CN108241629A - Keyword group technology and device - Google Patents
Keyword group technology and device Download PDFInfo
- Publication number
- CN108241629A CN108241629A CN201611206150.3A CN201611206150A CN108241629A CN 108241629 A CN108241629 A CN 108241629A CN 201611206150 A CN201611206150 A CN 201611206150A CN 108241629 A CN108241629 A CN 108241629A
- Authority
- CN
- China
- Prior art keywords
- keyword
- grouped
- speech
- grouping
- effect
- 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
-
- 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
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application proposes that a kind of keyword group technology and device, this method include：Determine the information of keyword to be grouped, described information includes：Effect is launched in part of speech and/or prediction；Grouping in existing grouping with the Keywords matching to be grouped is determined according to described information；The keyword to be grouped is divided into the matched grouping.This method can be automatically performed keyword grouping, so as to improve efficiency and accuracy and reduce cost.
Description
Technical field
This application involves Internet technical field more particularly to a kind of keyword group technology and devices.
Background technology
In search engine marketing (search engine marketing, SEM) system, advertiser is got used to will be crucial
Word is put into the different grouping of its account, gives different bids, matching to the keyword of different grouping according to the wish of oneself
Control and intention official documents and correspondence etc..
In the relevant technologies, typically manually keyword is divided into different grouping by advertiser.But with keyword
Increasing and cost of labor raising, the artificial mode for carrying out keyword division is in efficiency, accuracy and cost etc.
It is problematic in that.
Invention content
The application is intended to solve at least some of the technical problems in related technologies.
For this purpose, the purpose of the application is to propose a kind of keyword group technology, this method can be automatically performed pass
Keyword is grouped, so as to improve efficiency and accuracy and reduce cost.
Further object is to propose a kind of keyword apparatus for grouping.
In order to achieve the above objectives, the keyword group technology that the application first aspect embodiment proposes, including：It determines to treat point
The information of group keyword, described information include：Effect is launched in part of speech and/or prediction；It is determined in existing grouping according to described information
With the grouping of the Keywords matching to be grouped；The keyword to be grouped is divided into the matched grouping.
The keyword group technology that the application first aspect embodiment proposes, by determining the information of keyword to be grouped,
And it is determined according to the information and the grouping of Keywords matching to be grouped and keyword to be grouped is divided into matched grouping
In, it can realize the automatic grouping of keyword, not need to manually be grouped, so as to improve efficiency and accuracy and reduce cost.
In order to achieve the above objectives, the keyword apparatus for grouping that the application second aspect embodiment proposes, including：First determines
Module, for determining the information of keyword to be grouped, described information includes：Effect is launched in part of speech and/or prediction；Second determining mould
Block, for determining the grouping in existing grouping with the Keywords matching to be grouped according to described information；Grouping module, for inciting somebody to action
The keyword to be grouped is divided into the matched grouping.
The keyword apparatus for grouping that the application second aspect embodiment proposes, by determining the information of keyword to be grouped,
And it is determined according to the information and the grouping of Keywords matching to be grouped and keyword to be grouped is divided into matched grouping
In, it can realize the automatic grouping of keyword, not need to manually be grouped, so as to improve efficiency and accuracy and reduce cost.
The embodiment of the present application also proposed a kind of equipment, including：One or more processors；For storing one or more
The memory of program；When one or more of programs are performed by one or more of processors so that it is one or
Multiple processors perform the application first aspect embodiment any one of them method.
The embodiment of the present application also proposed a kind of non-transitorycomputer readable storage medium, when in the storage medium
When one or more programs are performed by the one or more processors of equipment so that one or more of processors perform this Shen
It please first aspect embodiment any one of them method.
The embodiment of the present application also proposed a kind of computer program product, when the computer program product is by equipment
When one or more processors perform so that one or more of processors perform any one of the application first aspect embodiment
The method.
The additional aspect of the application and advantage will be set forth in part in the description, and will partly become from the following description
It obtains significantly or is recognized by the practice of the application.
Description of the drawings
The application is above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Significantly and it is readily appreciated that, wherein：
Fig. 1 is the flow diagram for the keyword group technology that the application one embodiment proposes；
Fig. 2 is the flow diagram of the keyword group technology of the application another embodiment proposition；
Fig. 3 is the structure diagram for the keyword apparatus for grouping that the application one embodiment proposes；
Fig. 4 is the structure diagram of the keyword apparatus for grouping of the application another embodiment proposition.
Specific embodiment
Embodiments herein is described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar module or the module with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, and is only used for explaining the application, and it is not intended that limitation to the application.On the contrary, this
The embodiment of application includes falling into all changes in the range of the spirit and intension of attached claims, modification and equivalent
Object.
Fig. 1 is the flow diagram for the keyword group technology that the application one embodiment proposes.
As shown in Figure 1, the method for the present embodiment includes：
S11：Determine the information of keyword to be grouped, described information includes：Effect is launched in part of speech and/or prediction.
Under different application scene, keyword to be grouped can be different.For example, in SEM system, keyword to be grouped is
Refer to the keyword for needing to be divided into the grouping of advertiser account.The acquisition modes of keyword to be grouped do not limit, such as can be with
It collects to obtain using manual type, be obtained alternatively, can also use and open up word technology automatically.
Part of speech refers to broad sense part of speech, can include at least one in following item：Business part of speech, entity part of speech, linguistics
Part of speech.
Business part of speech is for distinguishing different business, for example, business part of speech includes：Producer's word joins word etc..
Entity part of speech is for distinguishing different entities, for example, entity part of speech includes：Region word, brand word etc..
Linguistics part of speech refers to the definition in linguistics, for example, linguistics part of speech includes：Noun, verb, adjective etc..
The method of the part of speech of specific identification keyword may refer to subsequent descriptions.
Prediction launch effect be treat grouping keyword dispensing effect predicted after obtain, specifically launch effect
It can be set according to application demand, included for example, launching effect：The corresponding advertisement of keyword to be grouped show rate, clicking rate,
Conversion ratio etc..
The method of the dispensing effect of specific prediction keyword may refer to subsequent descriptions.
S12：Grouping in existing grouping with the Keywords matching to be grouped is determined according to described information.
The grouping of existing grouping for example, advertiser account.
The existing grouping of advertiser account can be set according to application demand, for example, the existing grouping packet of advertiser account
It includes：The grouping of price word, interrogative grouping and conversion word grouping.
Correspondingly, in matching, it is thus necessary to determine that go out keyword to be grouped and belong to any in above-mentioned three kinds of groupings.Specifically
Matching process may refer to subsequent descriptions.
S13：The keyword to be grouped is divided into the matched grouping.
For example, the grouping with Keywords matching to be grouped is in the grouping of price word, then keyword to be grouped is divided into valency
In the grouping of lattice word.
If it is understood that keyword to be grouped can abandon this not with any group of matching in existing grouping
Keyword to be grouped.
In the present embodiment, by determining the information of keyword to be grouped, and determine according to the information and keyword to be grouped
Matched grouping and keyword to be grouped is divided into matched grouping, can realize the automatic grouping of keyword, be not required to
Very important person's work point group, so as to improve efficiency and accuracy and reduce cost.
Fig. 2 is the flow diagram of the keyword group technology of the application another embodiment proposition.
The present embodiment by keyword for being divided into the different grouping of advertiser account.
As shown in Fig. 2, the method for the present embodiment includes：
S21：The part of speech and prediction for determining keyword to be grouped launch effect.
Part of speech refers to broad sense part of speech, can be divided into following part of speech classification including a variety of part of speech classifications, such as part of speech：Business word
Property, entity part of speech and linguistics part of speech.
In the part of speech for identifying keyword, in general, a keyword is only capable of belonging to one kind under similar part of speech, one
Keyword may belong to a variety of inhomogeneity parts of speech.For example, under business part of speech, a keyword be only capable of being identified as producer's word or
Join word, and a keyword can not only be identified as producer's word, but also be identified as noun.
Different classes of part of speech has different identification methods, specific as follows：
(1) identification of business part of speech
The knowledge of business part of speech maybe identify that keyword to be grouped is producer's word or joins word etc..
During specific identification, it can be carried out based on the matched mode of substring, it will be belonging to the substring that included in keyword be grouped
Business part of speech, be determined as the business part of speech of keyword to be grouped.The substring that each business part of speech includes can be dug by data
The modes such as pick predefine, for example, passing through data mining, it may be determined that and " joining " this substring would generally be included by joining word, because
This, if can be identified as joining word by the keyword to be grouped comprising " joining " this substring in keyword to be grouped.
It is above-mentioned by be based on substring it is matched in a manner of identify business part of speech for, it is to be understood that be not limited to such mode,
It for example, can also be in a manner that disaggregated model be classified.For example, different business parts of speech is considered as different classifications, into
And part of speech identification mission is converted into classification task, training and estimating by disaggregated model can realize the industry to keyword
The identification for part of speech of being engaged in.The disaggregated model in specially various the relevant technologies, such as SVM models may be used in disaggregated model.
(2) identification of entity part of speech
The knowledge of entity part of speech maybe identify that keyword is region word or brand word etc..
During specific identification, sequence labelling model can be based on and carried out, sequence labelling model is widely used in text-processing
Related field, such as participle, part-of-speech tagging, name Entity recognition etc..Existing sequence labelling model mainly have HMM,
MEMM and CRF.By taking CRF models as an example, keyword to be grouped can be regard as input, output is the probability value of each entity,
The entity of probability value maximum is determined as to the entity part of speech of keyword to be grouped.
(3) identification of linguistics part of speech
The knowledge of linguistics part of speech maybe identify that keyword to be grouped is noun, verb or adjective etc..
The identification method that linguistics in the relevant technologies defines may be used in specific identification method.
S22：Determine the information of the existing grouping of advertiser account.
The information of existing grouping includes：Have in existing grouping keyword part of speech and, the attribute of existing grouping letter
Breath.
The part of speech identification method for having keyword is consistent with the above-mentioned part of speech identification method principle for treating grouping keyword, tool
Body can be carried out according to the part of speech identification method for treating grouping keyword, and this will not be detailed here.
The attribute information of existing grouping specifically includes：The classification of the word of existing grouping storage, such as the category of conversion word grouping
Property information be for preservation effect word.
Be described above the determination process of part of speech, the determination process for launching effect to prediction below illustrates.Specifically may be used
To include：
If keyword to be grouped is the keyword that history occurred, the history of keyword to be grouped is launched described in statistics
Effect is launched in effect, the prediction for determining keyword to be grouped according to statistical result；Alternatively,
If keyword to be grouped is the keyword that did not occurred of history, it is determined that history occurred described treats that grouping is closed
The approximate keyword of keyword, the history for counting the approximate keyword launch effect, are determined to treat that grouping is crucial according to statistical result
Effect is launched in the prediction of word.
When above-mentioned statistical history launches effect, statistic algorithm can be set according to demand, such as by the equal of historical shift rate
Value launches effect as prediction.
During above-mentioned determining approximate keyword, the similarity numerical value of keyword to be grouped and history keyword word, choosing can be calculated
The highest history keyword word of similarity numerical value is selected as approximate keyword.In the similarity numerical value between calculating two words, example
Such as can two words be first converted to term vector, then calculate the equidistant value of COS distance of two term vectors, using distance value as
Similarity numerical value between two words.
S23：Effect and the information of existing grouping are launched according to the part of speech of keyword to be grouped and prediction, determine have
In grouping with the grouping of Keywords matching to be grouped.
In some examples, it can be carried out according to the part of speech of keyword to be grouped and the part of speech of existing keyword, for example, doubting
Ask that the part of speech of the existing keyword in word grouping includes joining word, and the part of speech of keyword to be grouped also includes joining word, then will
Interrogative grouping is determined as matched grouping.
Further, if a keyword has a plurality of types of parts of speech, for example, the part of speech of a keyword includes adding
Alliance's word (business part of speech) and noun (linguistics part of speech) then in this case, can set different type according to application demand
The weight of part of speech determines matched grouping according to weight and corresponding part of speech.For example, business part of speech, entity can be set respectively
The weight of part of speech and linguistics part of speech can be matched later according to the highest part of speech of weight, for example, the highest part of speech of weight
It is business part of speech, then in each existing grouping, the business part of speech existing keyword consistent with keyword to be grouped is found, by this
Grouping where having keyword is used as matched grouping.It is above-mentioned for being matched according to highest weighting, it is to be understood that
It can also be weighted according to weight, specific weighting algorithm can be according to setting, and this will not be detailed here.
In some examples, can be launched according to the prediction of keyword to be grouped the attribute information of effect and existing grouping into
Row, if for example, keyword be grouped prediction launch effect meet preset condition, will for store the grouping of effect word work
For matched grouping, if for example, the prediction conversion ratio of keyword to be grouped is more than threshold value, conversion word grouping is determined as
The grouping matched.
S24：Keyword to be grouped is divided into matched grouping.
For example, according to part of speech, keyword to be grouped is consistent with the part of speech of the existing keyword in interrogative grouping, then will treat
Grouping keyword be divided into interrogative grouping in, if alternatively, keyword be grouped prediction dispensing effect meet preset condition,
Then keyword to be grouped is divided into conversion word grouping.
If it is understood that keyword to be grouped can abandon this not with any group of matching in existing grouping
Keyword to be grouped.
In the present embodiment, by determining the information of keyword to be grouped, and determine according to the information and keyword to be grouped
Matched grouping and keyword to be grouped is divided into matched grouping, can realize the automatic grouping of keyword, be not required to
Very important person's work point group, so as to improve efficiency and accuracy and reduce cost.In the present embodiment, by being directed to different types of word
Property corresponding identification method is provided, accuracy can be improved.
Fig. 3 is the structure diagram for the keyword apparatus for grouping that the application one embodiment proposes.
As shown in figure 3, the device 30 of the present embodiment includes：First determining module 31, the second determining module 32 and grouping mould
Block 33.
First determining module 31, for determining the information of keyword to be grouped, described information includes：Part of speech and/or prediction
Launch effect；
Second determining module 32, for according to described information determine in existing grouping with the Keywords matching to be grouped
Grouping；
Grouping module 33, for the keyword to be grouped to be divided into the matched grouping.
In some embodiments, referring to Fig. 4, the first determining mould, 31 include：
For determining the first determination sub-module 311 of the part of speech of keyword to be grouped；
First determination sub-module 311 is specifically used for：
When the part of speech includes business part of speech, based on substring matching or disaggregated model, keyword to be grouped is identified
Business part of speech；Alternatively,
When the part of speech includes entity part of speech, the entity part of speech based on sequence labelling Model Identification keyword to be grouped；
Alternatively,
When the part of speech includes linguistics part of speech, the linguistics word for identifying keyword to be grouped is defined based on linguistics
Property.
In some embodiments, referring to Fig. 4, first determining module 31 includes：
The second determination sub-module 312 of effect is launched in prediction for determining keyword to be grouped；
Second determination sub-module 312 is specifically used for：
If keyword to be grouped is the keyword that history occurred, the history of keyword to be grouped is launched described in statistics
Effect is launched in effect, the prediction for determining keyword to be grouped according to statistical result；Alternatively,
If keyword to be grouped is the keyword that did not occurred of history, it is determined that history occurred described treats that grouping is closed
The approximate keyword of keyword, the history for counting the approximate keyword launch effect, are determined to treat that grouping is crucial according to statistical result
Effect is launched in the prediction of word.
In some embodiments, referring to Fig. 4, second determining module 32 includes：
Third determination sub-module 321, for when described information includes part of speech, identifying have keyword in existing grouping
Part of speech will be grouped where the part of speech existing keyword consistent with the part of speech of the keyword to be grouped, and be determined as treating point with described
The grouping of group Keywords matching.
In some embodiments, referring to Fig. 4, second determining module 32 includes：
4th determination sub-module 322, for when described information includes prediction dispensing effect, effect to be launched in the prediction
When reaching preset condition, it will be used to store the grouping of effect word in existing grouping, be determined as and the Keywords matching to be grouped
Grouping.
It is understood that the device of the present embodiment is corresponding with above method embodiment, particular content may refer to method
The associated description of embodiment, is no longer described in detail herein.
In the present embodiment, by determining the information of keyword to be grouped, and determine according to the information and keyword to be grouped
Matched grouping and keyword to be grouped is divided into matched grouping, can realize the automatic grouping of keyword, be not required to
Very important person's work point group, so as to improve efficiency and accuracy and reduce cost.
The embodiment of the present application also proposed a kind of equipment, including：One or more processors；For storing one or more
The memory of program；When one or more of programs are performed by one or more of processors so that it is one or
Multiple processors perform：Determine the information of keyword to be grouped, described information includes：Effect is launched in part of speech and/or prediction；According to
Described information determines the grouping with the Keywords matching to be grouped in existing grouping；The keyword to be grouped is divided into institute
It states in matched grouping.
The embodiment of the present application also proposed a kind of non-transitorycomputer readable storage medium, when in the storage medium
When one or more programs are performed by the one or more processors of equipment so that one or more of processors perform：Really
Surely the information of keyword to be grouped, described information include：Effect is launched in part of speech and/or prediction；Determine have according to described information
In grouping with the grouping of the Keywords matching to be grouped；The keyword to be grouped is divided into the matched grouping.
The embodiment of the present application also proposed a kind of computer program product, when the computer program product is by equipment
When one or more processors perform so that one or more of processors perform：Determine the information of keyword to be grouped, institute
Information is stated to include：Effect is launched in part of speech and/or prediction；According to described information determine in existing grouping with the keyword to be grouped
Matched grouping；The keyword to be grouped is divided into the matched grouping.
Above-mentioned equipment can be server or terminal device.
It is understood that same or similar part can mutually refer in the various embodiments described above, in some embodiments
Unspecified content may refer to the same or similar content in other embodiment.
It should be noted that in the description of the present application, term " first ", " second " etc. are only used for description purpose, without
It is understood that indicate or implying relative importance.In addition, in the description of the present application, unless otherwise indicated, the meaning of " multiple "
Refer at least two.
Any process described otherwise above or method description are construed as in flow chart or herein, represent to include
Module, segment or the portion of the code of the executable instruction of one or more the step of being used to implement specific logical function or process
Point, and the range of the preferred embodiment of the application includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, to perform function, this should be by the application
Embodiment person of ordinary skill in the field understood.
It should be appreciated that each section of the application can be realized with hardware, software, firmware or combination thereof.Above-mentioned
In embodiment, software that multiple steps or method can in memory and by suitable instruction execution system be performed with storage
Or firmware is realized.If for example, with hardware come realize in another embodiment, can be under well known in the art
Any one of row technology or their combination are realized：With for the logic gates to data-signal realization logic function
Discrete logic, have suitable combinational logic gate circuit application-specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that realize all or part of step that above-described embodiment method carries
Suddenly it is that relevant hardware can be instructed to complete by program, the program can be stored in a kind of computer-readable storage medium
In matter, the program when being executed, one or a combination set of the step of including embodiment of the method.
In addition, each functional unit in each embodiment of the application can be integrated in a processing module, it can also
That each unit is individually physically present, can also two or more units be integrated in a module.Above-mentioned integrated mould
The form that hardware had both may be used in block is realized, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized in the form of software function module and is independent product sale or in use, can also be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..
In the description of this specification, reference term " one embodiment ", " example ", " is specifically shown " some embodiments "
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment or example of the application.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiments or example in combine in an appropriate manner.
Although embodiments herein has been shown and described above, it is to be understood that above-described embodiment is example
Property, it is impossible to the limitation to the application is interpreted as, those of ordinary skill in the art within the scope of application can be to above-mentioned
Embodiment is changed, changes, replacing and modification.
Claims (11)
1. a kind of keyword group technology, which is characterized in that including：
Determine the information of keyword to be grouped, described information includes：Effect is launched in part of speech and/or prediction；
Grouping in existing grouping with the Keywords matching to be grouped is determined according to described information；
The keyword to be grouped is divided into the matched grouping.
2. according to the method described in claim 1, it is characterized in that, the part of speech for determining keyword to be grouped includes：
When the part of speech includes business part of speech, based on substring matching or disaggregated model, the business of keyword to be grouped is identified
Part of speech；Alternatively,
When the part of speech includes entity part of speech, the entity part of speech based on sequence labelling Model Identification keyword to be grouped；Alternatively,
When the part of speech includes linguistics part of speech, the linguistics part of speech for identifying keyword to be grouped is defined based on linguistics.
3. according to the method described in claim 1, it is characterized in that, effect packet is launched in the prediction for determining keyword to be grouped
It includes：
If keyword to be grouped is the keyword that history occurred, the history of keyword to be grouped launches effect described in statistics
Effect is launched in fruit, the prediction for determining keyword to be grouped according to statistical result；Alternatively,
If keyword to be grouped is the keyword that history did not occurred, it is determined that the keyword to be grouped that history occurred
Approximate keyword, the history for counting the approximate keyword launches effect, keyword to be grouped determined according to statistical result
Effect is launched in prediction.
4. according to the method described in claim 1, it is characterized in that, described information include part of speech when, it is described according to the letter
Breath determines with the grouping of the Keywords matching to be grouped to include in existing grouping：
Identify have the part of speech of keyword in existing grouping, by related consistent with the part of speech of the keyword to be grouped of part of speech
It is grouped where keyword, is determined as the grouping with the Keywords matching to be grouped.
5. according to the method described in claim 1, it is characterized in that, described information include prediction launch effect when, described
Determine that the grouping in existing grouping with the Keywords matching to be grouped includes according to described information：
When the prediction launches effect and reaches preset condition, it will be used to store the grouping of effect word in existing grouping, be determined as
With the grouping of the Keywords matching to be grouped.
6. a kind of keyword apparatus for grouping, which is characterized in that including：
First determining module, for determining the information of keyword to be grouped, described information includes：Effect is launched in part of speech and/or prediction
Fruit；
Second determining module, for determining the grouping in existing grouping with the Keywords matching to be grouped according to described information；
Grouping module, for the keyword to be grouped to be divided into the matched grouping.
7. device according to claim 6, which is characterized in that first determining module includes：
For determining the first determination sub-module of the part of speech of keyword to be grouped；
First determination sub-module is specifically used for：
When the part of speech includes business part of speech, based on substring matching or disaggregated model, the business of keyword to be grouped is identified
Part of speech；Alternatively,
When the part of speech includes entity part of speech, the entity part of speech based on sequence labelling Model Identification keyword to be grouped；Alternatively,
When the part of speech includes linguistics part of speech, the linguistics part of speech for identifying keyword to be grouped is defined based on linguistics.
8. device according to claim 6, which is characterized in that first determining module includes：
The second determination sub-module of effect is launched in prediction for determining keyword to be grouped；
Second determination sub-module is specifically used for：
If keyword to be grouped is the keyword that history occurred, the history of keyword to be grouped launches effect described in statistics
Effect is launched in fruit, the prediction for determining keyword to be grouped according to statistical result；Alternatively,
If keyword to be grouped is the keyword that history did not occurred, it is determined that the keyword to be grouped that history occurred
Approximate keyword, the history for counting the approximate keyword launches effect, keyword to be grouped determined according to statistical result
Effect is launched in prediction.
9. device according to claim 6, which is characterized in that second determining module includes：
Third determination sub-module, will for when described information includes part of speech, identifying have the part of speech of keyword in existing grouping
It is grouped, is determined as and the keyword to be grouped where the part of speech existing keyword consistent with the part of speech of the keyword to be grouped
Matched grouping.
10. device according to claim 6, which is characterized in that second determining module includes：
4th determination sub-module, for when described information includes prediction dispensing effect, launching effect in the prediction and reaching pre-
If during condition, it will be used to store the grouping of effect word in existing grouping, be determined as the grouping with the Keywords matching to be grouped.
11. a kind of equipment, which is characterized in that including：
One or more processors；For storing the memory of one or more programs；
When one or more of programs are performed by one or more of processors so that one or more of processors
Perform such as claim 1-5 any one of them methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611206150.3A CN108241629A (en) | 2016-12-23 | 2016-12-23 | Keyword group technology and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611206150.3A CN108241629A (en) | 2016-12-23 | 2016-12-23 | Keyword group technology and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108241629A true CN108241629A (en) | 2018-07-03 |
Family
ID=62703383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611206150.3A Pending CN108241629A (en) | 2016-12-23 | 2016-12-23 | Keyword group technology and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108241629A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111782801A (en) * | 2019-05-17 | 2020-10-16 | 北京京东尚科信息技术有限公司 | Method and device for grouping keywords |
| CN112559895A (en) * | 2021-02-19 | 2021-03-26 | 深圳平安智汇企业信息管理有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN112749546A (en) * | 2021-01-13 | 2021-05-04 | 叮当快药科技集团有限公司 | Retrieval matching processing method and device for medical semantics |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090248671A1 (en) * | 2008-03-28 | 2009-10-01 | Daisuke Maruyama | Information classification system, information processing apparatus, information classification method and program |
| CN102426572A (en) * | 2011-07-05 | 2012-04-25 | 百度在线网络技术（北京）有限公司 | Method and equipment for classifying business entries |
| CN102937973A (en) * | 2012-10-15 | 2013-02-20 | 北京百度网讯科技有限公司 | Method and device for generating presentation configuration information used for information presentation |
| CN103136696A (en) * | 2013-03-26 | 2013-06-05 | 明日互动（北京）广告传媒有限公司 | Management method of media placement and system thereof |
| CN103164454A (en) * | 2011-12-15 | 2013-06-19 | 百度在线网络技术（北京）有限公司 | Keyword grouping method and keyword grouping system |
| CN103218432A (en) * | 2013-04-15 | 2013-07-24 | 北京邮电大学 | Named entity recognition-based news search result similarity calculation method |
| CN103425677A (en) * | 2012-05-18 | 2013-12-04 | 阿里巴巴集团控股有限公司 | Method for determining classified models of keywords and method and device for classifying keywords |
| CN103514191A (en) * | 2012-06-20 | 2014-01-15 | 百度在线网络技术（北京）有限公司 | Method and device for determining keyword matching mode of target popularization information |
| CN103577423A (en) * | 2012-07-23 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Keyword classification method and system |
| CN104077290A (en) * | 2013-03-26 | 2014-10-01 | 腾讯科技（深圳）有限公司 | Method and device for generating promoted accounts |
| CN104731788A (en) * | 2013-12-18 | 2015-06-24 | 阿里巴巴集团控股有限公司 | Processing method and equipment for promote information |
| CN104834647A (en) * | 2014-02-12 | 2015-08-12 | 腾讯科技（深圳）有限公司 | Method and device for obtaining informative abstract |
-
2016
- 2016-12-23 CN CN201611206150.3A patent/CN108241629A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090248671A1 (en) * | 2008-03-28 | 2009-10-01 | Daisuke Maruyama | Information classification system, information processing apparatus, information classification method and program |
| CN102426572A (en) * | 2011-07-05 | 2012-04-25 | 百度在线网络技术（北京）有限公司 | Method and equipment for classifying business entries |
| CN103164454A (en) * | 2011-12-15 | 2013-06-19 | 百度在线网络技术（北京）有限公司 | Keyword grouping method and keyword grouping system |
| CN103425677A (en) * | 2012-05-18 | 2013-12-04 | 阿里巴巴集团控股有限公司 | Method for determining classified models of keywords and method and device for classifying keywords |
| CN103514191A (en) * | 2012-06-20 | 2014-01-15 | 百度在线网络技术（北京）有限公司 | Method and device for determining keyword matching mode of target popularization information |
| CN103577423A (en) * | 2012-07-23 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Keyword classification method and system |
| CN102937973A (en) * | 2012-10-15 | 2013-02-20 | 北京百度网讯科技有限公司 | Method and device for generating presentation configuration information used for information presentation |
| CN103136696A (en) * | 2013-03-26 | 2013-06-05 | 明日互动（北京）广告传媒有限公司 | Management method of media placement and system thereof |
| CN104077290A (en) * | 2013-03-26 | 2014-10-01 | 腾讯科技（深圳）有限公司 | Method and device for generating promoted accounts |
| CN103218432A (en) * | 2013-04-15 | 2013-07-24 | 北京邮电大学 | Named entity recognition-based news search result similarity calculation method |
| CN104731788A (en) * | 2013-12-18 | 2015-06-24 | 阿里巴巴集团控股有限公司 | Processing method and equipment for promote information |
| CN104834647A (en) * | 2014-02-12 | 2015-08-12 | 腾讯科技（深圳）有限公司 | Method and device for obtaining informative abstract |
Non-Patent Citations (1)
| Title |
|---|
| 徐林海 等: "用Google做外贸之Google帮你找客户", 《电子商务世界》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111782801A (en) * | 2019-05-17 | 2020-10-16 | 北京京东尚科信息技术有限公司 | Method and device for grouping keywords |
| CN111782801B (en) * | 2019-05-17 | 2024-02-06 | 北京京东尚科信息技术有限公司 | Method and device for grouping keywords |
| CN112749546A (en) * | 2021-01-13 | 2021-05-04 | 叮当快药科技集团有限公司 | Retrieval matching processing method and device for medical semantics |
| CN112559895A (en) * | 2021-02-19 | 2021-03-26 | 深圳平安智汇企业信息管理有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN112559895B (en) * | 2021-02-19 | 2021-05-18 | 深圳平安智汇企业信息管理有限公司 | Data processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mukherjee et al. | Effect of negation in sentences on sentiment analysis and polarity detection | |
| Ramteke et al. | Election result prediction using Twitter sentiment analysis | |
| CN108121700B (en) | Keyword extraction method and device and electronic equipment | |
| CN111104526A (en) | Financial label extraction method and system based on keyword semantics | |
| CN110009430B (en) | Cheating user detection method, electronic device and computer readable storage medium | |
| Berger | Large scale multi-label text classification with semantic word vectors | |
| CN110046634B (en) | Interpretation method and device of clustering result | |
| CN110096572B (en) | Sample generation method, device and computer readable medium | |
| Bailey et al. | Few-shot text classification with pre-trained word embeddings and a human in the loop | |
| CN108241629A (en) | Keyword group technology and device | |
| CN111881671A (en) | Attribute word extraction method | |
| CN108153909A (en) | Word method, apparatus and electronic equipment, storage medium are opened up in keyword dispensing | |
| Ebert et al. | CIS-positive: A combination of convolutional neural networks and support vector machines for sentiment analysis in Twitter | |
| CN110990711A (en) | WeChat public number recommendation algorithm and system based on machine learning | |
| Wings et al. | A context-aware approach for extracting hard and soft skills | |
| CN110532562B (en) | Neural network training method, idiom misuse detection method and device and electronic equipment | |
| CN115455151A (en) | AI emotion visual identification method and system and cloud platform | |
| Hossain et al. | Product market demand analysis using nlp in banglish text with sentiment analysis and named entity recognition | |
| CN108804413B (en) | Text cheating identification method and device | |
| CN112328469B (en) | Function level defect positioning method based on embedding technology | |
| Anees et al. | Performance analysis of multiple classifiers using different term weighting schemes for sentiment analysis | |
| CN104778162A (en) | Subject classifier training method and system based on maximum entropy | |
| CN111488452A (en) | Webpage tampering detection method, detection system and related equipment | |
| Bocharova et al. | VacancySBERT: the approach for representation of titles and skills for semantic similarity search in the recruitment domain | |
| US11321527B1 (en) | Effective classification of data based on curated features |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for 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: 20180703 |