CN110069542A - Keyword appraisal procedure and device - Google Patents
Keyword appraisal procedure and device Download PDFInfo
- Publication number
- CN110069542A CN110069542A CN201710882220.5A CN201710882220A CN110069542A CN 110069542 A CN110069542 A CN 110069542A CN 201710882220 A CN201710882220 A CN 201710882220A CN 110069542 A CN110069542 A CN 110069542A
- Authority
- CN
- China
- Prior art keywords
- keyword
- assessed
- path
- jumps
- jump
- 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.)
- Granted
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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
Abstract
The invention discloses a kind of keyword appraisal procedure and device, at least one of available keyword to be assessed jumps path, wherein described jump path using the keyword to be assessed as starting point, using the target word in target phrase as terminal;Path is jumped according at least one of the keyword to be assessed, obtain the keyword to be assessed jumps statistical result, jumps statistical result wherein described and is used to indicate the keyword to be assessed to the contribution margin of the target word;According to the statistical result that jumps the keyword to be assessed is assessed, relative to existing from assessing for keyword to be assessed source word and target word in terms of, realization assesses the contribution margin of target word keyword to be assessed according to keyword to be assessed.
Description
Technical field
The present invention relates to technical field of internet application, more specifically, more particularly to a kind of keyword appraisal procedure and
Device.
Background technique
Transformation at present there are two ways to evaluation keyword, one is evaluation keyword as target word;It is another
Kind is to evaluate the source effect of keyword.Such as all SEM (Search Engine Marketing, search to Mr. Yu client
Engine marketing) for the keyword that PC (Personal Computer, personal computer) end is launched, when assessing keyword,
Any one keyword K can be selected, acquisition is related to all search results of keyword K, if keyword K is as source word
Number of the number or keyword K of (i.e. as first keyword once searched for) as target word is made according to keyword K
For the number as target word of number or keyword K of source word, the keyword K is assessed.
However when keyword K is as target word, during in source, word jumps to target word, source word may be first
Other one or more keywords are first jumped to, target word is then just jumped to.In current jump procedure, source word and mesh
Keyword among mark word also plays certain contribution.If crucial without the keyword among source word and target word
Word K will be reduced as the transformation of target word.
As it can be seen that above-mentioned number and keyword K using keyword K as source word assesses key as the number of target word
The method of word K has ignored contribution of the keyword to target word.
Summary of the invention
In view of the above problems, it proposes on the present invention overcomes the above problem or at least be partially solved in order to provide one kind
Keyword appraisal procedure and device, the technical solution for stating problem are as follows:
A kind of keyword appraisal procedure, which comprises
Obtain keyword to be assessed at least one jumps path, wherein described jump path with the keyword to be assessed
For starting point, using the target word in target phrase as terminal;
Path is jumped according at least one of the keyword to be assessed, obtain the keyword to be assessed jumps statistics
As a result, jumping statistical result described in wherein is used to indicate the keyword to be assessed to the contribution margin of the target word;
The keyword to be assessed is assessed according to the statistical result that jumps.
Optionally, the method also includes:
The source statistical result of the keyword to be assessed and the direct conversion results of the keyword to be assessed are obtained,
Described in source statistical result be used to indicate the keyword to be assessed as source word source act on, it is described directly conversion knot
Fruit is used to indicate transformation of the keyword to be assessed as the target word;
The statistical result that jumps according to assesses the keyword to be assessed, comprising: jumps statistics knot according to described
Fruit, the source statistical result and the direct conversion results assess the keyword to be assessed.
Optionally, described that statistical result, the source statistical result and the direct conversion results are jumped according to, it comments
Estimate the keyword to be assessed, comprising:
It is tied according to statistical result, the source statistical result, the direct conversion results, the statistics that jumps of jumping
Corresponding first weight of fruit, corresponding second weight of the source statistical result and the corresponding third power of the direct conversion results
Weight obtains the comprehensive assessment effect of the keyword to be assessed;
It is acted on according to the comprehensive assessment of the keyword to be assessed, assesses the keyword to be assessed.
Optionally, at least one of the acquisition keyword to be assessed jumps path, comprising:
It obtains all of each target word of the keyword to be assessed into target phrase and jumps path;
From the keyword to be assessed, all of each target word into target phrase are jumped in path, are each target
Word selected part jumps path, wherein selected every jumps path and jumps to corresponding mesh from the keyword to be assessed
The number of hops for marking word is no more than preset times.
Optionally, at least one according to the keyword to be assessed jumps path, obtains the key to be assessed
Word jumps statistical result, comprising:
It obtains and selected all jump every path for jumping path in path and jump probability;
The path for jumping path according to described every jumps probability and every target word for jumping path jumps road all
As the destination probability of target word in diameter, indicated described in jump statistical result jump statistical probability.
It is optionally, all selected by the acquisition to jump every path for jumping path in path and jump probability, comprising:
Path is jumped to selected all every jumped in path:
It obtains this and jumps the single that i-th of keyword jumps to i+1 keyword in path and jump probability, according to this
Item jumps all singles in path and jumps probability, obtains this and jump the path in path jumping probability, and wherein i is from 1 to N-1
Natural number, the N is the sum that keyword in path is jumped where i-th of keyword, and the keyword to be assessed is
First jumped in path the keyword, the target word are the n-th keyword jumped in path.
A kind of keyword assessment device, described device include: path acquiring unit, jump statistic unit and assessment unit,
The path acquiring unit, at least one for obtaining keyword to be assessed jumps path, wherein described jump
Path is using the keyword to be assessed as starting point, using the target word in target phrase as terminal;
It is described to jump statistic unit, for jumping path according at least one of the keyword to be assessed, obtain described
Keyword to be assessed jumps statistical result, jumps statistical result wherein described and is used to indicate the keyword to be assessed to described
The contribution margin of target word;
The assessment unit assesses the keyword to be assessed for jumping statistical result according to.
Optionally, described device further include: result acquiring unit, the source for obtaining the keyword to be assessed count
As a result with the direct conversion results of the keyword to be assessed, wherein the source statistical result is used to indicate the pass to be assessed
Keyword is acted on as the source of source word, and the direct conversion results are used to indicate the keyword to be assessed as the target
The transformation of word;
The assessment unit, specifically for jumped according to statistical result, the source statistical result and it is described directly
Conversion results assess the keyword to be assessed.
A kind of storage medium, the storage medium include the program of storage, wherein in described program operation described in control
Equipment where storage medium executes above-mentioned any keyword appraisal procedure.
A kind of processor, the processor is for running program, wherein described program executes above-mentioned any when running
Keyword appraisal procedure.
