CN109962983B

CN109962983B - Click rate statistical method and device

Info

Publication number: CN109962983B
Application number: CN201910250446.2A
Authority: CN
Inventors: 苏宁; 孙键; 陈炜鹏; 许静芳
Original assignee: Beijing Sogou Technology Development Co Ltd
Current assignee: Beijing Sogou Technology Development Co Ltd
Priority date: 2019-03-29
Filing date: 2019-03-29
Publication date: 2021-11-23
Anticipated expiration: 2039-03-29
Also published as: CN109962983A

Abstract

The invention provides a click rate statistical method and a device, wherein the method comprises the following steps: determining a target search result item from a plurality of search result items corresponding to the target query term; acquiring the click times of the target search result item which is clicked by a user within a first preset time period; acquiring the corresponding checking times of the target search result item in the first preset time period, wherein the checking times are used for representing the times of browsing the target search result item in a search result page by a user; and obtaining the click rate of the target search result item according to the click times and the test times. The invention solves the problem of low click rate obtained by the prior art, improves the accuracy of click rate statistics and the accuracy of prediction and sequencing of the search results corresponding to the user query words.

Description

Click rate statistical method and device

Technical Field

The invention relates to the technical field of statistics and network search, in particular to a click rate statistical method and device.

Background

The click rate of the search result reflects the relevance feedback of the user on the search result, and is widely applied to the work of relevance prediction of the search result, sequencing of the search result and the like.

The existing click rate calculation method comprises the following steps: click rate is the number of clicks/number of impressions. In a real mobile search scenario, a user inputs a query term and triggers a search operation, and a home page generally provides a plurality of search results. Through log analysis, it is found that a user often only browses a current display interface when using a search engine, and generally few scrolling operations are performed, that is, search result items located behind a first screen are not actually seen by the user, and naturally, there is no possibility of being clicked by the user.

However, according to the existing statistical method, the search results are still regarded as being shown, and times of the search results are accumulated, so that the click rate of the clicked search results is low in the actual statistical results, and the prediction and the sequencing of the search results are distorted.

Disclosure of Invention

In view of this, an object of the embodiments of the present invention is to provide a click rate statistical method and apparatus, which solve the problem of low click rate obtained in the prior art, improve the accuracy of click rate statistics, and improve the accuracy of prediction and ranking of search results corresponding to a user query term.

In a first aspect, the present application provides the following technical solutions through an embodiment of the present application:

a click rate statistical method comprises the following steps:

determining a target search result item from a plurality of search result items corresponding to the target query term;

acquiring the click times of the target search result item which is clicked by a user within a first preset time period;

acquiring the corresponding checking times of the target search result item in the first preset time period, wherein the checking times are used for representing the times of browsing the target search result item in a search result page by a user;

and obtaining the click rate of the target search result item according to the click times and the test times.

Preferably, the obtaining of the number of clicks of the target search result item, which is clicked by the user within the first preset time period, includes:

acquiring a search log of a search engine;

and counting the number of clicks of the target search result item which is clicked by the user in the first preset time period based on the search log.

Preferably, the counting the number of clicks of the target search result item by a user in the first preset time period includes:

and if the same user carries out multi-click operation on the target search result item within a second preset time period, the multi-click operation is designed as one-click operation, and the second preset time period is smaller than the first preset time period.

Preferably, the obtaining of the number of times of the corresponding verification of the target search result item in the first preset time period includes:

acquiring a window log of a search engine; the window log records relevant information of the user operating the search result page corresponding to each query term;

and analyzing and counting the user operation behaviors in the first preset time period based on the window log to obtain the corresponding test times of the target search result item in the first preset time period.

Preferably, the analyzing and counting the user operation behavior in the first preset time period based on the window log to obtain the number of times of the test corresponding to the target search result item in the first preset time period includes:

based on the window log, obtaining relevant information of the user for operating the search result page corresponding to each query word;

analyzing relevant information of operation of the user on a search result page corresponding to each query word to obtain a check operation corresponding to a target search result item, wherein the check operation corresponding to the target search result item is that the user operates the search result page to enable the target search result item to be displayed in a browsable area of the user;

and counting to obtain the number of times of testing corresponding to the target search result item in the first preset time period.

Preferably, the checking operation corresponding to the target search result item includes one or more of the following operations:

query operation corresponding to the target search result item, so that the target search result item is displayed in a browsable area of a user after the query operation is completed;

a scrolling operation corresponding to the target search result item such that the target search result item is presented within a browsable area of a user before the scrolling operation starts or after the scrolling operation stops;

a jump operation corresponding to the target search result item such that the target search result item is presented within a browsable area of a user before the jump operation begins;

a rollback operation corresponding to the target search result item such that the target search result item is displayed in a browsable area of a user after the rollback operation is completed;

switching operation corresponding to the target search result item, so that the target search result item is displayed in a browsable area of a user before or after the switching operation is triggered;

and clicking the target search result item.

