CN110069542B - Keyword evaluation method and device - Google Patents
Keyword evaluation method and device Download PDFInfo
- Publication number
- CN110069542B CN110069542B CN201710882220.5A CN201710882220A CN110069542B CN 110069542 B CN110069542 B CN 110069542B CN 201710882220 A CN201710882220 A CN 201710882220A CN 110069542 B CN110069542 B CN 110069542B
- Authority
- CN
- China
- Prior art keywords
- keyword
- evaluated
- jump
- path
- target word
- 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.)
- Active
Links
Images
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 keyword evaluation method and a keyword evaluation device, which can acquire at least one jump path of a keyword to be evaluated, wherein the jump path takes the keyword to be evaluated as a starting point and takes a target word in a target word group as an end point; obtaining a skipping statistical result of the keyword to be evaluated according to at least one skipping path of the keyword to be evaluated, wherein the skipping statistical result is used for indicating the contribution value of the keyword to be evaluated to the target word; and evaluating the keywords to be evaluated according to the jump statistical result, and evaluating the keywords to be evaluated according to the contribution value of the keywords to be evaluated to the target words compared with the conventional method for evaluating the keywords to be evaluated from the aspects of source words and target words.
Description
Technical Field
The invention relates to the technical field of internet application, in particular to a keyword evaluation method and device.
Background
At present, two methods for evaluating keywords are provided, wherein one method is to evaluate the conversion function of the keywords as target words; the other is to evaluate the source effect of the keywords. For example, for keywords released by a PC (Personal Computer) end of all SEMs (Search Engine Marketing) of a client, when evaluating the keywords, any keyword K may be selected, and all Search results related to the keyword K, such as the number of times that the keyword K is used as a source word (i.e., as a first keyword for a Search) or the number of times that the keyword K is used as a target word, may be obtained.
However, when the keyword K is used as a target word, in the process of jumping from the source word to the target word, the source word may jump to one or more other keywords first, and then jump to the target word. In the process of the jump, the keywords between the source words and the target words also play a certain contribution. If there is no keyword between the source word and the target word, the conversion function of the keyword K as the target word will be reduced.
Therefore, the method for evaluating the keyword K by using the times of the keyword K as the source word and the times of the keyword K as the target word ignores the contribution of the keyword to the target word.
Disclosure of Invention
In view of the above problems, the present invention is proposed to provide a keyword evaluation method and apparatus that overcomes or at least partially solves the above problems, and the technical solution is as follows:
a keyword evaluation method, the method comprising:
acquiring at least one jump path of a keyword to be evaluated, wherein the jump path takes the keyword to be evaluated as a starting point and takes a target word in a target word group as an end point;
obtaining a skipping statistical result of the keyword to be evaluated according to at least one skipping path of the keyword to be evaluated, wherein the skipping statistical result is used for indicating the contribution value of the keyword to be evaluated to the target word;
and evaluating the keywords to be evaluated according to the skip statistical result.
Optionally, the method further includes:
acquiring a source statistical result of the keyword to be evaluated and a direct conversion result of the keyword to be evaluated, wherein the source statistical result is used for indicating the keyword to be evaluated as a source function of a source word, and the direct conversion result is used for indicating the keyword to be evaluated as a conversion function of a target word;
the evaluating the keywords to be evaluated according to the skip statistic result comprises the following steps: and evaluating the keywords to be evaluated according to the skip statistical result, the source statistical result and the direct conversion result.
Optionally, the evaluating the keyword to be evaluated according to the skip statistical result, the source statistical result, and the direct conversion result includes:
obtaining a comprehensive evaluation function of the keyword to be evaluated according to the skip statistical result, the source statistical result, the direct conversion result, a first weight corresponding to the skip statistical result, a second weight corresponding to the source statistical result and a third weight corresponding to the direct conversion result;
and evaluating the keywords to be evaluated according to the comprehensive evaluation function of the keywords to be evaluated.
Optionally, the obtaining of at least one jump path of the keyword to be evaluated includes:
acquiring all jump paths from the keywords to be evaluated to each target word in the target word group;
and selecting a part of jump paths for each target word from all jump paths from the keyword to be evaluated to each target word in the target word group, wherein the jump times of each selected jump path from the keyword to be evaluated to the corresponding target word do not exceed the preset times.
Optionally, the obtaining a skip statistical result of the keyword to be evaluated according to the at least one skip path of the keyword to be evaluated includes:
acquiring the path skipping probability of each skipping path in all the selected skipping paths;
and obtaining the jump statistical probability representing the jump statistical result according to the path jump probability of each jump path and the target probability of the target word of each jump path as the target word in all the jump paths.
Optionally, the obtaining the path jump probability of each jump path in all the selected jump paths includes: for each jump path in all the selected jump paths:
obtaining the single skipping probability of the ith keyword skipping to the (i + 1) th keyword in the skipping path, and obtaining the path skipping probability of the skipping path according to all the single skipping probabilities in the skipping path, wherein i is a natural number from 1 to N-1, N is the total number of the keywords in the skipping path where the ith keyword is located, the keyword to be evaluated is the first keyword in the skipping path, and the target word is the Nth keyword in the skipping path.
A keyword evaluation apparatus, the apparatus comprising: a path acquisition unit, a jump statistic unit and an evaluation unit,
the path acquisition unit is used for acquiring at least one jump path of the keyword to be evaluated, wherein the jump path takes the keyword to be evaluated as a starting point and takes a target word in a target word group as an end point;
the skip statistical unit is used for obtaining a skip statistical result of the keyword to be evaluated according to at least one skip path of the keyword to be evaluated, wherein the skip statistical result is used for indicating a contribution value of the keyword to be evaluated to the target word;
and the evaluation unit is used for evaluating the keywords to be evaluated according to the skip statistical result.
Optionally, the apparatus further comprises: the result obtaining unit is used for obtaining a source statistical result of the keyword to be evaluated and a direct conversion result of the keyword to be evaluated, wherein the source statistical result is used for indicating the keyword to be evaluated as a source function of a source word, and the direct conversion result is used for indicating the keyword to be evaluated as a conversion function of a target word;
and the evaluation unit is specifically used for evaluating the keywords to be evaluated according to the skip statistical result, the source statistical result and the direct conversion result.
