CN110210507B

CN110210507B - Method and device for detecting machine click and readable storage medium

Info

Publication number: CN110210507B
Application number: CN201811265801.5A
Authority: CN
Inventors: 翁家才
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2018-10-29
Filing date: 2018-10-29
Publication date: 2023-06-02
Anticipated expiration: 2038-10-29
Also published as: CN110210507A

Abstract

The application discloses a method and a device for detecting machine clicking and a readable storage medium, and relates to the technical field of computers. The method comprises the following steps: acquiring click coordinate data of n target type contents; determining an ith vector to be detected and a target vector; and when the vector distance between the ith vector to be detected and the target vector is greater than a first distance threshold, determining the content of the ith target type as the content of the received machine click. The method comprises the steps of determining a target vector and an ith to-be-detected vector, wherein the target vector represents clicking characteristics when a clickable area is clicked manually, the ith to-be-detected vector is used for representing clicking characteristics of ith target type content, comparing similarity between the ith to-be-detected vector and the target vector, and considering the ith target type content as the content for receiving machine clicking when the vector distance is greater than a threshold value, so that the identification accuracy of the machine clicking is improved.

Description

Method and device for detecting machine click and readable storage medium

Technical Field

The embodiment of the application relates to the technical field of computers, in particular to a method and a device for detecting machine clicking and a readable storage medium.

Background

A pay Per Click (CPC) advertisement refers to an advertisement that a product provider pays for a distribution account on which the advertisement is distributed based on the amount of clicks received. A user can check the advertisement in a user interface of the terminal, click a clickable area in the advertisement, and then enter a detailed content introduction interface of a commodity corresponding to the advertisement, and the more the number of times the user clicks on the advertisement, the higher the reward obtained from a product provider corresponding to the advertisement by a release account for releasing the advertisement.

In order to obtain higher consideration, the account is issued, and the click amount of the advertisement is increased in a machine click manner, wherein machine click refers to virtual clicking on a clickable area by controlling a plurality of electronic devices through an automatic script or software, and the machine click generally refers to multiple clicks on the same coordinate in the clickable area. In the related art, when detecting whether an advertisement has a click rate increased by machine clicking, a server calculates entropy of the thermodynamic diagram after determining the thermodynamic diagram of the advertisement, and when the calculated entropy is higher than a threshold value, the distribution of the clicked areas of the advertisement is excessively scattered or excessively concentrated, and then determines whether the click rate of the advertisement has a cheating condition, wherein the thermodynamic diagram of the advertisement is used for indicating the number of click events received by each area of the advertisement.

However, when the detection is performed in the above manner, since the entropy of the thermodynamic diagram is higher than the threshold value, the position where the advertisement is clicked is only distributed too dispersedly or too concentrated in the advertisement (for example, concentrated at a certain red coordinate in the clickable area), and the judgment cannot be performed according to the difference between the machine click and the human click, when the mode of the machine click is changed, for example: when clicking is performed in a clickable area according to a certain rule, the problem of high judgment error rate is easily caused according to entropy of thermodynamic diagram.

Disclosure of Invention

The embodiment of the application provides a method and a device for detecting machine clicking and a readable storage medium, which can solve the problem that the judgment error rate is high easily caused by entropy according to thermodynamic diagrams. The technical scheme is as follows:

in a first aspect, a method for detecting a machine click is provided, the method comprising:

acquiring click coordinate data of n target type contents, wherein the n target type contents are n same types and comprise clickable area contents, and the click coordinate data are data generated according to click events received in the clickable area;

determining an ith vector to be detected according to the click coordinate data of the ith target type content, wherein the ith vector to be detected is used for representing the number of times that at least one pixel point in a clickable area of the ith target type content is clicked, and i is more than 0 and less than or equal to n;

Determining a target vector according to the click coordinate data of the n target type contents, wherein the target vector is used for representing the total number of times that at least one pixel point corresponding to the clickable areas of the n target type contents is clicked;

and when the vector distance between the ith vector to be detected and the target vector is greater than a first distance threshold, determining the content of the ith target type as the content which receives the machine click.

In another aspect, a device for detecting machine clicks is provided, the device comprising:

the acquisition module is used for acquiring click coordinate data of n target type contents, wherein the n target type contents are n same types and comprise clickable area contents, and the click coordinate data are data generated according to click events received in the clickable area;

the determining module is used for determining an ith vector to be detected according to the click coordinate data of the ith target type content, wherein the ith vector to be detected is used for representing the number of times that at least one pixel point in a clickable area of the ith target type content is clicked, and i is more than 0 and less than or equal to n;

the determining module is further configured to determine a target vector according to the click coordinate data of the n target type contents, where the target vector is used to represent a total number of times at least one pixel point corresponding to the clickable areas of the n target type contents is clicked;

And the judging module is used for determining the content of the ith target type as the content of the received machine click when the vector distance between the vector to be detected and the target vector is greater than a first distance threshold.

In another aspect, a server is provided, where the server includes a processor and a memory, where the memory stores at least one instruction, at least one program, a code set, or an instruction set, where the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement a method for detecting a machine click as described in an embodiment of the present application.

In another aspect, a computer readable storage medium is provided, where at least one instruction, at least one program, a set of codes, or a set of instructions is stored, where the at least one instruction, the at least one program, the set of codes, or the set of instructions are loaded and executed by the processor to implement a method for detecting machine clicks as described in the embodiments of the present application.

In another aspect, a computer program product is provided, which when run on a computer causes the computer to perform the method of machine click detection as described in the embodiments of the present application above.

The beneficial effects that technical scheme that this application embodiment provided include at least:

determining a target vector according to click coordinate data of n target type contents, wherein the target vector is used for representing a click feature when a clickable area is clicked manually, determining an ith to-be-detected vector according to the click data of the ith target type content, wherein the ith to-be-detected vector is used for representing the click feature of a click event received in the ith target type content, comparing a vector distance between the ith to-be-detected vector and the target vector, namely comparing similarity between the ith to-be-detected vector and the target vector, and when the vector distance is larger than a threshold value, indicating that the similarity between the ith to-be-detected vector and the target vector is lower, namely indicating that the click feature of the click event received in the ith target type content is lower than the click feature when the clickable area is clicked manually, and considering the ith target type content as the content which is clicked by a machine, thereby improving the recognition accuracy of the machine click.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic illustration of an implementation environment of a machine click detection system provided in accordance with an exemplary embodiment of the present application;

FIG. 2 is a flow chart of a method of detecting machine clicks provided in an exemplary embodiment of the present application;

FIG. 3 is a schematic diagram of mapping clickable areas to a coordinate system provided based on the embodiment shown in FIG. 2;

FIG. 4 is a flow chart of a method of detecting machine clicks provided in another exemplary embodiment of the present application;

FIG. 5 is a flow chart of a method of detecting machine clicks provided in another exemplary embodiment of the present application;

FIG. 6 is a schematic diagram of a distribution of click coordinates of recommendation information received for the same type of machine click provided based on the embodiment shown in FIG. 5;

FIG. 7 is a schematic diagram of a user interface for a voting choice provided by an exemplary embodiment of the present application;

FIG. 8 is a flow chart of a method of detecting machine clicks provided in another exemplary embodiment of the present application;

FIG. 9 is a block diagram of a machine click detection apparatus provided in one exemplary embodiment of the present application;

FIG. 10 is a block diagram of a machine click detection apparatus provided in another exemplary embodiment of the present application;

fig. 11 is a block diagram of a server according to an exemplary embodiment of the present application.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

First, a brief description will be given of terms involved in the present application:

thermodynamic diagrams: refers to displaying some event corresponding to different areas to different extents in a highlighted form. In the embodiment of the present application, the thermodynamic diagram refers to displaying the number of click events received by each region in a highlighted form, or displaying the number of click events received by each pixel in a highlighted form. Illustratively, in the clickable area, the number of times the pixel represented by the coordinates (10, 11) is clicked is 20, the number of times the pixel represented by the coordinates (10, 1) is clicked is 1, the number of times the pixel represented by the coordinates (14, 5) is clicked is 8, then in the thermodynamic diagram of the clickable area, the pixel represented by the coordinates (10, 11) is displayed as red, the pixel represented by the coordinates (14, 5) is displayed as yellow, and the pixel represented by the coordinates (10, 1) is displayed as blue.

Machine clicking: the method is that a plurality of electronic devices are controlled through an automatic script or software to click on the clickable area, namely, the clickable area can be clicked by no manual work, and the clicking amount of the clickable area can be increased. When the electronic device is operated by the automation script or software to click on the clickable area, as the automation script or software cannot realize truly random clicking, a certain rule is usually provided, such as: and clicking transversely every preset distance, or clicking for a plurality of times at a certain coordinate point. When clicking manually, the user typically clicks at a location most convenient for touching from the thumb, such as: the positions near the lower right corner in the clickable area are clicked more frequently, and the other positions are clicked more sporadically.

Secondly, schematically, the application scenario involved in the present application includes at least one of the following scenarios:

first kind: after clicking the recommended information released on the public platform, the user can check the detailed information of the recommended information, and when the recommended information is CPC recommended information, the clicking event increases the clicking amount received on the recommended information after clicking the recommended information, and the releasing account releasing the recommended information obtains consideration from the product provider corresponding to the recommended information according to the clicking amount received on the recommended information, so that in order to obtain higher consideration, the releasing account has the condition of increasing the clicking amount of the recommended information in a machine clicking manner;

second kind: the user can click on the options to be voted which participate in the voting, the clicking event increases the number of votes received on the options to be voted, and the options to be voted with the largest number of votes can obtain the win of the voting, so that the account corresponding to the options to be voted has the condition of increasing the number of votes in a machine clicking mode in order to win the win of the voting;

third kind: the public account is an account which is authenticated on the public platform and can be concerned, after a user pays attention to the public account to form vermicelli of the public account, the content of the public account released in the public platform can be checked, the number of vermicelli of the public account can be correspondingly increased, and the more the number of vermicelli of the public account is, the larger the generated influence is, so that in order to increase the number of vermicelli, the situation that the number of vermicelli is increased by a machine clicking mode exists in the public account.

It should be noted that all the above three application scenarios are illustrative examples, and in actual operation, the application scenario that generates the subsequent effect according to the number of click events may use the machine click detection method provided in the embodiment of the present application to detect the machine click, which is not limited in the embodiment of the present application.

Fig. 1 is a schematic view of an implementation environment of a machine click detection system according to an exemplary embodiment of the present application, taking a first application scenario (i.e. a scenario in which a user clicks on recommended information) of the three application scenarios as an example, as shown in fig. 1, the system includes: a terminal 11, an access server 12, a data storage server 13, a billing server 14, and a real-time calculation server 15;

the terminal 11 is configured to display the above recommended information, and receive a click event of a user on a clickable area in the recommended information, optionally, the terminal 11 is further configured to report the click event received on the clickable area to the access server 12, where the clickable area is an area where the click event in the clickable area is reported as an effective click event to the access server 12 after being clicked, optionally, the clickable area is a clicked area of a detail user interface that can display the recommended information on a display screen of the terminal after being clicked, where the detail user interface displays detailed information of a product corresponding to the recommended information.

Optionally, the click event reported by the terminal 11 to the access server 12 includes at least one of the following information: the account identification of the account that clicks on the clickable area, the information identification of the recommendation information that is clicked, the account identification of the publishing account that publishes the recommendation information, the coordinates of the clicked location in the clickable area, the internet protocol (Internet Protocol, IP) address of the terminal 11, and the generation time of the click event. Illustratively, the click event reported by the terminal 11 to the server 12 includes "abc123; product_a; def456; (15, 12); 192.168.31.1;10:12", wherein abc123 is the account number identification of the account number that clicks on the clickable area; product_A is the information identification of the clicked recommendation information; def456 is an account identifier of the publishing account that publishes the recommendation information; (15, 12) is coordinates of a clicked position in the clickable area; 192.168.31.1 is the IP address of the terminal 11, 10: reference numeral 12 denotes a generation time of the click event. Alternatively, all or part of the data in the click event may be used as the click coordinate data of the click event.

Optionally, the terminal 11 reports the click event received in the clickable area to the access server 12 through the communication network 16, where the communication network 16 may be a wired network or a wireless network.

It should be noted that, in this embodiment, only one terminal 11 is shown to report the click event to the access server 12, and in actual operation, the number of terminals 11 connected to the access server 12 and capable of reporting the click event to the access server 12 may be greater.

Optionally, the access server 12 reports the received click event reported by the terminal 11 to the data storage server 13, where the data storage server 13 is configured to store the click event reported by the access server 12, and optionally, the data storage server 13 may store the click event reported by the access server 12 for a preset duration, or store the click event reported by the access server 12 for a long time.

Optionally, after receiving the click event reported by the terminal 11, the access server 12 sends the click event to the charging server 14, and the charging server 14 charges the click event according to the click event reported by the access server 12, where the charging refers to recording the cost that the product provider corresponding to the recommendation information needs to pay to the publishing account that publishes the recommendation information. Illustratively, each time the product provider and the issued account contract recommendation information are clicked, charging is 0.2 element, and after receiving the click event reported by the access server 12, the charging server 14 charges 0.2 element when the click event meets the charging condition.

Optionally, the billing server 14 needs to determine whether the received click event meets the billing conditions through the real-time calculation server 15. Optionally, the billing server 14 sends a query request to the real-time computing server 15 based on the received click event. Illustratively, the query request includes an account identifier of a publishing account that publishes the recommendation information, and the real-time computing server 15 determines whether the recommendation information published by the publishing account has a condition of receiving a machine click according to the account identifier, or includes an information identifier of the clicked recommendation information in the query request, and the real-time computing server 15 determines whether the recommendation information is information of receiving the machine click according to the information identifier.

Alternatively, the real-time calculation server 15 determines the query result by acquiring data from the data storage server 12 and transmits the query result to the billing server 14. Illustratively, when the query request includes the account identifier of the publishing account for publishing the recommendation information, the real-time computing server 15 obtains the data corresponding to the account identifier from the data storage server 12, so as to calculate whether the recommendation information published by the publishing account has the condition of receiving the machine click; when the information identification of the clicked recommendation information is included in the query request, the real-time calculation server 15 acquires data corresponding to the recommendation information from the data storage server 12 to calculate whether the recommendation information is information of which machine click is received.

Alternatively, the above access server 12, the data storage server 13, the charging server 14, and the real-time computing server 15 may be implemented on different servers independently, and may be implemented on multiple servers in any combination, for example: the functions implemented by the access server 12 and the data storage server 13 are implemented by two modules on the server a respectively, or the access server 12, the data storage server 13, the charging server 14 and the real-time computing server 15 may be implemented as different modules on the same server, or the functions implemented by the server may be implemented by one or a group of server devices, for example: the functions implemented by the access server 12 are implemented by a combination of server a, server b, and server c, which is not limited in this embodiment of the present application.

In combination with the application scenario and the system for detecting machine clicks, the method for detecting machine clicks according to the embodiments of the present application is described, as shown in fig. 2, and the method may be executed by a server, which may be the real-time computing server 15 in the detection system shown in fig. 1, where the method includes:

in step 201, click coordinate data of n target type contents are acquired.

Optionally, the n target type contents are n contents of the same type and include a clickable area, and the click coordinate data is data generated according to a click event received in the clickable area.

Optionally, the click coordinate data includes an identification of the target type content and a pixel point clicked on the target type content.

Optionally, the click coordinate data may be click coordinate data within a last preset time period, all stored click coordinate data, or randomly acquired click coordinate data with a preset size, which is not limited in the embodiment of the present application.

Alternatively, when the step of acquiring the click coordinate data is performed by the real-time calculation server 15 in the detection system as shown in fig. 1, and the above-mentioned access server 12, data storage server 13, billing server 14, and real-time calculation server 15 are each independently implemented on a different server, the real-time calculation server 15 may acquire the click coordinate data from the data storage server 13; when the access server 12, the data storage server 13, the charging server 14 and the real-time computing server 15 are implemented on the same server, the server stores the click coordinate data, and the server can directly obtain the stored click coordinate data.

Optionally, the types of the n target types of content include any one of the following cases:

firstly, the n target type contents are recommendation information issued by n issued accounts, wherein the i target type contents are a set of recommendation information issued by the i issued accounts, and the clickable area is an area for checking the recommendation information;

secondly, n target type contents are n options to be voted which participate in voting, wherein the clickable area is a control for voting on the options to be voted;

thirdly, n pieces of recommended information issued to a public platform are n pieces of target type content, and the clickable area is an area for checking the recommended information;

fourth, the n target types are focus request messages corresponding to n public accounts, where the clickable area is a control focusing on the public accounts.

Optionally, the click coordinate data is used to represent a pixel point clicked on a clickable area in the n target type contents. Alternatively, the pixel point may be represented in the form of coordinates in the target coordinate system. Illustratively, as shown in fig. 3, the user interface 31 includes recommendation information 32, and a clickable area of the recommendation information 32 is an area 33 outlined by a dotted line, as seen in a coordinate system 34, where the coordinate system 34 includes an x-axis and a y-axis, and the area 33 is correspondingly represented in the coordinate system 34 as an area with a pixel of m×n. Illustratively, the click coordinate data of the recommendation information 32 includes: (6, 1), (3, 2), (5, 3), (6, 1), (3, 1), (6, 1), (3, 2), wherein the pixel represented by the coordinates (6, 1) is clicked three times, the pixel represented by the coordinates (3, 2) is clicked twice, and the pixel represented by the coordinates (5, 3), (3, 1) is clicked once.

Step 202, determining the ith vector to be detected according to the click coordinate data of the ith target type content, wherein i is more than 0 and less than or equal to n.

Optionally, the ith to-be-detected vector is used to represent the number of times at least one pixel point in the clickable area of the ith target type content is clicked.

Optionally, when the pixel point is represented in the form of coordinates in the target coordinate system, the i-th vector to be detected is used for representing the number of times that the coordinates corresponding to the clickable area of the i-th object type content are clicked, where the target coordinate system is used for representing the position of the pixel point in the clickable area in the form of coordinates. Alternatively, the target coordinate system may be referenced to a coordinate system 34 as shown in FIG. 3.

Optionally, the ith vector to be detected is a vector in p-q dimension, the value in the x dimension is the number of clicks received by the coordinate corresponding to the x dimension, and the expression mode of the ith vector to be detected is as follows:

wherein C is _i Representing the i-th vector to be detected,

represents the number k of clicks received by the coordinates (a, b), wherein the value of k is changed according to the number of clicks actually received by the coordinates.

Illustratively, the click coordinate data in recommendation information 32 includes: (3, 1), (3, 2), (1, 3), (3, 1), (2, 1), (3, 3), (3, 2), in C ₃₂ Representing the vector to be detected corresponding to the recommended information 32, the vector C to be detected corresponding to the recommended information 32 ₃₂ The following are provided:

wherein,,

for indicating that coordinate (1, 1) has not been clicked,/->

For indicating that the coordinates (1, 2) have not been clicked,

for indicating that the coordinates (1, 3) are clicked once, +.>

For indicating that coordinate (2, 1) is clicked once, +.>

For indicating that the coordinates (2, 2) have not been clicked on +.>

For indicating that the coordinates (2, 3) have not been clicked on +.>

For representing that coordinate (3, 1) is clicked twice,/->

For representing that the coordinate (3, 2) is clicked twice,/->

For indicating that the coordinates (3, 3) are clicked once.

And 203, determining the target vector according to the click coordinate data of the n target type contents.

Optionally, the target vector is used to represent the total number of times at least one pixel point corresponding to the clickable areas of the n target types of content is clicked.

Optionally, when the pixel points are represented in the form of coordinates in the target coordinate system, the target vector is used to represent the total number of times that the coordinates corresponding to the clickable areas of the n target type contents are clicked.

Optionally, the target detection vector is a vector in a p×q dimension, the value in an x-th dimension is the total number of clicks received by coordinates corresponding to n target type contents in the x-th dimension, and the expression mode of the target vector is as follows: c= (C _1,1 ,C _1,2 ,…，C _a,b ,…,C _p,q )

Wherein C represents a target vector, C _a,b Representing the total number of clicks the coordinates (a, b) receive in the n target type contents.

Illustratively, three pieces of recommended information, that is, recommended information a, recommended information B, and recommended information C, are taken as an example for explanation, wherein click coordinate data of recommended information a includes: (3, 1), (3, 2), (1, 3), click coordinate data of the recommendation information B includes: (3, 1), (2, 1), (3, 3), click coordinate data of the recommendation information C includes: (2, 1), (3, 3), (3, 2), the target vector C corresponding to the recommendation information a, the recommendation information B, and the recommendation information C is as follows:

C＝(C _1,1 ,C _1,2 ,C _1,3 ,C _2,1 ,C _2,2 ,C _2,3 ,C _3,1 ,C _3,2 ,C _3,3 )

the click coordinate data of the recommendation information A, the recommendation information B and the recommendation information C are combined, and the values of each dimension in the target vector C are respectively as follows:

C＝(0,0,1,2,0,0,2，2，2)

wherein C is _1,1 Corresponding to a value of 0, C _1,2 Corresponding to a value of 0, C _1,3 Corresponding to a value of 1, C _2,1 Corresponding to a value of 2, C _2,2 Corresponding to a value of 0, C _2，3 Corresponding to a value of 0, C _3,1 Corresponding to a value of 2, C _3,2 Corresponding to a value of 2, C _3,3 The corresponding value is 2, and (0,0,1,2,0,0,2,2,2) is used for indicating that the coordinate (1, 1) is not clicked in the three recommendation information, the coordinate (1, 2) is not clicked in the three recommendation information, the coordinate (1, 3) is clicked once in the three recommendation information, the coordinate (2, 1) is clicked twice in the three recommendation information, the coordinate (2, 2) is not clicked in the three recommendation information, the coordinate (2, 3) is not clicked twice in the three recommendation information, the coordinate (3, 1) is clicked twice in the three recommendation information, the coordinate (3, 2) is clicked twice in the three recommendation information, and the coordinate (3, 3) is clicked twice in the three recommendation information respectively.

It should be noted that, with respect to the

above steps

202 and 203, the step 202 may be performed first, then the step 203 may be performed, and then the step 202 and the step 203 may be performed simultaneously, which is not limited in the embodiment of the present application.

In step 204, when the vector distance between the ith vector to be detected and the target vector is greater than the first distance threshold, the content of the ith target type is determined to be the content of the received machine click.

Optionally, when the vector distance between the ith vector to be detected and the target vector is calculated according to the cosine similarity formula, the actual calculation is that the similarity between the ith vector to be detected and the target vector is calculated according to the cosine similarity formula, and when the similarity between the ith vector to be detected and the target vector is lower than the similarity threshold, the content of the ith target type is determined to be the content of the received machine click.

Illustratively, the calculation formula of the similarity between the ith vector to be detected and the target vector is as follows:

wherein C is _k For representing the i-th vector to be detected, C for representing the target vector,

for representing the sum of the number of times each coordinate is clicked in the clickable area of the i-th object type content, wherein the value of the abscissa is from 1 to p, the value of the ordinate is from 1 to q, and k represents the number of times the coordinate (a, b) is clicked >

The total number of clicks on coordinates (a, b) for the ith object type content is k times, C _a,b For the total number of times n target type content is clicked on coordinates (a, b), where p is 1, q is 1, a is 1, b is 1, and k is 0.

Optionally, the means for calculating the vector distance between the ith vector to be detected and the target vector includes at least one of the following means:

firstly, calculating a vector distance between an ith vector to be detected and a target vector through an Euclidean distance (English: euclidean distance) formula;

illustratively, the ith vector to be detected

Target vector c= (C _1,1 ,C _1,2 ,…,C _p,q ) When the distance d between the ith vector to be detected and the target vector is calculated by the Euclidean distance formula, the calculation formula is as follows:

secondly, calculating the vector distance between the ith vector to be detected and the target vector through a Markov distance (English: mahalanobis Distance) formula;

illustratively, the ith vector C to be detected is calculated by a horse-type distance formula _k And the distance d between the target vector C, the calculation formula is as follows:

wherein S is ^-1 For representing the covariance between each element of the two vectors.

Thirdly, calculating the vector distance between the ith vector to be detected and the target vector through a Manhattan distance formula.

Illustratively, the ith vector to be detected

optionally, when the vector distance between the ith vector to be detected and the target vector is greater than the first distance threshold, which indicates that the difference between the ith vector to be detected and the target vector is greater, determining that the ith target type content is the content of the received machine click.

Optionally, when the vector distance between the ith vector to be detected and the target vector is not greater than the first distance threshold, determining the ith target type content as the content which does not receive the machine click.

In summary, in the method for detecting machine clicking provided in the embodiment, the target vector is determined according to the click coordinate data of the n target type contents, where the target vector is used to represent the click feature when the clickable region is clicked manually, the ith vector to be detected is determined according to the click data of the ith target type content, where the ith vector to be detected is used to represent the click feature of the click event received in the ith target type content, and by comparing the vector distance between the ith vector to be detected and the target vector, that is, comparing the similarity between the ith vector to be detected and the target vector, when the vector distance is greater than the threshold value, it is indicated that the similarity between the ith vector to be detected and the target vector is lower, that is, the click feature of the click event received in the ith target type content is lower than the click feature when the clickable region is clicked manually, and the ith target type content is considered to be the content that receives the machine clicking, so as to improve the recognition accuracy of machine clicking.

In an alternative embodiment, the size of the clickable areas of the n target types of content may be different, and fig. 4 is a flowchart of a method for detecting machine clicks according to another exemplary embodiment of the present application, where the method may be performed by a server, which may be the real-time computing server 15 in the detection system shown in fig. 1, and the method includes:

in step 401, click coordinate data of n target type contents are acquired.

Optionally, before n target types of content are acquired, when the access server 12, the data storage server 13, the billing server 14 and the real-time computing server 15 in the detection system shown in fig. 1 are each independently implemented on different servers, the real-time computing server 15 receives a query request sent by the billing server 14, where the query request is used to request to query whether the i-th target type of content is a content that receives a machine click; when the access server 12, the data storage server 13, the charging server 14 and the real-time computing server 15 are implemented on the same server, the server obtains click coordinate data of n target types of content after receiving a click event reported by the terminal.

Optionally, in this embodiment, the description is given by taking the recommendation information that is issued by n issuing accounts as an example, where the i-th target type content is a set of recommendation information issued by the i-th issuing account, and the clickable area is an area for viewing the recommendation information;

step 402, let m _i The pixel points in the clickable area of the bar recommendation information are mapped to the target coordinate system.

Optionally, the target coordinate system is used to represent the position of the pixel point in the clickable area in the form of coordinates.

Alternatively, the m _i The clickable areas of the bar recommendation information may be the same size or different sizes.

Alternatively, the clickable area of the recommendation information may be mapped to the target coordinate system in a manner of referring to the clickable area 33 and the coordinate system 34 shown in fig. 3.

Alternatively, this step 402 may also be performed by the terminal 11 in the detection system shown in fig. 1.

In step 403, the clicked coordinates in the target coordinate system are determined according to the clicked pixel points in the clickable area.

Optionally, the clicked pixel point in the clickable area is mapped to the target coordinate system to obtain the clicked coordinate in the target coordinate system.

Step 404, let m _i Clicked in clickable area of bar recommendation informationThe coordinates of the shots are normalized.

Optionally, the normalization process is to normalize m _i The clickable area of the bar recommendation information is normalized to an area of the target size, and coordinates in the clickable area are normalized to coordinates at the target size.

Schematically, the target size is 5*5, the size of the recommended information a in the target coordinate system is 10×15, the clicked coordinates in the recommended information a include (6, 3), (8, 9), and when the recommended information a is normalized to the size of 5*5, the normalized clicked coordinates include (3, 1), (4, 3); the size of the recommended information B in the target coordinate system is 15×15, and the clicked coordinates in the recommended information B include (9, 3) and (6, 9), and when the recommended information B is normalized to the target size, the normalized clicked coordinates include (3, 1) and (2, 3).

And step 405, obtaining an ith vector to be detected according to the normalized total number of times the coordinates are clicked.

Optionally, when the pixel point is represented in the form of coordinates in the target coordinate system, the i-th vector to be detected is used for representing the number of times that the coordinates corresponding to the clickable area of the i-th object type content are clicked, where the target coordinate system is used for representing the position of the pixel point in the clickable area in the form of coordinates.

Illustratively, in combination with the above example, when the recommended information a is normalized to the size of 5*5, the normalized clicked coordinates include (3, 1), (4, 3), and when the recommended information B is normalized to the target size, the normalized clicked coordinates include (3, 1) and (2, 3), and then the number of times the coordinates (3, 1) are clicked is 1 time, and the number of times the coordinates (4, 3) and (2, 3) are clicked is 1 time. Alternatively, the number of times that the other coordinates represented in the vector to be detected are clicked is 0.

And step 406, mapping the pixel points in the clickable areas of the recommendation information issued by the n issued accounts to a target coordinate system.

Optionally, when mapping the pixel points in the clickable areas of the recommendation information issued by the n issued accounts to the target coordinate system, the pixel points in the clickable areas in each recommendation information issued by the n issued accounts need to be mapped to the target coordinate system. For the mapping method, please refer to the clickable area 33 and the coordinate system 34 shown in fig. 3.

In step 407, the clicked coordinates in the target coordinate system are determined according to the clicked pixel points in the clickable area.

And step 408, normalizing the clicked coordinates in the clickable areas of the recommendation information issued by the n issued accounts.

Optionally, the specific process of the normalization step may refer to step 404, which is not described herein.

And 409, obtaining a target vector according to the normalized total number of times the coordinates are clicked.

Optionally, the target vector is used for representing the total number of times that at least one pixel point corresponding to the clickable areas of the recommendation information issued by the n issued accounts is clicked.

Illustratively, the coordinates clicked by the user 1 on the recommendation information issued by the issuing account a are normalized (88, 14), the coordinates clicked by the user 1 on the recommendation information issued by the issuing account b are normalized (99, 39), the coordinates clicked by the user 2 on the recommendation information issued by the issuing account a are normalized (77, 15), the coordinates clicked by the user 3 on the recommendation information issued by the issuing account a are normalized (88, 14), the coordinates clicked by the user 4 on the recommendation information issued by the issuing account a are normalized (88, 16), and the following items (88, 14, 2), (88, 16, 1) and (77, 15, 1) are included in the vectors to be detected corresponding to the issuing account 1 after the issuing account is summarized, and the following items (99, 39,1) are included in the vectors to be detected corresponding to the issuing account 2.

It should be noted that, the steps 402 to 405 and the steps 406 to 409 may be performed first, then the steps 402 to 405 may be performed, then the steps 406 to 409 may be performed first, then the steps 402 to 405 may be performed, and then the steps 402 to 405 and the steps 406 to 409 may be performed simultaneously.

In step 410, when the vector distance between the ith vector to be detected and the target vector is greater than the first distance threshold, the ith target type content is determined to be the content of the received machine click.

Firstly, calculating a vector distance between an ith vector to be detected and a target vector through an Euclidean distance formula;

secondly, calculating the vector distance between the ith vector to be detected and the target vector through a Markov distance formula;

The method provided in this embodiment is achieved by combining m _i Normalization of the clickable area and the clicked coordinates in the clickable area of the bar recommendation information avoids the occurrence of m _i The difference in size between the i-th vector to be detected and the target vector caused by the difference in size of the clickable areas of the recommended information also increases the difference in size, that is, the difference between the i-th vector to be detected and the target vector is affected by the size factor, and the recognition accuracy of machine clicking is also reduced.

In an alternative embodiment, it may be determined whether the ith target type content and the kth target type content receive the same type of machine click by calculating the vector distance of the ith vector to be detected and the kth vector to be detected. Fig. 5 is a flowchart of a method for detecting machine clicks according to another exemplary embodiment of the present application, and as shown in fig. 5, the method may be performed by a server, which may be the real-time computing server 15 in the detection system shown in fig. 1, and the method includes:

step 501, a query request sent by a billing server is received.

Optionally, the query request includes an identifier corresponding to the ith target type content, where the query request is used to request a determination whether the ith target type content is the content that receives the machine click.

Step 502, acquiring click coordinate data of n target type contents.

Optionally, click coordinate data of n target type contents are obtained according to a query request sent by the charging server, and illustratively, the n target type contents are recommendation information issued by n issued accounts, and the query request includes an account identifier of the ith issued account.

And step 503, determining the ith vector to be detected according to the click coordinate data of the ith target type content, wherein i is more than 0 and less than or equal to n.

And step 504, determining the target vector according to the click coordinate data of the n target type contents.

It should be noted that, with respect to the

above steps

503 and 504, the step 503 may be performed first, then the step 504 may be performed, and then the step 503 may be performed simultaneously, which is not limited in the embodiment of the present application.

In step 505, when the vector distance between the ith vector to be detected and the target vector is greater than the first distance threshold, the content of the ith target type is determined to be the content of the received machine click.

And step 506, sending the query result to the charging server.

Optionally, the query result is used to indicate that the ith target type content is the content that received the machine click.

Optionally, when the vector distance between the ith vector to be detected and the target vector is smaller than or equal to the first distance threshold, the ith target type content is the content that does not receive the machine click, and the query result sent to the charging server is used for indicating that the ith target type content is the content that does not receive the machine click.

And 507, determining a kth vector to be detected 0 < k < n according to click coordinate data of the kth object type content.

Optionally, the kth vector to be detected is used to represent the number of times at least one pixel point in the clickable area of the kth target type content is clicked.

Optionally, when the pixel point is represented in the form of coordinates in the target coordinate system, the kth vector to be detected is used to represent the number of times that the coordinates corresponding to the clickable area of the kth target type content are clicked.

In step 508, when the vector distance between the ith vector to be detected and the kth vector to be detected is smaller than the second distance threshold, it is determined that the kth object type content and the ith object type content receive the same type of machine click.

Referring to fig. 6 schematically, fig. 6 shows N click coordinate distribution diagrams of recommended information, in which, a click coordinate distribution diagram 61 of recommended information a, a click coordinate distribution diagram 62 of recommended information B, a click coordinate distribution diagram 63 of recommended information C, and a click coordinate distribution diagram 64 of recommended information N are mainly shown, according to which N click distribution diagrams of recommended information a, a comprehensive distribution diagram 65 is obtained, in which, in the click coordinate distribution diagram 61 of recommended information a, the click coordinates are concentrated in a region 611, in the click coordinate distribution diagram 62 of recommended information B, the click coordinates are concentrated in a region 612, and in the comprehensive distribution diagram 65, the click coordinates are concentrated in a region 651, if the distance between the vector to be detected of recommended information a and the target vector is greater than the distance threshold, the recommended information a is confirmed to be the content of the received machine click, after normalizing the click coordinate distribution diagram of recommended information a and the click coordinate distribution diagram of recommended information B to obtain two vectors to be detected, and the vector distance between the vector to be detected corresponding to the recommended information B is less than the second distance threshold, so that the information a and the recommended information B are the same type of the machine click information.

According to the method provided by the embodiment, the kth vector to be detected is determined through the click data of the kth target type content, and is used for representing the click characteristic of the click event received in the kth target type content, and the recognition accuracy of the clicking of the machine of the same type is improved by comparing the vector distance between the ith vector to be detected and the kth vector to be detected, namely comparing the similarity between the ith vector to be detected and the kth vector to be detected, when the vector distance is smaller than the threshold value, the similarity between the ith vector to be detected and the kth vector to be detected is higher, namely the similarity between the click characteristic of the click event received in the ith target type content and the click characteristic of the click event received in the kth target type content is higher, and the recognition accuracy of the clicking of the machine of the same type is considered.

In an exemplary embodiment, n target types of content are taken as n to-be-voted options participating in a voting activity, and as shown in fig. 7, a clickable area 711 of the to-be-voted option a, a clickable area 712 of the to-be-voted option B, a clickable area 713 of the to-be-voted option C, and a clickable area 714 of the to-be-voted option D are displayed in a user interface 71 of the voting activity, and after the user clicks on the clickable area of the to-be-voted option, the user selects the voting control 72 to vote on the clicked to-be-voted option. Illustratively, after the user clicks the clickable area 711 of the to-be-voted option a and clicks the voting control 72, the terminal reports the to-be-voted event of the to-be-voted option a to the background server, for example: the access server 12 shown in fig. 1, and the charging server 14 shown in fig. 1 may be implemented as a billing server in this embodiment, and after the access server 12 sends the click event to the billing server, the billing server sends a query request to the real-time computing server 15. The real-time computing server 15 detects whether the machine click is received by the option a to be voted.

The implementation process is as shown in fig. 8, and the method comprises the following steps:

step 801, the terminal reports click coordinate data after receiving a click event.

Optionally, the click event reported by the terminal to the server includes at least one of the following information: the method comprises the steps of carrying out account identification of an account clicked on a clickable area, information identification of clicked recommendation information, account identification of a released account releasing the recommendation information, coordinates of a clicked position in the clickable area, an IP address of a terminal and generation time of a clicking event.

Optionally, the terminal reports the click coordinate data to the access server 12, and optionally, the terminal reports a click event to the access server 12, where the click event includes the click coordinate data.

Step 802, the server acquires click coordinate data corresponding to each option in a preset duration, and respectively assembles vectors to be detected.

Optionally, the step of summarizing the click coordinate data into the vector to be detected is described in detail in the above step 202, which is not described herein.

In step 803, the server generates a target vector according to the click coordinate data of each option, and determines a vector distance between the vector to be detected and the target vector.

Optionally, the step of generating the target vector according to the click coordinate data is described in detail in the above step 203, which is not described herein.

Step 804, it is determined whether the vector distance between the vector to be detected of the option a and the target vector exceeds a threshold.

In step 805, when the vector distance between the vector to be detected of the option a and the target vector exceeds the threshold, it is determined that the machine click is received by the option a.

In step 806, when the vector distance between the vector to be detected of the option a and the target vector does not exceed the threshold, it is determined that the machine click is not received by the option a.

In summary, according to the method for detecting machine clicking provided in the embodiment, the target vector is determined according to the click coordinate data of each option, the target vector is used for representing the click feature when the clickable area is clicked manually, the to-be-detected vector of the option a is determined according to the click data of the option a, the to-be-detected vector of the option a is used for representing the click feature of the click event received in the option a, the vector distance between the to-be-detected vector of the option a and the target vector is compared, that is, the similarity between the to-be-detected vector of the option a and the target vector is compared, when the vector distance is greater than the threshold value, the fact that the similarity between the to-be-detected vector of the option a and the target vector is lower is illustrated, that is, the click feature of the click event received in the option a and the click feature when the clickable area is clicked manually is lower is illustrated, the option a is considered to be the content of receiving machine clicking, and the recognition accuracy of machine clicking is improved.

Fig. 9 is a block diagram of a machine click detection apparatus according to an exemplary embodiment of the present application, and as shown in fig. 9, the apparatus may be implemented as a dedicated hardware circuit, or as a combination of hardware and software, to form all or a part of the real-time computing server 15 shown in fig. 1, and the apparatus includes: an acquisition module 91, a determination module 92, and a judgment module 93;

an obtaining module 91, configured to obtain click coordinate data of n target type contents, where the n target type contents are n content of the same type and include clickable areas, and the click coordinate data is data generated according to a click event received in the clickable areas;

a determining module 92, configured to determine an ith vector to be detected according to click coordinate data of the ith target type content, where the ith vector to be detected is used to represent a number of times that at least one pixel point in a clickable area of the ith target type content is clicked, where i is greater than 0 and less than or equal to n;

the determining module 92 is further configured to determine a target vector according to the click coordinate data of the n target types of content, where the target vector is used to represent a total number of times at least one pixel point corresponding to the clickable areas of the n target types of content is clicked;

And the judging module 93 is configured to determine that the ith target type content is the content that receives the machine click when the vector distance between the ith vector to be detected and the target vector is greater than a first distance threshold.

In an alternative embodiment, as shown in fig. 10, when the n target types of contents are recommendation information issued by n issuing accounts, the ith issuing account is issued with m _i Strip recommendation messageThe click coordinate data comprises the m _i In the recommendation information, pixels of each recommendation information, on which a clickable area is clicked;

a determination module 92 comprising

A mapping sub-module 921 for mapping the m _i Mapping the pixel points in the clickable area of the recommendation information to a target coordinate system, wherein the target coordinate system is used for representing the positions of the pixel points in the clickable area in a coordinate mode;

a determining submodule 922, configured to determine a clicked coordinate in the target coordinate system according to the clicked pixel point of the clickable area;

a normalization sub-module 923 for integrating the m _i Normalizing the clicked coordinates in the clickable area of the piece of recommendation information;

the determining submodule 922 is further configured to obtain the ith vector to be detected according to the normalized total number of times the coordinates are clicked.

In an optional embodiment, the n target types of content are recommendation information issued by n issuing accounts;

the determining module 92 includes:

a mapping sub-module 921, configured to map pixel points in the clickable areas of the recommendation information issued by the n issued accounts to a target coordinate system, where the target coordinate system is used to represent positions of the pixel points in the clickable areas;

a normalization sub-module 923, configured to normalize the clicked coordinates in the clickable areas of the recommendation information issued by the n issued accounts;

the determining submodule 922 is further configured to obtain the target vector according to the normalized total number of times the coordinate is clicked.

In an optional embodiment, the n target type contents are recommendation information issued by n issued accounts, the i target type contents are a set of recommendation information issued by the i issued accounts, and the clickable area is an area for viewing the recommendation information;

or alternatively, the first and second heat exchangers may be,

the n target type contents are n options to be voted which participate in voting, and the clickable area is a control for voting on the options to be voted;

Or alternatively, the first and second heat exchangers may be,

the n target type contents are n recommendation information issued to a public platform, and the clickable area is an area for viewing the recommendation information;

or alternatively, the first and second heat exchangers may be,

the n target types are attention request messages corresponding to n public accounts, and the clickable area is a control for focusing on the public accounts.

In an alternative embodiment, the determining module 92 is further configured to determine a kth vector to be detected according to click coordinate data of a kth object type content, where k is greater than 0 and less than or equal to n;

the determining module 92 is further configured to determine that the kth target type content and the ith target type content receive the same type of machine click when a vector distance between the ith vector to be detected and the kth vector to be detected is less than a second distance threshold.

In an optional embodiment, the determining module 93 is further configured to calculate a similarity between the ith vector to be detected and the target vector according to a cosine similarity formula, and determine that the ith target type content is the content that receives the machine click when the similarity between the ith vector to be detected and the target vector is lower than a similarity threshold.

In an alternative embodiment, the determining module 93 is further configured to calculate the vector distance between the i-th vector to be detected and the target vector by using a euclidean distance formula;

or alternatively, the first and second heat exchangers may be,

the judging module 93 is further configured to calculate the vector distance between the ith vector to be detected and the target vector according to a mahalanobis distance formula;

or alternatively, the first and second heat exchangers may be,

the determining module 93 is further configured to calculate the vector distance between the ith vector to be detected and the target vector according to a manhattan distance formula.

In an alternative embodiment, the apparatus further comprises:

a receiving module 94, configured to receive a query request sent by a charging server, where the query request includes an identifier corresponding to the ith target type content, and the query request is used to request to determine whether the ith target type content is a content that receives the machine click;

and a sending module 95, configured to send a query result to the charging server, where the query result is used to indicate that the ith target type content is the content that receives the machine click.

In summary, in the machine click detection device provided in the embodiment, the target vector is determined according to the click coordinate data of the n target type contents, where the target vector is used to represent the click feature when the clickable region is clicked manually, and the ith vector to be detected is determined according to the click data of the ith target type content, where the ith vector to be detected is used to represent the click feature of the click event received in the ith target type content, and by comparing the vector distance between the ith vector to be detected and the target vector, that is, comparing the similarity between the ith vector to be detected and the target vector, when the vector distance is greater than the threshold, it is indicated that the similarity between the ith vector to be detected and the target vector is lower, that is, the click feature of the click event received in the ith target type content is lower than the click feature when the clickable region is clicked manually, and then the ith target type content is considered to be the content that receives the machine click, so as to improve the recognition accuracy of the machine click.

The application also provides a server, which comprises a processor and a memory, wherein at least one instruction is stored in the memory, and the at least one instruction is loaded and executed by the processor to realize the detection method of machine clicking provided by each method embodiment. It should be noted that the server may be a server as provided in fig. 11 below.

Referring to fig. 11, a schematic structural diagram of a server according to an exemplary embodiment of the present application is shown. Specifically, the present invention relates to a method for manufacturing a semiconductor device. The server 1100 includes a Central Processing Unit (CPU) 1101, a system memory 1104 including a Random Access Memory (RAM) 1102 and a Read Only Memory (ROM) 1103, and a system bus 1105 connecting the system memory 1104 and the central processing unit 1101. The server 1100 also includes a basic input/output system (I/O system) 1106, which facilitates the transfer of information between the various devices within the computer, and a mass storage device 1107 for storing an operating system 1113, application programs 1114, and other program modules 1115.

The basic input/output system 1106 includes a display 1108 for displaying information and an input device 1109, such as a mouse, keyboard, etc., for a user to input information. Wherein the display 1108 and the input device 1109 are both coupled to the central processing unit 1101 through an input-output controller 1110 coupled to the system bus 1105. The basic input/output system 1106 may also include an input/output controller 1110 for receiving and processing input from a number of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, the input output controller 1110 also provides output to a display screen, a printer, or other type of output device.

The mass storage device 1107 is connected to the central processing unit 1101 through a mass storage controller (not shown) connected to the system bus 1105. The mass storage device 1107 and its associated computer-readable storage medium provide non-volatile storage for the server 1100. That is, the mass storage device 1107 may include a computer-readable storage medium (not shown) such as a hard disk or CD-ROI drive.

The computer-readable storage medium may include computer storage media and communication media without loss of generality. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, EPROM, EEPROM, flash memory or other solid state memory technology, CD-ROM, DVD or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will recognize that the computer storage medium is not limited to the one described above. The system memory 1104 and mass storage device 1107 described above may be collectively referred to as memory.

The memory stores one or more programs configured to be executed by the one or more central processing units 1101, the one or more programs containing instructions for implementing the method for detecting a machine click as described above, and the central processing unit 1101 executes the one or more programs to implement the method for detecting a machine click as provided by the respective method embodiments described above.

The server 1100 may also operate via a network, such as the internet, connected to a remote computer on the network, in accordance with various embodiments of the present invention. I.e., the server 1100 may be connected to the network 1112 through a network interface unit 1111 coupled to the system bus 1105, or the network interface unit 1111 may be used to connect to other types of networks or remote computer systems (not shown).

The memory further includes one or more programs stored in the memory, the one or more programs including steps executed by the server in the method for detecting machine clicks provided by the embodiments of the present invention.

Embodiments of the present application also provide a computer readable storage medium having at least one instruction, at least one program, a code set, or an instruction set stored therein, where the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor 1110 to implement a method for detecting a machine click as described in any one of fig. 2, 4, 5, and 8.

The present application also provides a computer program product, which when run on a computer, causes the computer to perform the method for detecting machine clicks provided by the above-mentioned method embodiments.

The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.

Claims

1. A method of detecting machine clicks, the method comprising:

receiving a query request sent by a charging server, wherein the query request comprises an identifier corresponding to an ith target type content, the query request is used for requesting to determine whether the ith target type content is the content which is clicked by the machine, the charging server is used for triggering the query request according to a clicking event received from an access server, the ith target type content is obtained from n target type contents, the n target type contents are n same types and comprise clickable area contents, i is more than 0 and less than or equal to n, and i and n are integers;

Acquiring click coordinate data of the n target type contents from a data storage server, wherein the click coordinate data are data generated according to click events received in the clickable area, and the data storage server is used for receiving the click events from the access server and determining the corresponding click coordinate data based on the click events;

determining an ith vector to be detected according to the click coordinate data of the ith target type content, wherein the ith vector to be detected is used for representing the number of times that at least one pixel point in a clickable area of the ith target type content is clicked;

when the vector distance between the ith vector to be detected and the target vector is greater than a first distance threshold, determining the ith target type content as the content which receives the machine click;

sending a query result to the charging server, wherein the query result is used for indicating that the ith target type content is the content which receives the machine click, and the charging server is used for charging the click event according to the query result;

Determining a kth vector to be detected according to click coordinate data of kth target type content, wherein the kth target type content is obtained from the n target type contents, k is more than 0 and less than or equal to n, and k is an integer;

and when the vector distance between the ith vector to be detected and the kth vector to be detected is smaller than a second distance threshold, determining that the kth target type content and the ith target type content receive the same type of machine click.

2. The method of claim 1, wherein when the n target types of content are recommendation information issued for n issue accounts, an i-th issue account is issued with m _i A piece of recommendation information, the click coordinate data including the m _i The pixel point of each piece of recommendation information, the clickable area of which is clicked;

the determining the ith vector to be detected according to the click coordinate data of the ith target type content comprises the following steps:

the m is set to _i The pixel points in the clickable area of the recommendation information are mapped to a target coordinate system, theThe target coordinate system is used for representing the position of the pixel point in the clickable area in a coordinate mode;

Determining clicked coordinates in the target coordinate system according to the clicked pixel points of the clickable area;

the m is set to _i Normalizing the clicked coordinates in the clickable area of the piece of recommendation information;

and obtaining the ith vector to be detected according to the normalized total clicked times of the coordinates.

3. The method of claim 1, wherein the n target types of content are recommendation information published for n published accounts;

the determining the target vector according to the click coordinate data of the n target type contents comprises the following steps:

mapping the pixel points in the clickable areas of the recommendation information issued by the n issued accounts to a target coordinate system, wherein the target coordinate system is used for representing the positions of the pixel points in the clickable areas;

normalizing the clicked coordinates in the clickable areas of the recommendation information issued by the n issued accounts;

and obtaining the target vector according to the normalized total number of times the coordinate is clicked.

4. A method according to any one of claims 1 to 3, wherein,

The n target type contents are recommendation information issued by n issued accounts, the i target type contents are a set of recommendation information issued by the i issued accounts, and the clickable area is an area for checking the recommendation information;

or alternatively, the first and second heat exchangers may be,

5. A method according to any one of claims 1 to 3, wherein said determining that the i-th target type content is the content that received the machine click when the vector distance between the i-th vector to be detected and the target vector is greater than a first distance threshold comprises:

and calculating the similarity between the ith vector to be detected and the target vector through a cosine similarity formula, and determining the content of the ith target type as the content of the received machine click when the similarity between the ith vector to be detected and the target vector is lower than a similarity threshold.

6. A method according to any one of claims 1 to 3, wherein when the vector distance between the i-th vector to be detected and the target vector is greater than a first distance threshold, determining that the i-th target type content is the content that received the machine click, further comprises:

calculating the vector distance between the ith vector to be detected and the target vector through an Euclidean distance formula;

or alternatively, the first and second heat exchangers may be,

calculating the vector distance between the ith vector to be detected and the target vector through a Markov distance formula;

or alternatively, the first and second heat exchangers may be,

and calculating the vector distance between the ith vector to be detected and the target vector through a Manhattan distance formula.

7. A device for detecting machine clicks, the device comprising:

the charging system comprises a receiving module, a charging server and a charging module, wherein the receiving module is used for receiving a query request sent by the charging server, the query request comprises an identifier corresponding to the ith target type content, the query request is used for requesting to determine whether the ith target type content is the content which is clicked by the machine, the charging server is used for triggering the query request according to a clicking event received from the access server, the ith target type content is obtained from n target type contents, the n target type contents are n content which are the same type and comprise clickable areas, i is more than 0 and less than or equal to n, and i and n are integers;

The acquisition module is used for acquiring click coordinate data of n target type contents from a data storage server, wherein the click coordinate data are data generated according to click events received in the clickable area, and the data storage server is used for receiving the click events from the access server and determining the corresponding click coordinate data based on the click events;

the judging module is used for determining the content of the ith target type as the content of the received machine click when the vector distance between the vector to be detected and the target vector is greater than a first distance threshold;

The sending module is used for sending a query result to the charging server, wherein the query result is used for indicating that the ith target type content is the content which receives the machine click, and the charging server is used for charging the click event according to the query result;

the determining module is further configured to determine a kth vector to be detected according to click coordinate data of kth object type content, where the kth object type content is obtained from the n object type contents, k is greater than 0 and less than or equal to n, and k is an integer;

the determining module is further configured to determine that the kth target type content and the ith target type content receive the same type of machine click when a vector distance between the ith vector to be detected and the kth vector to be detected is less than a second distance threshold.

8. The apparatus of claim 7, wherein when the n target types of contents are recommendation information issued for n issue accounts, an i-th issue account is issued with m _i A piece of recommendation information, the click coordinate data including the m _i In the recommendation information, pixels of each recommendation information, on which a clickable area is clicked;

The determining module includes:

a mapping sub-module for mapping the m _i Mapping the pixel points in the clickable area of the recommendation information to a target coordinate system, wherein the target coordinate system is used for representing the positions of the pixel points in the clickable area in a coordinate mode;

the determining submodule is used for determining clicked coordinates in the target coordinate system according to the clicked pixel points of the clickable area;

a normalization sub-module for normalizing the m _i Normalizing the clicked coordinates in the clickable area of the piece of recommendation information;

and the determination submodule is further used for obtaining the ith vector to be detected according to the normalized total clicked times of the coordinates.

9. The apparatus of claim 7, wherein the n target types of content are recommendation information published for n published accounts;

the determining module includes:

the mapping sub-module is used for mapping the pixel points in the clickable areas of the recommendation information issued by the n issued accounts to a target coordinate system, wherein the target coordinate system is used for representing the positions of the pixel points in the clickable areas;

the normalization sub-module is used for normalizing the clicked coordinates in the clickable areas of the recommendation information issued by the n issued accounts;

and the determination submodule is further used for obtaining the target vector according to the normalized total number of times the coordinates are clicked.

10. The apparatus according to any one of claims 7 to 9, wherein the determining module is further configured to calculate a similarity between the ith to-be-detected vector and the target vector according to a cosine similarity formula, and determine that the ith target type content is the content that receives the machine click when the similarity between the ith to-be-detected vector and the target vector is lower than a similarity threshold.

11. A server comprising a processor and a memory, wherein the memory stores at least one program, and wherein the at least one program is loaded and executed by the processor to implement the method for detecting machine clicks according to any of claims 1-6.

12. A computer readable storage medium, wherein at least one program is stored in the storage medium, and the at least one program is loaded and executed by a processor to implement the method for detecting a machine click according to any one of claims 1 to 6.