Preferably, the method further comprises:

and if the same user carries out a plurality of times of inspection operations on the target search result item within a third preset time period, the plurality of times of inspection operations are designed as one time of inspection operation, and the third preset time period is smaller than the first preset time period.

Preferably, the determining a target search result item from a plurality of search result items corresponding to the target query term includes:

the target search result item is determined from the top 10 search result items located in the top page presentation.

Preferably, the obtaining the click rate of the target search result item according to the number of clicks and the number of tests includes:

and taking the ratio of the click times to the test times as the click rate of the target search result item.

In a second aspect, based on the same inventive concept, the present application provides the following technical solutions through an embodiment of the present application:

a click-through rate statistics apparatus, comprising:

the target search result item determining module is used for determining a target search result item from a plurality of search result items corresponding to the target query word;

the click frequency acquisition module is used for acquiring the click frequency of the target search result item which is clicked by a user within a first preset time period;

the checking frequency acquisition module is used for acquiring the checking frequency corresponding to the target search result item in the first preset time period, wherein the checking frequency is used for representing the frequency of browsing the target search result item in a search result page by a user;

and the click rate obtaining module is used for obtaining the click rate of the target search result item according to the click times and the inspection times.

Preferably, the click number obtaining module is further configured to:

acquiring a search log of a search engine; and counting the number of clicks of the target search result item which is clicked by the user in the first preset time period based on the search log.

Preferably, the click number obtaining module is further configured to:

Preferably, the check number obtaining module is further configured to:

acquiring a window log of a search engine; the window log records relevant information of the user operating the search result page corresponding to each query term; and analyzing and counting the user operation behaviors in the first preset time period based on the window log to obtain the corresponding test times of the target search result item in the first preset time period.

Preferably, the check number obtaining module is further configured to:

based on the window log, obtaining relevant information of the user for operating the search result page corresponding to each query word; analyzing relevant information of operation of the user on a search result page corresponding to each query word to obtain a check operation corresponding to a target search result item, wherein the check operation corresponding to the target search result item is that the user operates the search result page to enable the target search result item to be displayed in a browsable area of the user; and counting to obtain the number of times of testing corresponding to the target search result item in the first preset time period.

and clicking the target search result item.

Preferably, the check number obtaining module is further configured to:

Preferably, the target search result item determination module is further configured to:

Preferably, the click rate obtaining module is further configured to:

In a third aspect, based on the same inventive concept, the present application provides the following technical solutions through an embodiment of the present application:

a click-through rate statistics apparatus comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured for execution by one or more processors the one or more programs include instructions for:

determining a target search result item from a plurality of search result items corresponding to the target query term; acquiring the click times of the target search result item which is clicked by a user within a first preset time period; acquiring the corresponding checking times of the target search result item in the first preset time period, wherein the checking times are used for representing the times of browsing the target search result item in a search result page by a user; and obtaining the click rate of the target search result item according to the click times and the test times.

In a fourth aspect, based on the same inventive concept, the present application provides the following technical solutions through an embodiment of the present application:

a computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:

One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

the invention provides a click rate statistical method and a device, wherein the method comprises the following steps: determining a target search result item from a plurality of search result items corresponding to the target query term; acquiring the click times of the target search result item which is clicked by a user within a first preset time period; acquiring the corresponding checking times of the target search result item in the first preset time period, wherein the checking times are used for representing the times of browsing the target search result item in a search result page by a user; and obtaining the click rate of the target search result item according to the click times and the test times. Because the number of times of examination is used for representing the real number of times that the user browses the target search result item in the search result page, compared with the prior art that whether the target search result item is browsed by the user is not concerned, and the number of times of statistics is recorded as long as the target search result item is displayed by a search engine, the method provided by the invention can be used for counting the click rate of the target search result item by obtaining the number of times of examination, thereby solving the problem that the click rate obtained by the prior art is low, improving the accuracy of the click rate statistics, and improving the accuracy of prediction and sequencing of the search result corresponding to the user query word.

In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

FIG. 1 is a flowchart of a click rate statistical method according to an embodiment of the present invention;

FIG. 2 is a flowchart illustrating an embodiment of step S20 of FIG. 1;

FIG. 3 is a flowchart illustrating an embodiment of step S30 of FIG. 1;

FIG. 4 is a functional block diagram of a click rate statistic apparatus according to a second embodiment of the present invention;

FIG. 5 is a block diagram illustrating an exemplary click rate statistics apparatus according to the present invention;

fig. 6 is a schematic structural diagram of an exemplary server according to the present invention.