A storage medium comprising a stored program, wherein the program, when executed, controls a device on which the storage medium is located to perform any of the above-described keyword evaluation methods.
A processor configured to run a program, wherein the program performs any of the above keyword evaluation methods when running.
By means of the technical scheme, the keyword evaluation method and the keyword evaluation device provided by the invention have the advantages that after at least one jump path of the keyword to be evaluated is obtained, the jump statistical result used for indicating the contribution value of the keyword to be evaluated to the target word is obtained according to the at least one jump path of the keyword to be evaluated, the keyword to be evaluated is evaluated according to the jump statistical result, and the keyword to be evaluated is evaluated according to the contribution value of the keyword to be evaluated to the target word according to the existing evaluation of the keyword to be evaluated from the aspects of source words and target words.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 illustrates a flowchart of a keyword evaluation method provided by an exemplary embodiment of the present disclosure;
FIG. 2 shows a schematic diagram of a jump path provided by an exemplary embodiment of the present disclosure;
FIG. 3 illustrates another flow chart of a keyword evaluation method provided by an exemplary embodiment of the present disclosure;
FIG. 4 is a schematic diagram illustrating an exemplary embodiment of a keyword evaluation apparatus according to the present disclosure;
fig. 5 shows another structural diagram of the keyword evaluation apparatus provided in the exemplary embodiment of the present disclosure.
Detailed Description
The exemplary embodiment of the present disclosure evaluates the contribution value of the keyword to be evaluated to the target word from the aspect of jumping from the keyword to the target word, so as to evaluate the keyword to be evaluated according to the contribution value of the keyword to be evaluated to the target word.
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Referring to fig. 1, a flowchart of a keyword evaluation method provided by an exemplary embodiment of the present disclosure is shown, where the keyword evaluation method evaluates a keyword to be evaluated based on a contribution value of the keyword to be evaluated to a target word, and specifically includes the following steps:
101: and acquiring at least one jump path of the keyword to be evaluated.
The jumping path takes the keyword to be evaluated as a starting point and takes the target word in the target word group as an end point, namely: the jump path is a path from the keyword to be evaluated to the target word, and the keyword to be evaluated can jump to the target word at least once.
As shown in fig. 2, a is a keyword to be evaluated, D is a target word in the target group, and there are three jumping paths from the keyword a to the target word D, where the three jumping paths are: the keyword A to be evaluated jumps to a target word D through the keyword A and the keyword C in sequence (the jumping frequency of the jumping path is three times); skipping the keyword A to be evaluated to a target word D through the keyword C (the skipping frequency of the skipping path is two times); the keyword a to be evaluated jumps to the target word directly (i.e. without passing through other keywords, the jumping time of the jumping path is one time).
For a target phrase, a target word and a keyword to be evaluated, the target word is a summary word of a target object desired by a user, for example, when the user searches for a certain target product (a feasible way of the target object) -a dress, the target word is a summary word of the dress, such as "women's yarn quality short broken flowers" of the dress, and the target phrase is a set of target words, which may be a set of target words of different users. The keywords to be evaluated are other keywords except for the target word used in the process of finding the target object, such as the source word used in the process of finding the target object or the intermediate word that jumps from the source word to the target word, for example, the keywords B and the keywords C in the jump path, and both types of the keywords to be evaluated need to be evaluated by the exemplary embodiment of the present disclosure.
The obtaining method of the skip path, the target word, the target phrase and the keyword to be evaluated includes but is not limited to the method set forth in the exemplary embodiment of the disclosure, and the obtaining method may include: specifically, each keyword in the search process is acquired according to the search process of finding a target object expected by a user, a specific operation (such as a purchase operation) is triggered when a click event of the search object corresponding to a certain keyword is retrieved, the keyword corresponding to the click event is used as the target word, the sequence of each keyword is determined according to the click event (such as the click time in the click event) of the search object corresponding to each keyword, and the sequence can be used for forming a jump path from the keyword to the target word.
For example, the keywords in a search process are: the method comprises the following steps that keyword 1, keyword 2 and keyword 3, when a click event of a search object corresponding to the keyword 2 is detected to trigger a purchase operation, the keyword 2 is used as a target word, an object corresponding to the purchase operation is used as a target object, and the sequence of the three keywords is determined according to click time in the click event of the search object corresponding to each keyword: and forming a jump path from the keyword 1 to the keyword 3 to the keyword 2 as follows: keyword 1 → keyword 3 → keyword 2.
In some exemplary embodiments of the present disclosure, a feasible way to obtain at least one jumping path of a keyword to be evaluated is: the method comprises the steps of obtaining all jump paths from a keyword to be evaluated to each target word in a target phrase, obtaining all jump paths from the keyword to be evaluated to all target words when the target phrase is a set of target words of different users, obtaining all jump paths from the keyword to be evaluated to all target words in a personalized mode except for obtaining all jump paths from the keyword to be evaluated to all target words when the target phrase is a set of target words of a single user, determining user information corresponding to the keyword to be evaluated, searching a corresponding target phrase according to the user information, and obtaining all jump paths from the keyword to be evaluated to each target word in the target phrase corresponding to the user information. And under the condition that the target phrase is a set of target words corresponding to a single keyword to be evaluated, the obtained jump path is a jump path from the keyword to be evaluated to each target word having a correlation relation with the keyword to be evaluated, wherein the correlation relation means that the keyword to be evaluated can jump to the target words.
In some exemplary embodiments of the present disclosure, a feasible way to obtain at least one jumping path of a keyword to be evaluated is: after all the jump paths from the keyword to be evaluated to each target word in the target word group are obtained, a part of jump paths are selected for each target word from all the jump paths from the keyword to be evaluated to each target word in the target word group, wherein the jump times of each selected jump path from the keyword to be evaluated to the corresponding target word do not exceed the preset times, and specific values of the preset times can be set according to practical applications, such as evaluation efficiency, evaluation accuracy and the like.
The reason why the jump path with the jump times not exceeding the preset times is selected is that: multiple reverse jumps may occur from the keyword to be evaluated to the target word, and the reverse jumps may cause a jump path from the keyword to be evaluated to the target word to fall into a dead loop, so that the acquisition of the jump path also falls into the dead loop, and thus the technical scheme provided by the exemplary embodiment of the present disclosure cannot be implemented. And the evaluation function of the jump path with the jump times exceeding the preset times on the keyword to be evaluated is smaller than the evaluation function of the jump path with the jump times not exceeding the preset times on the keyword to be evaluated, so that the jump times of each selected jump path from the keyword to be evaluated to the corresponding target word do not exceed the preset times under the condition of considering evaluation efficiency and evaluation accuracy.
The points to be explained here are: under the condition that the target phrase is a set of target words of different users or the target phrase is a set of target words for a single user, each target word in the target phrase may not have an association relationship with the keyword to be evaluated, so that no jump path exists between the keyword to be evaluated and the target word, and therefore, when the target phrase is in the two conditions, obtaining all jump paths from the keyword to be evaluated to each target word in the target phrase means: and acquiring all jump paths of each target word in the target word group and having a correlation with the keyword to be evaluated.
102: and obtaining a skipping statistical result of the keyword to be evaluated according to at least one skipping path of the keyword to be evaluated, wherein the skipping statistical result is used for indicating the contribution value of the keyword to be evaluated to the target word, so that the effect of the keyword to be evaluated assisting the target word through other keywords is reflected through the skipping statistical result.
In some exemplary embodiments of the present disclosure, the alternative manifestation of the jump statistic is: the method specifically comprises the steps of firstly acquiring the jumping times of each jumping path and then calculating the number of the jumping paths with the same jumping times.
In some exemplary embodiments of the present disclosure, the alternative manifestation of the jump statistic is: a hop statistical probability, which may indicate a probability of a keyword to be evaluated jumping to a target word. In an exemplary embodiment of the present disclosure, the hop statistical probability is obtained based on all the hop paths, and the obtaining process is as follows:
and acquiring the path hopping probability of each of all the hopping paths, and acquiring the hopping statistical probability representing the hopping statistical result according to the path hopping probability of each of the hopping paths and the target probability of the target word of each of the hopping paths as the target word in all the hopping paths.
To be provided with
Path jump outline representing jth jump pathRate, P (target word)Path jAnd the target probability of the target word representing the jth jump path in all the jump paths as the target word, and the calculation formula of the jump statistical probability obtained according to the two parameters is as follows:
m is the total number of the jump paths, and the calculation formula of the jump statistical probability can be known as follows: the jump statistical probability is the sum of the product of the jump path probability of all the jump paths and the target probability of the corresponding jump path.
The process for acquiring the path jump probability of each jump path comprises the following steps: for each jump path in all jump paths: obtaining the single skipping probability of the ith keyword skipping to the (i + 1) th keyword in the skipping path, and obtaining the path skipping probability of the skipping path according to all the single skipping probabilities in the skipping path, wherein i is a natural number from 1 to N-1, N is the total number of the keywords in the skipping path where the ith keyword is located, the keyword to be evaluated is the first keyword in the skipping path, and the target word is the Nth keyword in the skipping path.
With P (i key → i +1 key)Path jThe single jump probability of jumping from the ith keyword to the (i + 1) th keyword in the jth jump path is represented, and the calculation formula of the path jump probability of the jth jump path is as follows:
the calculation formula of the path jump probability can be known as follows: the path jump probability of each jump path is the product of all single jump probabilities in the jump path.
Still taking the three jump paths shown in fig. 2 as an example, assuming that all single jump probabilities in the jump path in which the keyword a to be evaluated jumps to the target word D sequentially through the keyword a and the keyword C are P (a → B), P (B → C), and P (C → D), the path jump probability of the jump path is: p (A → B). times.P (B → C). times.P (C → D). Similarly, the path hop probability for the remaining two hop paths of the three hop paths shown in fig. 2 is: p (A → D) and P (A → C). times.P (C → D). And then, assuming that the probability that the target word D is taken as the target word in all the jump paths is P (D), the jump statistical probability is:
((P (a → B) × P (B → C) × P (C → D) + P (a → C) × P (C → D)) × P (D)) + others; the others are the jumping probabilities from the keyword A to be evaluated to other target words, and the jumping probability is the product of the jumping path probability of the jumping path and the target probability of the corresponding jumping path.
The points to be explained here are: if part of the jump paths are selected when the jump paths of the keywords to be evaluated are obtained, the jump statistical results of the keywords to be evaluated are obtained based on all the selected jump paths instead of all the jump paths corresponding to the keywords to be evaluated, that is, the jump statistical results of the keywords to be evaluated are based on the jump paths of which the jump times do not exceed the preset times in all the jump paths corresponding to the keywords to be evaluated.
103: and evaluating the keywords to be evaluated according to the skip statistical result to determine the contribution value of the keywords to be evaluated to the target word, so that the keywords can be recommended according to the contribution value of the keywords to be evaluated to the target word.
If the contribution value of the keyword to be evaluated to the target word is greater than the contribution values of other keywords to be evaluated to the target word, recommending the keyword to be evaluated whose contribution value is greater than the contribution values of other keywords to be evaluated, or setting the contribution level of the keyword to be evaluated according to the contribution value of the keyword to be evaluated to the target word, recommending the keyword to be evaluated whose contribution level is within a preset level, where the preset level may be determined according to actual application, such as the number of preset recommended keywords, and the exemplary embodiment of the present disclosure is not limited.