By above-mentioned technical proposal, keyword appraisal procedure provided by the invention and device are obtaining keyword to be assessed
At least one jump path after, jump path according at least one of keyword to be assessed, obtain being used to indicate pass to be assessed
Keyword jumps statistical result to the contribution margin of target word, keyword to be assessed is assessed according to statistical result is jumped, relative to existing
Have in terms of source word and target word and assess for keyword to be assessed, realizes the tribute according to keyword to be assessed to target word
Value is offered to assess keyword to be assessed.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
A kind of flow chart for the keyword appraisal procedure that the exemplary embodiment that Fig. 1 shows the disclosure provides;
Fig. 2 shows the schematic diagrames for jumping path that the exemplary embodiment of the disclosure provides;
Another flow chart for the keyword appraisal procedure that the exemplary embodiment that Fig. 3 shows the disclosure provides;
A kind of structural schematic diagram for the keyword assessment device that the exemplary embodiment that Fig. 4 shows the disclosure provides;
Another structural schematic diagram for the keyword assessment device that the exemplary embodiment that Fig. 5 shows the disclosure provides.
Specific embodiment
The exemplary embodiment of the disclosure evaluates keyword to be assessed from the aspect that jumps of keyword to target word
To the contribution margin of target word, to assess the contribution margin of target word keyword to be assessed according to keyword to be assessed.
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
Referring to Fig. 1, a kind of process of the keyword appraisal procedure provided it illustrates the exemplary embodiment of the disclosure
Figure, the keyword appraisal procedure assess keyword to be assessed from contribution margin of the keyword to be assessed to target word, specifically
May comprise steps of:
101: obtain keyword to be assessed at least one jumps path.
Wherein, path is jumped using keyword to be assessed as starting point, using the target word in target phrase as terminal, it may be assumed that is jumped
Turning path is the path passed through from keyword to be assessed to target word, and the keyword to be assessed can be at least through once jumping
Jump to target word.
As shown in Fig. 2, A is keyword to be assessed in Fig. 2, D is a target word in target group, keyword to be assessed
A to target word D has three to jump path, this three jump path and are respectively: keyword A to be assessed successively pass through keyword A and
Keyword C jumps to target word D (this number of hops for jumping path is three times);Keyword A to be assessed is jumped by keyword C
Go to target word D (this number of hops for jumping path is twice);Keyword A to be assessed jumps directly to target word (i.e. not
By other keywords, this number of hops for jumping path is primary).
For target phrase, target word and keyword to be assessed, target word is the summary of user's expectation target object
Word, as user is searching for some target product (a kind of feasible pattern of target object) --- when one-piece dress, target word is then to connect
The summary word of clothing skirt, such as " the short design of scattered small flowers and plants of one-piece dress female's yarn matter ", target phrase is then the set of target word, can be different user
Target word set, of course for users ' individualized requirement is met, target phrase can be the target word for sole user
Set, as different user constructs corresponding target phrase respectively, and it is corresponding with user information to establish target phrase
Relationship, in order to which the lookup of succeeding target phrase or target phrase are the corresponding target words of single keyword to be assessed
Set.Keyword to be assessed is then to look for other keywords in addition to target word used during target object, such as searches
The source word or jump to the medium term between target word from source word that target object uses in the process, jump path Ru above-mentioned
In keyword B and keyword C, the exemplary implementation by the disclosure is required to for the keyword to be assessed of both types
Example carries out assessment processing.
The above-mentioned acquisition modes for jumping path, target word, target phrase and keyword to be assessed include but is not limited to this public affairs
The exemplary embodiment institute illustrative fashion opened, acquisition modes may include: searching according to the lookup desired target object of user
Rope process obtains, and the specific each keyword obtained in search process is retrieving the corresponding object search of some keyword
Click event triggering specific operation (such as triggering purchase operation), then using the corresponding keyword of click event as target word,
And each pass is determined according to the click event to the corresponding object search of each keyword (such as the click time in click event)
The sequencing of keyword, this sequencing then can be used for being formed keyword and jump path to target word.
For example, each keyword in a search process has: keyword 1, keyword 2 and keyword 3 are detecting
The click event triggering purchase operation of the corresponding object search of keyword 2, then regard keyword 2 as target word, purchase operation pair
The object answered is target object, and true according to the click time in the click event to the corresponding object search of each keyword
The sequencing of these three fixed keywords is: keyword 1 to keyword 3 to keyword 2, then what is formed jumps path are as follows: crucial
1 → keyword of word, 3 → keyword 2.
In some exemplary embodiments of the disclosure, obtain keyword to be assessed at least one jumps the feasible of path
Mode is: obtaining all of each target word of keyword to be assessed into target phrase and jumps path, is not in target phrase
In the case where set with the target word of user, the path that jumps got is keyword to be assessed owning to all target words
Jump path, if target phrase be the target word of sole user set in the case where, except available keyword to be assessed arrives
The all of all target words jump except path, can also jump path using customized manner acquisition, such as determine pass to be assessed
The corresponding user information of keyword, and corresponding target phrase is searched according to user information, keyword to be assessed is obtained to the user
The all of each target word in the corresponding target phrase of information jump path.It is single keyword pair to be assessed in target phrase
In the case where the set for the target word answered, the path that jumps got is from keyword to be assessed to related with keyword to be assessed
Each target word of connection relationship jumps path, and the incidence relation refers to that keyword to be assessed can jump to target word.
In some exemplary embodiments of the disclosure, obtain keyword to be assessed at least one jumps the feasible of path
Mode is: obtain each target word of keyword to be assessed into target phrase it is all jump path after, from pass to be assessed
The all of each target word of keyword into target phrase jump in path, jump path for each target word selected part,
In selected every jump path jumped to from keyword to be assessed corresponding target word number of hops be no more than it is default
The specific value of preset times can be arranged in number according to practical application in terms of such as assessing efficiency and assessment accuracy,
It is without restriction to the exemplary embodiment of this disclosure.
Why to choose number of hops no more than preset times jump path be because are as follows: from keyword to be assessed to
Target word will appear multiple reverse skip, and this reverse skip is possible to will cause keyword to be assessed jumping to target word
Path falls into endless loop, so that the acquisition for jumping path also falls into endless loop, to can not implement the exemplary implementation of the disclosure
The technical solution that example provides.And number of hops be more than preset times to jump path small to the assessment of keyword to be assessed effect
The assessment of keyword to be assessed is acted in the path that jumps that number of hops is no more than preset times, therefore is taking into account assessment efficiency
In the case where assessment accuracy, selected every jumps path and jumps to corresponding target word from keyword to be assessed
Number of hops is no more than preset times.
Herein it should be noted is that: be the set or target phrase of the target word of different user in target phrase
In the case where being the set for the target word of sole user, each target word in target phrase may be with keyword to be assessed
There is no incidence relations, jump path so that being not present between keyword to be assessed and target word, therefore be this in target phrase
When two kinds of situations, all paths that jump of each target word of the above-mentioned acquisition keyword to be assessed into target phrase refer to: obtaining
The all of each target word relevant with keyword to be assessed in target phrase are taken to jump path.
102: jumping path according at least one of keyword to be assessed, obtain keyword to be assessed jumps statistics knot
Fruit, wherein jumping statistical result is used to indicate keyword to be assessed to the contribution margin of target word, by jumping statistical result body
Existing keyword to be assessed assists the effect of target word by other keywords.
In some exemplary embodiments of the disclosure, jumps the optional of statistical result and take the form of: jumping path
Number of hops and the item number for jumping path with identical number of hops specifically obtain every first and jump jumping time for path
Number, then calculate the item number for jumping path with identical number of hops.
It in some exemplary embodiments of the disclosure, jumps the optional of statistical result and takes the form of: it is general to jump statistics
Rate, the statistical probability that jumps can indicate that keyword to be assessed jumps to the probability of target word.In the exemplary reality of the disclosure
It applies in example, jumps statistical probability and obtained based on all paths that jump, acquisition process is as follows:
Obtain it is all jump every path for jumping path in path and jump probability, and the path in path is jumped according to every
Probability and every target word for jumping path are jumped in all destination probabilities jumped in path as target word, obtains indicating to jump
Turn statistical result jumps statistical probability.
WithThe path that expression j-th strip jumps path jumps probability, P (target
Word)Path jIndicate that j-th strip jumps the target word in path in all destination probabilities jumped in path as target word, then according to this
The calculation formula for jumping statistical probability that two parameters obtain are as follows:
M is the sum for jumping path, it was found from the calculation formula for jumping statistical probability: jumping statistical probability is all jumps for jumping path
Turn the sum of products of path probability Yu corresponding destination probability for jumping path.
The acquisition process that wherein every path for jumping path jumps probability includes: to all every jumps jumped in path
Turn path: obtaining this and jump the single that i-th of keyword jumps to i+1 keyword in path and jump probability, according to this
Item jumps all singles in path and jumps probability, obtains this and jump the path in path jumping probability, and wherein i is from 1 to N-1
Natural number, N is the sum that keyword in path is jumped where i-th keyword, and keyword to be assessed is to jump in path
First keyword, target word are the n-th keyword jumped in path.
With P (i-th of keyword → i+1 keyword)Path jIndicate that j-th strip jumps i-th of keyword in path and jumps
Single to i+1 keyword jumps probability, then the path that j-th strip jumps path jumps the calculation formula of probability are as follows:It was found from path jumps the calculation formula of probability: every jumps path
Path jump probability be this jump the product that all singles in path jump probability.
For still three shown in above-mentioned Fig. 2 jump path, it is assumed that keyword A to be assessed successively passes through keyword A and pass
Keyword C jump to target word D this jump all singles in path jump probability be followed successively by P (A → B), P (B → C) and P (C →
D), then this path for jumping path jumps probability are as follows: P (A → B) × P (B → C) × P (C → D).Likewise, for Fig. 2 institute
Three shown jump remaining two paths for jumping path in path and jump probability are as follows: P (A → D) and P (A → C) × P (C →
D).Assume again that target word D it is all jump in path as the probability of target word be P (D), then jump statistical probability are as follows:
((P (A → B) × P (B → C) × P (C → D)+P (A → D)+P (A → C) × P (C → D)) × P (D))+other;Its
He to other target words jumps probability for keyword A to be assessed, jump probability be jump path jump path probability with respectively
The product of the self-corresponding destination probability for jumping path.
Herein it should be noted is that: if being jumped in the part that had chosen when jumping path for obtaining keyword to be assessed
Path, then obtain keyword to be assessed be when jumping statistical result based on it is selected it is all jump path, rather than it is to be evaluated
Estimate that keyword is corresponding all to jump path, that is to say, that the statistical result that jumps of keyword to be assessed is based on key to be assessed
Word it is corresponding it is all jump that number of hops in path is no more than preset times jump path.
103: assessing keyword to be assessed according to statistical result is jumped, the contribution with determination keyword to be assessed to target word
Value can thus carry out the recommendation of keyword according to keyword to be assessed to the contribution margin of target word.
As contribution margin of the keyword to be assessed to target word is greater than other keywords to be assessed to the contribution margin of target word, then
Contribution margin is recommended to be greater than the keyword to be assessed of other keywords to be assessed, or can be according to keyword to be assessed to target word
Contribution margin set the contribution level of keyword to be assessed, recommend contribution level to be located at the keyword to be assessed in predetermined level,
Wherein predetermined level can be according to practical application, depending on the quantity as preset recommended keywords, to the exemplary reality of this disclosure
It is without restriction to apply example.
In some exemplary embodiments of the disclosure, is taken the form of if jumping the optional of statistical result: jumping path
Number of hops and the item number for jumping path with identical number of hops, then assess key to be assessed according to jumping statistical result
The feasible pattern of word is: obtaining default number of hops range, the corresponding item number for jumping path of the default number of hops range
Range and the corresponding contribution level of the default number of hops range;This keyword to be assessed assessed corresponding is jumped into road
The number of hops of diameter and default number of hops range, keyword to be assessed of this assessment are corresponding with identical number of hops
The item number item number range for jumping path corresponding with default number of hops range for jumping path is compared, when number of hops position
In within the scope of default number of hops, and numerical digit is when within the scope of the corresponding item number for jumping path of default number of hops range,
This is preset into the contribution level that the corresponding contribution level of number of hops range is determined as keyword to be assessed, to pass through secondary attack grade
Keyword to be assessed is embodied to the contribution margin of target word, it is to be appreciated that contribution level is higher, and contribution margin is bigger.
Wherein presetting number of hops range can be multiple, that is, set that multiple number of hops are corresponding default to be jumped time
Number range, it is corresponding to need to set corresponding item number range for each default number of hops range, this is because passing through one
The accuracy for jumping the contribution margin that path determines of number of hops is less than the contribution margin for jumping path and determining of multiple number of hops,
And because by once jumping the contribution margin for jumping to target word greater than by repeatedly jumping the contribution margin for jumping to target word, institute
It is greater than the big default number of hops range of number of hops with the small corresponding contribution level of default number of hops range of number of hops
Corresponding contribution level.