Detailed Description

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.

For purposes of explanation and understanding, the following detailed description describes embodiments of the invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numbers indicate like or similar elements or elements having like or similar functionality throughout. The embodiments described below with reference to the drawings are illustrative only and should not be construed as limiting the invention.

As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.

It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

The term "plurality" as used herein generally refers to "more than two," including "two.

Example one

Referring to fig. 1, fig. 1 shows a flowchart of a click rate statistical method provided in this embodiment, and each step in the flowchart will be described in detail below. The method specifically comprises the following steps:

step S10: determining a target search result item from a plurality of search result items corresponding to the target query term;

step S20: acquiring the click times of the target search result item which is clicked by a user within a first preset time period;

step S30: acquiring the corresponding checking times of the target search result item in the first preset time period, wherein the checking times are used for representing the times of browsing the target search result item in a search result page by a user;

step S40: and obtaining the click rate of the target search result item according to the click times and the test times.

In step S10, a target search result item is determined from a plurality of search result items corresponding to the target query term. The target query term may be determined arbitrarily, and its representation form is not limited, and may be, for example, a picture, a character in any language, a number, a code, a symbol, and the like, which may be input to a search engine for retrieval.

The search result item is a result retrieved by the search engine after the user inputs the target query term, and the user in this embodiment may be any user, which is the same as that in the following and will not be described again. The search can be performed by the same user or different users each time the target query word is searched to obtain a search result item; that is, any user may use the target query term described in step S10 to perform the search, and obtain the search result.

The target search result item is determined arbitrarily among a plurality of search result items corresponding to the target query term, and the target search result item is the search result item needing to count the click rate.

In a preferred scheme, the search engine used for obtaining a plurality of search result items by searching the target query word for a plurality of times should be the same search engine.

In step S20, the number of clicks of the target search result item that is clicked by the user within a first preset time period is obtained. The first preset time period may be customized, for example: 1 hour, 6 hours, 24 hours, 7 days, 30 days, etc., and is not particularly limited herein.

And clicking operation, namely clicking operation performed on any search result item in the search result page by the user, and checking the page content corresponding to the search result item.

Referring to fig. 2, the obtaining of the number of clicks of the target search result item that is clicked by the user in the first preset time period in step S20 specifically includes:

step S21: acquiring a search log of a search engine;

step S22: and counting the number of clicks of the target search result item which is clicked by the user within a first preset time period based on the search log.

In step S21, the search log is generated by the user during the search operation using the search engine, and can be directly obtained and used in the embodiment of the present invention. The information contained in the search log includes, but is not limited to: the query terms used by the user, the generation time of the search log, and the ID number of the search result item clicked by the user.

In step S22, the number of clicks of the target search result item that is clicked by the user in the search result page within the first preset time period may be queried in the search log based on the ID number of the target search result item.

In step S22, in order to avoid statistical distortion caused by the same user clicking the same search result item multiple times in succession during the use of the search engine, the number of clicks may not be repeatedly recorded for multiple clicks of the same search result item by the same user within a second preset time period. That is, if the same user performs a multi-click operation on the target search result item within a second preset time period, the multi-click operation is counted as a one-click operation, where the second preset time period is smaller than the first preset time period. The second preset time period may be a time period taken for the user to start querying the target query term until the user quits viewing the search result page corresponding to the target query term, or may be a fixed time period, such as 1 minute, 5 minutes, 10 minutes, and the like. Wherein quitting viewing the search result page corresponding to the target query term may include: exiting the current search result page, closing the current search result page, inputting a new query term in the search box, starting the search, and the like, which is not specifically limited herein.

In step S30, a corresponding number of times of verification of the target search result item in the first preset time period is obtained, where the number of times of verification is used to indicate a real number of times that the user browses the target search result item in a search result page.

As an alternative embodiment, as shown in fig. 3, the obtaining of the corresponding number of times of verification of the target search result item in the first preset time period in step S30 includes:

step S31: acquiring a window log of a search engine, wherein relevant information of a user operating a search result page corresponding to each query word is recorded in the window log;

step S32: and analyzing and counting the user operation behaviors in the first preset time period based on the window log to obtain the corresponding test times of the target search result item in the first preset time period.

Window log, i.e. viewport log. The generation of the window log may be done on the terminal (e.g., smartphone, or tablet, etc.), and after the window log is generated, the terminal may send the window log to the server for statistical analysis.