In some exemplary embodiments of the present disclosure, if the alternative representation of the skip statistic is: and if the jumping times of the jumping paths and the number of the jumping paths with the same jumping times are the same, the feasible way of evaluating the keywords to be evaluated according to the jumping statistical result is as follows: acquiring a preset jump time range, a number range of jump paths corresponding to the preset jump time range and a contribution level corresponding to the preset jump time range; the method comprises the steps of comparing the jump times of jump paths corresponding to keywords to be evaluated at this time with a preset jump time range, and comparing the number of jump paths with the same jump times corresponding to the keywords to be evaluated at this time with the number range of the jump paths corresponding to the preset jump time range, and when the jump times are within the preset jump time range and the number of jump paths is within the number range of the jump paths corresponding to the preset jump time range, determining the contribution level corresponding to the preset jump time range as the contribution level of the keywords to be evaluated so as to reflect the contribution value of the keywords to be evaluated to a target word through an attack level, wherein the higher the contribution level is, the larger the contribution value is.
The preset jump times range can be multiple, that is, a preset jump times range corresponding to each of the multiple jump times is set, and a corresponding number range needs to be set for each preset jump times range, because the accuracy of the contribution value determined by the jump path of one jump time is smaller than the contribution value determined by the jump paths of the multiple jump times, and because the contribution value jumped to the target word by one jump is larger than the contribution value jumped to the target word by multiple jumps, the contribution level corresponding to the preset jump times range with a small jump time is larger than the contribution level corresponding to the preset jump times range with a large jump time.
In this case, the keyword to be evaluated may also be evaluated in other manners, for example, a contribution score of the keyword to be evaluated may be obtained according to the number of hops of the hop path and the number of the hop paths having the same number of hops, and the contribution score represents a contribution value of the keyword to be evaluated to the target word, and it may be understood that the higher the contribution score is, the larger the contribution value is. The specific process is as follows:
and comparing the jumping times of the jumping paths corresponding to the evaluated keyword to be evaluated at this time with a preset jumping time range, and comparing the number of the jumping paths with the same jumping times corresponding to the evaluated keyword to be evaluated at this time with the number range of the jumping paths corresponding to the preset jumping time range, and determining the contribution level corresponding to the preset jumping time range as the contribution level of the keyword to be evaluated when the jumping times are within the preset jumping time range and the number of the jumping paths are within the number range of the jumping paths corresponding to the preset jumping time range. After obtaining the contribution level corresponding to each hop count, obtaining a contribution score according to the obtained contribution level and the contribution weight of the obtained contribution level, where the higher the contribution level is, the larger the contribution weight is, and the value of the contribution weight is not limited in the exemplary embodiment of the present disclosure.
In some exemplary embodiments of the present disclosure, if the alternative representation of the skip statistic is: and (3) skipping statistical probability, namely, the feasible way of evaluating the keywords to be evaluated according to skipping statistical results is as follows: evaluating the contribution value of the keyword to be evaluated to the target word according to the hop statistical probability, for example, presetting a hop statistical probability range for different contribution values, comparing the obtained hop statistical probability with the hop statistical probability range, determining the hop statistical probability range in which the obtained hop statistical probability is located, and taking the contribution value corresponding to the hop statistical probability range as the contribution value of the keyword to be evaluated, wherein the hop statistical probability range corresponding to different contribution values is determined according to practical application, and the exemplary embodiment of the present disclosure is not limited.
Or under the condition that the skip statistical probability range is not preset, the skip statistical probabilities of different keywords to be evaluated can be compared, and the contribution value of the skip statistical probability which is greater than the skip statistical probabilities of other keywords to be evaluated is greater than that of the other keywords to be evaluated.
According to the technical scheme, after at least one jump path of the keyword to be evaluated is obtained, the jump statistical result used for indicating the contribution value of the keyword to be evaluated to the target word is obtained according to the at least one jump path of the keyword to be evaluated, the keyword to be evaluated is evaluated according to the jump statistical result, and the keyword to be evaluated is evaluated according to the contribution value of the keyword to be evaluated to the target word compared with the existing evaluation of the keyword to be evaluated from the aspects of source words and target words.
Referring to fig. 3, another flowchart of a keyword evaluation method provided by an exemplary embodiment of the present disclosure is shown, which evaluates a keyword to be evaluated based on three aspects, namely, a contribution value of the keyword to be evaluated to a target word, a source effect of the keyword to be evaluated, and a transformation effect of the keyword to be evaluated, and specifically may include the following steps:
301: and acquiring at least one jump path of the keyword to be evaluated, wherein the jump path takes the keyword to be evaluated as a starting point and takes a target word in the target word group as an end point.
302: and obtaining a skipping statistical result of the keyword to be evaluated according to at least one skipping path of the keyword to be evaluated, wherein the skipping statistical result is used for indicating the contribution value of the keyword to be evaluated to the target word, so that the effect of the keyword to be evaluated assisting the target word through other keywords is reflected through the skipping statistical result.
In the exemplary embodiment of the present disclosure, please refer to step 101 and step 102 for the implementation process and description of step 301 and step 302, and the exemplary embodiment of the present disclosure will not be described again.
303: and acquiring a source statistical result of the keyword to be evaluated and a direct conversion result of the keyword to be evaluated, wherein the source statistical result is used for indicating the keyword to be evaluated as a source function of a source word, and the direct conversion result is used for indicating the keyword to be evaluated as a conversion function of a target word.
In some exemplary embodiments of the disclosure, the selectable manifestations of the source statistics of the keywords to be evaluated are: the number of times of taking the keywords to be evaluated as source words, and the selectable expression form of the direct conversion result of the keywords to be evaluated is as follows: the number of times the keyword to be evaluated is taken as the target word.
In some exemplary embodiments of the disclosure, the selectable manifestations of the source statistics of the keywords to be evaluated are: the obtaining process of the source probability of the source word by using the keyword to be evaluated as the source word can be as follows: acquiring the times of taking the keywords to be evaluated as source words and the total times of appearance of the keywords to be evaluated, and acquiring the source probability of taking the keywords to be evaluated as the source words according to the times of taking the keywords to be evaluated as the source words and the total times of appearance of the keywords to be evaluated; likewise, alternative expressions of the direct conversion result of the keyword to be evaluated are: the target probability of the keyword to be evaluated as the target word may be obtained by the following steps: acquiring the times of the keywords to be evaluated as target words and the total times of the keywords to be evaluated, and obtaining the target probability of the keywords to be evaluated as the target words according to the times of the keywords to be evaluated as the target words and the total times of the keywords to be evaluated.