Keyword to be assessed can also be assessed using other modes in this case, as can be according to path is jumped
Number of hops and the item number for jumping path with identical number of hops, obtain the contribution score of keyword to be assessed, with described
Contribution score embodies keyword to be assessed to the contribution margin of target word, it is to be appreciated that contribution score is higher, and contribution margin is bigger.
Detailed process is as follows:
By the corresponding number of hops for jumping path of keyword to be assessed of this assessment and default number of hops range, sheet
The corresponding item number for jumping path with identical number of hops of the keyword to be assessed of secondary assessment and default number of hops range
The corresponding item number range for jumping path is compared, when number of hops is located within the scope of default number of hops, and numerical digit in
When within the scope of the default corresponding item number for jumping path of number of hops range, this is preset into corresponding contribution of number of hops range etc.
Grade is determined as the contribution level of keyword to be assessed.After obtaining the corresponding contribution level of each number of hops, according to acquisition
The contribution weight of contribution level and acquired contribution level obtains contribution score, and wherein contribution level is higher, and contribution weight is got over
Greatly, for the value of contribution weight, the exemplary embodiment of the disclosure is without restriction.
In some exemplary embodiments of the disclosure, is taken the form of if jumping the optional of statistical result: jumping statistics
Probability, then be according to jumping statistical result and assess the feasible pattern of keyword to be assessed: according to jumping, statistical probability assessment is to be evaluated
Keyword is estimated to the contribution margin of target word, and for example different contribution margins are default to jump statistical probability range, and acquired is jumped system
Meter probability is compared with statistical probability range is jumped, and determines that acquired jumping jumps statistical probability model locating for statistical probability
It encloses, jumps the corresponding contribution margin of statistical probability range as the contribution margin of keyword to be assessed, wherein different tributes for locating for it
The corresponding statistical probability range that jumps of value is offered depending on practical application, the exemplary embodiment of this disclosure is not limited
System.
Or it is not default jump statistical probability range in the case where, different keywords to be assessed can be jumped into system
Meter probability is compared, and the contribution margin for jumping statistical probability for jumping statistical probability greater than other keywords to be assessed is greater than other
Keyword to be assessed.
From above-mentioned technical proposal it is found that above-mentioned keyword appraisal procedure is jumped in obtain keyword to be assessed at least one
Behind path, path is jumped according at least one of keyword to be assessed, obtains being used to indicate keyword to be assessed to target word
Contribution margin jumps statistical result, keyword to be assessed is assessed according to statistical result is jumped, relative to existing from source word and mesh
It is assessed for keyword to be assessed in terms of mark word, realization assesses the contribution margin of target word according to keyword to be assessed to be evaluated
Estimate keyword.
Referring to Fig. 3, another stream of the keyword appraisal procedure provided it illustrates the exemplary embodiment of the disclosure
Cheng Tu, from keyword to be assessed to the source effect of the contribution margin of target word, keyword to be assessed and keyword to be assessed
These three aspects of transformation, which are set out, assesses keyword to be assessed, specifically may comprise steps of:
301: obtain keyword to be assessed at least one jumps path, wherein jumping path with keyword to be assessed and being
Initial point, using the target word in target phrase as terminal.
302: jumping path according at least one of keyword to be assessed, obtain keyword to be assessed jumps statistics knot
Fruit, wherein jumping statistical result is used to indicate keyword to be assessed to the contribution margin of target word, by jumping statistical result body
Existing keyword to be assessed assists the effect of target word by other keywords.
In an exemplary embodiment of the disclosure, the implementation process and explanation of step 301 and step 302 please refer to step
101 and step 102, the exemplary embodiment of this disclosure is no longer illustrated.
303: obtaining the source statistical result of keyword to be assessed and the direct conversion results of keyword to be assessed, wherein source
Head statistical result is used to indicate keyword to be assessed and acts on as the source of source word, and direct conversion results are used to indicate to be assessed
Transformation of the keyword as target word.
In some exemplary embodiments of the disclosure, the optional form of expression of the source statistical result of keyword to be assessed
Be: the optional of direct conversion results of number of the keyword to be assessed as source word, keyword to be assessed takes the form of: to
Assess number of the keyword as target word.
In some exemplary embodiments of the disclosure, the optional form of expression of the source statistical result of keyword to be assessed
Be: source probability of the keyword to be assessed as source word, acquisition process, which may is that, obtains keyword to be assessed as source
The total degree that the number of word and the keyword to be assessed occur, according to keyword to be assessed as the number of source word and
The total degree that the keyword to be assessed occurs, obtains source probability of the keyword to be assessed as source word;Likewise, to be evaluated
The optional of direct conversion results for estimating keyword takes the form of: destination probability of the keyword to be assessed as target word obtains
It takes process may is that obtain total time that keyword to be assessed occurs as the number of target word and the keyword to be assessed
Number obtains to be evaluated according to the total degree that keyword to be assessed occurs as the number of target word and the keyword to be assessed
Estimate destination probability of the keyword as target word.
304: according to statistical result, source statistical result and direct conversion results are jumped, keyword to be assessed is assessed, thus
Realize the conversion from keyword to be assessed to the source effect and keyword to be assessed of the contribution margin, keyword to be assessed of target word
It sets out in terms of acting on these three and assesses keyword to be assessed, assess accuracy relative to improving for single aspect.
It is according to a kind of feasible pattern for assessing keyword to be assessed in terms of above three wherein: is tied according to statistics is jumped
Fruit, direct conversion results, jumps corresponding first weight of statistical result, source statistical result corresponding at source statistical result
Two weights and the corresponding third weight of direct conversion results obtain the comprehensive assessment effect of keyword to be assessed, and according to be evaluated
The comprehensive assessment effect for estimating keyword, assesses keyword to be assessed.
For example, it is assumed that jumping statistical result is P (keyword to be assessed)Secondary attack, source statistical result is P (key to be assessed
Word)Source, direct conversion results are P (keyword to be assessed)It is straight to turn, the first weight is a, and the second weight is b, and third weight is c, then
The calculation formula of comprehensive assessment effect are as follows:
P (keyword to be assessed)Secondary attack× a+P (keyword to be assessed)Source× b+P (keyword to be assessed)It is straight to turn× c, i.e., will be comprehensive
Assessment score is closed to act on as comprehensive assessment, in the case where comprehensive assessment score is bigger, the comprehensive function of keyword to be assessed
It is bigger.For the value of the first weight, the second weight and third weight can depending on practical application, the disclosure it is exemplary
Embodiment is without restriction.
