CN110020045B

CN110020045B - Keyword path analysis method and device

Info

Publication number: CN110020045B
Application number: CN201710875913.1A
Authority: CN
Inventors: 葛婷
Original assignee: Beijing Gridsum Technology Co Ltd
Current assignee: Beijing Gridsum Technology Co Ltd
Priority date: 2017-09-25
Filing date: 2017-09-25
Publication date: 2021-07-27
Anticipated expiration: 2037-09-25
Also published as: CN110020045A

Abstract

The invention provides a keyword path analysis method and a device, which are used for acquiring at least one keyword path; the keyword path comprises at least one keyword which is sequentially connected according to a search sequence; counting click data of the target keywords according to click information of the target keywords in each keyword path; the target keyword is any keyword in any keyword path in the at least one keyword path; and calculating a release index of the target keyword according to the click data, wherein the release index is used for guiding the release of the target keyword. The keyword path analysis method and the keyword path analysis device solve the problem that a large number of keyword paths are difficult to analyze, and the target keyword is guided to be released through the release indexes, so that the keyword release accuracy is improved.

Description

Keyword path analysis method and device

Technical Field

The invention relates to the field of information processing, in particular to a keyword path analysis method and device.

Background

SEM (Search Engine Marketing: English Engine Marketing) is network Marketing based on a Search Engine platform, and keywords meeting user habits are released to target users when people Search information. However, when the accuracy of the released keywords is low, the conversion rate and efficiency of the keywords are low, and the search efficiency and the search effect are seriously affected.

When a user carries out keyword search for the same media for multiple times, keywords adopted by the multiple searches are connected in series to form a keyword path according to the searching sequence. The habits of the user on the keyword search sequence, the position information of the keywords in the keyword path and the potential relation between the keywords and the keywords are covered in the keyword path, so that theoretically, the accurate putting of the keywords can be ensured through the accurate analysis of the keyword path.

However, in the search history database, not only a keyword path formed by searching for a plurality of keywords by the same user but also a keyword path formed by searching for the same or different keywords by different users generally exist, so that keyword paths formed by a large number of users during the search process are mutually crossed or overlapped, and the keyword path relationship is complicated. Therefore, at present, there is no practical and effective keyword path analysis method, which can accurately analyze a large number of keyword paths, thereby improving the accuracy of keyword delivery.

Therefore, a technical solution capable of accurately and effectively analyzing the keyword path is urgently needed at present.

Disclosure of Invention

In view of this, the present invention provides a keyword path analysis method and apparatus, so as to practically and effectively implement accurate analysis on a keyword path and improve accuracy of keyword delivery.

In order to achieve the purpose, the invention provides the following technical scheme:

a keyword path analysis method includes:

acquiring at least one keyword path; the keyword path comprises at least one keyword which is sequentially connected according to a search sequence;

counting click data of the target keywords according to click information of the target keywords in each keyword path; the target keyword is any keyword in any keyword path in the at least one keyword path;

and calculating a release index of the target keyword according to the click data, wherein the release index is used for guiding the release of the target keyword.

Preferably, the click information includes a position, and the position includes: at least one of an initial position, an intermediate position, and an end position; the click data of the statistic target keyword comprises the following steps:

counting the number of clicks of the target keyword at the initial position, the middle position and the end position of each keyword path within a preset range; the preset range comprises the acquired at least one keyword path.

Preferably, the release indexes include an initial click rate, a middle click rate and an end click rate; the calculating the delivery index of the target keyword according to the click data comprises the following steps:

using formula K_a＝P₁×N_a/S+Q₁Calculating the initial click rate K of the target keyword by the multiplied by S/M_a；

Using formula K_b＝P₂×N_b/S+Q₂Calculating the middle of the target keyword by the x S/MClick rate K_b；

Using formula K_c＝P₃×N_c/S+Q₃Calculating the ending click rate K of the target keyword by multiplying by the maximum value (S/M)_c；

Wherein, P₁、P₂、P₃、Q₁、Q₂And Q₃Are all preset weights, N_aThe number of clicks of the target keyword at the initial position, N_bNumber of clicks for the target keyword at intermediate position, N_cThe number of clicks of the target keyword at the end position is S, the number of keyword paths containing the target keyword is S, and M is the total number of the at least one keyword path.

Preferably, the click information includes a click type, and the click type includes: at least one of click alone and self-jump; the click data of the statistic target keyword comprises the following steps:

respectively counting the independent click number and the self-jump number of the target keyword in each keyword path within a preset range; the preset range comprises the acquired at least one keyword path;

the keywords which are clicked independently are keywords which are not connected with any keyword in a keyword path; the self-jumping keyword is a keyword identical to a previous keyword in a keyword path.

Preferably, the release indexes include individual click rate and self-jump rate; the calculating the delivery index of the target keyword according to the click data comprises the following steps:

using formula K_d＝P₄×N_d/S+Q₄Calculating the single click rate K of the target keyword by the multiplied by S/M_d；

Using formula K_e＝P₅×N_e/S+Q₅Calculating the self-jumping rate K of the target keyword by multiplying by S/M_e；

Wherein, P₄、P₅、Q₄And Q₅Are all preset weights, N_dIs the target keywordNumber of individual clicks, N_eAnd S is the number of the self-jumping revolutions of the target keyword, S is the number of the keyword paths containing the target keyword, and M is the total number of the at least one keyword path.

