Message push method, device, equipment, readable storage medium and program product
By determining the message weight based on the message type and user data on a smartphone and pushing it at the right time, the problem of system pushing messages interfering with user operations is solved, and the user experience and resource utilization efficiency is improved.
Patent Information
- Application Number
- CN202211193560.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-09-28
- Publication Date
- 2024-12-17
- Estimated Expiration
- 2042-09-28
AI Technical Summary
System push messages received by smartphone users during use may be displayed during critical interactions, resulting in interference and degradation of user experience, and the prior art has failed to effectively control the timing of message push.
By storing messages to be pushed to the cache queue, the message weight is determined based on the message type and user-related data (such as user behavior data, configuration data and link data), and the message with the highest weight is pushed when a specific opportunity is met, using pre-trained messages Weight determination model for sorting and pushing.
It avoids the interference of message push to users, improves operation convenience and user experience, ensures the appropriate timing of message push, and reduces server resource consumption and data transmission.
Smart Images
Figure CN115604351B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the technical field of push message processing, and in particular to a message push method, device, equipment, readable storage medium and program product. Background Art
[0002] With the progress of society and the development of science and technology, the use of smart phones is becoming more and more common. When using smart phones, users often receive messages pushed by the system. Since the current message push mechanism is a one-way contact, that is, the user client will immediately display the system push message on the client when it receives it, this message push mechanism does not control the timing of message push display. Therefore, when the push message is displayed on the client, the user may be performing key interactive operations such as placing an order, which will interfere with the user and damage the user experience. Summary of the invention
[0003] Embodiments of the present disclosure provide a message push method, apparatus, device, storage medium, and program product.
[0004] In a first aspect, a message push method is provided in an embodiment of the present disclosure.
[0005] Specifically, the message push method includes:
[0006] In response to receiving the message to be pushed, storing the message to be pushed in a push message cache queue;
[0007] Acquire the type of message to be pushed and user-related data, and determine the weight of the message to be pushed according to the type of message to be pushed and the user-related data, wherein the user-related data includes one or more of the following data: user behavior data, user configuration data, and user link data;
[0008] The messages to be pushed in the push message cache queue are sorted according to the weights of the messages to be pushed, and when it is determined that the message push timing is met, one or more messages to be pushed with the highest weight in the push message cache queue are pushed.
[0009] In combination with the first aspect, in a first implementation of the first aspect of the present disclosure, determining the weight of the message to be pushed according to the type of the message to be pushed and the user-related data includes:
[0010] The type of message to be pushed and user-related data are input into a pre-trained message weight determination model to obtain the weight of the message to be pushed.
[0011] In combination with the first aspect and the first implementation of the first aspect, the embodiment of the present disclosure, in a second implementation of the first aspect, further includes:
[0012] The message weight determination model is trained.
[0013] In combination with the first aspect, the first implementation manner of the first aspect, and the second implementation manner of the first aspect, in a third implementation manner of the first aspect of the embodiment of the present disclosure, the training of the message weight determination model includes:
[0014] Determine an initial message weight determination model;
[0015] Acquire a historical message weight determination data set, wherein the historical message weight determination data set includes historical message weight determination input data and historical message weight determination result data corresponding to the historical message weight determination input data, and the historical message weight determination input data includes one or more of the following data: historical push message type, historical user behavior data, historical user configuration data, and historical user link data;
[0016] The historical message weight determination input data is used as input, and the corresponding historical message weight determination result data is used as output to train the initial message weight determination model to obtain a target message weight determination model.
[0017] In combination with the first aspect, the first implementation of the first aspect, the second implementation of the first aspect, and the third implementation of the first aspect, the embodiment of the present disclosure, in a fourth implementation of the first aspect, further includes:
[0018] The model input data and message weight determination results obtained when using the target message weight determination model to determine the message weight are added as new training data to the historical message weight determination data set of the target message weight determination model to train the target message weight determination model.
[0019] In combination with the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, and the fourth implementation manner of the first aspect, in a fifth implementation manner of the first aspect of the embodiment of the present disclosure, determining that the message push opportunity is met includes:
[0020] Acquire user current operation data, and determine a user interaction index according to the user current operation data, wherein the user interaction index is used to characterize the importance of the user interaction operation, and the user current operation data may include one or more of the following data: user current operation object, user current operation content, user current operation type, and user current operation duration;
[0021] When the user interaction index is lower than a preset index threshold, it is determined that the message push opportunity is met.
[0022] In combination with the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, and the fifth implementation manner of the first aspect, in a sixth implementation manner of the first aspect of the embodiment of the present disclosure, pushing one or more messages to be pushed with the highest weight in the push message cache queue includes:
[0023] Taking out one or more to-be-pushed messages with the highest weight in the push message cache queue;
[0024] The one or more messages to be pushed with the highest weight are rendered and displayed.
[0025] In a second aspect, a message push device is provided in an embodiment of the present disclosure.
[0026] Specifically, the message push device includes:
[0027] A storage module, configured to, in response to receiving a message to be pushed, store the message to be pushed in a push message cache queue;
[0028] A determination module is configured to obtain the type of message to be pushed and user-related data, and determine the weight of the message to be pushed according to the type of message to be pushed and the user-related data, wherein the user-related data includes one or more of the following data: user behavior data, user configuration data and user link data;
[0029] The push module is configured to sort the messages to be pushed in the push message cache queue according to the weights of the messages to be pushed, and when it is determined that the message push opportunity is met, push one or more messages to be pushed with the highest weight in the push message cache queue.
[0030] In combination with the second aspect, in a first implementation of the second aspect of the present disclosure, the part of the determination module that determines the weight of the message to be pushed according to the type of the message to be pushed and the user-related data is configured as follows:
[0031] The type of message to be pushed and user-related data are input into a pre-trained message weight determination model to obtain the weight of the message to be pushed.
[0032] In combination with the second aspect and the first implementation of the second aspect, the embodiment of the present disclosure, in the second implementation of the second aspect, further includes:
[0033] The training module is configured to train the message weight determination model.
[0034] In combination with the second aspect, the first implementation of the second aspect, and the second implementation of the second aspect, in a third implementation of the second aspect of the embodiment of the present disclosure, the training module is configured as follows:
[0035] Determine an initial message weight determination model;
[0036] Acquire a historical message weight determination data set, wherein the historical message weight determination data set includes historical message weight determination input data and historical message weight determination result data corresponding to the historical message weight determination input data, and the historical message weight determination input data includes one or more of the following data: historical push message type, historical user behavior data, historical user configuration data, and historical user link data;
[0037] The historical message weight determination input data is used as input, and the corresponding historical message weight determination result data is used as output to train the initial message weight determination model to obtain a target message weight determination model.
[0038] In combination with the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, and the third implementation manner of the second aspect, in a fourth implementation manner of the second aspect of the embodiment of the present disclosure, the training module is further configured as:
[0039] The model input data and message weight determination results obtained when using the target message weight determination model to determine the message weight are added as new training data to the historical message weight determination data set of the target message weight determination model to train the target message weight determination model.
[0040] In combination with the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, and the fourth implementation manner of the second aspect, in a fifth implementation manner of the second aspect of the embodiment of the present disclosure, the part of the push module that determines that the message push opportunity is met is configured as follows:
[0041] Acquire user current operation data, and determine a user interaction index according to the user current operation data, wherein the user interaction index is used to characterize the importance of the user interaction operation, and the user current operation data may include one or more of the following data: user current operation object, user current operation content, user current operation type, and user current operation duration;
[0042] When the user interaction index is lower than a preset index threshold, it is determined that the message push opportunity is met.
[0043] In combination with the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, and the fifth implementation manner of the second aspect, in a sixth implementation manner of the second aspect of the embodiment of the present disclosure, the part of the push module that pushes the one or more messages to be pushed with the highest weight in the push message cache queue is configured as follows:
[0044] Taking out one or more to-be-pushed messages with the highest weight in the push message cache queue;
[0045] The one or more messages to be pushed with the highest weight are rendered and displayed.
[0046] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising a memory and at least one processor, wherein the memory is used to store one or more computer instructions, and wherein the one or more computer instructions are executed by the at least one processor to implement the method steps of the above-mentioned message push method.
[0047] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium for storing computer instructions used by a message push device, which includes computer instructions involved in the message push device for executing the above-mentioned message push method.
[0048] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program / instructions, wherein the computer program / instructions implement the above-mentioned message push method when executed by a processor.
[0049] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:
[0050] In the above technical solution, the message or messages to be pushed are determined according to the type of message to be pushed and the user-related data, and when it is determined that the message push timing is met, the message to be pushed is pushed out. This technical solution can avoid the interference of message push on the user, provide operational convenience for the user, and improve the user experience.
[0051] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] Other features, objectives and advantages of the present disclosure will become more apparent through the following detailed description of non-limiting embodiments in conjunction with the accompanying drawings. In the accompanying drawings:
[0053] Figure 1 A flowchart showing a message push method according to an embodiment of the present disclosure is shown;
[0054] Figure 2 A structural block diagram of a message push device according to an embodiment of the present disclosure is shown;
[0055] Figure 3 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown;
[0056] Figure 4 It is a structural diagram of a computer system suitable for implementing a message push method according to an embodiment of the present disclosure. DETAILED DESCRIPTION
[0057] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. In addition, for the sake of clarity, parts not related to the description of the exemplary embodiments are omitted in the accompanying drawings.
[0058] In the present disclosure, it should be understood that terms such as "include" or "have" are intended to indicate the presence of features, numbers, steps, behaviors, components, parts, or a combination thereof disclosed in the present specification, and are not intended to exclude the possibility that one or more other features, numbers, steps, behaviors, components, parts, or a combination thereof exist or are added.
[0059] It should also be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0060] The technical solution provided by the embodiment of the present disclosure determines which message or messages to push according to the type of message to be pushed and user-related data, and pushes the message to be pushed when it is determined that the message push timing is met. The technical solution can avoid the interference of message push on the user, provide operational convenience for the user, and improve the user experience.
[0061] Figure 1 A flowchart of a message push method according to an embodiment of the present disclosure is shown. Figure 1 As shown, the message push method includes the following steps S101-S103:
[0062] In step S101, in response to receiving a message to be pushed, the message to be pushed is stored in a push message cache queue;
[0063] In step S102, the type of message to be pushed and user-related data are obtained, and the weight of the message to be pushed is determined according to the type of message to be pushed and the user-related data, wherein the user-related data includes one or more of the following data: user behavior data, user configuration data, and user link data;
[0064] In step S103, the messages to be pushed in the push message cache queue are sorted according to the weights of the messages to be pushed, and when it is determined that the message push opportunity is met, one or more messages to be pushed with the highest weight in the push message cache queue are pushed.
[0065] As mentioned above, with the progress of society and the development of science and technology, the use of smartphones is becoming more and more common. When using smartphones, users often receive messages pushed by the system. Since the current message push mechanism is a one-way contact, that is, the user client will immediately display the system push message on the client when it receives it, this message push mechanism does not control the timing of message push display. Therefore, when the push message is displayed on the client, the user may be performing key interactive operations such as placing an order, which will interfere with the user and damage the user experience.
[0066] In view of the above defects, in this embodiment, a message push method is proposed, which determines which message or messages to push according to the type of message to be pushed and user-related data, and pushes the message to be pushed when it is determined that the message push timing is met. This technical solution can avoid the interference of message push on the user, provide operational convenience for the user, and improve the user experience.
[0067] In one embodiment of the present disclosure, the message push method may be applicable to clients such as computers, computing devices, and electronic devices.
[0068] In one embodiment of the present disclosure, the message to be pushed refers to a message sent by a server or other message generator that needs to be pushed to a client for display. The message to be pushed can be a push message sent at a scheduled time or a push message related to the current scene. The message to be pushed may include data such as the content of the message to be pushed, the type of the message to be pushed, and the arrival link of the message to be pushed. The type of the message to be pushed refers to whether the message to be pushed is a scheduled push message or a scene push message.
[0069] In one embodiment of the present disclosure, the push message cache queue refers to a queue for caching received messages to be pushed. Whenever a new message to be pushed is received, the weight of the message to be pushed and the order of the messages to be pushed in the push message cache queue will be started.
[0070] In one embodiment of the present disclosure, the user-related data refers to user-related data that can be used to determine the weight of the message to be pushed. The user-related data may include one or more of the following data: user behavior data, user configuration data, and user link data, wherein the user behavior data refers to whether the user behavior is click, add to cart, browse, or place an order; the user configuration data refers to whether the user's current application system is configured as a standard version or a senior version; the user link data refers to whether the user is in an order link, a discount selection link, a browsing link, etc. When the user behavior is browsing, the user's current application system is configured as the standard version, or the user is in a browsing link, it means that the push message will not cause too much interference to the user at this time, and the weight of the corresponding message to be pushed can be set higher; when the user behavior is clicking to add to cart or placing an order, the user's current application system is configured as the senior version, or the user is in an order or selecting a discount link, it means that the push message will cause unexpected interference to the user at this time, and the weight of the corresponding message to be pushed can be set lower, that is, the higher the weight of the message to be pushed, the smaller the impact on the user's interaction, and the lower the weight of the message to be pushed, the greater the impact on the user's interaction.
[0071] In the above embodiment, after receiving the message to be pushed, it is not pushed first, but stored in the push message cache queue first; then the type of message to be pushed and the current user-related data are obtained, and the weight of the message to be pushed is determined according to the type of message to be pushed and the user-related data; then the messages to be pushed in the push message cache queue are sorted according to the weight of the message to be pushed, and finally when it is determined that the preset message pushing timing is met, one or more messages to be pushed with the highest weight in the push message cache queue are selected for pushing, wherein the number of messages pushed each time can be determined according to the needs of the actual application. For example, you can choose to push only the message to be pushed with the highest weight each time, or you can choose to push multiple messages to be pushed with the highest weight each time.
[0072] In an embodiment of the present disclosure, the step of determining the weight of the message to be pushed according to the type of the message to be pushed and the user-related data in step S102 may include the following steps:
[0073] The type of message to be pushed and user-related data are input into a pre-trained message weight determination model to obtain the weight of the message to be pushed.
[0074] In this embodiment, the weight of the message to be pushed is determined with the help of a pre-trained message weight determination model, wherein the input of the message weight determination model is the type of message to be pushed and user-related data, and the output is the weight of the message to be pushed.
[0075] In one embodiment of the present disclosure, the method may further include the following steps:
[0076] The message weight determination model is trained.
[0077] Further, in an embodiment of the present disclosure, the step of training the message weight determination model may include the following steps:
[0078] Determine an initial message weight determination model;
[0079] Acquire a historical message weight determination data set, wherein the historical message weight determination data set includes historical message weight determination input data and historical message weight determination result data corresponding to the historical message weight determination input data, and the historical message weight determination input data includes one or more of the following data: historical push message type, historical user behavior data, historical user configuration data, and historical user link data;
[0080] The historical message weight determination input data is used as input, and the corresponding historical message weight determination result data is used as output to train the initial message weight determination model to obtain a target message weight determination model.
[0081] In this embodiment, when training the message weight determination model, first determine an initial message weight determination model, wherein the initial message weight determination model can be selected according to the needs of the actual application; then obtain historical message weight determination input data and historical message weight determination result data corresponding to the historical message weight determination input data; then use the historical message weight determination input data as input, and use the historical message weight determination result data corresponding to the historical message weight determination input data as output to train the initial message weight determination model, and when the training results converge, the message weight determination model can be obtained. The learning and training of the above-mentioned message weight determination can be implemented by the learning and training methods commonly used in the prior art, and the present disclosure does not specifically limit the specific learning and training implementation methods for message weight determination.
[0082] The historical message weight determination input data may include one or more of the following data: historical push message type, historical user behavior data, historical user configuration data, and historical user link data. The historical push message type refers to whether the historical push message is a scheduled push message or a scene push message; the historical user behavior data refers to whether the user's behavior is click, add to cart, browse, or place an order when receiving the historical push message; the historical user configuration data refers to whether the user's application system is configured as a standard version or a senior version when receiving the historical push message; the historical user link data refers to whether the user is in an order link, a discount link, etc. when receiving the historical push message.
[0083] In one embodiment of the present disclosure, the method may further include the following steps:
[0084] The model input data and message weight determination results obtained when using the target message weight determination model to determine the message weight are added as new training data to the historical message weight determination data set of the target message weight determination model to train the target message weight determination model.
[0085] In order to improve the completeness of the historical message weight determination data set serving as the training data for the message weight determination model and to ensure the comprehensiveness of the message weight determination learning and training results, in this embodiment, a feedback mechanism is used to perform message weight determination, that is, after obtaining the message weight determination result using the message weight determination model based on the currently obtained message weight determination model input data, the message weight determination model input data and the corresponding message weight determination result data are added as new training data to the training data set of the message weight determination model, that is, the historical message weight determination data set, and then the message weight determination model is trained to enrich the training data, improve the accuracy of the message weight determination, and obtain a more complete message weight determination model to participate in the output of the next message weight determination result.
[0086] In one embodiment of the present disclosure, the step of determining in step S103 that a message push opportunity is met may include the following steps:
[0087] Acquire user current operation data, and determine a user interaction index according to the user current operation data, wherein the user interaction index is used to characterize the importance of the user interaction operation, and the user current operation data may include one or more of the following data: user current operation object, user current operation content, user current operation type, and user current operation duration;
[0088] When the user interaction index is lower than a preset index threshold, it is determined that the message push opportunity is met.
[0089] In this embodiment, when it is determined that the push of the message will not affect the important interactive operations of the user, it is determined that the push of the message can be executed. If the user interaction index is used to characterize the importance of the user interaction operation, the timing of the message push can be considered to be when the user interaction index is lower than the preset index threshold. In one embodiment of the present disclosure, the user interaction index can be calculated based on the user's current operation data, wherein the user's current operation data may include one or more of the following data: the user's current operation object, such as whether the user's current operation object is a product or an order, a product page or an order page, etc.; the user's current operation content, such as whether the user's current operation is a click or a stay, etc.; the user's current operation type, such as whether the user's current operation is an operation on an object or page, or a switch between pages; the user's current operation duration, such as the user's stay time on an object or page. If the user's current operation is clicking on a certain product, clicking on the order page, switching from non-important pages such as the product page to important pages such as the order page, etc., then it means that the user's current interactive operation is more important, and the corresponding user interaction index can be set higher. If the user's current operation is staying on a certain product, the length of time spent on the product page is greater than the preset time threshold, switching from important pages such as the order page to non-important pages such as the product page, etc., then it means that the user's current interactive operation is not so important, and the corresponding user interaction index can be set lower.
[0090] In one embodiment of the present disclosure, the step of pushing one or more to-be-pushed messages with the highest weight in the push message cache queue in step S103 may include the following steps:
[0091] Taking out one or more to-be-pushed messages with the highest weight in the push message cache queue;
[0092] The one or more messages to be pushed with the highest weight are rendered and displayed.
[0093] As mentioned above, the higher the weight of the message to be pushed, the smaller the impact on the user's interaction, and the lower the weight of the message to be pushed, the greater the impact on the user's interaction. Therefore, in this embodiment, after determining that the timing for message push is met, one or more messages to be pushed with the highest weight can be selected from the push message cache queue for push, that is, the messages to be pushed are rendered and displayed.
[0094] Since the push of messages and the determination of the timing of message push are both implemented on the client, the above implementation method can improve the real-time nature of message push, while effectively saving server resources and reducing the amount of data transmission between the client and the server. At the same time, since the client will use the timing of message push as the timing that will not affect the user's important interactive operations, for example, the client pushes messages when it confirms that the user is in a non-critical page browsing state or in a non-interactive state, it can effectively avoid the problem in the prior art that there is no precise control over the timing of message push, resulting in the user being in the process of placing an order or performing other interactive operations when the push message is displayed to the user. In more serious cases, there will be a situation where push messages accumulate and then cause user message explosions, that is, avoiding interference caused by message push to the user; providing operational convenience for the user; and improving the user experience.
[0095] The following are embodiments of the apparatus of the present disclosure, which can be used to execute embodiments of the method of the present disclosure.
[0096] Figure 2 FIG. 1 is a block diagram showing a message push device according to an embodiment of the present disclosure. The device can be implemented as part or all of an electronic device through software, hardware, or a combination of both. Figure 2 As shown, the message push device includes:
[0097] The storage module 201 is configured to store the message to be pushed in a push message cache queue in response to receiving the message to be pushed;
[0098] The determination module 202 is configured to obtain the type of message to be pushed and user-related data, and determine the weight of the message to be pushed according to the type of message to be pushed and the user-related data, wherein the user-related data includes one or more of the following data: user behavior data, user configuration data and user link data;
[0099] The push module 203 is configured to sort the messages to be pushed in the push message cache queue according to their weights, and push one or more messages to be pushed with the highest weight in the push message cache queue when it is determined that the message push opportunity is met.
[0100] As mentioned above, with the progress of society and the development of science and technology, the use of smartphones is becoming more and more common. When using smartphones, users often receive messages pushed by the system. Since the current message push mechanism is a one-way contact, that is, the user client will immediately display the system push message on the client when it receives it, this message push mechanism does not control the timing of message push display. Therefore, when the push message is displayed on the client, the user may be performing key interactive operations such as placing an order, which will interfere with the user and damage the user experience.
[0101] In view of the above defects, in this embodiment, a message push device is proposed, which determines which message or messages to push according to the type of message to be pushed and user-related data, and pushes the message to be pushed when it is determined that the message push timing is met. This technical solution can avoid the interference of message push on the user, provide operational convenience for the user, and improve the user experience.
[0102] In one embodiment of the present disclosure, the message push device may be implemented as a client such as a computer, a computing device, or an electronic device.
[0103] In one embodiment of the present disclosure, the message to be pushed refers to a message sent by a server or other message generator that needs to be pushed to a client for display. The message to be pushed can be a push message sent at a scheduled time or a push message related to the current scene. The message to be pushed may include data such as the content of the message to be pushed, the type of the message to be pushed, and the arrival link of the message to be pushed. The type of the message to be pushed refers to whether the message to be pushed is a scheduled push message or a scene push message.
[0104] In one embodiment of the present disclosure, the push message cache queue refers to a queue for caching received messages to be pushed. Whenever a new message to be pushed is received, the weight of the message to be pushed and the order of the messages to be pushed in the push message cache queue will be started.
[0105] In one embodiment of the present disclosure, the user-related data refers to user-related data that can be used to determine the weight of the message to be pushed. The user-related data may include one or more of the following data: user behavior data, user configuration data, and user link data, wherein the user behavior data refers to whether the user behavior is click, add to cart, browse, or place an order; the user configuration data refers to whether the user's current application system is configured as a standard version or a senior version; the user link data refers to whether the user is in an order link, a discount selection link, a browsing link, etc. When the user behavior is browsing, the user's current application system is configured as the standard version, or the user is in a browsing link, it means that the push message will not cause too much interference to the user at this time, and the weight of the corresponding message to be pushed can be set higher; when the user behavior is clicking to add to cart or placing an order, the user's current application system is configured as the senior version, or the user is in an order or selecting a discount link, it means that the push message will cause unexpected interference to the user at this time, and the weight of the corresponding message to be pushed can be set lower, that is, the higher the weight of the message to be pushed, the smaller the impact on the user's interaction, and the lower the weight of the message to be pushed, the greater the impact on the user's interaction.
[0106] In the above embodiment, after receiving the message to be pushed, it is not pushed first, but stored in the push message cache queue first; then the type of message to be pushed and the current user-related data are obtained, and the weight of the message to be pushed is determined according to the type of message to be pushed and the user-related data; then the messages to be pushed in the push message cache queue are sorted according to the weight of the message to be pushed, and finally when it is determined that the preset message pushing timing is met, one or more messages to be pushed with the highest weight in the push message cache queue are selected for pushing, wherein the number of messages pushed each time can be determined according to the needs of the actual application. For example, you can choose to push only the message to be pushed with the highest weight each time, or you can choose to push multiple messages to be pushed with the highest weight each time.
[0107] In an embodiment of the present disclosure, the part of the determination module 202 that determines the weight of the message to be pushed according to the type of the message to be pushed and the user-related data is configured as follows:
[0108] The type of message to be pushed and user-related data are input into a pre-trained message weight determination model to obtain the weight of the message to be pushed.
[0109] In one embodiment of the present disclosure, the device may further include:
[0110] The training module is configured to train the message weight determination model.
[0111] Further, in an embodiment of the present disclosure, the training module may be configured as follows:
[0112] Determine an initial message weight determination model;
[0113] Acquire a historical message weight determination data set, wherein the historical message weight determination data set includes historical message weight determination input data and historical message weight determination result data corresponding to the historical message weight determination input data, and the historical message weight determination input data includes one or more of the following data: historical push message type, historical user behavior data, historical user configuration data, and historical user link data;
[0114] The historical message weight determination input data is used as input, and the corresponding historical message weight determination result data is used as output to train the initial message weight determination model to obtain a target message weight determination model.
[0115] In this embodiment, when training the message weight determination model, first determine an initial message weight determination model, wherein the initial message weight determination model can be selected according to the needs of the actual application; then obtain historical message weight determination input data and historical message weight determination result data corresponding to the historical message weight determination input data; then use the historical message weight determination input data as input, and use the historical message weight determination result data corresponding to the historical message weight determination input data as output to train the initial message weight determination model, and when the training results converge, the message weight determination model can be obtained. The learning and training of the above-mentioned message weight determination can be implemented by the learning and training methods commonly used in the prior art, and the present disclosure does not specifically limit the specific learning and training implementation methods for message weight determination.
[0116] The historical message weight determination input data may include one or more of the following data: historical push message type, historical user behavior data, historical user configuration data, and historical user link data. The historical push message type refers to whether the historical push message is a scheduled push message or a scene push message; the historical user behavior data refers to whether the user's behavior is click, add to cart, browse, or place an order when receiving the historical push message; the historical user configuration data refers to whether the user's application system is configured as a standard version or a senior version when receiving the historical push message; the historical user link data refers to whether the user is in an order link, a discount link, etc. when receiving the historical push message.
[0117] In one embodiment of the present disclosure, the training module may also be configured as follows:
[0118] The model input data and message weight determination results obtained when using the target message weight determination model to determine the message weight are added as new training data to the historical message weight determination data set of the target message weight determination model to train the target message weight determination model.
[0119] In order to improve the completeness of the historical message weight determination data set serving as the training data for the message weight determination model and to ensure the comprehensiveness of the message weight determination learning and training results, in this embodiment, a feedback mechanism is used to perform message weight determination, that is, after obtaining the message weight determination result using the message weight determination model based on the currently obtained message weight determination model input data, the message weight determination model input data and the corresponding message weight determination result data are added as new training data to the training data set of the message weight determination model, that is, the historical message weight determination data set, and then the message weight determination model is trained to enrich the training data, improve the accuracy of the message weight determination, and obtain a more complete message weight determination model to participate in the output of the next message weight determination result.
[0120] In one embodiment of the present disclosure, the part of the push module 203 that determines the timing of message push can be configured as follows:
[0121] Acquire user current operation data, and determine a user interaction index according to the user current operation data, wherein the user interaction index is used to characterize the importance of the user interaction operation, and the user current operation data may include one or more of the following data: user current operation object, user current operation content, user current operation type, and user current operation duration;
[0122] When the user interaction index is lower than a preset index threshold, it is determined that the message push opportunity is met.
[0123] In this embodiment, when it is determined that the push of the message will not affect the important interactive operations of the user, it is determined that the push of the message can be executed. If the user interaction index is used to characterize the importance of the user interaction operation, the timing of the message push can be considered to be when the user interaction index is lower than the preset index threshold. In one embodiment of the present disclosure, the user interaction index can be calculated based on the user's current operation data, wherein the user's current operation data may include one or more of the following data: the user's current operation object, such as whether the user's current operation object is a product or an order, a product page or an order page, etc.; the user's current operation content, such as whether the user's current operation is a click or a stay, etc.; the user's current operation type, such as whether the user's current operation is an operation on an object or page, or a switch between pages; the user's current operation duration, such as the user's stay time on an object or page. If the user's current operation is clicking on a certain product, clicking on the order page, switching from non-important pages such as the product page to important pages such as the order page, etc., then it means that the user's current interactive operation is more important, and the corresponding user interaction index can be set higher. If the user's current operation is staying on a certain product, the length of time spent on the product page is greater than the preset time threshold, switching from important pages such as the order page to non-important pages such as the product page, etc., then it means that the user's current interactive operation is not so important, and the corresponding user interaction index can be set lower.
[0124] In one embodiment of the present disclosure, the part of the push module 203 that pushes the one or more messages to be pushed with the highest weight in the push message cache queue may be configured as follows:
[0125] Taking out one or more to-be-pushed messages with the highest weight in the push message cache queue;
[0126] The one or more messages to be pushed with the highest weight are rendered and displayed.
[0127] As mentioned above, the higher the weight of the message to be pushed, the smaller the impact on the user's interaction, and the lower the weight of the message to be pushed, the greater the impact on the user's interaction. Therefore, in this embodiment, after determining that the timing for message push is met, one or more messages to be pushed with the highest weight can be selected from the push message cache queue for push, that is, the messages to be pushed are rendered and displayed.
[0128] The present disclosure also discloses an electronic device, Figure 3 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown. Figure 3 As shown, the electronic device 300 includes a memory 301 and a processor 302; wherein,
[0129] The memory 301 is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor 302 to implement the above method steps.
[0130] Figure 4 It is a structural diagram of a computer system suitable for implementing a message push method according to an embodiment of the present disclosure.
[0131] like Figure 4 As shown, the computer system 400 includes a processing unit 401, which can perform various processes in the above-mentioned embodiments according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage part 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the computer system 400 are also stored. The processing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.
[0132] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. The drive 410 is also connected to the I / O interface 405 as needed. Removable media 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., are installed on the drive 410 as needed, so that the computer program read therefrom is installed into the storage section 408 as needed. Among them, the processing unit 401 can be implemented as a processing unit such as a CPU, a GPU, a TPU, an FPGA, an NPU, etc.
[0133] In particular, according to an embodiment of the present disclosure, the method described above can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program tangibly contained on a readable medium thereof, and the computer program includes a program code for executing the method. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 409, and / or installed from a removable medium 411.
[0134] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the road map or block diagram can represent a part of a module, program segment or code, and the part of the module, program segment or code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a different order from the order marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0135] The units or modules involved in the embodiments described in the present disclosure may be implemented by software or hardware. The units or modules described may also be set in a processor, and the names of these units or modules do not constitute limitations on the units or modules themselves in some cases.
[0136] As another aspect, the present disclosure further provides a computer-readable storage medium, which may be a computer-readable storage medium included in the device described in the above embodiment; or a computer-readable storage medium that exists independently and is not assembled into the device. The computer-readable storage medium stores one or more programs, and the programs are used by one or more processors to execute the method described in the present disclosure.
[0137] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present disclosure is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other.
Claims
1. A message push method, comprising: In response to receiving the message to be pushed, storing the message to be pushed in a push message cache queue; Acquire the type of message to be pushed and user-related data, and determine the weight of the message to be pushed according to the type of message to be pushed and the user-related data, wherein the user-related data includes one or more of the following data: user behavior data, user configuration data, and user link data; The messages to be pushed in the push message cache queue are sorted according to the weights of the messages to be pushed, and when it is determined that the timing for message pushing is met, one or more messages to be pushed with the highest weight in the push message cache queue are pushed; the determination of the timing for message pushing includes: obtaining the user's current operation data, and determining a user interaction index based on the user's current operation data, wherein the user interaction index is used to characterize the importance of the user interaction operation; when the user interaction index is lower than a preset index threshold, it is determined that the timing for message pushing is met.
2. The method according to claim 1, wherein determining the weight of the message to be pushed according to the type of the message to be pushed and the user-related data comprises: The type of message to be pushed and user-related data are input into a pre-trained message weight determination model to obtain the weight of the message to be pushed.
3. The method according to claim 2, further comprising: The message weight determination model is trained.
4. The method according to claim 3, wherein the training of the message weight determination model comprises: Determine an initial message weight determination model; Acquire a historical message weight determination data set, wherein the historical message weight determination data set includes historical message weight determination input data and historical message weight determination result data corresponding to the historical message weight determination input data, and the historical message weight determination input data includes one or more of the following data: historical push message type, historical user behavior data, historical user configuration data, and historical user link data; The historical message weight determination input data is used as input, and the corresponding historical message weight determination result data is used as output to train the initial message weight determination model to obtain a target message weight determination model.
5. The method according to claim 4, further comprising: The model input data and message weight determination results obtained when using the target message weight determination model to determine the message weight are added as new training data to the historical message weight determination data set of the target message weight determination model to train the target message weight determination model.
6. According to the method of claim 1, the user's current operation data may include one or more of the following data: the user's current operation object, the user's current operation content, the user's current operation type, and the user's current operation duration.
7. The method according to any one of claims 1 to 6, pushing one or more messages to be pushed with the highest weight in the push message cache queue, comprising: Taking out one or more to-be-pushed messages with the highest weight in the push message cache queue; The one or more messages to be pushed with the highest weight are rendered and displayed.
8. A message push device, comprising: A storage module, configured to, in response to receiving a message to be pushed, store the message to be pushed in a push message cache queue; A determination module is configured to obtain the type of message to be pushed and user-related data, and determine the weight of the message to be pushed according to the type of message to be pushed and the user-related data, wherein the user-related data includes one or more of the following data: user behavior data, user configuration data and user link data; The push module is configured to sort the messages to be pushed in the push message cache queue according to the weights of the messages to be pushed, and when it is determined that the time to push the messages is met, push one or more messages to be pushed with the highest weight in the push message cache queue; the part of the push module that determines the time to push the messages is configured to: obtain the user's current operation data, and determine the user interaction index based on the user's current operation data, wherein the user interaction index is used to characterize the importance of the user's interaction operation; when the user interaction index is lower than a preset index threshold, it is determined that the time to push the messages is met.
9. The device according to claim 8, wherein the part of the determination module that determines the weight of the message to be pushed according to the type of the message to be pushed and the user-related data is configured as follows: The type of message to be pushed and user-related data are input into a pre-trained message weight determination model to obtain the weight of the message to be pushed.
10. The apparatus according to claim 9, further comprising: The training module is configured to train the message weight determination model.
11. The apparatus according to claim 10, wherein the training module is configured to: Determine an initial message weight determination model; Get the historical message weight determination data set, where: The historical message weight determination data set includes historical message weight determination input data and historical message weight determination result data corresponding to the historical message weight determination input data, wherein the historical message weight determination input data includes one or more of the following data: historical push message type, historical user behavior data, historical user configuration data, and historical user link data; The historical message weight determination input data is used as input, and the corresponding historical message weight determination result data is used as output to train the initial message weight determination model to obtain a target message weight determination model.
12. The apparatus according to claim 11, wherein the training module is further configured to: The model input data and message weight determination results obtained when using the target message weight determination model to determine the message weight are added as new training data to the historical message weight determination data set of the target message weight determination model to train the target message weight determination model.
13. The device according to claim 8, wherein the user's current operation data may include one or more of the following data: the user's current operation object, the user's current operation content, the user's current operation type, and the user's current operation duration.
14. The device according to any one of claims 8 to 13, wherein the part of the push module that pushes the one or more messages to be pushed with the highest weight in the push message cache queue is configured as follows: Taking out one or more to-be-pushed messages with the highest weight in the push message cache queue; The one or more messages to be pushed with the highest weight are rendered and displayed.
15. An electronic device, characterized in that: The method comprises a memory and at least one processor; wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the at least one processor to implement the method steps described in any one of claims 1 to 7.
16. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the computer instructions are executed by a processor, the method steps described in any one of claims 1 to 7 are implemented.
17. A computer program product comprising a computer program / instructions, wherein: When the computer program / instructions are executed by a processor, the method steps described in any one of claims 1 to 7 are implemented.