Method and device for information recommendation

Abstract

The present application proposes an information recommendation method and device, the method comprising: obtaining a user serial number of a target user, the user serial number being an integer greater than or equal to 0; obtaining a first value corresponding to the user serial number; obtaining a user portrait score of the target user, and obtaining a second value corresponding to the user portrait score; when the user serial number is less than a first threshold, taking the sum of the first value and the second value as the target value of the target user; and outputting the target value to the target user. The implementation of the present application can improve the accuracy of recommended information, thereby improving the effect of network marketing operations.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an information recommendation method and device. Background Art

[0002] With the rapid development of Internet technology, online shopping is becoming more and more closely integrated with people's lives, and online marketing models are becoming more and more diverse. This kind of online marketing is often based on the premise that users complete designated operations. Merchants will provide certain preferential information to users who successfully complete designated operations, so that users can complete transactions at a lower price.

[0003] In existing online marketing activities, merchants can control the size of discounts by adjusting the difficulty of obtaining discount information. However, as users participating in the activities, they can only complete the specified operations according to the merchant's settings to obtain the corresponding discount information. In other words, the discount information obtained by users is actually completely determined by the merchant, the accuracy of discount information recommendation is relatively low, and the matching degree between users and discount information is low. Summary of the invention

[0004] In view of the above problems, the present application is proposed to provide a method and device for information recommendation that overcomes the above problems or at least partially solves the above problems.

[0005] In a first aspect, an embodiment of the present application provides an information recommendation method, which includes: obtaining a user serial number of a target user, where the user serial number is an integer greater than or equal to 0; obtaining a first numerical value corresponding to the user serial number; obtaining a user portrait score of the target user, and obtaining a second numerical value corresponding to the user portrait score; when the user serial number is less than a first threshold, using the sum of the first numerical value and the second numerical value as a target numerical value for the target user; and outputting the target numerical value to the target user.

[0006] In a possible implementation, the obtaining of the first numerical value corresponding to the user serial number includes: calling a first recommendation model to process the user serial number to obtain the first numerical value of the target user.

[0007] In another possible implementation, the obtaining of the second numerical value corresponding to the user portrait score includes: calling a second recommendation model to process the user portrait score to obtain the second numerical value corresponding to the user portrait score.

[0008] In another possible implementation, the user portrait score is a rational number greater than or equal to 0 and less than or equal to 1; the calling of the second recommendation model to process the user portrait score to obtain a second numerical value corresponding to the user portrait score includes: when the user portrait score is proportional to the target numerical value, obtaining the first percentile corresponding to the user portrait score; calling the second recommendation model to process the first percentile to obtain a second numerical value.

[0009] In another possible implementation, the user portrait score is a rational number greater than or equal to 0 and less than or equal to 1; the calling of the second recommendation model to process the user portrait score to obtain a second numerical value corresponding to the user portrait score includes: when the user portrait score is inversely proportional to the target numerical value, obtaining a second percentile corresponding to the difference between the user portrait score and 1; calling the second recommendation model to process the second percentile to obtain a second numerical value.

[0010] In another possible implementation, before calling the first recommendation model to process the user serial number, the method further includes: obtaining a first recommendation model, wherein the first recommendation model is constructed by control parameters, wherein the control parameters include the first threshold, the second threshold, the first characteristic value, the second characteristic value and trend information; the first threshold is used to represent the minimum number of participants; the second threshold is used to represent the maximum number of participants; the trend information is used to determine whether the slope of the straight line of the first recommendation model is a positive number or a negative number; the first threshold, the second threshold and the first characteristic value are used to determine the straight line intercept of the first recommendation model.

[0011] In another possible implementation, the above-mentioned using the sum of the first value and the second value as the target value of the target user includes: when the sum of the first value, the second value and the cumulative value of at least one user before the user serial number is greater than or equal to the first characteristic value, using the difference between the cumulative value of at least one user before the user serial number and the first characteristic value as the target value of the target user; otherwise, using the sum of the first value and the second value as the target value of the target user.

[0012] In another possible implementation, the method further includes: when the user serial number is greater than or equal to the first threshold, determining whether the random number corresponding to the target user is 1; if it is confirmed that the random number corresponding to the target user is 1, taking the difference between the cumulative value of at least one user before the user serial number and the second characteristic value as the target value of the target user; otherwise, executing the step of taking the sum of the first value and the second value as the target value of the target user.

[0013] In the second aspect, an embodiment of the present application provides an information recommendation device, including: an acquisition unit, used to acquire a user serial number of a target user, wherein the user serial number is an integer greater than or equal to 0; a first acquisition unit, used to obtain a first numerical value corresponding to the user serial number; the first acquisition unit is also used to acquire a user portrait score of the target user and obtain a second numerical value corresponding to the user portrait score; a recommendation unit, used to use the sum of the first numerical value and the second numerical value as a target numerical value for the target user when the user serial number is less than a first threshold; and an output unit, used to output the target numerical value to the target user.

[0014] In a possible implementation, the first obtaining unit is specifically configured to call a first recommendation model to process the user serial number to obtain the first numerical value of the target user.

[0015] In another possible implementation, the first obtaining unit is further configured to call a second recommendation model to process the user portrait score to obtain a second numerical value corresponding to the user portrait score.

[0016] In another possible implementation, the user portrait score is a rational number greater than or equal to 0 and less than or equal to 1; the first obtaining unit is further used to obtain the first percentile corresponding to the user portrait score when the user portrait score is proportional to the target value; and call the second recommendation model to process the first percentile to obtain a second value.

[0017] In another possible implementation, the user portrait score is a rational number greater than or equal to 0 and less than or equal to 1; the first obtaining unit is further used to obtain, when the user portrait score is inversely proportional to the target value, a second percentile corresponding to the difference between the user portrait score and 1; and the second recommendation model is called to process the second percentile to obtain a second value.

[0018] In another possible implementation, the device also includes: a second obtaining unit, used to obtain a first recommendation model, the first recommendation model is constructed by control parameters, the control parameters include the first threshold, the second threshold, the first characteristic value, the second characteristic value and trend information; the first threshold is used to represent the minimum number of participants; the second threshold is used to represent the maximum number of participants; the trend information is used to determine whether the slope of the straight line of the first recommendation model is a positive number, or a negative number; the first threshold, the second threshold and the first characteristic value are used to determine the straight line intercept of the first recommendation model.

[0019] In another possible implementation, the recommendation unit is specifically configured to, when the sum of the first value, the second value, and the cumulative value of at least one user before the user sequence number is greater than or equal to the first feature value, use the difference between the cumulative value of at least one user before the user sequence number and the first feature value as the target value of the target user;

[0020] Otherwise, the sum of the first value and the second value is used as the target value of the target user.

[0021] In another possible implementation, the device further includes: a judgment unit, configured to judge whether the random number corresponding to the target user is 1 when the user serial number is greater than or equal to the first threshold; the recommendation unit is further configured to, if it is confirmed that the random number corresponding to the target user is 1, use the difference between the cumulative value of at least one user before the user serial number and the second characteristic value as the target value of the target user; the recommendation unit is further configured to, otherwise, execute the step of using the sum of the first value and the second value as the target value of the target user.

[0022] In a third aspect, an embodiment of the present application provides an information recommendation device, comprising: a processor, an input device, an output device and a memory, wherein the memory is used to store a computer program that supports a server to execute the above method, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method of the first aspect.

[0023] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the methods described in the above aspects.

[0024] In a fifth aspect, an embodiment of the present application provides a computer program product comprising program instructions, which, when executed on a computer, enables the computer to execute the method as shown in the first aspect.

[0025] By implementing this application and outputting target values ​​to target users based on their user portrait scores, the accuracy of recommended information can be improved, thereby improving the efficiency and effectiveness of online marketing operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background technology, the drawings required for use in the embodiments of the present application or the background technology will be described below.

[0027] Figure 1 is an architecture diagram of an information recommendation system provided in an embodiment of the present application;

[0028] Figure 2 This is a flowchart of information recommendation provided by an embodiment of the present application;

[0029] Figure 3 is a flow chart of an information recommendation method provided by an embodiment of the present application;

[0030] Figure 4 is a flow chart of another information recommendation method provided by an embodiment of the present application;

[0031] Figure 5 is a structural diagram of an information recommendation device provided in an embodiment of the present application;

[0032] Figure 6 It is a structural diagram of a simplified information recommendation entity device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0034] The terms "first", "second", "third", etc. in the specification and claims of the present application and the drawings are used to distinguish different objects, rather than to describe a specific order. In addition, "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0035] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0036] The terms "server", "unit", "system", etc. used in this application are used to refer to computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a server can be, but is not limited to, a processor, a data processing platform, a computing device, a computer, two or more computers, etc.

[0037] See also Figure 1 , Figure 1 is an architecture diagram of an information recommendation system provided in an embodiment of the present application. Figure 1 As shown, the system includes an electronic device 10 and an information recommendation device 20. In a possible implementation, the electronic device 10 may be a portable terminal such as a mobile phone, a tablet computer, a notebook computer, or a non-portable terminal such as a desktop computer, or other devices capable of uploading data.

[0038] It should be noted that in Figure 1 In the information recommendation system shown: the electronic device 10 is used to provide the user serial number of the target user to the information recommendation device 20.

[0039] The information recommendation device 20 is used to obtain the user serial number corresponding to the electronic device 10 and obtain a first numerical value corresponding to the user serial number; the information recommendation device 20 is also used to obtain the user portrait score of the above-mentioned target user and obtain a second numerical value corresponding to the above-mentioned user portrait score; the information recommendation device 20 is also used to use the sum of the above-mentioned first numerical value and the above-mentioned second numerical value as the target numerical value of the above-mentioned target user when the above-mentioned user serial number is less than the first threshold value; the information recommendation device 20 is also used to output the above-mentioned target numerical value to the above-mentioned target user.

[0040] In another possible implementation, the electronic device 10 is used to provide the information recommendation device 20 with a user portrait score of the target user.

[0041] See also Figure 2 , Figure 2 is a flowchart of information recommendation provided by an embodiment of the present application, comprising Figure 2It can be seen from the information recommendation process shown that after the information recommendation device 20 obtains the first value and the second value corresponding to the electronic device 10 according to the user sequence number and the user portrait score, it is necessary to determine whether the user sequence number corresponding to the user is less than the first threshold value; if the user sequence number is less than the first threshold value, the information recommendation device 20 determines whether the sum of the cumulative values ​​of all previous users, the first value and the second value is greater than the first characteristic value; if the sum of the above values ​​is less than the first characteristic value, the information recommendation device 20 uses the sum of the first value and the second value as the target value of the user corresponding to the electronic device 10; otherwise, the information recommendation device 20 uses the difference between the cumulative values ​​of all previous users and the first characteristic value as the target value of the user corresponding to the electronic device 10.

[0042] Optionally, the information recommendation device 20 may obtain the user portrait score by calculating the user portrait score by receiving user data of the user; or by receiving data sent by an electronic device specifically used to calculate the user portrait score.

[0043] Depend on Figure 2 It can be seen from the information recommendation process shown that when the user serial number of the target user is greater than or equal to the first threshold, the information recommendation device 20 needs to further judge the random number corresponding to the user. For the target user who meets the conditions, the information recommendation device 20 uses the difference between the cumulative value of all users before the user and the second characteristic value as the target value of the user corresponding to the electronic device 10. That is, for the target user who does not meet the conditions, the information recommendation device 20 repeatedly executes the step of judging whether the sum of the cumulative value of all users before the user, the first value and the second value is greater than the first characteristic value until the target value corresponding to the target user is obtained. After outputting the target value of the corresponding user to the electronic device 10, the information recommendation device 20 ends the information recommendation process corresponding to the user.

[0044] See also Figure 3 , Figure 3 : is a flowchart of an information recommendation method provided in an embodiment of the present application, the method comprising:

[0045] S101. Obtain a user serial number of a target user, where the user serial number is an integer greater than or equal to 0.

[0046] Specifically, the user serial number of the target user is determined by the user's trigger time, which may be the time when the user clicks a specific link or the time when the user enters a system. The users are sorted according to their trigger time. The user with the earliest trigger time has a user serial number of 0, and other users whose trigger time is later than the user obtain user serial numbers corresponding to the sorting order of the trigger time.

[0047] For example, user A enters the limited-time discount system at 08:00, and user B enters the system at 09:30. The trigger times of the users are sorted, and the sorting order of the trigger times of user A and user B is 1st and 30th respectively. Then the user serial number of user A is 0, and the user serial number of user B is 29.

[0048] For another example, user A creates link A, and the user serial number of user A is 0; user B and user C are the third and fourth users who click on link A, respectively, and the user serial numbers of user B and user C are 3 and 4, respectively.

[0049] Furthermore, the information recommendation device pre-stores a plurality of numbering rules, and the information recommendation device determines the user serial number of the user according to the current setting.

[0050] In a possible implementation, the information recommendation device divides the user serial numbers into sections according to the user's triggering time.

[0051] For example, the first 100 users entering system A have user numbers A000 to A099, the 101st to 200th users entering system A have user numbers B000 to B099, and the 201st to 500th users entering system A have user numbers C000 to C299.

[0052] In another possible implementation, the information recommendation device numbers the user numbers according to the user's trigger time and user level information.

[0053] For example, after the 100th user clicks link A, user A and user B both click link A at 12:00:00. Since the level of user A is higher than that of user B, the user serial number of user A is 100 and the user serial number of user B is 101.

[0054] For another example, after the 100th user clicked on link A, user A and user B both clicked on link A at 12:00:00. Since user A has been registered for a longer time, the information recommendation device determines that user A's level is higher than user B. Then user A's user number is 100 and user B's user number is 101.

[0055] In another possible implementation, the information recommendation device randomly numbers users with the same trigger time. It should be understood that the above description is only used as an example, and the embodiment of the present application does not specifically limit the method for determining the user serial number.

[0056] S102: Obtain a first numerical value corresponding to the user serial number.

[0057] Specifically, the first recommendation model is called to process the user serial number to obtain the first numerical value of the target user.

[0058] For example, the slope of the first recommendation model is 0.01, the intercept is 0.1, and the expression is G(i)=0.01*i+0.1, where i is the user number. The user number of the target user is 10, so the first recommendation model is called to obtain the first value of the target user as 0.2.

[0059] For another example, the slope of the first recommendation model is -0.033, the intercept is 0.2, and the expression is G(i) = -0.033*i+0.2, where i is the user number. If the user number of the target user is 0, then the first recommendation model is called to obtain the first value of the target user as 0.2.

[0060] In a possible implementation, before calling the first recommendation model to process the user serial number, the method further includes: obtaining a first recommendation model, wherein the first recommendation model is constructed by control parameters, wherein the control parameters include the first threshold, the second threshold, the first characteristic value, the second characteristic value and trend information; the first threshold is used to represent the minimum number of participants; the second threshold is used to represent the maximum number of participants; the trend information is used to determine whether the slope of the straight line of the first recommendation model is a positive number or a negative number; the first threshold, the second threshold and the first characteristic value are used to determine the straight line intercept of the first recommendation model.

[0061] For example, when the first threshold in the control parameters is 3, the second threshold is 8, the first characteristic value is 0.7, and the second characteristic value is 0.9, and the trend information determines that the slope of the straight line of the first recommendation model is negative, the expression of the first recommendation model is as follows: G(i)=a*i+C, where a is a constant less than 0, and i is the user number. Then, the first value obtained by the user with user number M+1 is 0, and the sum of the first values ​​obtained by users with user numbers 0 to M is the first characteristic value.

[0062] Let 1-b represent the first characteristic value, then the expression of the first recommendation model is: The expression of constant C is

[0063] Since the constant C decreases monotonically with respect to M, the first threshold is 3, the second threshold is 8, and the first characteristic value is 0.3, it is determined that the serial number corresponding to the above M is 5. Substituting the value of M into the expression of the above first recommendation model, G(i)=-0.033*i+0.2 is obtained, where i is the user serial number.

[0064] S103: Obtain a user portrait score of the target user, and obtain a second value corresponding to the user portrait score.

[0065] Specifically, the obtaining of the second value corresponding to the user portrait score includes: calling a second recommendation model to process the user portrait score to obtain the second value corresponding to the user portrait score.

[0066] For example, the second value is the inverse cumulative probability distribution function φ of the standard normal distribution -1 The product of (x) and the standard deviation, when the standard deviation is 0.23 and the user portrait score is 0.975, the standard normal 97.5% quantile is 1.96 from the standard normal distribution table, and the above second value is 0.4508.

[0067] In one possible implementation, the user portrait score is a rational number greater than or equal to 0 and less than or equal to 1; the calling of the second recommendation model to process the user portrait score to obtain a second numerical value corresponding to the user portrait score includes: when the user portrait score is proportional to the target numerical value, obtaining the first percentile corresponding to the user portrait score; calling the second recommendation model to process the first percentile to obtain a second numerical value.

[0068] Furthermore, when the above-mentioned user portrait score is used to represent the user's consumption capacity and the above-mentioned target value is the discount value corresponding to virtual product A, the above-mentioned user portrait score is proportional to the above-mentioned target value, that is, the higher the above-mentioned user portrait score of a user (the stronger the corresponding consumption capacity), the greater the discount value obtained by the user.

[0069] For example, when the standard deviation is 0.23 and the user portrait scores of User A and User B are 0.975 and 0.16 respectively, the percentiles corresponding to User A and User B are obtained from the standard normal distribution table, and multiplied by the standard deviation, the second values ​​corresponding to User A and User B are obtained as 0.4508 and 0.0368 respectively.

[0070] In another possible implementation, the user portrait score is a rational number greater than or equal to 0 and less than or equal to 1; the calling of the second recommendation model to process the user portrait score to obtain a second numerical value corresponding to the user portrait score includes: when the user portrait score is inversely proportional to the target numerical value, obtaining a second percentile corresponding to the difference between the user portrait score and 1; calling the second recommendation model to process the second percentile to obtain a second numerical value.

[0071] Furthermore, when the user portrait score is used to represent the user's payment interest probability score, and the target value is the discount value corresponding to virtual product A, the user portrait score is inversely proportional to the target value, that is, the higher the user portrait score corresponding to a user (the greater the possibility of the user paying), the smaller the discount value obtained by the user.

[0072] For example, when User A obtains a user portrait score of 0.76, since the user portrait score is inversely proportional to the target value, the percentile -0.41 corresponding to 0.34 is obtained from the standard normal distribution table, and multiplied by the standard deviation of 0.23, the second value corresponding to User A is -0.0943.

[0073] In another possible implementation, the information recommendation device limits the range of input parameters of the second recommendation model, that is, sets the maximum and minimum values ​​of the user portrait score. When the user portrait score of a certain user is greater than the maximum value, the second recommendation model is called to process the maximum value; when the user portrait score of a certain user is less than the minimum value, the second recommendation model is called to process the minimum value.

[0074] For example, the maximum value of the user portrait score is set to 0.975, and the minimum value of the user portrait score is set to 0.25. When the user portrait score of user A is 0.98, the second recommendation model is called to process the maximum value (ie, 0.975).

[0075] For another example, when User A is a new user and obtains a randomly obtained user portrait score of 0.01, that is, when the user portrait score of the user is less than the minimum value, the second recommendation model is called to process the minimum value (i.e., 0.25).

[0076] S104: When the user serial number is less than a first threshold, the sum of the first value and the second value is used as a target value of the target user.

[0077] Specifically, when the sum of the first value, the second value and the cumulative value of at least one user before the user serial number is greater than or equal to the first characteristic value, the difference between the cumulative value of at least one user before the user serial number and the first characteristic value is used as the target value of the target user; otherwise, the sum of the first value and the second value is used as the target value of the target user.

[0078] In a possible implementation, the first characteristic value is the profit margin set by the event merchant, that is, the sum of the target values ​​obtained by all users cannot exceed the first characteristic value.

[0079] For example, when the user number of the target user is 2 and the user number is less than the first threshold, the cumulative value obtained by the users with user numbers from 0 to 1 is 0.3417, and the sum of the first value and the second value corresponding to the user with user number 2 is 0.1623. Based on the cumulative value 0.3417 obtained by the users with user numbers from 0 to 1 and the first characteristic value 0.7, it can be obtained that the maximum value of the target value of the user with user number 2 can be 0.3583. Since 0.1623 is less than 0.3583, the sum of the first value and the second value 0.1623 is used as the target value of the target user.

[0080] For another example, when the user number of the target user is 5 and the user number is less than the first threshold, the cumulative value obtained by the users with user numbers from 0 to 4 is 0.6576, and the sum of the first value and the second value corresponding to the user with user number 5 is 0.0701. Based on the cumulative value 0.6576 obtained by the users with user numbers from 0 to 1 and the first characteristic value 0.7, it can be obtained that the maximum value of the target value of the user with user number 5 can be 0.0424. Since 0.0701 is greater than 0.0424, that is, the sum of the first value, the second value, and the cumulative value of at least one user before the user number is greater than or equal to the first characteristic value, the difference of 0.0424 between the cumulative value of at least one user before the user number and the first characteristic value is taken as the target value of the target user.

[0081] S105: Output the target value to the target user.

[0082] In a possible implementation manner, the information recommendation device processes the target value according to the activity information in which the target user participates, and outputs the processed result to the target user.

[0083] For example, the activity in which the target user participates is a bargaining activity, the original price of the bargained item is 100 yuan, and the target value obtained by the target user is 0.5, that is, a prompt message "You have successfully bargained for 50 yuan" is output to the target user.

[0084] Furthermore, the information recommendation device outputs different forms of prompt information to the user according to the size of the target value.

[0085] For example, when the target value exceeds 0.2, the information recommendation device outputs animation prompt information to the target user.

[0086] For another example, when the target value is greater than 0.1 and less than 0.2, the information recommendation device outputs an applause animation to the target user; when the target value exceeds 0.2, the information recommendation device outputs a fireworks animation to the target user.

[0087] In another possible implementation manner, the information recommendation device outputs the target value to the target user in the form of an activity animation.

[0088] For example, when the user is waiting for the result of the target value, the information recommendation device displays different values ​​in the form of a lottery wheel animation, and outputs a picture to the target user in which the pointer in the lottery wheel animation just points to the target value.

[0089] For another example, the information recommendation device displays the specific value of the target value to the target user in the form of a double-color ball lottery animation.

[0090] Furthermore, before outputting the target value to the target user, the information recommendation device outputs activity information to the target user.

[0091] For example, when the target user participates in an online game mall activity, the information recommendation device outputs virtual game item discount information to the target user.

[0092] For another example, when the target user participates in an online shopping mall activity, the information recommendation device outputs preferential information of the target user's favorite products to the target user. It should be understood that the above example is only for illustration and does not specifically limit the output method of the information recommendation device.

[0093] In the embodiment of the present application, the target value corresponding to the user is obtained based on the user's user serial number and user portrait score, which can improve the accuracy of the recommended information and thus improve the effect of network marketing operations.

[0094] See also Figure 4 , Figure 4 : is a flow chart of another information recommendation method provided in an embodiment of the present application, the method comprising:

[0095] S201. Obtain a user serial number of a target user, where the user serial number is an integer greater than or equal to 0.

[0096] The specific implementation of this step can be found in Figure 3 The step S101 of the above embodiment will not be described in detail here.

[0097] S202: Obtain a first numerical value corresponding to the user serial number.

[0098] The specific implementation of this step can be found in Figure 3The step S102 of the above embodiment will not be described in detail here.

[0099] S203: Obtain a user portrait score of the target user, and obtain a second value corresponding to the user portrait score.

[0100] The specific implementation of this step can be found in Figure 3 The step S103 of the above embodiment will not be described in detail here.

[0101] S204: When the user serial number is less than a first threshold, the sum of the first value and the second value is used as a target value of the target user.

[0102] The specific implementation of this step can be found in Figure 3 Step S104 of the above embodiment will not be described in detail here.

[0103] S205: When the user serial number is greater than or equal to the first threshold, determine whether the random number corresponding to the target user is 1.

[0104] In a possible implementation, the information recommendation device may provide a higher target value for a target user whose user serial number exceeds the first threshold.

[0105] For example, when the user serial number of user A is greater than the first threshold, user A has a 70% probability of obtaining a random number of 1 generated by the information recommendation device, and correspondingly, user A has a 30% probability of obtaining a random number of 0 generated by the information recommendation device.

[0106] Furthermore, the information recommendation device sets the probability of generating a random number to 1 according to the activities in which the target user participates.

[0107] For example, if the target user participates in a rare game item discount activity, the information recommendation device sets the probability of generating a random number of 1 to 10%.

[0108] For another example, if the target user participates in a promotion activity for daily necessities, the information recommendation device sets the probability of generating a random number of 1 to 80%.

[0109] In another possible implementation, the information recommendation device sets the probability of generating a random number to 1 according to the user portrait score of the user.

[0110] For example, if the user portrait score of user number 0 exceeds 0.6, the information recommendation device sets the probability of generating a random number of 1 to 60%, and the probability of all users whose user numbers are greater than or equal to the first threshold to obtain a random number of 1 is 60%.

[0111] For another example, when the user serial number is greater than or equal to the first threshold, the information recommendation device judges the user portrait scores of these users. If the user portrait score exceeds 0.7, the probability of generating a random number of 1 is set to 60%; otherwise, the probability of generating a random number of 1 is randomly assigned to the user in the range of 5% to 15%.

[0112] For another example, when the user serial number is greater than or equal to the first threshold, the information recommendation device obtains the probability of generating a random number of 1 corresponding to a certain user portrait score according to the corresponding relationship between the user portrait score and the probability.

[0113] S206: If it is confirmed that the random number corresponding to the target user is 1, the difference between the accumulated value of at least one user before the user number and the second characteristic value is used as the target value of the target user.

[0114] In a possible implementation, the information recommendation device confirms that a target user whose user number exceeds the first threshold is eligible to obtain a higher target value.

[0115] For example, the activity in which the target user participates is a bargaining activity. Since the target user is eligible to obtain a higher target value, the user can obtain a lower discount. For the target user, if the target user does not obtain the qualification, since the cumulative value of at least one user before the user's corresponding user number is 0.6576 and the first characteristic value is 0.7, the target value obtained by the user is 0.0424; after obtaining the qualification, since the cumulative value of at least one user before the user's corresponding user number is 0.6576 and the second characteristic value is 0.9, the target value obtained by the user is 0.2424.

[0116] For another example, the target user participates in a bargaining activity. Since the target user can get a lower discount, the target user can bargain to the lowest price at one time. For the user, if he does not obtain the qualification, since the sum of the first value and the second value corresponding to the user is 0.0771, the target value obtained by the user is 0.0771; after obtaining the qualification, since the cumulative value of at least one user before the user's corresponding user number is 0.5805 and the first characteristic value is 0.7, the target value obtained by the user is 0.1195.

[0117] In another possible implementation, the target user is not eligible for a higher target value, and the information recommendation device uses the sum of the first value and the second value of the target user as the target value of the target user.

[0118] Specifically, if it is confirmed that the random number corresponding to the target user is not 1, the step of taking the sum of the first value and the second value as the target value of the target user is performed.

[0119] S207: Output the target value to the target user.

[0120] The specific implementation of this step can be found in Figure 3 Step S105 of the above embodiment will not be described in detail here.

[0121] In the embodiment of the present application, based on the user's user serial number and user portrait score, each user is scored with distinction, thereby obtaining the target value corresponding to the user. The present application can improve the accuracy of recommended information and increase the fun of the recommended information process, thereby improving the effect of network marketing operations.

[0122] See also Figure 5 , Figure 5 is a structural diagram of an information recommendation device provided in an embodiment of the present application, such as Figure 5 The information recommendation device shown may include: an acquisition unit 301, a first acquisition unit 302, a recommendation unit 303 and an output unit 304; optionally, the information recommendation device further includes: a second acquisition unit 305; optionally, the information recommendation device further includes: a judgment unit 306.

[0123] An acquisition unit 301 is used to acquire a user serial number of a target user, where the user serial number is an integer greater than or equal to 0;

[0124] A first obtaining unit 302 is used to obtain a first value corresponding to the user serial number;

[0125] The first obtaining unit 302 is further used to obtain a user portrait score of the target user, and obtain a second value corresponding to the user portrait score;

[0126] A recommendation unit 303, configured to use the sum of the first value and the second value as a target value of the target user when the user sequence number is less than a first threshold;

[0127] The output unit 304 is used to output the target value to the target user.

[0128] In a possible implementation, the first obtaining unit 302 is specifically configured to call a first recommendation model to process the user serial number to obtain the first numerical value of the target user.

[0129] In another possible implementation, the first obtaining unit 302 is further configured to call a second recommendation model to process the user portrait score to obtain a second numerical value corresponding to the user portrait score.

[0130] In another possible implementation, the user portrait score is a rational number greater than or equal to 0 and less than or equal to 1; the first obtaining unit 302 is further specifically used to obtain the first percentile corresponding to the user portrait score when the user portrait score is proportional to the target value; and call the second recommendation model to process the first percentile to obtain a second value.

[0131] In another possible implementation, the user portrait score is a rational number greater than or equal to 0 and less than or equal to 1; the first obtaining unit 302 is further specifically used to obtain, when the user portrait score is inversely proportional to the target value, a second percentile corresponding to the difference between the user portrait score and 1; and the second recommendation model is called to process the second percentile to obtain a second value.

[0132] In another possible implementation, the device further includes: a second obtaining unit 305, used to obtain a first recommendation model, wherein the first recommendation model is constructed by control parameters, wherein the control parameters include the first threshold, the second threshold, the first characteristic value, the second characteristic value and trend information; the first threshold is used to indicate the minimum number of participants; the second threshold is used to indicate the maximum number of participants; the trend information is used to determine whether the slope of the straight line of the first recommendation model is a positive number or a negative number; the first threshold, the second threshold and the first characteristic value are used to determine the straight line intercept of the first recommendation model.

[0133] In another possible implementation, the recommendation unit 303 is specifically used to, when the sum of the first value, the second value and the cumulative value of at least one user before the user number is greater than or equal to the first characteristic value, use the difference between the cumulative value of at least one user before the user number and the first characteristic value as the target value of the target user; otherwise, use the sum of the first value and the second value as the target value of the target user.

[0134] In yet another possible implementation, the apparatus further includes:

[0135] A judging unit 306, configured to judge whether the random number corresponding to the target user is 1 when the user serial number is greater than or equal to the first threshold;

[0136] The recommendation unit 303 is further configured to, if it is confirmed that the random number corresponding to the target user is 1, use the difference between the cumulative value of at least one user before the user number and the second characteristic value as the target value of the target user;

[0137] The recommendation unit 303 is further specifically configured to, otherwise, execute the step of taking the sum of the first value and the second value as the target value of the target user.

[0138] For a more detailed description of the acquisition unit 301, the first acquisition unit 302, the recommendation unit 303, the output unit 304, the second acquisition unit 305 and the judgment unit 306, please refer to the above Figure 3 and Figure 4 The relevant description of the information recommendation method in the method embodiment is directly obtained and will not be repeated here.

[0139] According to an information recommendation device provided by an embodiment of the present application, based on the user's user serial number and user portrait score, each user is scored with a degree of differentiation, thereby obtaining the target value corresponding to the user. The present application can improve the accuracy of recommended information, increase the fun of the process of recommending information, and thus improve the effect of network marketing operations.

[0140] See also Figure 6 , Figure 6 is a schematic diagram of a physical device structure of an information recommendation device provided in an embodiment of the present application. Figure 6 The information recommendation device in the embodiment shown may include: a processor 401, an input device 402, an output device 403 and a memory 404. The processor 401, the input device 402, the output device 403 and the memory 404 may be interconnected via a bus.

[0141] The memory includes, but is not limited to, a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, and may also be an electrically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory can be independent and connected to the processor through a bus. The memory can also be integrated with the processor.

[0142] The processor may also be referred to as a processing component, a processing unit, a processing board, a processing module, a processing device, etc. The processor may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and an NP. The processor may include one or more processors, for example, one or more central processing units. When the processor is a CPU, the CPU may be a single-core CPU or a multi-core CPU.

[0143] The memory is used to store program codes and data of the network device.

[0144] The input device is used to input data and / or signals, and the output device is used to output data and / or signals. The output device and the input device can be independent devices or an integrated device.

[0145] The processor is used to call the program code and data in the memory and execute the following steps: obtain the user serial number of the target user, the user serial number is an integer greater than or equal to 0; obtain a first numerical value corresponding to the user serial number; obtain a user portrait score of the target user, and obtain a second numerical value corresponding to the user portrait score; when the user serial number is less than a first threshold, use the sum of the first numerical value and the second numerical value as the target numerical value of the target user; and control the output device to output the target numerical value to the target user.

[0146] In a possible implementation, the processor executes the step of obtaining the first numerical value corresponding to the user serial number, including: calling a first recommendation model to process the user serial number to obtain the first numerical value of the target user.

[0147] In another possible implementation, the processor executes the step of obtaining the second value corresponding to the user portrait score, including: calling a second recommendation model to process the user portrait score to obtain the second value corresponding to the user portrait score.

[0148] In another possible implementation, the user portrait score is a rational number greater than or equal to 0 and less than or equal to 1; the processor executes the step of calling the second recommendation model to process the user portrait score to obtain the second numerical value corresponding to the user portrait score, including: when the user portrait score is proportional to the target numerical value, obtaining the first percentile corresponding to the user portrait score; calling the second recommendation model to process the first percentile to obtain the second numerical value.

[0149] In another possible implementation, the user portrait score is a rational number greater than or equal to 0 and less than or equal to 1; the processor executes the step of calling the second recommendation model to process the user portrait score to obtain the second numerical value corresponding to the user portrait score, including: when the user portrait score is inversely proportional to the target numerical value, obtaining the second percentile corresponding to the difference between the user portrait score and 1; calling the second recommendation model to process the second percentile to obtain the second numerical value.

[0150] In another possible implementation, before executing the step of calling the first recommendation model to process the user serial number, the processor is also used to execute the following steps: obtaining a first recommendation model, the first recommendation model is constructed by control parameters, the control parameters include the first threshold, the second threshold, the first characteristic value, the second characteristic value and trend information; the first threshold is used to represent the minimum number of participants; the second threshold is used to represent the maximum number of participants; the trend information is used to determine whether the slope of the straight line of the first recommendation model is a positive number, or a negative number; the first threshold, the second threshold and the first characteristic value are used to determine the straight line intercept of the first recommendation model.

[0151] In another possible implementation, the processor executes the step of using the sum of the first value and the second value as the target value of the target user, including: when the sum of the first value, the second value and the cumulative value of at least one user before the user serial number is greater than or equal to the first characteristic value, using the difference between the cumulative value of at least one user before the user serial number and the first characteristic value as the target value of the target user; otherwise, using the sum of the first value and the second value as the target value of the target user.

[0152] In another possible implementation, the processor is further used to perform the following steps, including: when the user serial number is greater than or equal to the first threshold, determining whether the random number corresponding to the target user is 1; if it is confirmed that the random number corresponding to the target user is 1, taking the difference between the cumulative value of at least one user before the user serial number and the second characteristic value as the target value of the target user; otherwise, executing the step of taking the sum of the first value and the second value as the target value of the target user.

[0153] Understandably, Figure 6 Only a simplified design of the information recommendation device is shown. In practical applications, the information recommendation device may also include other necessary components, including but not limited to any number of network interfaces, input devices, output devices, processors, memories, etc., and all computing platforms that can implement the embodiments of the present application are within the protection scope of the present application.

[0154] In the present application, the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0155] In addition, the functional components in the various embodiments of the present application may be integrated into one component, or each component may exist physically separately, or two or more components may be integrated into one component. The above integrated components may be implemented in the form of hardware or in the form of software functional units.

[0156] If the integrated components are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or partly contributed to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., and other media that can store program codes.

[0157] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

[0158] It should be understood that in various embodiments of the present application, the size of the sequence number of each process does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. Although the present application is described herein in conjunction with various embodiments, however, in the process of the present application claimed for protection by the embodiments, those skilled in the art can understand and implement other changes of the disclosed embodiments.

Claims

1. An information recommendation method, characterized in that: include: Acquire a user serial number of a target user from an electronic device, where the user serial number is an integer greater than or equal to 0, and the user serial number is determined by the time when the target user clicks the link, wherein the user with the user serial number 0 creates the link; Obtaining a first value corresponding to the user serial number, comprising: obtaining a first recommendation model, the first recommendation model being constructed by control parameters, the control parameters comprising a first threshold, a second threshold, a first characteristic value, a second characteristic value, and trend information, the first threshold being used to represent a minimum number of participants, the second threshold being used to represent a maximum number of participants, the trend information being used to determine whether a straight line slope of the first recommendation model is a positive number or a negative number, the first threshold, the second threshold, and the first characteristic value being used to determine a straight line intercept of the first recommendation model, wherein it is determined that a first value obtained by a user with a user serial number of M+1 is 0, the sum of first values ​​obtained by users with user serial numbers from 0 to M is the first characteristic value, and M is a positive integer; Acquire a user portrait score of the target user from the electronic device, and obtain a second value corresponding to the user portrait score, wherein the user portrait score is a rational number greater than or equal to 0 and less than or equal to 1, and when the user portrait score is proportional to the target value of the target user, obtain the percentile corresponding to the user portrait score from a standard normal distribution table; when the user portrait score is inversely proportional to the target value, obtain the percentile corresponding to the difference between 1 and the user portrait score from the standard normal distribution table; and multiply the obtained percentile by the standard deviation of the standard normal distribution table to obtain the second value; When the user serial number is less than the first threshold, if the sum of the first value, the second value and the cumulative value of at least one user before the user serial number is greater than or equal to the first characteristic value, the difference between the cumulative value of at least one user before the user serial number and the first characteristic value is used as the target value; otherwise, the sum of the first value and the second value is used as the target value; According to the user portrait score of user number 0, the probability of all users whose user numbers are greater than or equal to the first threshold to obtain a random number of 1 is set; when the user number is greater than or equal to the first threshold and the random number corresponding to the target user is 1, the difference between the accumulated value of at least one user before the user number and the second feature value is used as the target value; and, The target value is output to the electronic device, so that the electronic device outputs prompt information to the target user according to the target value.

2. An information recommendation device, characterized in that: include: an acquisition unit, configured to acquire a user serial number of a target user from an electronic device, wherein the user serial number is an integer greater than or equal to 0, and the user serial number is determined by the time when the target user clicks a link, wherein the user with the user serial number 0 creates the link; a second obtaining unit, configured to obtain a first recommendation model, wherein the first recommendation model is constructed by control parameters, wherein the control parameters include a first threshold, a second threshold, a first characteristic value, a second characteristic value, and trend information, wherein the first threshold is used to indicate a minimum number of participants, and the second threshold is used to indicate a maximum number of participants, and the trend information is used to determine whether the slope of a straight line of the first recommendation model is a positive number or a negative number, and the first threshold, the second threshold, and the first characteristic value are used to determine a straight line intercept of the first recommendation model, wherein a first value obtained by a user with a user number of M+1 is determined to be 0, and a sum of first values ​​obtained by users with user numbers from 0 to M is the first characteristic value, and M is a positive integer; A first obtaining unit is used to call the first recommendation model to obtain a first value corresponding to the user serial number; obtain a user portrait score of the target user from the electronic device to obtain a second value corresponding to the user portrait score, wherein the user portrait score is a rational number greater than or equal to 0 and less than or equal to 1, and when the user portrait score is proportional to the target value of the target user, the percentile corresponding to the user portrait score is obtained from a standard normal distribution table; when the user portrait score is inversely proportional to the target value, the percentile corresponding to the difference between 1 and the user portrait score is obtained from the standard normal distribution table; the second value is obtained by multiplying the obtained percentile by the standard deviation of the standard normal distribution table; A recommendation unit, for, when the user number is less than the first threshold, if the sum of the first value, the second value and the cumulative value of at least one user before the user number is greater than or equal to the first characteristic value, taking the difference between the cumulative value of at least one user before the user number and the first characteristic value as the target value; otherwise, taking the sum of the first value and the second value as the target value; setting the probability that all users whose user numbers are greater than or equal to the first threshold obtain a random number of 1 according to the user portrait score of the user number 0; when the user number is greater than or equal to the first threshold and the random number corresponding to the target user is 1, taking the difference between the cumulative value of at least one user before the user number and the second characteristic value as the target value; and, The output unit is used to output the target value to the electronic device, so that the electronic device outputs prompt information to the target user according to the target value.

3. An information recommendation device, characterized in that: include: A processor, an input device, an output device and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method according to claim 1.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to claim 1 is implemented.

Images