Preferably, the click information includes a click type, and the click type includes: at least one of roll-out and roll-in; the click data of the statistic target keyword comprises the following steps:

respectively counting the roll-out number and the roll-in number of the target keyword in each keyword path within a preset range; the preset range comprises the acquired at least one keyword path.

Preferably, the delivery indexes comprise a jump rate, a jumped rate and a heart rate; the calculating the delivery index of the target keyword according to the click data comprises the following steps:

using formula K_f＝N_f(S) calculating the jump rate K of the target keyword_f；

Using formula K_g＝N_g(S) calculating the skipped rate K of the target keyword_g；

Using formula K_h＝(N_f+N_g) (S) calculating the center rate K of the target keyword_h；

Wherein N is_fFor the number of roll-outs of the target keyword, N_gAnd S is the number of the keyword paths containing the target keywords.

A keyword path analysis apparatus comprising:

a path acquisition unit for acquiring at least one keyword path; the keyword path comprises at least one keyword which is sequentially connected according to a search sequence;

the data statistics unit is used for counting the click data of the target keywords according to the click information of the target keywords in each keyword path; the target keyword is any keyword in any keyword path in the at least one keyword path;

and the index calculation unit is used for calculating the releasing index of the target keyword according to the click data, wherein the releasing index is used for guiding the releasing of the target keyword.

A storage medium, the storage medium comprising a stored program, wherein when the program runs, a device where the storage medium is located is controlled to execute the foregoing keyword path analysis method.

A processor configured to execute a program, wherein the program executes the keyword path analysis method.

According to the technical scheme, the keyword path analysis method and the keyword path analysis device provided by the invention have the advantages that at least one keyword path is obtained; counting click data of the target keyword according to click information of the target keyword in each keyword path; and calculating the releasing indexes of the target keywords according to the click data, taking the specific releasing indexes as analysis results of the keyword paths, and solving the problem that a large number of keyword paths are difficult to analyze without analyzing complex relations among the keyword paths. In addition, according to the delivery index calculated according to the click data, the system and the method have sufficient quantitative data as support, and can realize accurate analysis of the keyword path, so that delivery of the target keyword is guided through the delivery index, and the accuracy of keyword delivery can be improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

Fig. 1 is a flowchart of a keyword path analysis method according to an embodiment of the present disclosure;

fig. 2 is another flowchart of a keyword path analysis method according to an embodiment of the present disclosure;

fig. 3 is another flowchart of a keyword path analysis method according to an embodiment of the present disclosure;

fig. 4 is another flowchart of a keyword path analysis method according to an embodiment of the present application;

fig. 5 is a flowchart of another keyword path analysis method according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of a keyword path analysis apparatus according to an embodiment of the present disclosure;

fig. 7 is another schematic structural diagram of a keyword path analysis apparatus according to an embodiment of the present disclosure;

fig. 8 is a schematic structural diagram of a keyword path analysis apparatus according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of a keyword path analysis apparatus according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of a keyword path analysis apparatus according to an embodiment of the present application.

Detailed Description

For the sake of reference and clarity, the descriptions, abbreviations or abbreviations of the technical terms used hereinafter are summarized as follows:

key words: the keywords are derived from English "keywords", and refer to the vocabulary used by a single media in making the index.

Keyword path: when the same user carries out at least one keyword search on the same media, the keywords searched at least once form a search sequence relation according to the sequence during the search, and the path formed by connecting the keywords searched at least once is called a keyword path according to the search sequence relation.

Graph database: a graph database (graph database) is a non-relational database that uses graph theory to store relationship information between entities.

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Referring to fig. 1, fig. 1 is a flowchart of a keyword path analysis method according to an embodiment of the present disclosure.

As shown in fig. 1, the method includes:

s101: at least one keyword path is obtained.

The keyword path includes at least one keyword sequentially connected according to a search order.

When a user searches media for a plurality of keywords, the keywords adopted by each search can be sequentially connected into a keyword path according to a search sequence, each keyword path comprises at least one keyword which is sequentially connected according to the search sequence, and the at least one keyword comprises one or more keywords.

S102: and counting the click data of the target keywords according to the click information of the target keywords in each keyword path.

The target keyword is any keyword in any keyword path in the at least one keyword path.

Different users may form different keyword paths or the same keyword path when searching for different media at different stages. Therefore, a large number of keyword paths formed by a large number of users searching a large number of media at different stages are mutually crossed and repeated, and the relationship is complex, and if the keyword paths are analyzed based on the relationship between the keyword paths, the difficulty is high, and the realization is difficult.

According to the method, the click data of the target keywords are counted according to the click information of the target keywords in each keyword path, the counted data is used as an analysis basis, the complex relation among the keyword paths does not need to be analyzed, the analysis of the keyword paths becomes possible, and the method is easy to realize.

The click refers to a specific operation of the user on the keyword during the search, and the click information refers to operation information of the keyword in a keyword path, such as a position, a click type, and the like. The click data refers to data on click information, such as the number of clicks at different positions, the number of clicks of different click types, and the like.

S103: and calculating the release index of the target keyword according to the click data.

And the delivery index is used for guiding the delivery of the target keyword.

The click data is actually statistical data, and according to the relevant statistical data of the target keyword, relevant delivery indexes of the target keyword can be calculated so as to guide delivery of the target keyword. For example, when a certain index of a target keyword is high, it indicates that the target keyword is more suitable for delivery to a certain user group.

The keyword path analysis method provided by this embodiment obtains at least one keyword path; counting click data of the target keyword according to click information of the target keyword in each keyword path; and calculating the releasing indexes of the target keywords according to the click data, taking the specific releasing indexes as analysis results of the keyword paths, and solving the problem that a large number of keyword paths are difficult to analyze without analyzing complex relations among the keyword paths. In addition, according to the delivery index calculated according to the click data, the system and the method have sufficient quantitative data as support, and can realize accurate analysis of the keyword path, so that delivery of the target keyword is guided through the delivery index, and the accuracy of keyword delivery can be improved.

Referring to fig. 2, fig. 2 is another flowchart of a keyword path analysis method according to an embodiment of the present disclosure.

In this embodiment, the click information of the target keyword in each keyword path includes a position. The location includes: at least one of an initial position, an intermediate position, and an end position. The release indexes of the keywords comprise an initial click rate, a middle click rate and an end click rate.

As shown in fig. 2, the method further comprises:

s201: at least one keyword path is obtained.

Step S201 is similar to step S101 in the previous embodiment, and is not described herein again.

S202: according to the click information of the target keyword in each keyword path, respectively counting the number of clicks of the target keyword at the initial position, the middle position and the end position of each keyword path within a preset range.

Each keyword path includes different positions, and the most basic positions include an initial position, a middle position and an end position.

In an example, the initial position may refer to a position of a first keyword in the keyword path, the end position may refer to a position of a last keyword in the keyword path, and the intermediate position may refer to a position of a keyword between the first keyword and the last keyword in the keyword path.

In another example, the initial position may also refer to the position of the first x keywords in the keyword path, the end position may refer to the position of the last y keywords in the keyword path, and the middle position may refer to the position of the keyword between the x-th keyword and the (z-y +1) -th keyword in the keyword path, where z is the total number of keywords in the keyword path, and x + y < z.

The preset range comprises the acquired at least one keyword path. The click data of the target keyword includes the number of clicks of the target keyword at the initial position, the intermediate position and the end position of each keyword path. For example, when the preset range includes a first keyword path, a second keyword path, a third keyword path, and a fourth keyword path, the position of the target keyword in the first keyword path is an initial position, the position in the second keyword path is an intermediate position, the position in the third keyword path is an end position, and the position in the fourth keyword path is an initial position, then the number of clicks of the target keyword in the initial position, the intermediate position, and the end position is counted as 2, 1, and 1, respectively, within the preset range.

In an example, the present step S202 can be used to implement step S102 in the foregoing embodiments.

S203: using formula K_a＝P₁×N_a/S+Q₁Calculating the initial click rate K of the target keyword by the multiplied by S/M_a。

S204: using formula K_b＝P₂×N_b/S+Q₂Calculating the middle click rate K of the target keyword by multiplying S/M_b。

S205: using formula K_c＝P₃×N_c/S+Q₃Calculating the ending click rate K of the target keyword by multiplying by the maximum value (S/M)_c。

In one example, steps S203-S205 may be used to implement step S103 in the foregoing embodiments.

By using the formula, the initial click rate K of the target keyword can be respectively calculated_aMiddle click rate K_bAnd end click rate K_c. Wherein, P₁、P₂And P₃The weighted values of (A) may be the same or different; q₁、Q₂And Q₃The weighted values of (a) may be the same or different. In particular, P may be paired according to different types of users₁、P₂、P₃、Q₁、Q₂And Q₃The weight value of (2) is adjusted.

In one example, Q₁、Q₂And Q₃All weight values of (1) are 0, P₁、P₂And P₃The weighted value of (1) is all 1.

In another example, Q₁、Q₂And Q₃The weighted value of (2) is not 0, so that the situation that the click rate of a certain position of the target keyword is too high and the overall error occurs can be avoided.

And according to the calculated initial click rate, the calculated middle click rate and the calculated end click rate of the target keyword, the method can be used for guiding the release of the target keyword. Thus, in an example, the method further comprises:

s206: when the initial click rate K_aAnd when the target keyword is larger than a first preset threshold value, releasing the target keyword to the user in the initial search stage.

The user in the initial search stage is the user who initially establishes the account, and the keywords with the large initial click rate are released to the user in the initial search stage, so that the method is beneficial to attracting new customer sources and expanding the popularity.

S207: when the intermediate click rate K_bAnd when the target keyword is larger than a second preset threshold value, delivering the target keyword to the user in the middle-term search stage.

The user in the middle-stage search stage refers to a user who has established an account for a certain period, and the keywords with a high middle click rate are released to the user in the middle-stage search stage, so that the market expansion is facilitated.

S208: when the end click rate K_cAnd when the target keyword is larger than a third preset threshold value, releasing the target keyword to the user in the mature searching stage.

The first preset threshold, the second preset threshold and the third preset threshold may be the same preset threshold, or may be different preset thresholds.

The user in the mature search stage refers to a user who has established an account for a long time, and the keyword with a large end click rate is released to the user in the mature search stage, so that more accurate service positioning can be ensured.

In other examples, the type of the keyword with the highest click rate at different positions can be determined, so that the search habit of the user is analyzed and explained, for example, the type of the keyword which is most likely to appear at the initial position is usually a query word, so that it can be determined that the user in the initial search stage is biased to search with the query word.

According to the keyword path analysis method provided by the embodiment, according to the click information of the target keyword in each keyword path, in a preset range, the number of clicks of the target keyword at the initial position, the middle position and the end position of each keyword path is respectively counted, and the keyword path is analyzed according to the number of clicks, so that three release indexes, namely the initial click rate, the middle click rate and the end click rate of the target keyword are calculated, release of the target keyword is guided through the release indexes, and the accuracy of keyword release is improved. And the target keyword can be accurately delivered to a suitable user through three delivery indexes, namely the initial click rate, the middle click rate and the end click rate of the target keyword.

Referring to fig. 3, fig. 3 is a flowchart illustrating a keyword path analysis method according to an embodiment of the present disclosure.

In this embodiment, the click information of the target keyword in each keyword path includes a click type, where the click type includes: at least one of click alone and self-jump. The target keyword release indexes comprise individual click rate and self-jumping rate.

As shown in fig. 3, the method includes:

s301: at least one keyword path is obtained.

Step S301 is similar to step S101 in the previous embodiment, and is not described herein again.

S302: according to the click information of the target keyword in each keyword path, respectively counting the independent click number and the self-jump number of the target keyword in each keyword path within a preset range.

The preset range comprises the acquired at least one keyword path. The click data of the target keyword comprises the individual number of clicks and the number of self-jumping revolutions of the target keyword in each keyword path. For example, when the preset range includes a first keyword path, a second keyword path, a third keyword path, and a fourth keyword path, the click type of the target keyword in the first keyword path is single click, the click type in the second keyword path is self-skip, the click type in the third keyword path is self-skip, and the click type in the fourth keyword path is self-skip, then, within the preset range, the number of single clicks and the number of self-skip of the target keyword are respectively counted as 1 and 3.

Step S302 may be used to implement step S102 in the foregoing embodiments.

S303: using formula K_d＝P₄×N_d/S+Q₄Calculating the single click rate K of the target keyword by the multiplied by S/M_d。

S304: using formula K_e＝P₅×N_e/S+Q₅Calculating the self-jumping rate K of the target keyword by multiplying by S/M_e。

Wherein, P₄、P₅、Q₄And Q₅Are all preset weights, N_dNumber of individual clicks for the target keyword, N_eAnd S is the number of the self-jumping revolutions of the target keyword, S is the number of the keyword paths containing the target keyword, and M is the total number of the at least one keyword path.

In one example, steps S303-S304 may be used to implement step S103 in the foregoing embodiments.

By usingThe above formula can respectively calculate the individual click rate K of the target keyword_dAnd self-jump rate K_e. Wherein, P₄And P₅The weighted values of (A) may be the same or different; q₄And Q₅The weighted values of (a) may be the same or different. In particular, P may be paired according to different types of users₄、P₅、Q₄And Q₅The weight value of (2) is adjusted.

In one example, Q₄And Q₅All weight values of (1) are 0, P₄And P₅The weighted value of (1) is all 1.

In another example, Q₄And Q₅The weighted value of (2) is not 0, so that the situation that the click rate of a certain position of the target keyword is too high and the overall error occurs can be avoided.

And according to the calculated individual click rate and the self-jumping rate of the target keyword, the method can be used for guiding the release of the target keyword. For example, for a keyword with an individual click rate greater than an individual click rate threshold, the release control is required to minimize the release of a keyword with a higher individual click rate. In addition, the keywords with the self-skipping rate greater than the self-skipping rate threshold value may be set according to specific requirements, and are not limited herein.

According to the keyword path analysis method provided by the embodiment, individual click number and self-skip number of the target keyword in each keyword path are respectively counted in a preset range according to click information of the target keyword in each keyword path, and the keyword path is analyzed accordingly, so that two release indexes, namely the individual click rate and the self-skip rate of the target keyword are calculated, and accurate and rigorous guidance basis is provided for keyword release.

Referring to fig. 4, fig. 4 is a flowchart illustrating a keyword path analysis method according to an embodiment of the present disclosure.

In this embodiment, the click information of the target keyword in each keyword path includes a click type, where the click type includes: at least one of roll-out and roll-in. The target keyword release indexes comprise a jumping rate, a jumped rate and a heart rate.

As shown in fig. 4, the method includes:

s401: at least one keyword path is obtained.

Step S401 is similar to step S101 in the previous embodiment, and is not described herein again.

S402: according to the click information of the target keyword in each keyword path, respectively counting the roll-out number and the roll-in number of the target keyword in each keyword path within a preset range.

The number of the target keyword in each keyword path may also be referred to as the number of the target keyword in each keyword path, and the number of the target keyword in each keyword path may also be referred to as the number of the target keyword in each keyword path.

The target keyword is any keyword in any keyword path in the at least one keyword path. The preset range comprises the acquired at least one keyword path. The click data of the target keyword comprises the roll-out number and the roll-in number of the target keyword in each keyword path. For example, when the preset range includes a first keyword path, a second keyword path, a third keyword path and a fourth keyword path, the click type of the target keyword in the first keyword path is a turn-in, the click type in the second keyword path includes a turn-in and a turn-out, the click type in the third keyword path is a turn-out, and the click type in the fourth keyword path is a turn-in, then, within the preset range, the individual turn-out number and the turn-in number of the target keyword are respectively counted to be 3 and 2.

Wherein, the step S402 can be used to implement the step S102 in the foregoing embodiments.

S403: using formula K_f＝N_f(S) calculating the jump rate K of the target keyword_f。

S404: using formula K_g＝N_gPer-meterCalculating the skipped rate K of the target keyword_g。

S405: using formula K_h＝(N_f+N_g) (S) calculating the center rate K of the target keyword_h。

In one example, steps S403-S404 may be used to implement step S103 in the foregoing embodiments.

By using the formula, the jump rate K of the target keyword can be respectively calculated_fThe rate of being jumped to K_gRegulating the Heart Rate K_h. According to the jump rate K of the key words_fThe rate of being jumped to K_gRegulating the Heart Rate K_hThe stickiness of the keywords may be analyzed, for example, determining keywords with a hop rate greater than a hop rate threshold as the most active keywords, determining keywords with a hop rate greater than a hop rate threshold as the most popular keywords, and determining keywords with a center rate greater than a heart rate threshold as the most affinity keywords. Therefore, the calculated jump rate and the calculated intermediate heart rate of the target keyword can be used for guiding the target keyword to be delivered in the same way.

According to the keyword path analysis method provided by the embodiment, the roll-out number and the roll-in number of the target keyword in each keyword path are respectively counted in a preset range according to the click information of the target keyword in each keyword path, and the keyword paths are analyzed accordingly, so that three release indexes, namely the jump rate, the jumped rate and the central rate of the target keyword are calculated, and an accurate and precise guide basis is provided for keyword release.

Referring to fig. 5, fig. 5 is a flowchart illustrating a keyword path analysis method according to an embodiment of the present disclosure.

As shown in fig. 5, the method includes:

s501: at least one keyword path is obtained.

S502: and counting the click data of the target keywords according to the click information of the target keywords in each keyword path.

S503: and calculating the release index of the target keyword according to the click data.

The release index is used for guiding release of the target keyword;

steps S501 to S503 are similar to steps S101 to S103 in the foregoing embodiment, and are not described again here.

S504: storing the at least one keyword path in a graph database in a directed graph mode;

wherein, the nodes in the directed graph are keywords in the at least one keyword path;

the attribute of the node comprises click data of the keyword;

the directed edges between the nodes and the adjacent nodes are used for representing the searching sequence relation between the keywords and the adjacent keywords;

the attribute of the directed edge comprises search times, and the search times are the times of sequentially searching the keywords and the adjacent keywords according to the search sequence relation.

In the keyword path analysis method provided by this embodiment, at least one acquired keyword path is stored in a graph database in a directed graph manner, a node in the directed graph is defined as a keyword in the at least one keyword path, an attribute of the node includes click data of the keyword, a directed edge between the node and an adjacent node is used to represent a search order relationship between the keyword and the adjacent keyword, an attribute of the directed edge includes a search frequency, and the search frequency is a frequency for sequentially searching the keyword and the adjacent keyword according to the search order relationship, so that complex keyword search path query becomes possible, and efficient query of keyword path information can be realized.

Corresponding to the keyword path analysis method, the embodiment of the invention also provides a corresponding keyword path analysis device.

Referring to fig. 6, fig. 6 is a schematic structural diagram of a keyword path analysis apparatus according to an embodiment of the present disclosure.

The keyword path analyzing apparatus of the present embodiment is configured to implement the keyword path analyzing method of the foregoing embodiment, and as shown in fig. 6, the apparatus includes:

a path obtaining unit U101, configured to obtain at least one keyword path; the keyword path includes at least one keyword sequentially connected according to a search order.

The data statistics unit U102 is used for counting click data of the target keyword according to click information of the target keyword in each keyword path; the target keyword is any keyword in any keyword path in the at least one keyword path.

And an index calculation unit U103, configured to calculate a delivery index of the target keyword according to the click data, where the delivery index is used to guide delivery of the target keyword.

The keyword path analysis device provided by the embodiment acquires at least one keyword path; counting click data of the target keyword according to click information of the target keyword in each keyword path; and calculating the releasing indexes of the target keywords according to the click data, taking the specific releasing indexes as analysis results of the keyword paths, and solving the problem that a large number of keyword paths are difficult to analyze without analyzing complex relations among the keyword paths. In addition, according to the delivery index calculated according to the click data, the system and the method have sufficient quantitative data as support, and can realize accurate analysis of the keyword path, so that delivery of the target keyword is guided through the delivery index, and the accuracy of keyword delivery can be improved.

Referring to fig. 7, fig. 7 is a schematic structural diagram of a keyword path analysis apparatus according to an embodiment of the present disclosure.

The keyword path analysis apparatus of the present embodiment includes a keyword releasing unit U104 in addition to the path obtaining unit U101, the data statistics unit U102, and the index calculation unit U103 in the foregoing embodiments. The data statistical unit U102 includes:

and the position counting unit U1021 is used for counting the number of clicks of the target keyword in the initial position, the middle position and the end position of each keyword path within a preset range according to the click information of the target keyword in each keyword path.

The index calculation unit U103 includes:

a first calculating unit U1031 for using formula K_a＝P₁×N_a/S+Q₁Calculating the initial click rate K of the target keyword by the multiplied by S/M_a。

A second calculation unit U1032 for using the formula K_b＝P₂×N_b/S+Q₂Calculating the middle click rate K of the target keyword by multiplying S/M_b。

A third computing unit U1033 for utilizing the formula K_c＝P₃×N_c/S+Q₃Calculating the ending click rate K of the target keyword by multiplying by the maximum value (S/M)_c。

Wherein, P₁、P₂、P₃、Q₁、Q₂And Q₃Are all preset weights, N_aThe number of clicks of the target keyword at the initial position, N_bNumber of clicks for the target keyword at intermediate position, N_cThe number of clicks of the target keyword at the end position, S the number of keyword paths containing the target keyword, and M the total number of the at least one keyword pathAnd (4) counting.

The keyword putting unit U104 includes:

a first release unit U1041 for releasing the initial click rate K_aAnd when the target keyword is larger than a first preset threshold value, releasing the target keyword to the user in the initial search stage.

A second dropping unit U1042 for dropping the intermediate click rate K_bAnd when the target keyword is larger than a second preset threshold value, delivering the target keyword to the user in the middle-term search stage.

A third putting unit U1043, configured to when the end click rate K is reached_cAnd when the target keyword is larger than a third preset threshold value, releasing the target keyword to the user in the mature searching stage.

According to the keyword path analysis device provided by the embodiment, according to the click information of the target keyword in each keyword path, in a preset range, the number of clicks of the target keyword at the initial position, the middle position and the end position of each keyword path is respectively counted, and the keyword path is analyzed according to the number of clicks, so that three release indexes, namely the initial click rate, the middle click rate and the end click rate of the target keyword are calculated, release of the target keyword is guided through the release indexes, and the accuracy of keyword release is improved. And the target keyword can be accurately delivered to a suitable user through three delivery indexes, namely the initial click rate, the middle click rate and the end click rate of the target keyword.

Referring to fig. 8, fig. 8 is a schematic structural diagram of a keyword path analysis apparatus according to an embodiment of the present disclosure.

The keyword path analysis apparatus of the present embodiment includes the path obtaining unit U101, the data statistics unit U102, the index calculation unit U103, and the keyword releasing unit U104 in the foregoing embodiments.

Wherein, the data statistics unit U102 further includes:

the type counting unit U1022 is configured to count, within a preset range, individual click numbers and self-skip numbers of the target keyword in each keyword path according to click information of the target keyword in each keyword path;

the preset range comprises the acquired at least one keyword path;

The index calculation unit U103 includes:

a fourth calculating unit U1034 for using the formula K_d＝P₄×N_d/S+Q₄Calculating the single click rate K of the target keyword by the multiplied by S/M_d。

A fifth calculating unit U1035 for using the formula K_e＝P₅×N_e/S+Q₅Calculating the self-jumping rate K of the target keyword by multiplying by S/M_e。

By using the formula, the individual click rates K of the target keywords can be respectively calculated_dAnd self-jump rate K_e. Wherein, P₄And P₅The weighted values of (A) may be the same or different; q₄And Q₅The weighted values of (a) may be the same or different. In particular, P may be paired according to different types of users₄、P₅、Q₄And Q₅The weight value of (2) is adjusted.

And according to the calculated individual click rate and the self-jumping rate of the target keyword, the method can be used for guiding the release of the target keyword.

In an example, the keyword putting unit U104 may further include a fourth putting unit U1044 for determining the individual click rate K_dAnd when the target keyword is larger than a fourth preset threshold value, the target keyword is prevented from being released.

In the example, the release control is performed on the keywords with the larger single click rate, and the release of the keywords with the higher single click rate is reduced as much as possible. In addition, the keywords with the self-skipping rate greater than the self-skipping rate threshold value may be set according to specific requirements, and are not limited herein.

According to the keyword path analysis device provided by the embodiment, the independent click number and the self-skip number of the target keyword in each keyword path are respectively counted in the preset range according to the click information of the target keyword in each keyword path, and the keyword path is analyzed according to the independent click number and the self-skip number, so that two release indexes of the independent click rate and the self-skip rate of the target keyword are calculated, and an accurate and precise guide basis is provided for keyword release.

Referring to fig. 9, fig. 9 is a schematic structural diagram of a keyword path analysis apparatus according to an embodiment of the present disclosure.

The keyword path analysis apparatus of the present embodiment includes the path obtaining unit U101, the data statistics unit U102, and the index calculation unit U103 in the foregoing embodiments.

The type statistics unit U1022 in the data statistics unit U102 is further configured to respectively count the roll-out number and the roll-in number of the target keyword in each keyword path within a preset range according to the click information of the target keyword in each keyword path;

the index calculation unit U103 further includes:

a sixth calculating unit U1036 for calculating a value using the formula K_f＝N_f(S) calculating the jump rate K of the target keyword_f。

A seventh calculation unit U1037 for using the formula K_g＝N_g(S) calculating the skipped rate K of the target keyword_g。

An eighth calculation unit U1038 for using the formula K_h＝(N_f+N_g) (S) calculating the center rate K of the target keyword_h。

According to the keyword path analysis device provided by the embodiment, the roll-out number and the roll-in number of the target keyword in each keyword path are respectively counted in a preset range according to the click information of the target keyword in each keyword path, and the keyword paths are analyzed accordingly, so that three release indexes, namely the jump rate, the jumped rate and the central rate of the target keyword are calculated, and an accurate and precise guide basis is provided for keyword release.

Referring to fig. 10, fig. 10 is a schematic structural diagram of a keyword path analysis apparatus according to an embodiment of the present disclosure.

The keyword path analysis apparatus of the present embodiment includes a data storage unit U105 in addition to the path obtaining unit U101, the data statistics unit U102, the index calculation unit U103, and the keyword release unit U104 in the foregoing embodiments, and the data storage unit includes a graph database.

The data storage unit U105 is configured to store the at least one keyword path in a graph database in a directed graph manner.

the attribute of the node comprises click data of the keyword;

The keyword path analysis device provided in this embodiment stores at least one acquired keyword path in a graph database in a directed graph manner, and defines a node in the directed graph as a keyword in the at least one keyword path, where an attribute of the node includes click data of the keyword, a directed edge between the node and an adjacent node is used to represent a search order relationship between the keyword and the adjacent keyword, and an attribute of the directed edge includes a search frequency, where the search frequency is a frequency for sequentially searching the keyword and the adjacent keyword according to the search order relationship, so that a complex keyword search path query becomes possible, and efficient query of keyword path information can be realized.

The keyword path analyzing apparatus provided in an embodiment of the present invention includes a processor and a memory, where the path obtaining unit U101, the data statistics unit U102, the index calculation unit U103, the keyword releasing unit U104, the data storage unit U105, the location statistics unit U1021, the type statistics unit U1022, the first calculation unit U1031, the second calculation unit U1032, the third calculation unit U1033, the fourth calculation unit U1034, the fifth calculation unit U1035, the sixth calculation unit U1036, the seventh calculation unit U1037, the eighth calculation unit U1038, the first releasing unit U1041, the second releasing unit U1042, and the third releasing unit U1043 are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement 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 than one, and the technical problem that a large number of keyword paths are difficult to analyze at present is solved by adjusting 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.

The embodiment of the invention provides a storage medium, which comprises a stored program, wherein when the program runs, equipment where the storage medium is located is controlled to execute the keyword path analysis method.

The embodiment of the invention provides a processor, which is used for running a program, wherein the keyword path analysis 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:

Using formula K_b＝P₂×N_b/S+Q₂Calculating the middle click rate K of the target keyword by multiplying S/M_b；

Preferably, after calculating the target keyword placement index, the method further includes:

when the initial click rate K_aWhen the target keyword is larger than a first preset threshold value, the target keyword is released to a user in an initial search stage;

when the intermediate click rate K_bWhen the target keyword is larger than a second preset threshold value, the target keyword is released to the user in the middle-stage search;

when the end click rate K_cWhen the target keyword is larger than a third preset threshold value, the target keyword is released to the user in the mature searching stage;

Using formula K_e＝P₅×N_e/S+Q₅Calculating the target keyword by x S/MSelf-jump rate K_e；

Preferably, the method further comprises:

storing the at least one keyword path in a graph database in a directed graph mode;

the attribute of the node comprises click data of the keyword;

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:

Preferably, the method further comprises:

the attribute of the node comprises click data of the keyword;

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 is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, 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.

The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.

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

1. A keyword path analysis method is characterized by comprising the following steps:

counting click data of the target keywords according to click information of the target keywords in each keyword path; the target keyword is any keyword in any keyword path in the at least one keyword path; the click information includes a location, the location including: at least one of an initial position, an intermediate position, and an end position; the click data of the statistic target keyword comprises the following steps: counting the number of clicks of the target keyword at the initial position, the middle position and the end position of each keyword path within a preset range; the preset range comprises the acquired at least one keyword path;

calculating a release index of the target keyword according to the click data, wherein the release index is used for guiding release of the target keyword; the releasing indexes comprise an initial click rate, a middle click rate and an end click rate; the calculating the delivery index of the target keyword according to the click data comprises the following steps:

calculating the initial click rate Ka of the target keyword by using the formula Ka-P1 xNa/S + Q1 xS/M;

calculating the intermediate click rate Kb of the target keyword by using the formula Kb-P2 XNb/S + Q2 XS/M;

calculating an end click rate Kc of the target keyword using a formula Kc-P3 × Nc/S + Q3 × S/M;

p1, P2, P3, Q1, Q2 and Q3 are all preset weights, Na is the number of clicks of the target keyword at an initial position, Nb is the number of clicks of the target keyword at a middle position, Nc is the number of clicks of the target keyword at an end position, S is the number of keyword paths including the target keyword, and M is the total number of the at least one keyword path.

2. A keyword path analysis method is characterized by comprising the following steps:

counting click data of the target keywords according to click information of the target keywords in each keyword path; the target keyword is any keyword in any keyword path in the at least one keyword path; the click information comprises click types, and the click types comprise: at least one of click alone and self-jump; the click data of the statistic target keyword comprises the following steps: respectively counting the independent click number and the self-jump number of the target keyword in each keyword path within a preset range; the preset range comprises the acquired at least one keyword path; the keywords which are clicked independently are keywords which are not connected with any keyword in a keyword path; the self-jumping keyword is the same keyword as the previous keyword in the keyword path;

calculating a release index of the target keyword according to the click data, wherein the release index is used for guiding release of the target keyword; the putting indexes comprise individual click rate and self-jumping rate; the calculating the delivery index of the target keyword according to the click data comprises the following steps:

calculating an individual click rate Kd of the target keyword using a formula Kd of P4 × Nd/S + Q4 × S/M;

calculating a self-jumping rate Ke of the target keyword using a formula of Ke 5 × Ne/S + Q5 × S/M;

p4, P5, Q4 and Q5 are all preset weights, Nd is an individual number of clicks of the target keyword, Ne is a number of self-jumping revolutions of the target keyword, S is a number of keyword paths including the target keyword, and M is a total number of the at least one keyword path.

3. A keyword path analysis method is characterized by comprising the following steps:

counting click data of the target keywords according to click information of the target keywords in each keyword path; the target keyword is any keyword in any keyword path in the at least one keyword path; the click information comprises click types, and the click types comprise: at least one of roll-out and roll-in; the click data of the statistic target keyword comprises the following steps: respectively counting the roll-out number and the roll-in number of the target keyword in each keyword path within a preset range; the preset range comprises the acquired at least one keyword path;

calculating a release index of the target keyword according to the click data, wherein the release index is used for guiding release of the target keyword; the putting indexes comprise jumping rate, jumped rate and middle heart rate; the calculating the delivery index of the target keyword according to the click data comprises the following steps:

calculating the jump rate Kf of the target keyword by using a formula Kf-Nf/S;

calculating the skipped rate Kg of the target keyword by using a formula Kg to Ng/S;

calculating a center rate Kh of the target keyword by using a formula Kh ═ Nf + Ng)/S;

wherein Nf is the transfer-out number of the target keyword, Ng is the transfer-in number of the target keyword, and S is the number of keyword paths containing the target keyword.

4. A keyword path analysis apparatus, comprising:

the data statistics unit is used for counting the click data of the target keywords according to the click information of the target keywords in each keyword path; the target keyword is any keyword in any keyword path in the at least one keyword path; the click information includes a location, the location including: at least one of an initial position, an intermediate position, and an end position; the click data of the statistic target keyword comprises the following steps: counting the number of clicks of the target keyword at the initial position, the middle position and the end position of each keyword path within a preset range; the preset range comprises the acquired at least one keyword path;

the index calculation unit is used for calculating a release index of the target keyword according to the click data, wherein the release index is used for guiding release of the target keyword; the releasing indexes comprise an initial click rate, a middle click rate and an end click rate; the calculating the delivery index of the target keyword according to the click data comprises the following steps:

5. A keyword path analysis apparatus, comprising:

the data statistics unit is used for counting the click data of the target keywords according to the click information of the target keywords in each keyword path; the target keyword is any keyword in any keyword path in the at least one keyword path; the click information comprises click types, and the click types comprise: at least one of click alone and self-jump; the click data of the statistic target keyword comprises the following steps: respectively counting the independent click number and the self-jump number of the target keyword in each keyword path within a preset range; the preset range comprises the acquired at least one keyword path; the keywords which are clicked independently are keywords which are not connected with any keyword in a keyword path; the self-jumping keyword is the same keyword as the previous keyword in the keyword path;

the index calculation unit is used for calculating a release index of the target keyword according to the click data, wherein the release index is used for guiding release of the target keyword; the putting indexes comprise individual click rate and self-jumping rate; the calculating the delivery index of the target keyword according to the click data comprises the following steps:

6. A keyword path analysis apparatus, comprising:

the data statistics unit is used for counting the click data of the target keywords according to the click information of the target keywords in each keyword path; the target keyword is any keyword in any keyword path in the at least one keyword path; the click information comprises click types, and the click types comprise: at least one of roll-out and roll-in; the click data of the statistic target keyword comprises the following steps: respectively counting the roll-out number and the roll-in number of the target keyword in each keyword path within a preset range; the preset range comprises the acquired at least one keyword path;

the index calculation unit is used for calculating a release index of the target keyword according to the click data, wherein the release index is used for guiding release of the target keyword; the putting indexes comprise jumping rate, jumped rate and middle heart rate; the calculating the delivery index of the target keyword according to the click data comprises the following steps:

calculating the jump rate Kf of the target keyword by using a formula Kf-Nf/S;

7. A storage medium comprising a stored program, wherein the apparatus on which the storage medium is located is controlled to execute the keyword path analysis method according to any one of claims 1 to 3 when the program is executed.

8. A processor, configured to run a program, wherein the program when running performs the keyword path analysis method according to any one of claims 1 to 3.