From above-mentioned technical proposal it is found that above-mentioned keyword appraisal procedure is jumped in obtain keyword to be assessed at least one
Behind path, path is jumped according at least one of keyword to be assessed, obtains being used to indicate keyword to be assessed to target word
Contribution margin jumps statistical result, and obtains the source statistical result of keyword to be assessed and the direct conversion of keyword to be assessed
As a result, according to jumping statistical result, source statistical result and direct conversion results, to assess keyword to be assessed, realize to
Assess keyword to the transformation of the source effect of the contribution margin of target word, keyword to be assessed and keyword to be assessed this three
A aspect assesses keyword to be assessed, and then improves assessment accuracy.
Corresponding with above method embodiment, the present invention also provides a kind of keywords to assess device.
As shown in figure 4, a kind of keyword provided in an embodiment of the present invention assesses device, it may include: path acquiring unit
100, statistic unit 200 and assessment unit 300 are jumped,
The path acquiring unit 100, at least one for obtaining keyword to be assessed jumps path;
Wherein, path is jumped using keyword to be assessed as starting point, using the target word in target phrase as terminal, it may be assumed that is jumped
Turning path is the path passed through from keyword to be assessed to target word, and the keyword to be assessed can be at least through once jumping
Jump to target word.
For target phrase, target word and keyword to be assessed, target word is the summary of user's expectation target object
Word, as user is searching for some target product (a kind of feasible pattern of target object) --- when one-piece dress, target word is then to connect
The summary word of clothing skirt, such as " the short design of scattered small flowers and plants of one-piece dress female's yarn matter ", target phrase is then the set of target word, can be different user
Target word set, of course for users ' individualized requirement is met, target phrase can be the target word for sole user
Set, as different user constructs corresponding target phrase respectively, and it is corresponding with user information to establish target phrase
Relationship, in order to which the lookup of succeeding target phrase or target phrase are the corresponding target words of single keyword to be assessed
Set.Keyword to be assessed is then to look for other keywords in addition to target word used during target object, such as searches
The source word that uses during target object jumps to medium term between target word from source word.
The above-mentioned acquisition modes for jumping path, target word, target phrase and keyword to be assessed include but is not limited to this public affairs
The exemplary embodiment institute illustrative fashion opened, acquisition modes may include: searching according to the lookup desired target object of user
Rope process obtains, and the specific each keyword obtained in search process is retrieving the corresponding object search of some keyword
Click event triggering specific operation (such as triggering purchase operation), then using the corresponding keyword of click event as target word,
And each pass is determined according to the click event to the corresponding object search of each keyword (such as the click time in click event)
The sequencing of keyword, this sequencing then can be used for being formed keyword and jump path to target word.
Wherein, the path acquiring unit 100 may include: that All Paths obtain subelement and path selection subelement,
The All Paths obtain subelement, for obtaining each target of the keyword to be assessed into target phrase
The all of word jump path;
Choose subelement, the institute for each target word from the keyword to be assessed into target phrase in the path
It jumps in path, jumps path for each target word selected part, wherein selected every jumps path from described to be evaluated
Estimate keyword and jumps to the number of hops of corresponding target word no more than preset times.
Why to choose number of hops no more than preset times jump path be because are as follows: from keyword to be assessed to
Target word will appear multiple reverse skip, and this reverse skip is possible to will cause keyword to be assessed jumping to target word
Path falls into endless loop, so that the acquisition for jumping path also falls into endless loop, to can not implement the exemplary implementation of the disclosure
The technical solution that example provides.And number of hops be more than preset times to jump path small to the assessment of keyword to be assessed effect
The assessment of keyword to be assessed is acted in the path that jumps that number of hops is no more than preset times, therefore is taking into account assessment efficiency
In the case where assessment accuracy, selected every jumps path and jumps to corresponding target word from keyword to be assessed
Number of hops is no more than preset times.
Herein it should be noted is that: be the set or target phrase of the target word of different user in target phrase
In the case where being the set for the target word of sole user, each target word in target phrase may be with keyword to be assessed
There is no incidence relations, jump path so that being not present between keyword to be assessed and target word, therefore be this in target phrase
When two kinds of situations, all paths that jump of each target word of the above-mentioned acquisition keyword to be assessed into target phrase refer to: obtaining
The all of each target word relevant with keyword to be assessed in target phrase are taken to jump path.
It is described to jump statistic unit 200, for jumping path according at least one of the keyword to be assessed, obtain institute
That states keyword to be assessed jumps statistical result, jumps statistical result wherein described and is used to indicate the keyword to be assessed to institute
State the contribution margin of target word;
Wherein, described to jump statistic unit 200, it may include: to jump probability to obtain subelement and statistical probability acquisition
Unit,
In some exemplary embodiments of the disclosure, jumps the optional of statistical result and take the form of: jumping path
Number of hops and the item number for jumping path with identical number of hops specifically obtain every first and jump jumping time for path
Number, then calculate the item number for jumping path with identical number of hops.
The probability that jumps obtains subelement, selected all jump in path every for obtaining and jumps the road in path
Diameter jumps probability;
The statistical probability obtains subelement, and the path for jumping path according to described every jumps probability and every jump
Turn the target word in path in all destination probabilities jumped in path as target word, indicated described in jump statistical result
Jump statistical probability.
Further, the probability that jumps obtains subelement, can be specifically used for: all jumping in path to selected
Every jumps path:
It obtains this and jumps the single that i-th of keyword jumps to i+1 keyword in path and jump probability, according to this
Item jumps all singles in path and jumps probability, obtains this and jump the path in path jumping probability, and wherein i is from 1 to N-1
Natural number, the N is the sum that keyword in path is jumped where i-th of keyword, and the keyword to be assessed is
First jumped in path the keyword, the target word are the n-th keyword jumped in path.
The assessment unit 300 assesses the keyword to be assessed for jumping statistical result according to.
As contribution margin of the keyword to be assessed to target word is greater than other keywords to be assessed to the contribution margin of target word, then
Contribution margin is recommended to be greater than the keyword to be assessed of other keywords to be assessed, or can be according to keyword to be assessed to target word
Contribution margin set the contribution level of keyword to be assessed, recommend contribution level to be located at the keyword to be assessed in predetermined level,
Wherein predetermined level can be according to practical application, depending on the quantity as preset recommended keywords, to the exemplary reality of this disclosure
It is without restriction to apply example.
From above-mentioned technical proposal it is found that above-mentioned keyword assessment device is jumped in obtain keyword to be assessed at least one
Behind path, path is jumped according at least one of keyword to be assessed, obtains being used to indicate keyword to be assessed to target word
Contribution margin jumps statistical result, keyword to be assessed is assessed according to statistical result is jumped, relative to existing from source word and mesh
It is assessed for keyword to be assessed in terms of mark word, realization assesses the contribution margin of target word according to keyword to be assessed to be evaluated
Estimate keyword.
As shown in figure 5, another kind keyword provided in an embodiment of the present invention assesses device, on device basic shown in Fig. 4,
It can also include: result acquiring unit 400, for obtaining the source statistical result of the keyword to be assessed and described to be assessed
The direct conversion results of keyword, wherein the source statistical result is used to indicate the keyword to be assessed as source word
Source effect, the direct conversion results are used to indicate transformation of the keyword to be assessed as the target word;
The assessment unit 300 can be specifically used for jumping statistical result, the source statistical result and institute according to
Direct conversion results are stated, the keyword to be assessed is assessed.
Further, the assessment unit 300 may include: that comprehensive assessment subelement and keyword assess subelement,
The comprehensive assessment subelement, for jumped according to statistical result, the source statistical result, it is described directly
Conversion results described jump corresponding first weight of statistical result, corresponding second weight of the source statistical result and described
The corresponding third weight of direct conversion results obtains the comprehensive assessment effect of the keyword to be assessed;
The keyword assesses subelement, for being acted on according to the comprehensive assessment of the keyword to be assessed, described in assessment
Keyword to be assessed.
In some exemplary embodiments of the disclosure, the optional form of expression of the source statistical result of keyword to be assessed
Be: the optional of direct conversion results of number of the keyword to be assessed as source word, keyword to be assessed takes the form of: to
Assess number of the keyword as target word.
In some exemplary embodiments of the disclosure, the optional form of expression of the source statistical result of keyword to be assessed
Be: source probability of the keyword to be assessed as source word, acquisition process, which may is that, obtains keyword to be assessed as source
The total degree that the number of word and the keyword to be assessed occur, according to keyword to be assessed as the number of source word and
The total degree that the keyword to be assessed occurs, obtains source probability of the keyword to be assessed as source word;Likewise, to be evaluated
The optional of direct conversion results for estimating keyword takes the form of: destination probability of the keyword to be assessed as target word obtains
It takes process may is that obtain total time that keyword to be assessed occurs as the number of target word and the keyword to be assessed
Number obtains to be evaluated according to the total degree that keyword to be assessed occurs as the number of target word and the keyword to be assessed
Estimate destination probability of the keyword as target word.
It is according to a kind of feasible pattern for assessing keyword to be assessed in terms of above three wherein: is tied according to statistics is jumped
Fruit, direct conversion results, jumps corresponding first weight of statistical result, source statistical result corresponding at source statistical result
Two weights and the corresponding third weight of direct conversion results obtain the comprehensive assessment effect of keyword to be assessed, and according to be evaluated
The comprehensive assessment effect for estimating keyword, assesses keyword to be assessed.
From above-mentioned technical proposal it is found that above-mentioned keyword assessment device is jumped in obtain keyword to be assessed at least one
Behind path, path is jumped according at least one of keyword to be assessed, obtains being used to indicate keyword to be assessed to target word
Contribution margin jumps statistical result, and obtains the source statistical result of keyword to be assessed and the direct conversion of keyword to be assessed
As a result, according to jumping statistical result, source statistical result and direct conversion results, to assess keyword to be assessed, realize to
Assess keyword to the transformation of the source effect of the contribution margin of target word, keyword to be assessed and keyword to be assessed this three
A aspect assesses keyword to be assessed, and then improves assessment accuracy.
Keyword assessment device includes processor and memory, above-mentioned path acquiring unit, jump statistic unit and
Assessment unit etc. stores in memory as program unit, executes above procedure list stored in memory by processor
Member realizes corresponding function.
Include kernel in processor, is gone in memory to transfer corresponding program unit by kernel.Kernel can be set one
Or more, by adjusting kernel parameter come realize keyword assess.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flashRAM), memory includes at least one storage
Chip.
The embodiment of the invention provides a kind of storage mediums, are stored thereon with program, real when which is executed by processor
The existing keyword Evaluation Method.
The embodiment of the invention provides a kind of processor, the processor is for running program, wherein described program operation
Keyword appraisal procedure described in Shi Zhihang.
The embodiment of the invention provides a kind of equipment, equipment include processor, memory and storage on a memory and can
The program run on a processor, processor perform the steps of when executing program
Obtain keyword to be assessed at least one jumps path, wherein described jump path with the keyword to be assessed
For starting point, using the target word in target phrase as terminal;
Path is jumped according at least one of the keyword to be assessed, obtain the keyword to be assessed jumps statistics
As a result, jumping statistical result described in wherein is used to indicate the keyword to be assessed to the contribution margin of the target word;
The keyword to be assessed is assessed according to the statistical result that jumps.
Optionally, it can also be performed the steps of when processor executes program
The source statistical result of the keyword to be assessed and the direct conversion results of the keyword to be assessed are obtained,
Described in source statistical result be used to indicate the keyword to be assessed as source word source act on, it is described directly conversion knot
Fruit is used to indicate transformation of the keyword to be assessed as the target word;
The statistical result that jumps according to assesses the keyword to be assessed, comprising: jumps statistics knot according to described
Fruit, the source statistical result and the direct conversion results assess the keyword to be assessed.
Optionally, described that statistical result, the source statistical result and the direct conversion results are jumped according to, it comments
Estimate the keyword to be assessed, comprising:
It is tied according to statistical result, the source statistical result, the direct conversion results, the statistics that jumps of jumping
Corresponding first weight of fruit, corresponding second weight of the source statistical result and the corresponding third power of the direct conversion results
Weight obtains the comprehensive assessment effect of the keyword to be assessed;
It is acted on according to the comprehensive assessment of the keyword to be assessed, assesses the keyword to be assessed.
Optionally, at least one of the acquisition keyword to be assessed jumps path, comprising:
It obtains all of each target word of the keyword to be assessed into target phrase and jumps path;
From the keyword to be assessed, all of each target word into target phrase are jumped in path, are each target
Word selected part jumps path, wherein selected every jumps path and jumps to corresponding mesh from the keyword to be assessed
The number of hops for marking word is no more than preset times.
Optionally, at least one according to the keyword to be assessed jumps path, obtains the key to be assessed
Word jumps statistical result, comprising:
It obtains and selected all jump every path for jumping path in path and jump probability;
The path for jumping path according to described every jumps probability and every target word for jumping path jumps road all
As the destination probability of target word in diameter, indicated described in jump statistical result jump statistical probability.
It is optionally, all selected by the acquisition to jump every path for jumping path in path and jump probability, comprising:
Path is jumped to selected all every jumped in path:
It obtains this and jumps the single that i-th of keyword jumps to i+1 keyword in path and jump probability, according to this
Item jumps all singles in path and jumps probability, obtains this and jump the path in path jumping probability, and wherein i is from 1 to N-1
Natural number, the N is the sum that keyword in path is jumped where i-th of keyword, and the keyword to be assessed is
First jumped in path the keyword, the target word are the n-th keyword jumped in path.
Equipment herein can be server, PC, PAD, mobile phone etc..
Present invention also provides a kind of computer program products, when executing on data processing equipment, are adapted for carrying out just
The program of beginningization there are as below methods step:
Obtain keyword to be assessed at least one jumps path, wherein described jump path with the keyword to be assessed
For starting point, using the target word in target phrase as terminal;
Path is jumped according at least one of the keyword to be assessed, obtain the keyword to be assessed jumps statistics
As a result, jumping statistical result described in wherein is used to indicate the keyword to be assessed to the contribution margin of the target word;
The keyword to be assessed is assessed according to the statistical result that jumps.
Optionally, above procedure can also initialize following steps:
The source statistical result of the keyword to be assessed and the direct conversion results of the keyword to be assessed are obtained,
Described in source statistical result be used to indicate the keyword to be assessed as source word source act on, it is described directly conversion knot
Fruit is used to indicate transformation of the keyword to be assessed as the target word;
The statistical result that jumps according to assesses the keyword to be assessed, comprising: jumps statistics knot according to described
Fruit, the source statistical result and the direct conversion results assess the keyword to be assessed.
Optionally, described that statistical result, the source statistical result and the direct conversion results are jumped according to, it comments
Estimate the keyword to be assessed, comprising:
It is tied according to statistical result, the source statistical result, the direct conversion results, the statistics that jumps of jumping
Corresponding first weight of fruit, corresponding second weight of the source statistical result and the corresponding third power of the direct conversion results
Weight obtains the comprehensive assessment effect of the keyword to be assessed;
It is acted on according to the comprehensive assessment of the keyword to be assessed, assesses the keyword to be assessed.
Optionally, at least one of the acquisition keyword to be assessed jumps path, comprising:
It obtains all of each target word of the keyword to be assessed into target phrase and jumps path;
From the keyword to be assessed, all of each target word into target phrase are jumped in path, are each target
Word selected part jumps path, wherein selected every jumps path and jumps to corresponding mesh from the keyword to be assessed
The number of hops for marking word is no more than preset times.
Optionally, at least one according to the keyword to be assessed jumps path, obtains the key to be assessed
Word jumps statistical result, comprising:
It obtains and selected all jump every path for jumping path in path and jump probability;
The path for jumping path according to described every jumps probability and every target word for jumping path jumps road all
As the destination probability of target word in diameter, indicated described in jump statistical result jump statistical probability.
It is optionally, all selected by the acquisition to jump every path for jumping path in path and jump probability, comprising:
Path is jumped to selected all every jumped in path:
It obtains this and jumps the single that i-th of keyword jumps to i+1 keyword in path and jump probability, according to this
Item jumps all singles in path and jumps probability, obtains this and jump the path in path jumping probability, and wherein i is from 1 to N-1
Natural number, the N is the sum that keyword in path is jumped where i-th of keyword, and the keyword to be assessed is
First jumped in path the keyword, the target word are the n-th keyword jumped in path.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flashRAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including element
There is also other identical elements in process, method, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can provide as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The above is only embodiments herein, are not intended to limit this application.To those skilled in the art,
Various changes and changes are possible in this application.It is all within the spirit and principles of the present application made by any modification, equivalent replacement,
Improve etc., it should be included within the scope of the claims of this application.
Claims (10)
1. a kind of keyword appraisal procedure, which is characterized in that the described method includes:
Obtain keyword to be assessed at least one jumps path, jumps path wherein described with the keyword to be assessed and is
Initial point, using the target word in target phrase as terminal;
Path is jumped according at least one of the keyword to be assessed, obtain the keyword to be assessed jumps statistics knot
Fruit jumps statistical result and is used to indicate the keyword to be assessed to the contribution margin of the target word wherein described;
The keyword to be assessed is assessed according to the statistical result that jumps.
2. the method according to claim 1, wherein the method also includes:
The source statistical result of the keyword to be assessed and the direct conversion results of the keyword to be assessed are obtained, wherein institute
The source effect that source statistical result is used to indicate the keyword to be assessed as source word is stated, the direct conversion results are used
In transformation of the instruction keyword to be assessed as the target word;
The statistical result that jumps according to assesses the keyword to be assessed, comprising: jumps statistical result, institute according to described
Source statistical result and the direct conversion results are stated, the keyword to be assessed is assessed.
3. according to the method described in claim 2, it is characterized in that, described jump statistical result, source system according to
Result and the direct conversion results are counted, the keyword to be assessed is assessed, comprising:
It jumps statistical result according to described, the source statistical result, the direct conversion results, described jump statistical result pair
The first weight, corresponding second weight of the source statistical result and the corresponding third weight of the direct conversion results answered,
Obtain the comprehensive assessment effect of the keyword to be assessed;
It is acted on according to the comprehensive assessment of the keyword to be assessed, assesses the keyword to be assessed.
4. the method according to any one of described claims 1 to 3, which is characterized in that described to obtain key to be assessed
At least one of word jumps path, comprising:
It obtains all of each target word of the keyword to be assessed into target phrase and jumps path;
From the keyword to be assessed, all of each target word into target phrase are jumped in path, are each target selected ci poem
Part is taken to jump path, wherein selected every jumps path and jumps to corresponding target word from the keyword to be assessed
Number of hops be no more than preset times.
5. according to the method described in claim 4, it is characterized in that, described jump according at least one of the keyword to be assessed
Turn path, obtain the keyword to be assessed jumps statistical result, comprising:
It obtains and selected all jump every path for jumping path in path and jump probability;
The path for jumping path according to described every jumps probability and every target word for jumping path jumps in path all
As the destination probability of target word, indicated described in jump statistical result jump statistical probability.
6. according to the method described in claim 5, it is characterized in that, all selected by the acquisition jump every jump in path
The path for turning path jumps probability, comprising: jumps path to selected all every jumped in path:
It obtains this and jumps the single that i-th of keyword jumps to i+1 keyword in path and jump probability, jumped according to this
All singles turned in path jump probability, obtain this and jump the path in path jumping probability, wherein i be from 1 to N-1 from
So number, the N are the sum that i-th of keyword place jumps keyword in path, and the keyword to be assessed is described
First keyword in path is jumped, the target word is the n-th keyword jumped in path.
7. a kind of keyword assesses device, which is characterized in that described device include: path acquiring unit, jump statistic unit and
Assessment unit,
The path acquiring unit, at least one for obtaining keyword to be assessed jumps path, wherein described jump path
Using the keyword to be assessed as starting point, using the target word in target phrase as terminal;
It is described to jump statistic unit, for jumping path according at least one of the keyword to be assessed, obtain described to be evaluated
That estimates keyword jumps statistical result, jumps statistical result wherein described and is used to indicate the keyword to be assessed to the target
The contribution margin of word;
The assessment unit assesses the keyword to be assessed for jumping statistical result according to.
8. device according to claim 7, which is characterized in that described device further include: result acquiring unit, for obtaining
The direct conversion results of the source statistical result of the keyword to be assessed and the keyword to be assessed, wherein the source is united
Meter result is used to indicate the keyword to be assessed and acts on as the source of source word, and the direct conversion results are used to indicate institute
State transformation of the keyword to be assessed as the target word;
The assessment unit, specifically for jumping statistical result, the source statistical result and the direct conversion according to
As a result, the assessment keyword to be assessed.
9. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein run in described program
When control the storage medium where equipment execute such as keyword appraisal procedure of any of claims 1-6.
10. a kind of processor, which is characterized in that the processor is for running program, wherein executed such as when described program is run
Keyword appraisal procedure of any of claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710882220.5A CN110069542B (en) | 2017-09-26 | 2017-09-26 | Keyword evaluation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710882220.5A CN110069542B (en) | 2017-09-26 | 2017-09-26 | Keyword evaluation method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110069542A true CN110069542A (en) | 2019-07-30 |
CN110069542B CN110069542B (en) | 2021-06-29 |
Family
ID=67364373
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710882220.5A Active CN110069542B (en) | 2017-09-26 | 2017-09-26 | Keyword evaluation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110069542B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103164521A (en) * | 2013-03-11 | 2013-06-19 | 亿赞普(北京)科技有限公司 | Keyword calculation method and device based on user browse and search actions |
CN104731867A (en) * | 2015-02-27 | 2015-06-24 | 百度在线网络技术(北京)有限公司 | Object clustering method and device |
CN105045901A (en) * | 2015-08-05 | 2015-11-11 | 百度在线网络技术(北京)有限公司 | Search keyword push method and device |
US20160085757A1 (en) * | 2014-09-22 | 2016-03-24 | Casio Computer Co., Ltd. | Information display device, information display method, and storage medium |
CN105808725A (en) * | 2016-03-08 | 2016-07-27 | 腾讯科技(深圳)有限公司 | Method and apparatus for processing application information |
US20170091814A1 (en) * | 2015-09-25 | 2017-03-30 | Microsoft Technology Licensing, Llc | Compressing an Original Query while Preserving its Intent |
-
2017
- 2017-09-26 CN CN201710882220.5A patent/CN110069542B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103164521A (en) * | 2013-03-11 | 2013-06-19 | 亿赞普(北京)科技有限公司 | Keyword calculation method and device based on user browse and search actions |
US20160085757A1 (en) * | 2014-09-22 | 2016-03-24 | Casio Computer Co., Ltd. | Information display device, information display method, and storage medium |
CN104731867A (en) * | 2015-02-27 | 2015-06-24 | 百度在线网络技术(北京)有限公司 | Object clustering method and device |
CN105045901A (en) * | 2015-08-05 | 2015-11-11 | 百度在线网络技术(北京)有限公司 | Search keyword push method and device |
US20170091814A1 (en) * | 2015-09-25 | 2017-03-30 | Microsoft Technology Licensing, Llc | Compressing an Original Query while Preserving its Intent |
CN105808725A (en) * | 2016-03-08 | 2016-07-27 | 腾讯科技(深圳)有限公司 | Method and apparatus for processing application information |
Non-Patent Citations (1)
Title |
---|
周丽杰等: "基于改进的TF-IDF方法的文本相似度算法研究", 《泰山学院学报》 * |
Also Published As
Publication number | Publication date |
---|---|
CN110069542B (en) | 2021-06-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI777010B (en) | Prediction of information conversion rate, information recommendation method and device | |
Kwakkel et al. | Developing dynamic adaptive policy pathways: a computer-assisted approach for developing adaptive strategies for a deeply uncertain world | |
TWI360754B (en) | Web page analysis using multiple graphs | |
Qian et al. | Understanding public opinions on social media for financial sentiment analysis using AI-based techniques | |
CN107590690B (en) | Data processing method and device and server | |
CN110019668A (en) | A kind of text searching method and device | |
CN110008397B (en) | Recommendation model training method and device | |
US11468291B2 (en) | Method for protecting a machine learning ensemble from copying | |
CN108550046A (en) | A kind of resource and market recommendation method, apparatus and electronic equipment | |
CN106920119A (en) | The evaluation method and device of a kind of user's value | |
CN108062342A (en) | The recommendation method and device of application program | |
CN108268534A (en) | Propagating influence computational methods and device | |
CN107193824B (en) | Abnormal data detection method and device | |
CN109359346A (en) | A kind of heat load prediction method, apparatus, readable medium and electronic equipment | |
Huang et al. | A filter approach to feature selection based on mutual information | |
CN115829159B (en) | Social media vermicelli newly-added prediction method, device, equipment and storage medium | |
CN112016840A (en) | Method, device, equipment and storage medium for selecting index data | |
CN109559245B (en) | Method and device for identifying specific user | |
CN107665208A (en) | User preference measure and device | |
CN109886299A (en) | A kind of user draws a portrait method, apparatus, readable storage medium storing program for executing and terminal device | |
CN110069542A (en) | Keyword appraisal procedure and device | |
CN110472143A (en) | A kind of information-pushing method, device, readable storage medium storing program for executing and terminal device | |
CN108062338A (en) | A kind of method and device of the homing capability of the evaluation function page | |
CN112507244B (en) | Social data recommendation method and device, distributed computing cluster and storage medium | |
CN110309273A (en) | Answering method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 100080 No. 401, 4th Floor, Haitai Building, 229 North Fourth Ring Road, Haidian District, Beijing Applicant after: Beijing Guoshuang Technology Co.,Ltd. Address before: 100086 Beijing city Haidian District Shuangyushu Area No. 76 Zhichun Road cuigongfandian 8 layer A Applicant before: Beijing Guoshuang Technology Co.,Ltd. |
|
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |