Method, device, server and storage medium for calculating user activity

Abstract

Embodiments of the present application provide a method, device and storage medium for calculating user activity. Specifically, first, user data of a target user may be obtained, the user data including the order in which the target user triggers multiple game events. Then, the game event image of the target user may be determined based on the user data of the target user. Among them, the game event image is used to indicate the order in which the target user triggers each game event. Then, the game event image of the target user may be analyzed, and the user activity of the target user may be determined based on the texture features of the game event image of the target user. In this way, by converting the data of the user in the game into an image, and obtaining the texture features of the game event image based on image processing means, the user activity of the target user may be determined based on the texture features. In this way, the activity of the target user may be determined more accurately.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, server and storage medium for calculating user activity. Background Art

[0002] For an online game, the higher the proportion of active users, the greater the commercial value of the game. Therefore, in order to improve the commercial value of the game and adjust the game's operating strategy in a timely manner, it is necessary to accurately determine the user activity of the game users.

[0003] Currently, user activity is mostly determined by the game tasks that the user completes. For example, a game manufacturer can pre-set multiple game tasks and set an activity parameter for each game task. If a user completes a game task, the activity parameter corresponding to the game task can be added to the user activity of the user. In this way, the more game tasks a user completes, the more operations the user performs when playing the game, and the more active the user is.

[0004] The user activity calculated by the above method can reflect the activity of game users when playing games to a certain extent. However, if game users are only interested in part of the game content and do not deliberately complete a large number of game tasks, the user activity calculated by the above method cannot accurately measure the activity of game users when playing games. Summary of the invention

[0005] In view of this, embodiments of the present application provide a method, device, server, and storage medium for calculating user activity, aiming to accurately calculate the user activity of game users.

[0006] In a first aspect, an embodiment of the present application provides a method for calculating user activity, the method comprising:

[0007] Acquire user data of a target user, wherein the user data includes a sequence in which the target user triggers multiple game events;

[0008] Determine, according to the user data of the target user, a game event image of the target user, wherein the game event image is used to represent a sequence rule in which the target user triggers the multiple game events;

[0009] Based on the texture features of the game event image of the target user, the user activity of the target user is determined, wherein the stronger the texture features of the game event image of the target user, the higher the user activity of the target user.

[0010] In some possible implementations, determining the game event image of the target user according to the user data of the target user includes:

[0011] Determining a set of game event parameters according to the order in which the target user triggers the multiple game events;

[0012] A game event image of the target user is determined according to the game event parameter set.

[0013] In some possible implementations, the game event parameter set includes a plurality of game event parameters, and the game event parameters are used to indicate the possibility of the target user triggering two game events in sequence;

[0014] The determining the game event image of the target user according to the game event parameter set comprises:

[0015] Determine a pixel position corresponding to each of the plurality of game event parameters in the game event image;

[0016] According to the game event parameters in the game event parameter set, the values ​​of the pixel positions corresponding to the game event parameters in the game event image are determined.

[0017] In some possible implementations, the plurality of game event parameters include a first game event parameter, and the first game event parameter is used to indicate a possibility that the target user triggers the first game event first and then triggers the second game event;

[0018] Determining the pixel position corresponding to each of the plurality of game event parameters in the game event image comprises:

[0019] According to the order of the first game event in the plurality of game events and the order of the second game event in the plurality of game events, pixel positions from the first game event to the second game event in the game event image are determined.

[0020] In some possible implementations, determining a set of game event parameters according to the order in which the target user triggers the multiple game events includes:

[0021] Determine a first number and a second number according to the user data of the target user, the first number being the number of times the target user continues to trigger the second game event after triggering the first game event, the second number being the number of times the target user continues to trigger a third game event after triggering the first game event, the third game event being the game event with the highest probability of being continuously triggered by the target user after triggering the first game event;

[0022] The first game event parameter is determined according to a ratio of the first number to the second number.

[0023] In some possible implementations, the texture features of the game event image of the target user include any one or more of roughness, contrast, directionality, linearity, and regularity of the game event image.

[0024] In some possible implementations, the texture features of the game event image of the target user include roughness, contrast, directionality, linearity, and regularity of the game event image;

[0025] The determining the user activity of the target user based on the texture feature of the game event image of the target user comprises:

[0026] Obtaining an average directionality of active users and an average linearity of the active users, wherein the user activity of the active users is higher than a user activity threshold;

[0027] Determining a first parameter according to the average directionality of the active users and the directionality of the game event image;

[0028] determining a second parameter according to the average linearity of the active users and the linearity of the game event image;

[0029] Determine the user activity of the target user according to the roughness of the game event image, the contrast of the game event image, the linearity of the game event image, the first parameter, and the second parameter

[0030] In a second aspect, an embodiment of the present application provides a device for calculating user activity, the device comprising:

[0031] An acquisition unit, configured to acquire user data of a target user, wherein the user data indicates a sequence in which the target user triggers multiple game events;

[0032] A processing unit determines a game event image of the target user according to the user data of the target user, wherein the game event image is used to represent a sequence of the multiple game events triggered by the target user; and determines the user activity of the target user based on texture features of the game event image of the target user, wherein the stronger the texture features of the game event image of the target user, the higher the user activity of the target user.

[0033] In a third aspect, an embodiment of the present application provides a server, comprising a memory and a processor, wherein the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the server executes the method for calculating user activity as described in any one of the first aspects above.

[0034] In a fourth aspect, an embodiment of the present application provides a computer storage medium, in which a code is stored. When the code is executed, the device executing the code implements the method for calculating user activity as described in any one of the first aspects above.

[0035] In a fifth aspect, a computer program product comprising instructions is provided, which, when executed on a computer, enables the computer to execute the method for calculating user activity described in the first aspect.

[0036] The embodiment of the present application provides a method, device and storage medium for calculating user activity. Among them, the method for calculating user activity can be used to calculate the user activity of the target user. Specifically, when executing the technical solution provided by the embodiment of the present application, the user data of the target user can be obtained first, and the user data is used to indicate the order in which the target user triggers multiple game events, for example, it can include the time when the target user triggers multiple game events. Then, the game event image of the target user can be determined according to the user data of the target user. Among them, the game event image is used to indicate the order of the target user triggering each game event. Then, the game event image of the target user can be analyzed, and the user activity of the target user can be determined based on the texture features of the game event image of the target user. In this way, by converting the data of the user in the game into an image, and obtaining the texture features of the game event image based on the means of image processing, the user activity of the target user can be determined according to the texture features. In this way, the activity of the target user can be determined more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in this embodiment or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 A schematic diagram of a flow chart of a method for calculating user activity provided in an embodiment of the present application;

[0039] Figure 2-A A schematic diagram of a game event image provided by an embodiment of the present application;

[0040] Figure 2-B Another schematic diagram of a game event image provided by an embodiment of the present application;

[0041] Figure 3 A schematic diagram of the structure of an apparatus for calculating user activity provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] User activity is an important indicator for measuring the user value of game users. Currently, game manufacturers can determine the user activity of game users based on the completion of game tasks in the game. However, for some users who specialize in a small part of the content in the game, the above method cannot accurately determine the user activity of game users.

[0043] In order to solve this problem, some game manufacturers have introduced game duration as a reference parameter for determining user activity. In this way, the longer the game user is online, the higher the game user's activity. In this way, the accuracy of determining the game user's activity can be improved to a certain extent.

[0044] However, the method of judging the user activity of a game user by the game time of the game user cannot effectively judge the idle user. For example, if a game user opens the game but does not perform any operation, the game time of the game user will be relatively long, resulting in a higher user activity, which is inconsistent with the actual activity of the game user in playing the game.

[0045] In addition, the traditional method of setting game tasks to measure user activity also has the disadvantage of poor flexibility. For example, if a game has a major update, adding new game content or causing the original game to be affected, then the game manufacturer will need to delete the game tasks corresponding to the original game content and design game tasks corresponding to the new game content. In addition, the game tasks corresponding to each game are relatively independent, and the game tasks of one game cannot be applied to another game. In this way, when a new game is launched, the game manufacturer needs to design new game tasks, and the game operation is relatively complicated.

[0046] In order to solve the above problems, the embodiments of the present application provide a method, device, server and storage medium for calculating user activity, which is intended to guide users to trigger preset game events. Among them, the method for calculating user activity can be applied to a terminal device or a server. The terminal device can be, for example, a terminal device running a game client. The server can be a game background server for processing data in the game. In other words, assuming that the target user plays the game through the client, the technical solution provided by the embodiment of the present application can be executed by the client of the target user or by the background server of the game. Accordingly, if the technical solution provided by the embodiment of the present application is executed by the client of the target user, the client can send the user activity of the target user to the background server after determining the user activity of the target user.

[0047] The following is an explanation of the method for calculating user activity provided by the embodiment of the present application from the perspective of the server. Obviously, the described embodiment is only a part of the embodiment of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0048] See also Figure 1 , Figure 1 A method flow diagram of a method for calculating user activity provided in an embodiment of the present application includes:

[0049] S101: Acquire user data of a target user.

[0050] In order to determine the user activity of the target user, the user data of the target user can be obtained first. Among them, the user data of the target user is used to indicate the order in which the target user triggers multiple game events. The game event can be a game task preset in the game, or a combination of one or more continuous game operations performed by the target user, or one or more conditions satisfied by the target user. Specifically, the game event can be a regular change of game data preset in the game. It is understandable that different game events can correspond to different game data. In an embodiment of the present application, the game event can be pre-set in the client of the game.

[0051] In a possible implementation, the user data of the target user may include the time when the target user triggers a game event. Through the event of the target user triggering the game event, the order of the target user triggering the game event can be determined. For example, the client of the target user can detect and record the triggering of each game event when the target user plays the game, so as to obtain the user data of the target user. Specifically, the game event monitoring process can be pre-set in the client of the game. When the target user runs the game client of the target user, the game event monitoring process preset in the client can monitor the triggering of each game event in the game. After detecting that a certain game event is triggered, the game event monitoring process can record the event of the target user triggering the game event in the log. The game event monitoring process can send logs to the server regularly or irregularly so that the server can obtain the user data of the target user.

[0052] S102: Determine a game event image of the target user according to the user data of the target user.

[0053] After obtaining the user data of the target user, the server can determine the game event image of the target user based on the user data of the target user. The game event image of the target user is used to represent the order in which the target user triggers multiple game events. In other words, the server can convert the user data of the target user into an image so as to analyze the user activity of the target user by image processing in the subsequent process.

[0054] In some possible implementations, if the user data of the target user includes the time when the target user triggers a game event, the server can first determine the order in which the target user triggers multiple game events based on the user data of the target user, then determine the game event parameter set based on the order in which the target user triggers the game events, and finally determine the game event image of the target user based on the game event parameter set. Among them, the game event parameter set can include multiple game event parameters. Each game event parameter can be used to indicate the possibility of the target user triggering two game events in sequence.

[0055] That is to say, the game event parameter can correspond to two game events, indicating the possibility that the target user triggers the two game events in sequence. For example, suppose the target user triggers game event A first and then triggers game event B 10 times, while the target user triggers game event B first and then triggers game event A 5 times. Then the game event parameter corresponding to "game event A-game event B" can be 10, and the game event parameter corresponding to "game event B-game event A" can be 5.

[0056] In the computer field, an image can be identified in the form of a matrix. Each element in the matrix corresponds to a pixel in the image, and the value of the element represents the color of the pixel. In an embodiment of the present application, a plurality of game event parameters included in the game event parameter set can be arranged in sequence, and each game event parameter corresponds to a pixel in the game event image. The value of the game event parameter represents the color of the pixel. Accordingly, when determining the game event image according to the game event parameter set, the server first determines the pixel position corresponding to the game event parameter in the game event image according to the order of the game event parameters in the game event parameter set. Then, the specific value of the game event image at the pixel position can be determined according to the value of the game event parameter. In this way, the color of each pixel in the game event image can be determined by the game event parameter set, thereby obtaining the game event image.

[0057] The following takes a specific implementation as an example to introduce a method for determining a target user's game event image based on the target user's user data. It is understandable that the implementation described below is only an example and does not mean that the technical solution provided in the embodiment of the present application can only determine the target user's game event image through this method.

[0058] Assuming that there are N game events preset in the game, the server can first establish an N*N matrix A and determine the value of each element in the matrix based on the user data of the target user. ij The value of (i and j are both positive integers less than or equal to N) is the game event parameter corresponding to the i-th game event and the j-th game event. ij The value of represents the number of times the target user continues to execute the jth game event after executing the i-th game event in the user data of the target user.

[0059] For example, suppose that after the target user triggers the first game event, the number of times the target user continues to execute the second game event is 1, and the number of times the target user continues to trigger the third game event is 2. After the target user triggers the second game event, the number of times the target user continues to execute the third game event is 3. Then the element A in matrix A 12 The value of is 1, and the element A in matrix A 13 The value of is 2, and the element A in matrix A 23 The value of is 3.

[0060] After determining matrix A, the server can map matrix A to image matrix B. Image matrix B is a matrix representation of the game event image. Optionally, the server can map the element to the corresponding position in matrix B according to the position of the element in matrix A. That is, element B in matrix B ij The value of is determined by the element A in the matrix A ijThe value of is determined.

[0061] That is to say, when determining the pixel positions corresponding to the game event parameters of the i-th game event and the j-th game event in the game event image, the server can determine the row of the pixel position corresponding to the game event parameter in the game event image based on i, and determine the column number of the pixel position corresponding to the game event parameter in the game event based on j.

[0062] In some possible implementations, the game event image may be a grayscale image. Accordingly, the value of each element in the matrix B may be between 0 and 255. ij The larger the value of , the closer the color of the pixel in the i-th row and j-th column in the game event image is to white.

[0063] In actual application scenarios, the amount of user data may be relatively large, resulting in a relatively large value for each element in matrix A. Accordingly, in the process of mapping matrix A to matrix B, the server may perform mapping processing on each element in matrix A.

[0064] In a first possible implementation, the server may map all elements in matrix A as a whole. That is, the server may first determine the largest element in matrix A and map the value of the element to 255. Then, the server may multiply the value of each element in matrix A by 255 and divide the result of the multiplication by the largest element in matrix A. The final result is the value of the corresponding position of the element in matrix B.

[0065] That is, B ij The value of can be determined by the following formula:

[0066]

[0067] Among them, A max is the largest element in matrix A.

[0068] In a second possible implementation, the server may map each element in matrix A row by row. That is, the server may divide matrix A into N rows and map the elements in each row. Specifically, when mapping the elements in the i-th row of matrix A, the server may first obtain the largest element in the i-th row of matrix A and map the value of the element to 255. Then, the server may multiply the value of each element in the i-th row of matrix A by 255, and divide the result of the multiplication by the largest element in the i-th row of matrix A. The final result is the value of the element at the corresponding position in matrix B.

[0069] In this way, even if there is an element with a larger value in a row of matrix A, through the above row-by-row mapping method, the element with a larger value will not affect the values ​​of elements in other rows of matrix A in matrix B. In this way, the texture features in the game event image can be further highlighted.

[0070] That is, B ij The value of can be determined by the following formula:

[0071]

[0072] Among them, A imax is the largest element in the i-th row of matrix A.

[0073] S103: Determine the user activity of the target user based on the texture features of the game event image of the target user.

[0074] After acquiring the game event image of the target user, the server can analyze the texture features of the game event image of the target user to determine the activity of the target user. In the embodiment described above, the more times the target user triggers two game events in succession, the closer the color of the pixels corresponding to the two game events in the game event image is to white. It can be seen that the order in which the target user triggers game events can be analyzed through the texture features of the game event image. The higher the frequency of the target user triggering game events, the higher the user activity of the target user. Specifically, the game event image corresponding to the active user can be as follows: Figure 2-A As shown, the game event image corresponding to the inactive user can be as follows Figure 2-B shown.

[0075] In the embodiment of the present application, the texture features of the game event image may include any one or more of roughness, contrast, directionality, linearity and regularity, which are introduced below.

[0076] The roughness of the game event image corresponds to the grayscale value of the game event image. The roughness is calculated by first calculating the average grayscale value of each pixel in the game event image within a certain range, and then calculating the average value of the results of all pixels. For the game event image, two adjacent pixels in the same row represent the frequency of the target user jumping from one game event to the next game event; two adjacent points in the same column represent the frequency of jumping from other events to this event. Since active users have more game behaviors than inactive users, the horizontal and vertical frequencies of some pixels in the game event image of active users will be greater than those of inactive users, so the average grayscale value will also be significantly greater than that of inactive users. In other words, the greater the roughness of the game event image, the greater the user activity of the target user.

[0077] The contrast of the game event image is used to reflect the discreteness of the pixel distribution of the game event image. The contrast is obtained by statistics on the distribution of pixel intensity. Since active users operate more game behaviors, after the user data of active users is converted into game event images, the brightness distribution of each pixel in the game event image is relatively discrete, that is, the values ​​of the pixels in the game event image have multiple values ​​between 0 and 255. Inactive users have fewer game events, and the pixel distribution is relatively concentrated, that is, the values ​​of the pixels in the game event image have a few values ​​between 0 and 255. In other words, the greater the contrast of the game event image, the greater the user activity of the target user.

[0078] The directionality of the game event image is used to reflect the divergence or concentration of the texture in the image of the game event image. That is, whether the white part in the middle of the game event image has a value that is radiated or concentrated in certain directions. Since most active users trigger game tasks regularly, the discrete degree of the directionality of active users is weaker, and the discrete degree of the directionality of inactive users is higher. In other words, the higher the discrete degree of the directionality of the game event image, the lower the user activity of the target user.

[0079] The linearity of the game event image is used to reflect the degree of discreteness of the linear texture in the game event image. Active users may trigger more game events, and the order of triggering game events may be different, so the light-colored area on the game event image of active users will be close to the block structure with a larger area. Inactive users trigger fewer game events, so there will be relatively more linear structures in the game event image of inactive users. In other words, the greater the linearity of the game event image, the lower the user activity of the target user.

[0080] The regularity of the game event image is used to reflect the difference in texture values ​​of different window areas in the game event image. For inactive users, the game event image is mostly black, so when the texture values ​​between most windows are not very different, the regularity of the game event image of inactive users will be relatively large. The order in which active users trigger game events each time may be irregular, so the regularity of the game event image of active users will be relatively small. In other words, the greater the regularity of the game event image, the lower the user activity of the target user.

[0081] In a possible implementation, the texture rule of the game event image includes the roughness, contrast, directionality, linearity and regularity of the game event image. Accordingly, the server can determine the user activity of the target user by the following formula:

[0082]

[0083] Among them, F active is the user activity of the target user, F coa is the roughness of the target user’s game event image, F con is the contrast of the game event image of the target user, F dir is the direction of the target user’s game event image, M dir is the average orientation of the game event images of active users, F lin is the linearity of the game event image of the target user, M lin is the average linearity of the game event images of active users, F reg is the regularity of the game event image of the target user. The active user is a user whose user activity is higher than the user activity threshold among the users of the game.

[0084] It is understandable that the server may also determine the user activity of the target user in other ways, which will not be elaborated here.

[0085] The embodiment of the present application provides a method for calculating user activity. Specifically, when executing the technical solution provided by the embodiment of the present application, the user data of the target user can be obtained first, and the user data includes the order in which the target user triggers multiple game events. Then, the game event image of the target user can be determined based on the user data of the target user. Among them, the game event image is used to indicate the order of the target user triggering each game event, reflecting the law of the target user triggering the game event. Then, the game event image of the target user can be analyzed, and the user activity of the target user can be determined based on the texture features of the game event image of the target user. In this way, by converting the data of the user in the game into an image, and obtaining the texture features of the game event image based on the means of image processing, the user activity of the target user can be determined according to the texture features. In this way, the activity of the target user can be determined more accurately.

[0086] The above are some specific implementations of the method for calculating user activity provided in the embodiments of the present application. Based on this, the present application also provides a corresponding device for calculating user activity. The device for calculating user activity provided in the embodiments of the present application will be introduced from the perspective of functional modularization.

[0087] See also Figure 3 The structure diagram of the device 300 for calculating user activity is shown, and the device 300 includes an acquisition unit 310 and a processing unit 320.

[0088] The acquisition unit 310 is used to acquire user data of a target user, wherein the user data includes a sequence in which the target user triggers multiple game events.

[0089] The processing unit 320 is used to determine a game event image of the target user based on the user data of the target user, wherein the game event image is used to represent the sequence of the target user triggering the multiple game events; based on the texture features of the game event image of the target user, determine the user activity of the target user, wherein the stronger the texture features of the game event image of the target user, the higher the user activity of the target user.

[0090] The embodiment of the present application provides a device for calculating user activity. Specifically, the device can first obtain user data of a target user, and the user data includes events in which the target user triggers multiple game events. Then, the game event image of the target user can be determined based on the user data of the target user. Among them, the game event image is used to indicate the regularity of the target user triggering each game event, reflecting the regularity of the target user triggering the game event. Then, the game event image of the target user can be analyzed, and the user activity of the target user can be determined based on the texture features of the game event image of the target user. In this way, by converting the data of the user in the game into an image, and obtaining the texture features of the game event image based on image processing means, the user activity of the target user can be determined based on the texture features. In this way, the activity of the target user can be determined more accurately.

[0091] Optionally, in some possible implementations, the processing unit 320 is specifically used to determine a set of game event parameters according to the order in which the target user triggers the multiple game events; and determine a game event image of the target user according to the set of game event parameters.

[0092] Optionally, in some possible implementations, the game event parameter set includes multiple game event parameters, and the game event parameters are used to indicate the possibility of the target user triggering two game events in sequence; the processing unit 320 is specifically used to determine the pixel position corresponding to each game event parameter among the multiple game event parameters in the game event image; and determine the value of the pixel position corresponding to the game event parameter in the game event image according to the game event parameters in the game event parameter set.

[0093] Optionally, in some possible implementations, the multiple game event parameters include a first game event parameter, which is used to indicate the possibility that the target user triggers the first game event first and then triggers the second game event; the processing unit 320 is specifically used to determine the pixel positions from the first game event to the second game event in the game event image according to the order of the first game event in the multiple game events and the order of the second game event in the multiple game events.

[0094] Optionally, in some possible implementations, the processing unit 320 is specifically used to determine a first quantity and a second quantity based on the user data of the target user, the first quantity being the number of times the target user continues to trigger the second game event after triggering the first game event, the second quantity being the number of times the target user continues to trigger a third game event after triggering the first game event, the third game event being the game event with the highest probability that the target user will continue to trigger after triggering the first game event; the first game event parameter is determined based on the ratio of the first quantity to the second quantity.

[0095] Optionally, in some possible implementations, the texture features of the game event image of the target user include any one or more of roughness, contrast, directionality, linearity and regularity of the game event image.

[0096] Optionally, in some possible implementations, the acquisition unit 310 is specifically configured to acquire the average directionality of active users and the average linearity of the active users, and the user activity of the active users is higher than the user activity threshold. The processing unit 320 is specifically configured to determine a first parameter based on the average directionality of the active users and the directionality of the game event image; determine a second parameter based on the average linearity of the active users and the linearity of the game event image; and determine the user activity of the target user based on the roughness of the game event image, the contrast of the game event image, the linearity of the game event image, the first parameter, and the second parameter.

[0097] The embodiments of the present application also provide corresponding servers, computer storage media and computer program products for implementing the technical solutions provided in the embodiments of the present application.

[0098] The server includes a memory and a processor, the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the server executes the method for calculating user activity described in any embodiment of the present application.

[0099] The computer storage medium stores codes, and when the codes are executed, the device executing the codes implements the method for calculating user activity described in any embodiment of the present application.

[0100] When the computer program product is run on a computer, it can enable the computer to execute the method for calculating user activity described in any embodiment of the present application.

[0101] The "first" and "second" in the names such as "first" and "second" (if any) mentioned in the embodiments of the present application are only used as name identifiers and do not represent the first or second in order.

[0102] Through the description of the above implementation methods, it can be known that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus a general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a storage medium, such as a read-only memory (ROM) / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network communication device such as a router) to execute the methods described in each embodiment of the present application or some parts of the embodiments.

[0103] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0104] The above description is merely an exemplary embodiment of the present application and is not intended to limit the protection scope of the present application.

Claims

1. A method for calculating user activity, characterized in that: The method comprises: Acquire user data of a target user, wherein the user data indicates a sequence in which the target user triggers multiple game events; Determine, according to the user data of the target user, a game event image of the target user, wherein the game event image is used to represent a sequence rule in which the target user triggers the multiple game events; Determining the user activity of the target user based on the texture features of the game event image of the target user, wherein the texture features of the game event image of the target user include any one or more of the roughness, contrast, directionality, linearity and regularity of the game event image, the roughness and the contrast are positively correlated with the user activity of the target user, and the discrete degree of the directionality, the linearity and the regularity are negatively correlated with the user activity of the target user; The determining the user activity of the target user based on the texture feature of the game event image of the target user comprises: Obtaining an average directionality of active users and an average linearity of the active users, wherein the user activity of the active users is higher than a user activity threshold; Determining a first parameter according to the average directionality of the active users and the directionality of the game event image; determining a second parameter according to the average linearity of the active users and the linearity of the game event image; The user activity of the target user is determined according to the roughness of the game event image, the contrast of the game event image, the linearity of the game event image, the first parameter, and the second parameter.

2. The method according to claim 1, characterized in that Determining the game event image of the target user according to the user data of the target user comprises: Determining a set of game event parameters according to the order in which the target user triggers the multiple game events; A game event image of the target user is determined according to the game event parameter set.

3. The method according to claim 2, characterized in that The game event parameter set includes a plurality of game event parameters, and the game event parameters are used to indicate the possibility of the target user triggering two game events in sequence; The determining the game event image of the target user according to the game event parameter set comprises: Determine a pixel position corresponding to each of the plurality of game event parameters in the game event image; According to the game event parameters in the game event parameter set, the values ​​of the pixel positions corresponding to the game event parameters in the game event image are determined.

4. The method according to claim 3, characterized in that The plurality of game event parameters include a first game event parameter, wherein the first game event parameter is used to indicate the possibility that the target user first triggers the first game event and then triggers the second game event; Determining the pixel position corresponding to each of the plurality of game event parameters in the game event image comprises: According to the order of the first game event in the plurality of game events and the order of the second game event in the plurality of game events, pixel positions from the first game event to the second game event in the game event image are determined.

5. The method according to claim 4, characterized in that Determining a set of game event parameters according to the order in which the target user triggers the multiple game events includes: Determine a first number and a second number according to the user data of the target user, the first number being the number of times the target user continues to trigger the second game event after triggering the first game event, the second number being the number of times the target user continues to trigger a third game event after triggering the first game event, the third game event being the game event with the highest probability of being continuously triggered by the target user after triggering the first game event; The first game event parameter is determined according to a ratio of the first number to the second number.

6. A device for calculating user activity, characterized in that: The device comprises: An acquisition unit, configured to acquire user data of a target user, wherein the user data indicates a sequence in which the target user triggers multiple game events; A processing unit determines, based on the user data of the target user, a game event image of the target user, wherein the game event image is used to represent a sequence of the target user triggering the multiple game events; and determines the user activity of the target user based on texture features of the game event image of the target user, wherein the texture features of the game event image of the target user include any one or more of the roughness, contrast, directionality, linearity, and regularity of the game event image, wherein the roughness and the contrast are positively correlated with the user activity of the target user, and the discrete degree of the directionality, the linearity, and the regularity are negatively correlated with the user activity of the target user; The determining the user activity of the target user based on the texture feature of the game event image of the target user comprises: Obtaining an average directionality of active users and an average linearity of the active users, wherein the user activity of the active users is higher than a user activity threshold; Determining a first parameter according to the average directionality of the active users and the directionality of the game event image; determining a second parameter according to the average linearity of the active users and the linearity of the game event image; The user activity of the target user is determined according to the roughness of the game event image, the contrast of the game event image, the linearity of the game event image, the first parameter, and the second parameter.

7. A server, characterized in that: The server includes a memory and a processor, the memory is used to store programs or codes, and the processor is used to execute the programs or codes stored in the memory to implement the method for calculating user activity as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that: The method comprises instructions, programs or codes, which, when executed on a computer, enable the computer to execute the method for calculating user activity as described in any one of claims 1 to 5.

Images