304: and evaluating the keywords to be evaluated according to the skip statistical result, the source statistical result and the direct conversion result, so that the keywords to be evaluated are evaluated from the three aspects of the contribution value of the keywords to be evaluated to the target word, the source action of the keywords to be evaluated and the conversion action of the keywords to be evaluated, and the evaluation accuracy is improved compared with that from a single aspect.
One possible way to evaluate the keywords to be evaluated according to the above three aspects is: and obtaining the comprehensive evaluation function of the keywords to be evaluated according to the skip statistical result, the source statistical result, the direct conversion result, the first weight corresponding to the skip statistical result, the second weight corresponding to the source statistical result and the third weight corresponding to the direct conversion result, and evaluating the keywords to be evaluated according to the comprehensive evaluation function of the keywords to be evaluated.
For example, assume that the skip statistic is P (keyword to be evaluated)Attack-assisting toolThe statistical result of the source is P (the keyword to be evaluated)Source headDirect conversion of the result to P (keyword to be evaluated)Direct rotationIf the first weight is a, the second weight is b, and the third weight is c, the calculation formula of the comprehensive evaluation function is:
p (to-be-evaluated keyword)Attack-assisting toolX a + P (keyword to be evaluated)Source headX b + P (keyword to be evaluated)Direct rotationAnd xc, namely, taking the comprehensive evaluation score as the comprehensive evaluation function, wherein the larger the comprehensive evaluation score is, the larger the comprehensive function of the keyword to be evaluated is. The values of the first weight, the second weight and the third weight may be determined according to practical applications, and exemplary embodiments of the present disclosure are not limited.
According to the technical scheme, after at least one jump path of the keyword to be evaluated is obtained, a jump statistical result used for indicating the contribution value of the keyword to be evaluated to the target word is obtained according to the at least one jump path of the keyword to be evaluated, a source statistical result of the keyword to be evaluated and a direct conversion result of the keyword to be evaluated are obtained, the keyword to be evaluated is evaluated according to the jump statistical result, the source statistical result and the direct conversion result, evaluation of the keyword to be evaluated is achieved from the three aspects of the contribution value of the keyword to be evaluated to the target word, the source effect of the keyword to be evaluated and the conversion effect of the keyword to be evaluated, and evaluation accuracy is further improved.
Corresponding to the embodiment of the method, the invention also provides a keyword evaluation device.
As shown in fig. 4, an apparatus for evaluating keywords according to an embodiment of the present invention may include: a path acquisition unit 100, a hop statistics unit 200 and an evaluation unit 300,
the path obtaining unit 100 is configured to obtain at least one jumping path of a keyword to be evaluated;
the jumping path takes the keyword to be evaluated as a starting point and takes the target word in the target word group as an end point, namely: the jump path is a path from the keyword to be evaluated to the target word, and the keyword to be evaluated can jump to the target word at least once.
For a target phrase, a target word and a keyword to be evaluated, the target word is a summary word of a target object desired by a user, for example, when the user searches for a certain target product (a feasible way of the target object) -a dress, the target word is a summary word of the dress, such as "women's yarn quality short broken flowers" of the dress, and the target phrase is a set of target words, which may be a set of target words of different users. The keywords to be evaluated are other keywords except for the target words adopted in the process of searching the target object, such as source words adopted in the process of searching the target object or intermediate words jumping from the source words to the target words.
The obtaining method of the skip path, the target word, the target phrase and the keyword to be evaluated includes but is not limited to the method set forth in the exemplary embodiment of the disclosure, and the obtaining method may include: specifically, each keyword in the search process is acquired according to the search process of finding a target object expected by a user, a specific operation (such as a purchase operation) is triggered when a click event of the search object corresponding to a certain keyword is retrieved, the keyword corresponding to the click event is used as the target word, the sequence of each keyword is determined according to the click event (such as the click time in the click event) of the search object corresponding to each keyword, and the sequence can be used for forming a jump path from the keyword to the target word.
Wherein the path obtaining unit 100 may include: a total path acquisition subunit and a path selection subunit,
the all-path obtaining subunit is configured to obtain all skip paths from the keyword to be evaluated to each target word in the target word group;
and the path selection subunit is used for selecting a part of jump paths for each target word from all jump paths from the keyword to be evaluated to each target word in the target word group, wherein the jump times of each selected jump path from the keyword to be evaluated to the corresponding target word do not exceed the preset times.
The reason why the jump path with the jump times not exceeding the preset times is selected is that: multiple reverse jumps may occur from the keyword to be evaluated to the target word, and the reverse jumps may cause a jump path from the keyword to be evaluated to the target word to fall into a dead loop, so that the acquisition of the jump path also falls into the dead loop, and thus the technical scheme provided by the exemplary embodiment of the present disclosure cannot be implemented. And the evaluation function of the jump path with the jump times exceeding the preset times on the keyword to be evaluated is smaller than the evaluation function of the jump path with the jump times not exceeding the preset times on the keyword to be evaluated, so that the jump times of each selected jump path from the keyword to be evaluated to the corresponding target word do not exceed the preset times under the condition of considering evaluation efficiency and evaluation accuracy.
The points to be explained here are: under the condition that the target phrase is a set of target words of different users or the target phrase is a set of target words for a single user, each target word in the target phrase may not have an association relationship with the keyword to be evaluated, so that no jump path exists between the keyword to be evaluated and the target word, and therefore, when the target phrase is in the two conditions, obtaining all jump paths from the keyword to be evaluated to each target word in the target phrase means: and acquiring all jump paths of each target word in the target word group and having a correlation with the keyword to be evaluated.
The skip statistical unit 200 is configured to obtain a skip statistical result of the keyword to be evaluated according to at least one skip path of the keyword to be evaluated, where the skip statistical result is used to indicate a contribution value of the keyword to be evaluated to the target word;
the skip statistic unit 200 may include: a hop probability acquisition subunit and a statistical probability acquisition subunit,
in some exemplary embodiments of the present disclosure, the alternative manifestation of the jump statistic is: the method specifically comprises the steps of firstly acquiring the jumping times of each jumping path and then calculating the number of the jumping paths with the same jumping times.
The jump probability obtaining subunit is configured to obtain a path jump probability of each of all the selected jump paths;
and the statistical probability obtaining subunit is used for obtaining the jump statistical probability representing the jump statistical result according to the path jump probability of each jump path and the target probability of the target word of each jump path serving as the target word in all the jump paths.
Further, the jump probability obtaining subunit may be specifically configured to: for each jump path in all the selected jump paths:
obtaining the single skipping probability of the ith keyword skipping to the (i + 1) th keyword in the skipping path, and obtaining the path skipping probability of the skipping path according to all the single skipping probabilities in the skipping path, wherein i is a natural number from 1 to N-1, N is the total number of the keywords in the skipping path where the ith keyword is located, the keyword to be evaluated is the first keyword in the skipping path, and the target word is the Nth keyword in the skipping path.
The evaluation unit 300 is configured to evaluate the keyword to be evaluated according to the skip statistic result.
If the contribution value of the keyword to be evaluated to the target word is greater than the contribution values of other keywords to be evaluated to the target word, recommending the keyword to be evaluated whose contribution value is greater than the contribution values of other keywords to be evaluated, or setting the contribution level of the keyword to be evaluated according to the contribution value of the keyword to be evaluated to the target word, recommending the keyword to be evaluated whose contribution level is within a preset level, where the preset level may be determined according to actual application, such as the number of preset recommended keywords, and the exemplary embodiment of the present disclosure is not limited.
According to the technical scheme, after the keyword evaluation device obtains at least one jump path of the keyword to be evaluated, the jump statistical result used for indicating the contribution value of the keyword to be evaluated to the target word is obtained according to the at least one jump path of the keyword to be evaluated, the keyword to be evaluated is evaluated according to the jump statistical result, and the keyword to be evaluated is evaluated according to the contribution value of the keyword to be evaluated to the target word compared with the conventional evaluation of the keyword to be evaluated from the aspects of source words and target words.
As shown in fig. 5, another keyword evaluation apparatus provided in the embodiment of the present invention may further include, based on the apparatus shown in fig. 4: a result obtaining unit 400, configured to obtain a source statistical result of the keyword to be evaluated and a direct conversion result of the keyword to be evaluated, where the source statistical result is used to indicate that the keyword to be evaluated serves as a source of a source word, and the direct conversion result is used to indicate that the keyword to be evaluated serves as a conversion of the target word;
the evaluation unit 300 may be specifically configured to evaluate the keyword to be evaluated according to the skip statistical result, the source statistical result, and the direct conversion result.
Further, the evaluation unit 300 may include: a comprehensive evaluation subunit and a keyword evaluation subunit,
the comprehensive evaluation subunit is configured to obtain a comprehensive evaluation function of the keyword to be evaluated according to the skip statistical result, the source statistical result, the direct conversion result, a first weight corresponding to the skip statistical result, a second weight corresponding to the source statistical result, and a third weight corresponding to the direct conversion result;
and the keyword evaluation subunit is used for evaluating the keywords to be evaluated according to the comprehensive evaluation function of the keywords to be evaluated.
In some exemplary embodiments of the disclosure, the selectable manifestations of the source statistics of the keywords to be evaluated are: the number of times of taking the keywords to be evaluated as source words, and the selectable expression form of the direct conversion result of the keywords to be evaluated is as follows: the number of times the keyword to be evaluated is taken as the target word.
In some exemplary embodiments of the disclosure, the selectable manifestations of the source statistics of the keywords to be evaluated are: the obtaining process of the source probability of the source word by using the keyword to be evaluated as the source word can be as follows: acquiring the times of taking the keywords to be evaluated as source words and the total times of appearance of the keywords to be evaluated, and acquiring the source probability of taking the keywords to be evaluated as the source words according to the times of taking the keywords to be evaluated as the source words and the total times of appearance of the keywords to be evaluated; likewise, alternative expressions of the direct conversion result of the keyword to be evaluated are: the target probability of the keyword to be evaluated as the target word may be obtained by the following steps: acquiring the times of the keywords to be evaluated as target words and the total times of the keywords to be evaluated, and obtaining the target probability of the keywords to be evaluated as the target words according to the times of the keywords to be evaluated as the target words and the total times of the keywords to be evaluated.
One possible way to evaluate the keywords to be evaluated according to the above three aspects is: and obtaining the comprehensive evaluation function of the keywords to be evaluated according to the skip statistical result, the source statistical result, the direct conversion result, the first weight corresponding to the skip statistical result, the second weight corresponding to the source statistical result and the third weight corresponding to the direct conversion result, and evaluating the keywords to be evaluated according to the comprehensive evaluation function of the keywords to be evaluated.
According to the technical scheme, after the keyword evaluation device obtains at least one jump path of the keyword to be evaluated, the jump statistical result used for indicating the contribution value of the keyword to be evaluated to the target word is obtained according to the at least one jump path of the keyword to be evaluated, the source statistical result of the keyword to be evaluated and the direct conversion result of the keyword to be evaluated are obtained, the keyword to be evaluated is evaluated according to the jump statistical result, the source statistical result and the direct conversion result, the keyword to be evaluated is evaluated from the three aspects of the contribution value of the keyword to be evaluated to the target word, the source effect of the keyword to be evaluated and the conversion effect of the keyword to be evaluated, and the evaluation accuracy is further improved.
The keyword evaluation device comprises a processor and a memory, wherein the path acquisition unit, the jump statistic unit, the evaluation unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more, and the keyword evaluation is realized by adjusting the kernel parameters.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
An embodiment of the present invention provides a storage medium on which a program is stored, the program implementing the keyword evaluation method when executed by a processor.
The embodiment of the invention provides a processor, which is used for running a program, wherein the keyword evaluation method is executed when the program runs.
The embodiment of the invention provides equipment, which comprises a processor, a memory and a program which is stored on the memory and can run on the processor, wherein the processor executes the program and realizes the following steps:
acquiring at least one jump path of a keyword to be evaluated, wherein the jump path takes the keyword to be evaluated as a starting point and takes a target word in a target word group as an end point;
obtaining a skipping statistical result of the keyword to be evaluated according to at least one skipping path of the keyword to be evaluated, wherein the skipping statistical result is used for indicating the contribution value of the keyword to be evaluated to the target word;
and evaluating the keywords to be evaluated according to the skip statistical result.
Optionally, the following steps may be implemented when the processor executes the program:
acquiring a source statistical result of the keyword to be evaluated and a direct conversion result of the keyword to be evaluated, wherein the source statistical result is used for indicating the keyword to be evaluated as a source function of a source word, and the direct conversion result is used for indicating the keyword to be evaluated as a conversion function of a target word;
the evaluating the keywords to be evaluated according to the skip statistic result comprises the following steps: and evaluating the keywords to be evaluated according to the skip statistical result, the source statistical result and the direct conversion result.
Optionally, the evaluating the keyword to be evaluated according to the skip statistical result, the source statistical result, and the direct conversion result includes:
obtaining a comprehensive evaluation function of the keyword to be evaluated according to the skip statistical result, the source statistical result, the direct conversion result, a first weight corresponding to the skip statistical result, a second weight corresponding to the source statistical result and a third weight corresponding to the direct conversion result;
and evaluating the keywords to be evaluated according to the comprehensive evaluation function of the keywords to be evaluated.
Optionally, the obtaining of at least one jump path of the keyword to be evaluated includes:
acquiring all jump paths from the keywords to be evaluated to each target word in the target word group;
and selecting a part of jump paths for each target word from all jump paths from the keyword to be evaluated to each target word in the target word group, wherein the jump times of each selected jump path from the keyword to be evaluated to the corresponding target word do not exceed the preset times.
Optionally, the obtaining a skip statistical result of the keyword to be evaluated according to the at least one skip path of the keyword to be evaluated includes:
acquiring the path skipping probability of each skipping path in all the selected skipping paths;
and obtaining the jump statistical probability representing the jump statistical result according to the path jump probability of each jump path and the target probability of the target word of each jump path as the target word in all the jump paths.
Optionally, the obtaining the path jump probability of each jump path in all the selected jump paths includes: for each jump path in all the selected jump paths:
obtaining the single skipping probability of the ith keyword skipping to the (i + 1) th keyword in the skipping path, and obtaining the path skipping probability of the skipping path according to all the single skipping probabilities in the skipping path, wherein i is a natural number from 1 to N-1, N is the total number of the keywords in the skipping path where the ith keyword is located, the keyword to be evaluated is the first keyword in the skipping path, and the target word is the Nth keyword in the skipping path.
The device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:
acquiring at least one jump path of a keyword to be evaluated, wherein the jump path takes the keyword to be evaluated as a starting point and takes a target word in a target word group as an end point;
obtaining a skipping statistical result of the keyword to be evaluated according to at least one skipping path of the keyword to be evaluated, wherein the skipping statistical result is used for indicating the contribution value of the keyword to be evaluated to the target word;
and evaluating the keywords to be evaluated according to the skip statistical result.
Optionally, the program may further initialize the following steps:
acquiring a source statistical result of the keyword to be evaluated and a direct conversion result of the keyword to be evaluated, wherein the source statistical result is used for indicating the keyword to be evaluated as a source function of a source word, and the direct conversion result is used for indicating the keyword to be evaluated as a conversion function of a target word;
the evaluating the keywords to be evaluated according to the skip statistic result comprises the following steps: and evaluating the keywords to be evaluated according to the skip statistical result, the source statistical result and the direct conversion result.
Optionally, the evaluating the keyword to be evaluated according to the skip statistical result, the source statistical result, and the direct conversion result includes:
obtaining a comprehensive evaluation function of the keyword to be evaluated according to the skip statistical result, the source statistical result, the direct conversion result, a first weight corresponding to the skip statistical result, a second weight corresponding to the source statistical result and a third weight corresponding to the direct conversion result;
and evaluating the keywords to be evaluated according to the comprehensive evaluation function of the keywords to be evaluated.
Optionally, the obtaining of at least one jump path of the keyword to be evaluated includes:
acquiring all jump paths from the keywords to be evaluated to each target word in the target word group;
and selecting a part of jump paths for each target word from all jump paths from the keyword to be evaluated to each target word in the target word group, wherein the jump times of each selected jump path from the keyword to be evaluated to the corresponding target word do not exceed the preset times.
Optionally, the obtaining a skip statistical result of the keyword to be evaluated according to the at least one skip path of the keyword to be evaluated includes:
acquiring the path skipping probability of each skipping path in all the selected skipping paths;
and obtaining the jump statistical probability representing the jump statistical result according to the path jump probability of each jump path and the target probability of the target word of each jump path as the target word in all the jump paths.
Optionally, the obtaining the path jump probability of each jump path in all the selected jump paths includes: for each jump path in all the selected jump paths:
obtaining the single skipping probability of the ith keyword skipping to the (i + 1) th keyword in the skipping path, and obtaining the path skipping probability of the skipping path according to all the single skipping probabilities in the skipping path, wherein i is a natural number from 1 to N-1, N is the total number of the keywords in the skipping path where the ith keyword is located, the keyword to be evaluated is the first keyword in the skipping path, and the target word is the Nth keyword in the skipping path.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (8)
1. A keyword evaluation method, the method comprising:
acquiring at least one jump path of a keyword to be evaluated, wherein the jump path takes the keyword to be evaluated as a starting point and takes a target word in a target word group as an end point;
obtaining a skipping statistical result of the keyword to be evaluated according to at least one skipping path of the keyword to be evaluated, wherein the skipping statistical result is used for indicating the contribution value of the keyword to be evaluated to the target word;
acquiring a source statistical result of the keyword to be evaluated and a direct conversion result of the keyword to be evaluated, wherein the source statistical result is used for indicating the keyword to be evaluated as a source function of a source word, and the direct conversion result is used for indicating the keyword to be evaluated as a conversion function of a target word;
and evaluating the keywords to be evaluated according to the skip statistical result, the source statistical result and the direct conversion result.
2. The method according to claim 1, wherein the evaluating the keyword to be evaluated according to the skip statistical result, the source statistical result and the direct conversion result comprises:
obtaining a comprehensive evaluation function of the keyword to be evaluated according to the skip statistical result, the source statistical result, the direct conversion result, a first weight corresponding to the skip statistical result, a second weight corresponding to the source statistical result and a third weight corresponding to the direct conversion result;
and evaluating the keywords to be evaluated according to the comprehensive evaluation function of the keywords to be evaluated.
3. The method according to any one of claims 1 to 2, wherein the obtaining at least one jump path of the keyword to be evaluated comprises:
acquiring all jump paths from the keywords to be evaluated to each target word in the target word group;
and selecting a part of jump paths for each target word from all jump paths from the keyword to be evaluated to each target word in the target word group, wherein the jump times of each selected jump path from the keyword to be evaluated to the corresponding target word do not exceed the preset times.
4. The method according to claim 3, wherein obtaining the skip statistic result of the keyword to be evaluated according to at least one skip path of the keyword to be evaluated comprises:
acquiring the path skipping probability of each skipping path in all the selected skipping paths;
and obtaining the jump statistical probability representing the jump statistical result according to the path jump probability of each jump path and the target probability of the target word of each jump path as the target word in all the jump paths.
5. The method according to claim 4, wherein the obtaining the path jump probability of each of all the selected jump paths comprises: for each jump path in all the selected jump paths:
obtaining the single skipping probability of the ith keyword skipping to the (i + 1) th keyword in the skipping path, and obtaining the path skipping probability of the skipping path according to all the single skipping probabilities in the skipping path, wherein i is a natural number from 1 to N-1, N is the total number of the keywords in the skipping path where the ith keyword is located, the keyword to be evaluated is the first keyword in the skipping path, and the target word is the Nth keyword in the skipping path.
6. A keyword evaluation apparatus, characterized in that the apparatus comprises: a path acquisition unit, a jump statistic unit, a result acquisition unit and an evaluation unit,
the path acquisition unit is used for acquiring at least one jump path of the keyword to be evaluated, wherein the jump path takes the keyword to be evaluated as a starting point and takes a target word in a target word group as an end point;
the skip statistical unit is used for obtaining a skip statistical result of the keyword to be evaluated according to at least one skip path of the keyword to be evaluated, wherein the skip statistical result is used for indicating a contribution value of the keyword to be evaluated to the target word;
the result obtaining unit is used for obtaining a source statistical result of the keyword to be evaluated and a direct conversion result of the keyword to be evaluated, wherein the source statistical result is used for indicating the keyword to be evaluated as a source function of a source word, and the direct conversion result is used for indicating the keyword to be evaluated as a conversion function of a target word;
and the evaluation unit is used for evaluating the keywords to be evaluated according to the skip statistical result, the source statistical result and the direct conversion result.
7. A storage medium, characterized in that the storage medium comprises a stored program, wherein a device on which the storage medium is located is controlled to execute the keyword evaluation method according to any one of claims 1 to 5 when the program is executed.
8. A processor, characterized in that the processor is configured to run a program, wherein the program when running performs the keyword evaluation method according to any one of claims 1 to 5.
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 CN110069542A (en) | 2019-07-30 |
| CN110069542B true 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 (4)
| 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 |
| 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 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6507541B2 (en) * | 2014-09-22 | 2019-05-08 | カシオ計算機株式会社 | INFORMATION DISPLAY DEVICE, INFORMATION DISPLAY PROGRAM, AND INFORMATION DISPLAY METHOD |
| US10248967B2 (en) * | 2015-09-25 | 2019-04-02 | 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 (4)
| 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 |
| 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 |
|---|
| 基于改进的TF-IDF方法的文本相似度算法研究;周丽杰等;《泰山学院学报》;20150531;第37卷(第3期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110069542A (en) | 2019-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109885842B (en) | Processing text neural networks | |
| US11055360B2 (en) | Data write-in method and apparatus in a distributed file system | |
| US11563818B2 (en) | Generating attribute preference models based on disparate attribute spectrums | |
| US8880548B2 (en) | Dynamic search interaction | |
| CN106557480B (en) | Method and device for realizing query rewriting | |
| US10846241B2 (en) | Score-based cache admission and eviction | |
| CN108416616A (en) | The sort method and device of complaints and denunciation classification | |
| CN110020912B (en) | Page display method, device and equipment | |
| US11061948B2 (en) | Method and system for next word prediction | |
| CN111680063B (en) | Method and device for paging query data by elastic search | |
| WO2015185020A1 (en) | Information category obtaining method and apparatus | |
| US20200387926A1 (en) | Methods and apparatus to determine informed holdouts for an advertisement campaign | |
| JP7200069B2 (en) | Information processing device, vector generation method and program | |
| CN111241391A (en) | Task recommendation method and device | |
| US11782947B2 (en) | Apparatus for recommending feature and method for recommending feature using the same | |
| CN110069542B (en) | Keyword evaluation method and device | |
| CN112507244B (en) | Social data recommendation method and device, distributed computing cluster and storage medium | |
| CN108241643B (en) | Index data analysis method and device for keywords | |
| CN114254204A (en) | Data processing method, device, medium and electronic equipment | |
| CN111144098B (en) | Recall method and device for extended question | |
| JP5555238B2 (en) | Information processing apparatus and program for Bayesian network structure learning | |
| CN110264333B (en) | Risk rule determining method and apparatus | |
| CN110059272B (en) | Page feature recognition method and device | |
| CN112491816A (en) | Service data processing method and device | |
| JP2020102035A (en) | Information processor and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| 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. |
|
| CB02 | Change of applicant information | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |