Method and apparatus for determining message push time, computer device, and storage medium

Abstract

The application discloses a message pushing time determination method and device, computer equipment and a storage medium, and relates to the field of data processing.The method comprises the following steps: acquiring the number of times that a plurality of users use each channel in each time period and the user information of each user; determining the first time period use probability of each channel in each time period based on the number of times; classifying the plurality of users based on the user information of each user; calculating the second time period use probability of the users of each user category based on the number of times that the users of the user category use each channel in each time period; updating the first time period use probability based on the second time period use probability to obtain the third time period use probability of the users of each user category using each channel in each time period; and determining the message pushing time period based on the third time period use probability.Based on this, the message pushing time of users of different user categories is consistent with the use preferences of the users, and the message pushing service has strong pertinence.

Description

Technical Field

[0001] This invention relates to the field of data processing, and in particular to a method, apparatus, computer device, and storage medium for determining message push time. Background Technology

[0002] In the process of pushing messages, how to let users know or perceive the right content at the right time and through the right channel is one of the main research directions at present. Although it is possible to determine users' usage habits based on big data analysis, there are always certain differences between different users, and analysis based on a single user requires a very high cost, so it is not feasible.

[0003] Therefore, how to provide users with targeted message push services is one of the problems that needs to be solved at this stage. Summary of the Invention

[0004] In view of this, the present invention provides a method, apparatus, computer equipment, and storage medium for determining message push time that can be applied to the fields of fintech and other technologies, in order to solve the problem of how to provide targeted message push services to users.

[0005] In a first aspect, embodiments of the present invention provide a method for determining message push time, comprising:

[0006] The system obtains the number of times multiple users use different communication channels at different times, as well as the user information of each user, wherein the communication channel refers to the platform on which the user receives push notifications;

[0007] Based on the number of uses, determine the probability of use of each of the communication channels in the first time period of each of the time periods;

[0008] Based on the user information of each user, the multiple users are divided into multiple user categories;

[0009] For each user category, based on the number of times users of that user category use different communication channels in different time periods, calculate the second time period usage probability of users of that user category using different communication channels in different time periods;

[0010] Based on the second time period usage probability of users of each user category, the first time period usage probability of each of the communication channels is updated to obtain the third time period usage probability of users of each user category using different communication channels in each of the time periods;

[0011] Based on the usage probability of the third time period, the message push time periods for each of the communication channels for users of different user categories are determined.

[0012] Optionally, in one feasible embodiment of the present invention, updating the first time-period usage probability of each communication channel based on the second time-period usage probability of users of each user category to obtain the third time-period usage probability of users of each user category using different communication channels in each time period includes:

[0013] Based on the second time period usage probability of users in each user category and the Dirichlet conjugate function, the first time period usage probability of each of the communication channels is updated to obtain the third time period usage probability of users in each user category using different communication channels in each of the time periods.

[0014] Optionally, in one feasible embodiment of the present invention, the method further includes:

[0015] Based on the usage probability of the first time period, the message push time for each of the communication channels for new users is determined.

[0016] Optionally, in one feasible embodiment of the present invention, the sum of the probabilities of use of each communication channel in the first time period, the sum of the probabilities of use in the second time period, and the sum of the probabilities of use in the third time period are all 1 in the same time period.

[0017] Optionally, in one feasible embodiment of the present invention, the communication channel includes at least two of the following: WeChat, SMS, WeChat Work, lobby self-service robot, remote service, and human customer service.

[0018] Secondly, embodiments of the present invention provide a device for setting message push time, comprising:

[0019] The acquisition module is used to acquire the number of times multiple users use different communication channels at different time periods, as well as the user information of each user, wherein the communication channel refers to the platform on which the user receives message push;

[0020] A determining module is configured to determine the probability of use of each of the communication channels in the first time period of each of the time periods based on the number of times of use;

[0021] The segmentation module is used to divide the multiple users into multiple user categories based on the user information of each user;

[0022] The calculation module is used to calculate, for each user category, the probability of a user category using different communication channels in a second time period based on the number of times the user of that user category uses different communication channels in different time periods.

[0023] The update module is used to update the first time period usage probability of each of the communication channels based on the second time period usage probability of users of each user category, so as to obtain the third time period usage probability of users of each user category using different communication channels in each of the time periods;

[0024] The push confirmation module is used to determine the message push period for each of the communication channels for users of different user categories based on the usage probability of the third time period.

[0025] Optionally, in one feasible embodiment of the present invention, the updating module is further configured to update the first time period usage probability of each communication channel based on the second time period usage probability of users of each user category and the Dirichlet conjugate function, so as to obtain the third time period usage probability of users of each user category using different communication channels in each time period.

[0026] Optionally, in one feasible embodiment of the present invention, the apparatus further includes:

[0027] The settings module is used to determine the message push time for each of the communication channels for new users based on the usage probability of the first time period.

[0028] Thirdly, embodiments of the present invention provide a computer device, including a memory and a processor. The memory stores a computer program, and the computer program, when run on the processor, executes a message push time determination method as disclosed in any of the first aspects.

[0029] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when run on a processor, executes a method for determining message push time as disclosed in any of the first aspects.

[0030] The method for determining message push time provided in this invention first obtains the usage frequency of multiple users using different communication channels at different time periods, as well as the user information of each user. Next, based on the usage frequency, the first-period usage probability of each communication channel in each time period is determined, which represents the usage preferences of all users. Then, based on the user information of each user, the multiple users are divided into multiple user categories. Subsequently, for each user category, based on the usage frequency of users of that user category using different communication channels at different time periods, the second-period usage probability of users of that user category using different communication channels in different time periods is calculated, which represents the usage preferences of users of different user categories. Following this, based on the second-period usage probability of users of each user category, the first-period usage probability of each communication channel is updated to obtain a third-period usage probability of users of each user category using different communication channels in each time period, so that the first-period usage probability approaches the second-period usage probability. Finally, based on the third-period usage probability, the message push time period for each communication channel for users of different user categories is determined. Based on this, this invention ensures that the message push time and message push channel for users of different user categories match their usage preferences, thereby effectively pushing messages to users and making the message push service highly targeted. Attached Figure Description

[0031] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope of protection of the present invention. In the various drawings, similar components are numbered similarly.

[0032] Figure 1 A flowchart illustrating the first method for determining message push time provided by an embodiment of the present invention is shown;

[0033] Figure 2 A flowchart illustrating the second method for determining message push time provided in an embodiment of the present invention is shown.

[0034] Figure 3 A flowchart illustrating the third method for determining message push time provided in an embodiment of the present invention is shown.

[0035] Figure 4 A schematic diagram of the structure of the message push time determination device provided in an embodiment of the present invention is shown. Detailed Implementation

[0036] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0037] The components of the embodiments of the invention described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0038] In the following, the terms “comprising,” “having,” and their cognates, which may be used in various embodiments of the invention, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as excluding, firstly, the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations thereof.

[0039] Furthermore, the terms "first," "second," and "third" are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0040] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of the invention pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be interpreted as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of the invention.

[0041] Example 1

[0042] Reference Figure 1 The diagram illustrates a flowchart of a first method for determining message push time provided by an embodiment of the present invention. The method for determining message push time provided by an embodiment of the present invention includes:

[0043] Step S110: Obtain the number of times multiple users use different communication channels at different times, and the user information of each user, wherein the communication channel refers to the platform on which the user receives message push.

[0044] In other words, this embodiment of the invention will collect real-time data on how each user actively receives message push notifications across various communication channels. For example, a user's message reception within a day might be as follows: checking messages via WeChat from 8:00 to 9:00, checking messages via WeChat Work from 9:00 to 10:00, and checking messages via the self-service robot in the bank lobby from 12:00 to 13:00.

[0045] It is understandable that, because this embodiment of the invention needs to determine the user's usage time preference for each communication channel by recording the user's message acquisition through various communication channels, and thus determine the message push time, this embodiment of the invention will collect the usage frequency of all users using different communication channels at different time periods. It should be noted that "all users" and "multiple users" in this embodiment of the invention refer to the service customer group corresponding to the enterprise. For example, when the enterprise is a bank, "all users" and "multiple users" can be understood as all users who have opened an account / card.

[0046] Furthermore, in this embodiment of the invention, the number of uses refers to the total number of times all users / multiple users use different communication channels at different times. For example, suppose there are 50 users in total, and there are two types of communication channels: Channel A and Channel B. If 30 users send and receive messages through Channel A during a certain time period, and the other 20 users send and receive messages through Channel B during the same time period, then the number of uses for Channel A during this time period is 30, and the number of uses for Channel B during this time period is 20.

[0047] It is also understood that the communication channel in the embodiments of the present invention refers to the platform on behalf of the user to obtain message push. In one optional method provided in the embodiments of the present invention, the communication channel includes at least two of WeChat, SMS, WeChat Work, lobby self-service robot, remote service, and human customer service.

[0048] In another feasible approach, communication channels, in addition to the aforementioned WeChat, SMS, WeChat Work, lobby self-service robots, remote services, and human customer service, also include Apps, AI outbound calls, lobby services, and AiKe (a customer service platform).

[0049] It should also be noted that the user information in the embodiments of the present invention refers to the user's personal information, including but not limited to information such as age, occupation and place of residence.

[0050] Furthermore, it is understood that the embodiments of the present invention do not limit the specific method of obtaining the number of times multiple users use different communication channels at different times. The method of obtaining the above-mentioned number of times of use is set according to the actual situation. For example, in one feasible way, the embodiments of the present invention have performed data tracking on each channel, so that when a user actively obtains a message through a channel, the number of times of use corresponding to the channel will be automatically recorded / updated.

[0051] In addition, it should be noted that the time period in the embodiments of the present invention can be set according to the actual situation. For example, in one instance, the time period in the embodiments of the present invention is 60 seconds, and the period targeted is the entire 24 hours of the day. Thus, the embodiments of the present invention will collect the user's usage of various communication channels every minute of the day to obtain the number of times it is used.

[0052] Step S120: Based on the number of uses, determine the probability of use of each of the communication channels in the first time period of each of the time periods.

[0053] In other words, the embodiments of the present invention will determine the probability of all users / multiple users using a certain communication channel in any given time period based on the number of times the users use different communication channels in different time periods, that is, the probability of using the communication channel in the first time period of each time period.

[0054] It's important to understand that since all users should use a single communication channel to receive push notifications at the same time, if all users use a particular channel during the same time period, then the probability of using that channel in the first time period at that time is 1 or 100%, while the probability of using other communication channels in the first time period at that time is 0 or 0%. It's easy to understand that, at the same time, the sum of the probabilities of using all communication channels in the first time period is 1 or 100%.

[0055] It should also be understood that the first time period usage probability in this embodiment of the invention represents the probability that all users will use any one of the communication channels at the same time. For example, assuming all users are 50, and there are two communication channels, Channel A and Channel B, if 30 users send and receive messages through Channel A during a given time period, and the other 20 users send and receive messages through Channel B during the same time period, then the usage frequency of Channel A during this time period is 30, and the usage frequency of Channel B during this time period is 20. Therefore, the first time period usage probability of Channel A is 0.6% or 60%, and the first time period usage probability of Channel B is 0.4% or 40%.

[0056] Step S130: Based on the user information of each user, the multiple users are divided into multiple user categories.

[0057] That is, in this embodiment of the invention, based on the user information of each user, all users are clustered to divide all users into multiple user categories. Exemplarily, in one feasible embodiment of the invention, the aforementioned multiple user categories include categories for those who have not completed their studies, those who have worked for less than 3 years, those who are retired, those who are not yet married, and those who have children.

[0058] It is understood that the above user categories are merely illustrative examples, and the user categories in this embodiment of the invention are content that can be set according to actual circumstances.

[0059] Meanwhile, the process of determining the user category based on the user's information is also something that can be set according to the actual situation. Existing technologies can be directly referenced, and this embodiment of the invention does not impose any limitations on it.

[0060] Step S140: For each user category, based on the number of times users of the user category use different communication channels in different time periods, calculate the second time period usage probability of users of the user category using different communication channels in different time periods.

[0061] That is, for each category of users, the embodiments of the present invention will calculate the probability that users of this category will use different communication channels at different times based on the number of times users of a category use different communication channels at different times.

[0062] It is important to understand that the usage probability in the first time period indicates the usage time preference of all users, that is, at a certain moment, what is the probability that any one user among all users will choose a certain communication channel to receive message pushes.

[0063] However, it is important to understand that the first probability of use is based on statistics. In real life, human behavior is uncertain and difficult to reproduce. Furthermore, due to the limitations of data collection, the number of times users use the data at different times and through different communication channels is not comprehensive. Also, because the validity of the data and storage costs need to be considered when storing the data, the collected data is usually not permanently stored.

[0064] Based on the above, while big data analytics can analyze all users or a portion of user groups, it is difficult to predict / set usage preferences for specific users.

[0065] Based on this, the embodiments of the present invention will determine the user's usage preferences based on Bayesian inference. That is, based on the observed / recorded user data of each category, i.e. the number of times each category of users uses different communication channels at different times, the usage preferences / probabilities of each category of user data in each communication channel at each time period are determined, and then the actual usage preferences are predicted using this usage probability.

[0066] To better illustrate the second probability of use in the embodiments of the present invention, please refer to the following example:

[0067] Suppose there are two communication channels, Channel A and Channel B, with a total of 30 users. All users are divided into two categories: Category 1 (10 users) and Category 2 (20 users). Among these 30 users, 10 users use Channel A to receive push notifications during a given time period; of these 10 users, 4 are in Category 1 and 6 are in Category 2. The remaining 20 users use Channel B to receive push notifications during the same time period; of these 20 users, 6 are in Category 1 and 14 are in Category 2. Therefore, the probability of using Channel A during the first time period at this moment is 10 / 30, and the probability of using Channel B during the first time period at this moment is 20 / 30. Furthermore, the probability of users in Category 1 using Channel A during the second time period at this moment is 4 / 10, and the probability of using Channel B during the second time period at this moment is 6 / 10. And the probability of users in Category 2 using Channel A during the second time period at this moment is 6 / 20, and the probability of using Channel B during the second time period at this moment is 14 / 20.

[0068] Step S150: Based on the second time period usage probability of users of each user category, update the first time period usage probability of each of the communication channels to obtain the third time period usage probability of users of each user category using different communication channels in each of the time periods.

[0069] In other words, this embodiment of the invention will use Bayesian inference to update the first-period usage probability of users of each user category in different communication channels at different times, based on the second-period usage probability of users in each user category in different communication channels at different times, thereby obtaining the third-period usage probability. For example, if the first-period usage probability of channel A at a certain moment is 10 / 30, and the second-period usage probability of users of the first category using channel A at this moment is 4 / 10, this embodiment of the invention will use 4 / 10 to update 10 / 30, so that 10 / 30 is close to 4 / 10 but not identical to 4 / 10.

[0070] It should be understood that due to the difficulty and incompleteness of data collection and the limitations of data storage, the usage probability of the second time period in the embodiments of the present invention cannot fully represent the user's usage preferences, but only represents the relatively effective usage preferences / probabilities. Therefore, the embodiments of the present invention only make the usage probability of the first time period approach the usage probability of the second time period.

[0071] It should also be understood that the method for updating the usage probability of the first period using the usage probability of the second period is something that can be set according to the actual situation. An exemplary feasible method provided in this embodiment of the invention can be found in [reference needed]. Figure 2The diagram illustrates a second method for determining message push time according to an embodiment of the present invention. In this feasible mode, step S150 specifically includes:

[0072] Step S141: Based on the second time period usage probability of users of each user category and the Dirichlet conjugate function, update the first time period usage probability of each of the communication channels to obtain the third time period usage probability of users of each user category using different communication channels in each of the time periods.

[0073] In other words, this embodiment of the invention will utilize the Dirichlet function to update the usage probability for the first time period. It should be understood that the specific process of updating based on the Dirichlet function is customizable according to actual circumstances, and this embodiment of the invention will not provide a detailed explanation of it.

[0074] Step S160: Based on the usage probability of the third time period, determine the message push time period for each of the communication channels for users of different user categories.

[0075] In other words, since the updated third-period usage probability is close to the second-period usage probability obtained based on user observation data, the third-period usage probability of each user type can be close to the second-period usage probability based on the overall usage preference (i.e., the first-period usage probability). Thus, the third-period usage probability of each type of user using each communication channel at different times can be determined with high accuracy, i.e., user preference.

[0076] Therefore, based on the usage probability of the third time period, the embodiments of the present invention set the message push time periods for different user categories for each communication channel, and adjust the priority of message push for each communication channel in different time periods based on its usage probability of the third time period.

[0077] As an example, suppose that in the first user category, the probability of using channel A in the third time period is 75% and the probability of using channel B in the third time period is 25%, then the message push of channel A has a higher priority than that of channel B; while in the second user category, the probability of using channel A in the third time period is 15% and the probability of using channel B in the third time period is 85%, then the message push of channel B has a higher priority than that of channel A.

[0078] Based on this, the embodiments of the present invention enable the message push time for users of different user categories to match their usage preferences, thereby effectively pushing messages to users and making the message push service more targeted.

[0079] Optionally, in one feasible embodiment of the present invention, please refer to the following: Figure 3The diagram illustrates a third method for determining message push time according to an embodiment of the present invention. In this feasible mode, the method further includes:

[0080] Step S170: Based on the usage probability of the first time period, determine the message push time for each of the communication channels for new users.

[0081] It should be understood that, in the embodiments of the present invention, a new user refers to a user whose user information is non-existent or incomplete, and who has no usage record in any communication channel.

[0082] In this feasible approach, the embodiments of the present invention, for new users with no records or relevant information, will utilize the usage preferences of all users, i.e., the usage probability in the first time period, to set the message push time for each communication channel corresponding to this new user. This ensures that the message push for the new user can be pushed in a way that conforms to big data analysis, thereby having a certain degree of effectiveness and thus guaranteeing the user experience.

[0083] Optionally, in one feasible embodiment of the present invention, the sum of the probabilities of use of each communication channel in the first time period, the sum of the probabilities of use in the second time period, and the sum of the probabilities of use in the third time period are all 1 in the same time period.

[0084] Therefore, the usage probabilities of the first, second, and third time periods for each communication channel are cumulative, which allows for the determination of the probability values ​​of all communication channels in the corresponding time periods based on the needs of each level of business, thus enabling flexible message push settings.

[0085] Example 2

[0086] Corresponding to the message push time determination method provided in Embodiment 1 of the present invention, Embodiment 2 of the present invention also provides a message push time determination device, referring to... Figure 4 The diagram shows a schematic of the structure of a message push time determination device provided in an embodiment of the present invention. The message push time determination device 200 provided in an embodiment of the present invention includes:

[0087] The acquisition module 210 is used to acquire the number of times multiple users use different communication channels at different time periods, as well as the user information of each user, wherein the communication channel refers to the platform on which the user receives message push;

[0088] The determining module 220 is used to determine the probability of use of each of the communication channels in the first time period of each of the time periods based on the number of times of use;

[0089] The segmentation module 230 is used to segment the multiple users into multiple user categories based on the user information of each user;

[0090] Calculation module 240 is used to calculate, for each user category, the probability of a user category using different communication channels in a second time period based on the number of times the user of the user category uses different communication channels in different time periods.

[0091] The update module 250 is used to update the first time period usage probability of each of the communication channels based on the second time period usage probability of users of each user category, so as to obtain the third time period usage probability of users of each user category using different communication channels in each of the time periods;

[0092] The push determination module 260 is used to determine the message push period for each of the communication channels for users of different user categories based on the usage probability of the third time period.

[0093] Optionally, in one feasible embodiment of the present invention, the updating module is further configured to update the first time period usage probability of each communication channel based on the second time period usage probability of users of each user category and the Dirichlet conjugate function, so as to obtain the third time period usage probability of users of each user category using different communication channels in each time period.

[0094] Optionally, in one feasible embodiment of the present invention, the apparatus further includes:

[0095] The settings module is used to determine the message push time for each of the communication channels for new users based on the usage probability of the first time period.

[0096] Optionally, in one feasible embodiment of the present invention, the sum of the probabilities of use of each communication channel in the first time period, the sum of the probabilities of use in the second time period, and the sum of the probabilities of use in the third time period are all 1 in the same time period.

[0097] Optionally, in one feasible embodiment of the present invention, the communication channel includes at least two of the following: WeChat, SMS, WeChat Work, lobby self-service robot, remote service, and human customer service.

[0098] The message push time determination device 200 provided in this application embodiment can implement each process of the message push time determination method corresponding to Embodiment 1, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0099] This invention also provides a computer device, including a memory and a processor. The memory stores a computer program, and the computer program executes a message push time determination method as described in Embodiment 1 when it runs on the processor.

[0100] This invention also provides a computer-readable storage medium storing a computer program, which, when run on a processor, executes a method for determining the message push time as described in Embodiment 1.

[0101] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that, as an alternative implementation, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0102] In addition, the functional modules or units in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0103] If the aforementioned functions are implemented as software functional modules 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 this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0104] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for determining message push time, characterized in that, include: The system obtains the number of times multiple users use different communication channels at different times, as well as user information for each user. The communication channel refers to the platform through which the user receives push notifications; the number of times of use refers to the total number of times all users use different communication channels at different times. Based on the number of uses, determine the probability of use of each of the communication channels in the first time period of each of the time periods; Based on the user information of each user, the multiple users are divided into multiple user categories; For each user category, based on the number of times users of that user category use different communication channels in different time periods, calculate the second time period usage probability of users of that user category using different communication channels in different time periods; Based on the second time period usage probability of users of each user category, the first time period usage probability of each of the communication channels is updated to obtain the third time period usage probability of users of each user category using different communication channels in each of the time periods; Based on the usage probability of the third time period, the message push time periods for each of the communication channels for users of different user categories are determined; The method of updating the first-time-period usage probability of each communication channel based on the second-time-period usage probability of users of each user category in each of the said time periods to obtain the third-time-period usage probability of users of each user category using different communication channels in each of the said time periods includes: Based on the second time period usage probability of users in each user category and the Dirichlet conjugate function, the first time period usage probability of each of the communication channels is updated to obtain the third time period usage probability of users in each user category using different communication channels in each of the time periods.

2. The method for determining message push time according to claim 1, characterized in that, The method further includes: Based on the usage probability of the first time period, the message push time for each of the communication channels for new users is determined.

3. The method for determining message push time according to claim 1, characterized in that, The sum of the probabilities of use for each of the aforementioned communication channels in the first, second, and third time periods during the same time period is 1.

4. The method for determining message push time according to claim 1, characterized in that, The communication channels include at least two of the following: WeChat, SMS, WeChat Work, lobby self-service robot, remote service, and human customer service.

5. A device for determining message push time, characterized in that, include: The acquisition module is used to acquire the number of times multiple users use different communication channels at different time periods, as well as the user information of each user. The communication channel refers to the platform on which the user receives message pushes; the number of times of use refers to the total number of times all users use different communication channels at different time periods. A determining module is configured to determine the probability of use of each of the communication channels in the first time period of each of the time periods based on the number of times of use; The segmentation module is used to divide the multiple users into multiple user categories based on the user information of each user; The calculation module is used to calculate, for each user category, the probability of a user category using different communication channels in a second time period based on the number of times the user of that user category uses different communication channels in different time periods. The update module is used to update the first time period usage probability of each of the communication channels based on the second time period usage probability of users of each user category, so as to obtain the third time period usage probability of users of each user category using different communication channels in each of the time periods; The push confirmation module is used to determine the message push period for each of the communication channels for users of different user categories based on the usage probability of the third time period. The update module is further configured to update the first time period usage probability of each communication channel based on the second time period usage probability of users of each user category and the Dirichlet conjugate function, so as to obtain the third time period usage probability of users of each user category using different communication channels in each time period.

6. The device for determining message push time according to claim 5, characterized in that, The device further includes: The settings module is used to determine the message push time for each of the communication channels for new users based on the usage probability of the first time period.

7. A computer device, characterized in that, It includes a memory and a processor, the memory storing a computer program, which, when executed on the processor, performs the message push time setting method as described in any one of claims 1-4.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed on a processor, performs the message push time setting method as described in any one of claims 1-4.

Images