred to as " associated apparatus ") be used for named entity associates comprises the first obtaining means 1 and determining device 2.
First obtaining means 1 according to the visit information of user, obtain described visit information for named entity.
Wherein, described visit information comprises any to user's information that the page of current accessed is relevant in computer equipment; Preferably, described visit information includes but not limited to: the address information, access time information, the information relevant to the content in current page (if the content in current page is a document, described content information includes but not limited to the name information, identification information, recommended information etc. of the document) etc. of current page.
Wherein, described named entity comprises any entity that can be called mark with name; Preferably, described named entity includes but not limited to: name, place name, organization names, description of goods etc.
Particularly, the first obtaining means 1 according to the visit information of user, obtain described visit information for the implementation of named entity include but not limited to:
1) the first obtaining means 1 directly extract from the visit information of user this visit information for named entity.
Such as, the content in current page is a document, and the visit information of user comprises the title of the document " Hainan Scenic spot introduction ", then computer equipment extract from this title this visit information for named entity " Hainan ".
2) corresponding relation between visit information and named entity is previously stored with in computer equipment, first obtaining means 1 is according to the visit information of user, and in conjunction with described corresponding relation, read the named entity corresponding with this visit information from this locality of this computer equipment.
Such as, the corresponding relation between the address information of the page and named entity is previously stored with in computer equipment.First obtaining means 1 of computer equipment obtains address information that comprise in the visit information of user, current page, and reads the named entity corresponding with this address information according to this corresponding relation from this locality.
Again such as, the corresponding relation between the name information of document and named entity is previously stored with in computer equipment.First obtaining means 1 of computer equipment obtains name information that comprise in the visit information of user, document, and reads the named entity corresponding with this name information according to this corresponding relation from this locality.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any visit information according to user, obtain described visit information for the implementation of named entity, all should be within the scope of the present invention.
It should be noted that, the named entity that the first obtaining means 1 obtains can be multiple; Such as, the content in current page is a document, and the visit information of user comprises the title of the document " Mount Taishan and Song Shan culture ", the first obtaining means 1 obtain this visit information for named entity comprise: " Mount Taishan " and " Song Shan ".
Determining device 2, according to the history access record of user, determines that at least one being associated with described named entity associates named entity.
Wherein, described association named entity mark and user current for relevant other named entities of named entity.
Wherein, described history access record comprises any record relevant to the history accessing operation of user; Preferably, described history access record includes but not limited to:
1) user's history for named entity.
Wherein, user's history for named entity represent the named entity obtained for this user institute history.
Such as, first obtaining means 1 is according to the visit information of user at current time " 2015-04-2809:30 ", the named entity obtained is " Mount Taishan ", then in this prior before the time, the named entity " Song Shan " that first obtaining means 1 obtains for this user institute history, " Qingdao ", as user's history for named entity.
2) user's history for named entity corresponding history access time.
Such as, based on 1) in user's history for the citing of named entity, wherein, the history access time corresponding with the named entity " Song Shan " that user institute history obtains is " 2015-04-2809:28 ", and the named entity " Qingdao " that user institute history obtains corresponding history access time is " 2015-04-2809:25 ".
It should be noted that, if named entity repeatedly by history institute for, then the described history access time comprise this named entity at every turn by history for time.
3) user's history for named entity between incidence relation.
Wherein, described incidence relation be used to indicate user's history for named entity between association.
Such as, user's history for named entity as follows: " Mount Taishan ", " Song Shan ", " Need For Speed ", " zillionaire ", " Qingdao ".Between the instruction of described incidence relation " Mount Taishan ", " Song Shan ", " Qingdao ", there is association, and " Need For Speed ", there is association between " zillionaire ".
It should be noted that, above-mentioned history access record is only citing, and those skilled in the art will be understood that any record relevant to the history accessing operation of user, all should be included in the scope of history access record of the present invention.
Particularly, determining device 2, according to the history access record of user, determines that the implementation that at least one being associated with described named entity associates named entity includes but not limited to:
1) described history access record comprise described history for named entity and the described history access time, described determining device 2 comprises the first sub-determining device (not shown) further.
The named entity that first sub-determining device was accessed according to described history and described access time, by user's history at least one named entity of accessing near the time point of the described visit information of access, as with described visit information for named entity be associated at least one associate named entity.
As an example, user's history for named entity comprise: " Song Shan ", " Qingdao ", " Need For Speed ", " zillionaire ", and the history access time of " Song Shan " correspondence is " 2015-04-2809:28 ", the history access time of " Qingdao " correspondence is " 2015-04-2809:25 ", the history access time that " Need For Speed " is corresponding is " 2015-04-2808:10 ", and the history access time that " zillionaire " is corresponding is " 2015-04-2808:50 ".First obtaining means 1 is according to the visit information of user at current time " 2015-04-2809:30 ", and the named entity obtained is " Mount Taishan "; " Song Shan " that distance current time nearest institute history was accessed by the first sub-determining device, associates named entity as what be associated with named entity " Mount Taishan ".
As another example, user's history for named entity comprise: " Song Shan ", " Qingdao ", " Need For Speed ", " zillionaire ", and the history access time of " Song Shan " correspondence is " 2015-04-2809:28 ", the history access time of " Qingdao " correspondence is " 2015-04-2809:25 ", the history access time that " Need For Speed " is corresponding is " 2015-04-2809:21 ", and the history access time that " zillionaire " is corresponding is " 2015-04-2808:50 ".First obtaining means 1 is according to the visit information of user at current time " 2015-04-2809:30 ", and the named entity obtained is " Mount Taishan "; First first sub-determining device determines the time range (2015-04-2809:20 near the time point of this visit information of access, 2015-04-2809:30), then, computer equipment history in this time range was accessed named entity " Song Shan ", " Qingdao ", " Need For Speed ", associate named entity as what be associated with named entity " Mount Taishan ".
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any named entity of accessing according to described history and described access time, by user's at least one named entity that history was accessed near the time point of the described visit information of access, as with described visit information for named entity be associated at least one associate the implementation of named entity, all should be within the scope of the present invention.
2) described history access record comprise user's history for named entity between incidence relation, described determining device 2 comprises the second sub-determining device (not shown) further.
Second sub-determining device according to described incidence relation, determine with described visit information for named entity be associated at least one associate named entity.
Such as, user's history for named entity as follows: " Mount Taishan ", " Song Shan ", " Need For Speed ", " zillionaire ", " Qingdao ".Between the instruction of described incidence relation " Mount Taishan ", " Song Shan ", " Qingdao ", there is association, and " Need For Speed ", there is association between " zillionaire ".First obtaining means 1 obtain current for named entity " Mount Taishan ", the second sub-determining device, based on above-mentioned incidence relation, determines that the named entity that associates be associated with " Mount Taishan " comprises: " Song Shan ", " Qingdao ".
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any according to described incidence relation, determine with described visit information for named entity be associated at least one associate the implementation of named entity, all should be within the scope of the present invention.
3) described history access record comprise user's history for named entity, described determining device 2 comprises the 3rd sub-determining device (not shown) further.
3rd sub-determining device named entity that described history was accessed and described visit information for named entity mate, determine with described visit information for named entity be associated at least one associate named entity.
Wherein, described coupling is included in the coupling that multiple aspect is carried out, as semantic matches, type matching etc.
As an example of this implementation, user's history for named entity as follows: " Eastern Mountain ", " Song Shan ", " Need For Speed ", " zillionaire ", " Qingdao "; First obtaining means 1 obtains named entity for " Mount Taishan ", then the 3rd sub-determining device by these history for named entity and " Mount Taishan " carry out semantic matches, determine that the semantic matching degree between " Eastern Mountain " and " Mount Taishan " is the highest, then determine that the named entity that associates be associated with " Mount Taishan " is " Eastern Mountain ".
As another example of this implementation, user's history for named entity as follows: " Eastern Mountain ", " Song Shan ", " Need For Speed ", " zillionaire ", " Qingdao "; First obtaining means 1 obtains named entity for " Mount Taishan ", then the 3rd sub-determining device by these history for named entity and " Mount Taishan " carry out type matching, determine " Eastern Mountain ", " Song Shan ", " Qingdao " and " Mount Taishan " be place name, then determine associate relevant to " Mount Taishan " named entity is " Eastern Mountain ", " Song Shan ", " Qingdao ".
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any named entity that described history was accessed and described visit information for named entity mate, determine with described visit information for named entity be associated at least one associate the implementation of named entity, all should be within the scope of the present invention.
It should be noted that, above-mentioned implementation 1), 2), 3) between can be combined with each other.Such as, implementation 1) and 2) combine, the named entity that determining device 2 was accessed according to described history and described access time, obtain the named entity that history was accessed near the time point of the described visit information of access, and according to the incidence relation waited corresponding to named entity that this history was accessed, determine with described visit information for named entity be associated at least one associate named entity.Again such as, implementation 2) and 3) combine, determining device 2 by the first obtaining means 1 obtain named entity and user's history for named entity mate, and the named entity obtained according to coupling and the incidence relation corresponding with mating the named entity that obtains, determine with described visit information for named entity be associated at least one associate named entity.Again such as, the named entity that determining device 2 was accessed according to described history and described access time, obtain the named entity that history was accessed near the time point of the described visit information of access, afterwards, the named entity that these history obtained were accessed by computer equipment mates with the named entity that the first obtaining means 1 obtains, and the named entity of at least one history matched being accessed associates named entity as what obtain that named entity is associated with the first obtaining means 1.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any history access record according to described user, determine that at least one being associated with described named entity associates the implementation of named entity, all should be within the scope of the present invention.
As a kind of preferred version of determining device 2, described determining device 2 also comprises the 4th sub-determining device (not shown).
4th sub-determining device determines the weight information of at least one association named entity described.
Wherein, described weight information is used to indicate the weight of association named entity.
Particularly, the 4th sub-determining device determines that the implementation of the weight information of at least one association named entity includes but not limited to:
1) the 4th sub-determining device according to this at least one association named entity and visit information institute for named entity between matching degree, determine this at least one associate the weight information of named entity.
Wherein, association named entity and visit information for named entity between matching degree higher, the weight of this association named entity is larger.
2) the 4th sub-determining device is according to described history access record, determines the weight information of at least one association named entity.
Such as, the time point of the history access time distance access described visit information of association corresponding to named entity is nearer, and the weight of this association named entity is larger.
Again such as, association named entity by history for number of times more, the weight of this association named entity is larger.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any implementation determining the weight information of at least one association named entity described, all should be within the scope of the present invention.
As a kind of preferred version of the present embodiment, the associated apparatus of the present embodiment also comprises the second obtaining means (not shown).
Second obtaining means by that obtain for multiple user, described visit information for the relevant named entity of named entity be polymerized, obtain the associated entity set of described named entity.
Such as, Fig. 3 is the schematic diagram being obtained the associated entity set of named entity by polymerization of the present invention's example; Visit information for named entity be " Mount Taishan ", it is " Confucian temple ", " Song Shan ", " Thailand " that determining device 2 obtains for user A the named entity that associates be associated with " Mount Taishan ", obtaining for user B the named entity that associates be associated with " Mount Taishan " is " Eastern Mountain " and " Mount Huang ", " Confucian temple ", and obtaining for user C the named entity that associates be associated with " Mount Taishan " is " Confucian temple ", " park, South Mountain "; Then the relevant named entity in " Mount Taishan " that obtains for user A, B, C is polymerized by the second obtaining means, obtains the associated entity set in " Mount Taishan ": " Song Shan ", " Mount Huang ", " Eastern Mountain ", " Confucian temple ", " park, South Mountain ", " Thailand ".
Preferably, the associated apparatus of this preferred version also comprises updating device (not shown).
The weight information of at least one the association named entity in described associated entity set is determined or upgraded to updating device, according to following at least one item:
The appearance situation information of-one association named entity in described relevant named entity;
-one association named entity and described visit information for named entity between matching degree.
Wherein, described occur situation information comprise any to associate named entity the relevant information of appearance situation in relevant named entity; Preferably, describedly occur that situation information includes but not limited to: the number of times that association named entity occurs in the relevant named entity of institute, associate named entity the time sequencing etc. that occurs in relevant named entity.
As an example of this preferred version, based on Fig. 3, the second obtaining means obtain visit information for the associated entity set of named entity " Mount Taishan " comprising: " Song Shan ", " Mount Huang ", " Eastern Mountain ", " Confucian temple ", " park, South Mountain ", " Thailand ", updating device is according to the matching degree between above-mentioned 6 association named entities and " Mount Taishan ", determine the weight information of these 6 association named entities, the weight of this weight information instruction " Eastern Mountain " is the highest (" Eastern Mountain " and " Mount Taishan " refer to same entity), " Confucian temple ", the weight in " park, South Mountain " is taken second place (" Confucian temple ", " park, South Mountain " and " Mount Taishan " are the place name being positioned at Shandong), " Song Shan ", the weight in " Mount Huang " third (" Song Shan ", " Mount Huang " and " Mount Taishan " are place name within Chinese territory), the weight of " Thailand " is minimum (" Thailand " is external place name).
As another example of this preferred version, based on Fig. 3, the second obtaining means obtain visit information for the associated entity set of named entity " Mount Taishan " comprising: " Song Shan ", " Mount Huang ", " Eastern Mountain ", " Confucian temple ", " park, South Mountain ", " Thailand "; Updating device according to above-mentioned 6 association named entities shown in Fig. 3 the appearance situation information in relevant named entity determine the weight of " Confucian temple " the highest (" Confucian temple " has occurred three times in this relevant named entity of institute).
Preferably, the 4th sub-determining device for a user, determine this user current for named entity at least one association named entity weight information; Then updating device upgrades the weight information of this at least one association named entity.Such as, the first obtaining means 1, according to the visit information of user C, obtains named entity " Mount Taishan "; 4th sub-determining device determines that the association named entity in " Mount Taishan " is for " Confucian temple " and " park, South Mountain ", and determines that the weight information of " Confucian temple " is 0.8, and the weight information in " park, South Mountain " is 0.7; Updating device based on Fig. 3, according to " Confucian temple " and " park, South Mountain " obtain for user A, B, C the number of times that occurs in relevant named entity, will, the weight information of " Confucian temple " increases to 0.9.
It should be noted that, the weight information of the whole association named entities in associated entity set can be determined or upgrade to computer equipment, or, only determine or upgrade the weight information of the partial association named entity in associated entity set.Wherein, computer equipment can adopt various ways to select partial association named entity from associated entity set; Such as, computer equipment Stochastic choice partial association named entity from associated entity set; Again such as, computer equipment select from associated entity set access described visit information time point near for partial association named entity.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any implementation determining the weight information of at least one association named entity described, all should be within the scope of the present invention.
As the another kind of preferred version of the present embodiment, the associated apparatus of the present embodiment be also included in determining device 2 after the generator (not shown) of executable operations.
Generator is supplied to described user by with at least one content association information associating named entity corresponding described.
Wherein, corresponding to associating named entity described content association information comprises the relevant information of any content association associating named entity with this; Preferably, described content association information includes but not limited to: the address information, identification information, recommended information etc. of the content association of association named entity.
Particularly, generator can after determining device 2 direct executable operations, user is supplied to by with determining device 2 at least one content association information associating named entity corresponding determined, or, executable operations after the second obtaining means, is supplied to user by with the content association information that at least one in associated entity set associates named entity corresponding.
As a kind of preferred version of generator, generator comprises sub-generator (not shown) further.Sub-generator, according to the weight information of at least one association named entity described, is supplied to described user by with at least one content association information associating named entity corresponding described.
Such as, sub-generator is according to the weight information of at least one association named entity described, and to this, at least one association named entity sorts, and is supplied to user based on this sequence content association information that at least one association named entity is corresponding by this.
Again such as, the weight information of sub-generator at least one association named entity according to this, selects the predetermined quantity association named entity that weight is higher, and is supplied to user by with the content association information that this predetermined quantity associates named entity corresponding.
It should be noted that, above-mentioned citing is only and technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any by with described at least one associate the implementation that the corresponding content association information of named entity is supplied to described user, all should be within the scope of the present invention.
In prior art, named entity, as an important composition composition of natural language understanding, is widely used in various field, as commercial field, service field etc.At present, usual employing associates named entity based on the method for similarity of character string, such as, for named entity " rainbow like a chain of pearls or a string of beads ", computer equipment based on similarity of character string method obtain with the implication of this named entity similar associate named entity, as " seven coloured silks like a chain of pearls or a string of beads ", " five sons like a chain of pearls or a string of beads " etc.; Also namely, other only similar or close to named entity implication named entities, can be associated to this named entity.
According to the scheme of the present embodiment, can based on the history access record of user, determine that at least one being associated with named entity associates named entity, also be, and not only consider current to user for close or similar in implication of named entity, but from user perspective, determine at least one association named entity, thus avoid when carrying out the association of named entity, omit in implication and more dissimilar named entities, thus more website traffic can be covered, can better provide user oriented recommendation or extension service; In addition, can by obtain for multiple user, visit information for the relevant named entity of named entity be polymerized, obtain the associated entity set of described named entity, thus carry out more extensively, more fully associating; Further, by determining or upgrade the weight information of association named entity, and the content association information corresponding with associating named entity can be provided according to weight information to user, thus realize more effective recommendation or extension service.
It should be noted that the present invention can be implemented in the assembly of software and/or software restraint, such as, each device of the present invention can adopt special IC (ASIC) or any other similar hardware device to realize.In one embodiment, software program of the present invention can perform to realize step mentioned above or function by processor.Similarly, software program of the present invention (comprising relevant data structure) can be stored in computer readable recording medium storing program for performing, such as, and RAM storer, magnetic or CD-ROM driver or flexible plastic disc and similar devices.In addition, steps more of the present invention or function can adopt hardware to realize, such as, as coordinating with processor thus performing the circuit of each step or function.
To those skilled in the art, obviously the invention is not restricted to the details of above-mentioned one exemplary embodiment, and when not deviating from spirit of the present invention or essential characteristic, the present invention can be realized in other specific forms.Therefore, no matter from which point, all should embodiment be regarded as exemplary, and be nonrestrictive, scope of the present invention is limited by claims instead of above-mentioned explanation, and all changes be therefore intended in the implication of the equivalency by dropping on claim and scope are included in the present invention.Any Reference numeral in claim should be considered as the claim involved by limiting.In addition, obviously " comprising " one word do not get rid of other unit or step, odd number does not get rid of plural number.Multiple unit of stating in system claims or device also can be realized by software or hardware by a unit or device.First, second word such as grade is used for representing title, and does not represent any specific order.
Claims (20)
1. in computer equipment to the method that named entity associates, wherein, the method comprises:
According to the visit information of user, obtain described visit information for named entity;
According to the history access record of described user, determine that at least one being associated with described named entity associates named entity.
2. method according to claim 1, wherein, the history access record of described user comprises following at least one item:
-described user's history for named entity;
-with described history for named entity corresponding history access time;
-described user's history for named entity between incidence relation.
3. method according to claim 2, wherein, described history access record comprises the named entity and described history access time that described history accessed, and describedly determines that the step of at least one association named entity comprises:
The named entity of accessing according to described history and described history access time, by user's history at least one named entity of accessing near the time point of the described visit information of access, as with described visit information for named entity be associated at least one associate named entity.
4. method according to claim 2, wherein, described history access record comprises described incidence relation, and the described step determining that at least one associates named entity comprises:
According to described incidence relation, determine with described visit information for named entity be associated at least one associate named entity.
5. method according to claim 2, wherein, described history access record comprises the named entity that described history was accessed, and the described step determining that at least one associates named entity comprises:
The named entity that described history was accessed and described visit information for named entity mate, determine with described visit information for named entity be associated at least one associate named entity.
6. method according to any one of claim 1 to 5, wherein, the described step determining that at least one associates named entity also comprises:
-determine the weight information of at least one association named entity described.
7. method according to any one of claim 1 to 6, wherein, the method also comprises:
By that obtain for multiple user, described visit information for the relevant named entity of named entity be polymerized, obtain the associated entity set of described named entity.
8. method according to claim 7, wherein, the method also comprises:
According to following at least one item, determine or upgrade the weight information of at least one the association named entity in described associated entity set:
The appearance situation information of-one association named entity in described relevant named entity;
-one association named entity and described visit information for named entity between matching degree.
9. method according to any one of claim 1 to 8, wherein, described determine the step of at least one named entity be associated with described named entity after, the method also comprises:
-be supplied to described user by with at least one content association information associating named entity corresponding described.
10. method according to claim 9, wherein, by with described at least one associate the step that the corresponding associated access information of named entity is supplied to described user and comprise:
According to the weight information of at least one association named entity described, be supplied to described user by with at least one content association information associating named entity corresponding described.
11. 1 kinds in computer equipment to the device that named entity associates, wherein, this device comprises:
First obtaining means, for the visit information according to user, obtain described visit information for named entity;
Determining device, for the history access record according to described user, determines that at least one being associated with described named entity associates named entity.
12. devices according to claim 11, wherein, the history access record of described user comprises following at least one item:
-described user's history for named entity;
-with described history for named entity corresponding history access time;
-described user's history for named entity between incidence relation.
13. devices according to claim 12, wherein, described history access record comprises the named entity and described history access time that described history accessed, and described determining device comprises:
First sub-determining device, for the named entity of accessing according to described history and described history access time, by user's history at least one named entity of accessing near the time point of the described visit information of access, as with described visit information for named entity be associated at least one associate named entity.
14. devices according to claim 12, wherein, described history access record comprises described incidence relation, and described determining device comprises:
Second sub-determining device, for according to described incidence relation, determine with described visit information for named entity be associated at least one associate named entity.
15. devices according to claim 12, wherein, described history access record comprises the named entity that described history was accessed, and described determining device comprises:
3rd sub-determining device, for named entity that described history was accessed and described visit information for named entity mate, determine with described visit information for named entity be associated at least one associate named entity.
16. according to claim 11 to the device according to any one of 15, and wherein, described determining device also comprises:
4th sub-determining device, for determining the weight information of at least one association named entity described.
17. according to claim 11 to the device according to any one of 16, and wherein, this device also comprises:
Second obtaining means, for by that obtain for multiple user, described visit information for the relevant named entity of named entity be polymerized, obtain the associated entity set of described named entity.
18. devices according to claim 17, wherein, this device also comprises:
Updating device, for according to following at least one item, determine or upgrade the weight information of at least one the association named entity in described associated entity set:
The appearance situation information of-one association named entity in described relevant named entity;
-one association named entity and described visit information for named entity between matching degree.
19. according to claim 11 to the device according to any one of 18, wherein, this device be also included in described determining device after executable operations with lower device:
Generator, for being supplied to described user by with at least one content association information associating named entity corresponding described.
20. devices according to claim 19, wherein, described generator comprises:
Sub-generator, for the weight information according at least one association named entity described, is supplied to described user by with at least one content association information associating named entity corresponding described.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510310542.3A CN105095347A (en) | 2015-06-08 | 2015-06-08 | Method and device for associating named entities |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510310542.3A CN105095347A (en) | 2015-06-08 | 2015-06-08 | Method and device for associating named entities |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105095347A true CN105095347A (en) | 2015-11-25 |
Family
ID=54575784
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510310542.3A Pending CN105095347A (en) | 2015-06-08 | 2015-06-08 | Method and device for associating named entities |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105095347A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110263226A (en) * | 2019-05-10 | 2019-09-20 | 平安科技（深圳）有限公司 | For the database update method, apparatus and electronic device of drug |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080114749A1 (en) * | 2006-11-14 | 2008-05-15 | Nikhil Chandhok | Event Searching |
| CN102436456A (en) * | 2010-09-29 | 2012-05-02 | 国际商业机器公司 | Method and device for classifying named entities |
| CN102902806A (en) * | 2012-10-17 | 2013-01-30 | 深圳市宜搜科技发展有限公司 | Method and system for performing inquiry expansion by using search engine |
| CN103678668A (en) * | 2013-12-24 | 2014-03-26 | 乐视网信息技术（北京）股份有限公司 | Prompting method of relevant search result, server and system |
-
2015
- 2015-06-08 CN CN201510310542.3A patent/CN105095347A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080114749A1 (en) * | 2006-11-14 | 2008-05-15 | Nikhil Chandhok | Event Searching |
| CN102436456A (en) * | 2010-09-29 | 2012-05-02 | 国际商业机器公司 | Method and device for classifying named entities |
| CN102902806A (en) * | 2012-10-17 | 2013-01-30 | 深圳市宜搜科技发展有限公司 | Method and system for performing inquiry expansion by using search engine |
| CN103678668A (en) * | 2013-12-24 | 2014-03-26 | 乐视网信息技术（北京）股份有限公司 | Prompting method of relevant search result, server and system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110263226A (en) * | 2019-05-10 | 2019-09-20 | 平安科技（深圳）有限公司 | For the database update method, apparatus and electronic device of drug |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10289700B2 (en) | Method for dynamically matching images with content items based on keywords in response to search queries | |
| CN106415537B (en) | Locally applied search result is inserted into WEB search result | |
| US20160357867A1 (en) | Creating rules for use in third-party tag management systems | |
| US10216848B2 (en) | Method and system for recommending cloud websites based on terminal access statistics | |
| US10572489B2 (en) | Synthesis of webpage snippets using sub-pages of the webpage | |
| CN104102639B (en) | Popularization triggering method based on text classification and device | |
| JP2014515514A (en) | Method and apparatus for providing suggested words | |
| CN107391561B (en) | Advertisement processing method in content source page, server and computer readable medium | |
| CN103064826A (en) | Method, device and system used for imputing expressions | |
| JP6165955B1 (en) | Method and system for matching images and content using whitelist and blacklist in response to search query | |
| US10275472B2 (en) | Method for categorizing images to be associated with content items based on keywords of search queries | |
| US10496686B2 (en) | Method and system for searching and identifying content items in response to a search query using a matched keyword whitelist | |
| CN104919444A (en) | Topic collections | |
| US20170255647A1 (en) | Method for selecting images for matching with content based on metadata of images and content in real-time in response to search queries | |
| CN103077217A (en) | Method, device and equipment for providing result additional information matched with query sequence | |
| CN103207892A (en) | Method and device for sharing document through network | |
| WO2014108038A1 (en) | Frequently-used website generation client terminal, server, system and method | |
| JP2016527615A (en) | Application information search method and apparatus | |
| CN104268473A (en) | Method and device for detecting application programs | |
| CN104090904A (en) | Method and equipment for providing target search result | |
| CN104657474A (en) | Advertisement display method, advertisement inquiring server and client side | |
| CN110502299B (en) | Method and equipment for providing novel information | |
| US11308154B2 (en) | Method and system for dynamically overlay content provider information on images matched with content items in response to search queries | |
| US20170004220A1 (en) | Automatic Grouping of Browser Bookmarks | |
| CN110955855B (en) | Information interception method, device and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151125 |