The specific implementation of generating the window log may be: a section of code is embedded in a search result page of a search engine, and the code can record operation behaviors of scrolling, jumping, switching, page turning, clicking and the like on the search result page by a user to obtain a window log. Meanwhile, the embedded code can also obtain the size of an area capable of displaying the search result item on the terminal display screen, the size of a display font, the typesetting mode of the search result item to be displayed and the like, so that the search result item currently displayed to the user on the terminal display screen is determined, and the ID number of the search result item is recorded in a window log.

In a specific implementation process, the analyzing and counting, based on the window log, user operation behaviors in a first preset time period to obtain the number of tests corresponding to the target search result item in the first preset time period in step S32 may include:

and obtaining relevant information of the user operating the search result page corresponding to each query word based on the window log, analyzing the relevant information to obtain the test operation corresponding to the target search result item, and counting the test times corresponding to the target search result item in the first preset time period.

Wherein, the checking operation may refer to: the user operates the search result page so that the corresponding search result items are displayed in the browsable area of the user. Therefore, the verification operation corresponding to the target search result item may refer to: the user manipulates the search results page so that the target search result item is presented within the user's viewable area (i.e., displayed on the display screen of the user device).

The checking operation corresponding to the target search result item can include one or more of the following modes (A1-A6):

a1, query operation corresponding to the target search result item; the query operation is used for querying a plurality of search result items corresponding to the target query term; the query operation corresponding to the target search result item may be such that the target search result item is presented within the user's viewable area (i.e., on the display of the user device) after the query operation is completed. At this time, it can be approximately determined that the user browses the target search result item.

A2, a scroll operation corresponding to the target search result item; the scrolling operation is used for controlling the search result page to scroll up and down to display different search result items; the scrolling operation corresponding to the target search result item may be such that the target search result item is presented within the user's viewable area (i.e., on the display of the user device) before the scrolling operation begins or after the scrolling operation has stopped. At this time, it can be approximately determined that the user browses the target search result item.

A3, jumping operation corresponding to the target search result item; the skipping operation is used for leaving the current search result page and skipping to other pages; the jump operation corresponding to the target search result item may be such that the target search result item is presented within the user's viewable area (i.e., on the display of the user device) before the jump operation begins. At this time, it can be approximately determined that the user browses the target search result item.

For example, the jump operation may be: and (4) jumping operation generated after the user inputs the content in the browser website input field/search engine search box.

A4, a rollback operation corresponding to the target search result item; wherein the rollback operation is used for returning to the search result page by other pages; the rollback operation corresponding to the target search result item may be such that the target search result item is presented within the viewable area of the user (i.e., on the display screen of the user device) after the rollback operation is completed. At this time, it can be approximately determined that the user browses the target search result item.

A5, switching operation corresponding to the target search result item; the switching operation is used for switching the label pages on the browser; the switching operation corresponding to the target search result item may be such that the target search result item is presented within the viewable area of the user (i.e., on the display screen of the user device) before or after the switching operation is triggered or completed. At this time, it can be approximately determined that the user browses the target search result item.

For example, the switching operation includes: (1) a user opens a certain search result item by using a new tab page in a browser, and if the operation of leaving a search result page corresponding to a target query word is performed, the corresponding target search result item is displayed in a browsable area of the user before the switching operation is triggered; (2) and correspondingly, after the switching operation is finished, the target search result item is displayed in the browsable area of the user.

A6, click operation on the target search result item. If the user clicks the target search result item on the search result page, it can be approximately determined that the user browses the target search result item.

In the specific implementation process, if the same user repeatedly performs the checking operation in a short time or in the same time aiming at the query process of the target query term, the statistical result is distorted. In order to improve the accuracy of the statistics of the inspection operations, if multiple inspection operations are performed on the target search result item within a third preset time period for the same user, the multiple inspection operations can be counted as one inspection time, and the third preset time period is smaller than the first preset time period. The third preset time period may be a time period from the time when the target query term is queried to the time when the search result page corresponding to the target query term exits, or may be a fixed time period, such as 1 minute, 5 minutes, 10 minutes, and the like.

For example, in one search for the same query term by the same user, a plurality of window logs are correspondingly generated, and the number of times of check of the search can be directly counted as 1.

In a specific implementation process, based on the window log, the corresponding test times of the target search result item in a first preset time period can be counted.

Next, a generation process of the window log will be explained.

In particular implementations, the window log may be generated by one or more of the following (B1-B6):

b1, when the query operation of the user is detected, a window log can be generated; wherein the window log records: the ID number of the search result item displayed on the search result page, the time for generating the window log, the query ID corresponding to the current query term, and the like.

The query operation of the user may include, but is not limited to, the user inputting a query term in a search box of a search engine to perform a query; the number of queries using the query term may include, but is not limited to, how many times the current query is the first query in a search engine.

When determining the search result item displayed on the search result page, the determination may be made according to factors such as the size of an area available for displaying the search result item on the terminal display screen, the size of a display font, and the type setting mode of the search result item to be displayed.

B2, when detecting the scroll operation of the user, generating a scroll start window log, where the scroll start window log records: the ID number of the search result item presented on the search result page at the start of the scroll operation, the time at which the window log was generated, and so on; when the stop of the scroll operation is detected, generating a scroll end window log, wherein the scroll end window log records: the ID number of the search result item displayed on the search result page when the scrolling operation is stopped, the time for generating the window log, the query ID corresponding to the current query term, and the like.

The scrolling operation of the user may include, but is not limited to, scrolling down from the top position of the first page of the search result page, scrolling up or up from the search result page currently displayed in the window, and the like.

B3, when the jump operation of the user is detected, a window log can be generated; wherein the window log records: skipping away from the ID number of the search result item presented on the current search results page, the time at which the window log was generated, and so on.

The user's skip operation may include, but is not limited to, skipping away from the current search result page after the user inputs other websites or other query terms.

B4, when detecting the rollback operation of the user, generating a window log, where: the ID number of the search result item displayed on the returned search result page, the time for generating the window log, the query ID corresponding to the current query term, and the like.

The backspacing operation of the user can be but is not limited to that the user clicks a return button on a landing page of a certain search result item to return to the search result page; or the user clicks a return button on the current search result page, returns to the previous search result page, and so on.

B5, when detecting the switching operation of the user, generating a window log, where the window log records: the ID number of the search result item displayed on the search result page before or after the switching operation is triggered, the time for generating the window log, the query ID corresponding to the current query term, and the like.

The switching operation of the user may include, but is not limited to: switching the user from other tab pages to the tab page where the search result page is located; or, the user opens a certain search result item in the browser by using the new tab page, and leaves the search result page corresponding to the target query term.

B6, when a click operation of the user is detected, a window log may be generated, where the window log records: the ID number of the search result item, the time at which the window log was generated, the query ID corresponding to the current query term, and so on.

In this embodiment of the application, the obtaining of the click rate of the target search result item according to the number of clicks and the number of tests in step S40 shown in fig. 1 may specifically include:

and obtaining the click rate of the target search result item according to the ratio of the click times to the test times. For example: click rate is the number of clicks/number of tests.

In addition, in other schemes, the click rate can be obtained by adopting the click times and the check times through other calculation methods. For example, different weights are respectively matched with the click times or the check times, or the click times or the check times are multiplied by corresponding correction coefficients, and then ratio calculation is performed to obtain the click rate.

As an alternative embodiment, the determining a target search result item from a plurality of search result items corresponding to a target query term in step S10 shown in fig. 1 may specifically include:

In a specific implementation process, in a mobile application scenario of a small-screen electronic device such as a mobile phone or a tablet computer, a user inputs a target query term, and after a search result item is obtained, a home page generally provides 10-15 search results, but due to the limitation of a small-screen display space, the user can only see the first 1-3 search result items in a first screen. Through search log analysis, the user often only browses the first page of a search result page when using a search engine, and page turning is rarely performed. When the first few search result items of the home page cannot well meet the requirements of the user, the user can perform scrolling operation, browse subsequent search result items, perform checking, clicking and other operations. When the user scrolls to the tail of the home page, if the user's own requirements cannot be met, the user may tentatively click the last results, so that the click times of the results are high, and distortion exists.

According to data statistics, based on the click rate curve of the position level of the test behavior, there is a significant tail-warp phenomenon from the 10 th position, i.e. the 10 th position and the 10 th position are followed by the user's trial click. Therefore, when the click rate is calculated, the search result items corresponding to the query terms can be filtered, and the first 10 relatively accurate search result items are reserved. In some embodiments, if the number of results presented on the top page is less than 10, further analysis is required to consider retaining the first N relatively accurate search result items according to the click-through rate curve, where N is less than or equal to the total number of search result items presented on the top page.

In order to more clearly explain the method and the effect thereof in the present embodiment, a specific example is provided in the present embodiment:

aiming at a certain user to search by using a search engine, the following operations are sequentially executed:

(a) the user inputs a query word q, executes query operation and page loading, 11 results are obtained, the first screen displays 3 results, and a window log (search result items are represented by arrangement sequence numbers) is generated:

window Log 1: time load 1,2, 3.

Wherein, the field [ time ] represents the generation time of the window log 1, the field [ load ] represents the loading state (the state is caused by the query operation), and the field [ results:1,2,3] represents that the display screen of the user equipment currently shows the search result items with the sequence numbers 1,2,3 after the query.

(b) The user clicks the first search result item, the jump operation and the page jump occur, and a window log is generated:

window log 2: time Leave results 1,2, 3.

In addition, since the first search result item is clicked, a search log for clicking the first search result item is generated.

In the window log 2, a field [ time ] represents the generation time of the window log 2, a field [ leave ] represents the leaving state (the leaving state is caused by the jump operation), and a field [ results:1,2,3] represents that the display screen of the user equipment before the page jump currently shows search result items with sequence numbers 1,2, 3.

(c) The user falls back to the search results page, generating a window log:

window log 3: time load 1,2, 3.

In the window log 3, a field [ time ] represents the generation time of the window log 3, a field [ load ] represents the loading state (the state is caused by rollback operation), and a field [ results:1,2,3] represents that search result items with sequence numbers 1,2,3 are currently shown on the display screen of the user equipment after page rollback.

(d) The user generates a scroll operation on a search result page to generate a window log:

window log 4: [ time ] [ scroll start ] [ results:1,2,3 ].

In the window log 4, a field [ time ] represents the generation time of the window log 4, a field [ scroll start ] represents the scroll start state (the state is caused by the scroll operation), and a field [ results:1,2,3] represents that the search result items with sequence numbers 1,2,3 are currently shown on the display screen of the user equipment before the scroll start.

(e) The user stops the scrolling operation, the 3 rd and 4 th search result items are displayed in the current screen, and a window log is generated:

window log 5: [ time ] [ scroll stop ] [ results:3,4 ].

In the window log 5, a field [ time ] represents the generation time of the window log 5, a field [ scroll stop ] represents a scroll stop state (the state is caused by a scroll operation), and fields [ results:3,4] represent that search result items with sequence numbers 3 and 4 are currently shown on the display screen of the user equipment when the scroll is stopped.

(f) The user clicks the 4 th search result item by using a new tag opening method to generate a window log:

window log 6: time ] [ hidden ] [ results:3,4 ].

In the window log 6, a field [ time ] represents the generation time of the window log 6, a field [ hidden ] represents a hidden state (the hidden state is caused by switching operation), and fields [ results:3,4] represent that search result items with sequence numbers 3,4 are currently shown on the display screen of the user equipment before the tab page is switched.

(g) The user switches to the original label page to generate a window log:

window log 7: time [ visible ] [ results:3,4 ].

In the window log 7, a field [ time ] represents the generation time of the window log 7, a field [ visible ] represents the display state (the state is caused by switching operation), and a field [ results:3,4] represents that the search result items with sequence numbers 3,4 are currently displayed on the display screen of the user equipment after the tab page is switched.

(h) The user inputs other websites, leaves the current search engine page, and generates a window log:

window log 8: time Leave results 3, 4.

In the window log 8, a field [ time ] represents the generation time of the window log, a field [ leave ] represents the leaving state (the leaving state is caused by the jump operation), and fields [ results:3,4] represent that the search result items with sequence numbers 3,4 are currently shown on the display screen of the user equipment before the page jump.

According to the window log, the user checks the results 1,2,3 and 4, and the statistical results of the search are as follows by combining the search log of the search engine:

note that: result 1 represents a search result item with a number 1, result 2 represents a search result item with a number 2, result 3 represents a search result item with a number 3, and so on. The table keeps only the top 10 results of the search result items and discards the results after the 10 th result when counting. The table records only one user click, check and reveal in one search action. In one search, the number of tests and clicks of a certain result may only be 1 or 0, that is, tested or not tested, clicked or not clicked, and both the number of clicks and the number of tests are 1.

Wherein "number of presentations" is for the prior art, all search result items included in the search result page currently presented are regarded as being presented by default (i.e., all count as 1), even though some search result items are not actually presented on the terminal screen and actually browsed by the user. For example, as shown in the above table, all of the above 10 search result items are counted to be presented 1 time, but actually, all of the search result items 5 to 10 are not presented on the terminal screen and are actually browsed by the user, and if the method is still based on the calculation manner of "click rate ═ click number/presentation number" in the existing method, the denominator is larger, and the calculation result is smaller, which is not in accordance with the actual situation.

In the embodiment, only the search result items displayed on the screen are counted to obtain the number of times of examination, and when the click rate is calculated based on the click rate as the click rate/the examination number, the denominator is closer to the actual situation, and the accuracy is higher.

Taking result 4 as a target search result item as an example:

in a first preset time period (for example, within 1 hour immediately after the past), the target query word is q, the result 4 is determined to be clicked 50 times by the all-network user (or the specific user group) within the first preset time period based on the search log, and the result 4 is determined to be checked 100 times by the all-network user (or the specific user group) within the first preset time period based on the window log, then based on the calculation method in the present embodiment, the click rate is 50/100-50%. Here, the number of times of the check is the number of times that the result 4 is actually displayed on the display screen of the user equipment, which is approximately the actual number of times that the user browses the result 4, so that the final click rate is closer to the actual situation, and the accuracy rate is higher.

The technical scheme in the embodiment of the application at least has the following technical effects or advantages:

in this embodiment, a click rate statistical method includes: determining a target search result item from a plurality of search result items corresponding to the target query term; acquiring the click times of the target search result item which is clicked by a user within a first preset time period; acquiring the corresponding checking times of the target search result item in the first preset time period, wherein the checking times are used for representing the times of browsing the target search result item in a search result page by a user; and obtaining the click rate of the target search result item according to the click times and the test times. Because the number of times of examination is used for representing the real number of times that the user browses the target search result item in the search result page, compared with the prior art that whether the target search result item is browsed by the user is not concerned, and the number of times of statistics is recorded as long as the target search result item is displayed by a search engine, the method provided by the invention can be used for counting the click rate of the target search result item by obtaining the number of times of examination, thereby solving the problem that the click rate obtained by the prior art is low, improving the accuracy of the click rate statistics, and improving the accuracy of prediction and sequencing of the search result corresponding to the user query word.

Example two

Based on the same inventive concept, please refer to fig. 4, in this embodiment, a click rate statistical apparatus 600 is provided, which includes:

a target search result item determining module 601, configured to determine a target search result item from a plurality of search result items corresponding to a target query term;

a click frequency obtaining module 602, configured to obtain a click frequency of the target search result item that is clicked by a user within a first preset time period;

a checking frequency obtaining module 603, configured to obtain a checking frequency corresponding to the target search result item in the first preset time period, where the checking frequency is used to indicate a frequency of browsing the target search result item in a search result page by a user;

and a click rate obtaining module 604, configured to obtain a click rate of the target search result item according to the number of clicks and the number of tests.

As an optional implementation manner, the click number obtaining module 602 is further configured to:

As an optional implementation manner, the examination number obtaining module 603 is further configured to:

As an optional implementation manner, the checking operation corresponding to the target search result item includes one or more of the following operations:

and clicking the target search result item.

As an optional implementation manner, the target search result item determining module 601 is further configured to:

As an optional implementation manner, the click rate obtaining module 604 is further configured to:

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Referring to fig. 5, the present invention further provides an exemplary click rate statistical apparatus 800, and fig. 5 is a block diagram of the apparatus 800. For example, the apparatus 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.

Referring to fig. 5, the apparatus 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, and communication component 816.

The processing component 802 generally controls overall operation of the device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing elements 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operation at the device 800. Examples of such data include instructions for any application or method operating on device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

Power component 806 provides power to the various components of device 800. The power components 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device 800.

The multimedia component 808 includes a screen that provides an output interface between the device 800 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user.

The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front-facing camera and/or the rear-facing camera may receive external multimedia data when the device 800 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the apparatus 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the device 800. For example, the sensor assembly 814 may detect the open/closed state of the device 800, the relative positioning of the components, such as a display and keypad of the apparatus 800, the sensor assembly 814 may also detect a change in position of the apparatus 800 or a component of the apparatus 800, the presence or absence of user contact with the apparatus 800, orientation or acceleration/deceleration of the apparatus 800, and a change in temperature of the apparatus 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate communications between the apparatus 800 and other devices in a wired or wireless manner. The device 800 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast associated information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communications component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the methods provided in the above-described method embodiments.

In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 804 comprising instructions, executable by the processor 820 of the device 800 to perform the above-described method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

A computer-readable storage medium, in particular a non-transitory computer-readable storage medium, having instructions which, when executed by a processor of a mobile terminal, enable the mobile terminal to perform a click-through rate statistics method, the method comprising: determining a target search result item from a plurality of search result items corresponding to the target query term; acquiring the click times of the target search result item which is clicked by a user within a first preset time period; acquiring the corresponding checking times of the target search result item in the first preset time period, wherein the checking times are used for representing the times of browsing the target search result item in a search result page by a user; and obtaining the click rate of the target search result item according to the click times and the test times.

Fig. 6 is a schematic structural diagram of a server in an embodiment of the present invention. The server 1900 may vary widely by configuration or performance and may include one or more Central Processing Units (CPUs) 1922 (e.g., one or more processors) and memory 1932, one or more storage media 1930 (e.g., one or more mass storage devices) storing applications 1942 or data 1944. Memory 1932 and storage medium 1930 can be, among other things, transient or persistent storage. The program stored in the storage medium 1930 may include one or more modules (not shown), each of which may include a series of instructions operating on a server. Still further, a central processor 1922 may be provided in communication with the storage medium 1930 to execute a series of instruction operations in the storage medium 1930 on the server 1900.

The server 1900 may also include one or more power supplies 1926, one or more wired or wireless network interfaces 1950, one or more input-output interfaces 1958, one or more keyboards 1956, and/or one or more operating systems 1941, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.

It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.

The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A click rate statistical method is characterized by comprising the following steps:

acquiring the corresponding checking times of the target search result item in the first preset time period, wherein the checking times are used for representing the times of browsing the target search result item in a search result page by a user; wherein, include: acquiring a window log of a search engine; the window log records relevant information of the user operating the search result page corresponding to each query word; analyzing and counting the user operation behavior in the first preset time period based on the window log to obtain the number of times of inspection corresponding to the target search result item in the first preset time period;

2. The method of claim 1, wherein obtaining the number of clicks of the target search result item that is clicked by a user within a first preset time period comprises:

acquiring a search log of a search engine;

3. The method according to claim 2, wherein the counting the number of clicks of the target search result item by a user within the first preset time period comprises:

4. The method according to claim 1, wherein the analyzing and counting the user operation behavior in the first preset time period based on the window log to obtain the number of tests corresponding to the target search result item in the first preset time period comprises:

analyzing relevant information of the user operating the search result page corresponding to each query term to obtain a checking operation corresponding to the target search result term, wherein the checking operation corresponding to the target search result term is as follows: the user operates the search result page to enable the target search result item to be displayed in a browsable area of the user;

5. The method of claim 4, wherein the verification operation corresponding to the target search result item comprises one or more of the following operations:

and clicking the target search result item.

6. The method of claim 4, further comprising:

7. The method of claim 1, wherein determining the target search result item from a plurality of search result items corresponding to the target query term comprises:

8. The method according to any one of claims 1 to 7, wherein obtaining the click rate of the target search result item according to the number of clicks and the number of tests comprises:

9. A click rate statistic device, comprising:

the checking frequency acquisition module is used for acquiring the checking frequency corresponding to the target search result item in the first preset time period, wherein the checking frequency is used for representing the frequency of browsing the target search result item in a search result page by a user; and is also used for: acquiring a window log of a search engine; the window log records relevant information of the user operating the search result page corresponding to each query word; analyzing and counting the user operation behavior in the first preset time period based on the window log to obtain the number of times of inspection corresponding to the target search result item in the first preset time period;

10. The apparatus of claim 9, wherein the click number obtaining module is further configured to:

11. The apparatus of claim 10, wherein the click number obtaining module is further configured to:

12. The apparatus of claim 9, wherein the inspection number obtaining module is further configured to:

based on the window log, obtaining relevant information of the user for operating the search result page corresponding to each query word; analyzing relevant information of the user operating the search result page corresponding to each query term to obtain a checking operation corresponding to the target search result term, wherein the checking operation corresponding to the target search result term is as follows: the user operates the search result page to enable the target search result item to be displayed in a browsable area of the user; and counting to obtain the number of times of testing corresponding to the target search result item in the first preset time period.

13. The apparatus of claim 12, wherein the verification operation corresponding to the target search result item comprises one or more of the following operations:

and clicking the target search result item.

14. The apparatus of claim 12, wherein the inspection number obtaining module is further configured to:

15. The apparatus of claim 9, wherein the target search result item determination module is further configured to:

16. The apparatus according to any one of claims 9 to 15, wherein the click rate obtaining module is further configured to:

17. A click-through rate statistics apparatus comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory, and wherein execution of the one or more programs by one or more processors comprises instructions for:

acquiring the corresponding checking times of the target search result item in the first preset time period, wherein the checking times are used for representing the times of browsing the target search result item in a search result page by a user; which comprises the following steps: acquiring a window log of a search engine; the window log records relevant information of the user operating the search result page corresponding to each query word; analyzing and counting the user operation behavior in the first preset time period based on the window log to obtain the number of times of inspection corresponding to the target search result item in the first preset time period;

18. A computer-readable storage medium, on which a computer program is stored, which program, when executed by a processor, carries out the steps of: