WO2018153179A1 - Message pushing method, device and programmable device - Google Patents

Abstract

Disclosed in the present invention are a message pushing method, a device and a programmable device. The method comprises: pushing a message according to a preset message pushing interval on the basis of a message pushing list of users; and detecting the message pushing state of users according to a preset coverage detection interval so as to determine an unpushed user who did not open the pushed message so as to trigger pushing the message again to said unpushed user. According to the present invention, messages are pushed to different users accurately, and the overall coverage rate of message pushing is effectively improved.

Description

Message push method, device and programmable device Technical field

The present invention relates to the field of data push technology, and in particular, to a message push method, device, and programmable device.

Background technique

With the rapid development of mobile Internet technology and the popularity of electronic devices, people have long been accustomed to accessing the Internet to obtain information. The Internet has become one of the mainstream information dissemination platforms. At the same time, message push has become the dissemination of information through the Internet. One of the means.

Message push is usually carried out by an information dissemination platform (for example, an application service platform with a message push function, such as a news release platform, etc.) to estimate information that the user desires to obtain (such as news, promotion articles, etc.) to be sent to the user in the form of a message. Effectively improve the user's activity on the information dissemination platform.

However, the current method of message push is mainly to consider how to achieve accurate push of the message by the user. In practical applications, only the message of the user group in a small range can be accurately pushed, which often leads to the overall coverage of the message push. Not high enough to effectively improve the overall activity of the information dissemination platform.

Summary of the invention

It is an object of the present invention to provide a new technical solution for message push.

According to a first aspect of the present invention, a message pushing method is provided, comprising:

Pushing a message based on a user's message push list according to a preset message push interval,

The message push list includes a plurality of messages to be pushed to the corresponding user in a specific order;

According to the preset coverage detection interval, the message push status of the user is detected to determine that the unpushed user who has not opened the push message to re-trigger the message push to the unpushed user.

Optionally, the step of performing message push based on the user-based message push list includes:

Descending the user quality according to the user quality of each user to determine the user push order,

The user quality includes at least an activity level of the corresponding user;

And according to the user pushing order, sequentially pushing the message to the user based on the corresponding message pushing list.

Optionally, the step of performing message push based on the user-based message push list includes:

When the user is online, the user is sequentially pushed to the predetermined number of messages in the corresponding message push list;

When the user is offline, the first message in the corresponding message push list is pushed to the user.

Optionally, the message pushing method further includes:

Setting corresponding message push intervals according to user quality of each user;

and / or

According to the user classification of each user, the coverage detection interval of the user is separately set, and the user classification is obtained according to the user quality division.

The user quality includes at least the activity of the corresponding user.

Optionally, the step of re-triggering the message push to the unpushed user includes:

Descending the user quality according to the quality of each of the unpushed users to determine the user re-push order,

The user quality includes at least an activity level of the corresponding user;

Retrieving the interval according to the preset message, and sequentially pushing the message to the unpushed user based on the corresponding message push list according to the user re-pushing order.

Optionally, the message pushing method further includes:

Constructing a message library, the message library containing all messages to be pushed;

Extracting a user feature for each user, and selecting a message that matches the message feature from the message library, and then sorting the selected message in descending order according to the corresponding predicted click conversion rate to generate a corresponding user. Message push list

The user feature includes at least one of historical behavior information, activity, interest classification label, location information, and device information of the user.

The message feature includes at least one of message classification information, keyword information, and quality evaluation information.

Further optionally, the message pushing method further includes:

When a message to be pushed is added to the message library, the user whose user feature matches the message feature of the newly added message is determined to be an update user;

Adding the newly added message to the message push list of the update user, and sorting all the messages included in the message push list in descending order according to the corresponding predicted click conversion rate, and updating the message push list of the corresponding user.

According to a second aspect of the present invention, a message pushing device is provided, comprising:

The message pushing unit performs message pushing based on the user's message push list according to a preset message pushing interval.

The message push list includes a plurality of messages to be pushed to the corresponding user in a specific order;

And a message re-pushing unit, configured to detect a message push state of the user according to the preset coverage detection interval, to determine an unpush user that does not open the push message, to re-trigger the message push to the un-push user.

Optionally, the message pushing device further includes:

a message library building unit, configured to construct a message library, where the message library includes all messages to be pushed;

a message push list generating unit, configured to extract a user feature for each user, and select a message that the message feature matches the user feature from the message library, and then perform the selected message according to the corresponding predicted click conversion rate. Sorting in descending order to generate a message push list corresponding to the user;

The user feature includes at least one of historical behavior information, activity, interest classification label, location information, and device information of the user.

The message feature includes at least one of message classification information, keyword information, and quality evaluation information.

According to a third aspect of the present invention, there is also provided a programmable device comprising a memory and a processor for storing instructions for controlling the processor to operate to perform the first aspect of the invention The message push method provided.

According to the embodiment of the present invention, the message is pushed according to the message push list of the user according to the message push interval, and the user push message status is detected according to the cover detection interval to determine that the user is not pushed, and the push message is retriggered by the unpushed user to realize the difference. The user can accurately push the message and effectively improve the overall coverage of the message push.

Other features and advantages of the present invention will become apparent from the Detailed Description of the <RTIgt;

DRAWINGS

The accompanying drawings, which are incorporated in FIG

1 is a block diagram showing an example of a hardware configuration that can be used to implement an implementation environment of an embodiment of the present invention.

FIG. 2 is a flow chart showing a message pushing method according to an embodiment of the present invention.

FIG. 3 shows a flow chart of obtaining a message push list in the embodiment of the present invention.

FIG. 4 is a flow chart showing message push in the embodiment of the present invention.

FIG. 5 is a flow chart showing the re-trigger message push in the embodiment of the present invention.

FIG. 6 is a schematic diagram of an example of a message pushing method according to an embodiment of the present invention.

FIG. 7 is a schematic block diagram of a message pushing device according to an embodiment of the present invention.

detailed description

Various exemplary embodiments of the present invention will now be described in detail with reference to the drawings. It should be noted that the relative arrangement of the components and steps, numerical expressions and numerical values set forth in the embodiments are not intended to limit the scope of the invention unless otherwise specified.

The following description of the at least one exemplary embodiment is merely illustrative and is in no way

Techniques, methods and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail, but the techniques, methods and apparatus should be considered as part of the specification, where appropriate.

In all of the examples shown and discussed herein, any specific values are to be construed as illustrative only and not as a limitation. Thus, other examples of the exemplary embodiments may have different values.

It should be noted that similar reference numerals and letters indicate similar items in the following figures, and therefore, once an item is defined in one figure, it is not required to be further discussed in the subsequent figures.

<Hardware Configuration>

FIG. 1 is a block diagram showing a hardware configuration of an implementation environment 1000 in which an embodiment of the present invention can be implemented. As shown in FIG. 1, the implementation environment 1000 includes a server 1100, a client 1200, and a network 1300.

The server 1100 can be, for example, a blade server or the like. In one example, server 1100 can be a computer. In another example, the server 1100 can include a processor 1110, a memory 1120, an interface device 1130, a communication device 1140, a display device 1150, and an input device 1160, as shown in FIG. Although the server may also include a speaker, a microphone, etc., these components are not relevant to the present invention and are therefore omitted herein. The processor 1110 may be, for example, a central processing unit CPU, a microprocessor MCU, or the like. The memory 1120 includes, for example, a ROM (Read Only Memory), a RAM (Random Access Memory), a nonvolatile memory such as a hard disk, and the like. The interface device 1130 includes, for example, a USB interface, a serial interface, and the like. The communication device 1140 can perform, for example, wired or wireless communication. The display device 1150 is, for example, a liquid crystal display. Input device 1160 can include, for example, a touch screen, a keyboard, and the like.

The client 1200 can be a portable computer (1200-1), a desktop computer (1200-2), a mobile phone (1200-3), a tablet (1200-4), and the like.

The communication network 1300 can be a wireless network or a network, and can be a local area network or a wide area network. In the configuration environment 1000 shown in FIG. 1, the clients 1200-1, 1200-2, 1200-3, 1200-4, and the server 1100 can communicate over the communication network 1300.

The configuration environment 1100 shown in Figure 1 is merely illustrative and is in no way intended to limit the invention, its application or use. In the embodiment of the present invention, the memory 1120 of the server 1100 is configured to store an instruction for controlling the processor 1110 to perform any of the message pushing methods provided by the embodiments of the present invention. It will be understood by those skilled in the art that although a plurality of devices are illustrated for server 1100 in FIG. 1, the present invention may relate only to some of the devices therein, for example, server 1100 only relates to processor 1110 and storage device 1120, and the like. A technician can design instructions in accordance with the disclosed aspects of the present invention. How the instructions control the processor for operation is well known in the art and will not be described in detail herein.

<Example>

<method>

In this embodiment, a message pushing method is provided, as shown in FIG. 2, including: steps S2100-S2200.

Step S2100: Perform message push based on the user's message push list according to a preset message push interval.

Specifically, the message is information that the user is expected to obtain, such as news, information, hot articles, and the like. The message pushing interval is a time interval for pushing a message to the user. In a specific implementation, the corresponding message pushing interval may be preset according to a specific message pushing scenario. For example, for news with high timeliness, it may be set during pushing. Short message push intervals to ensure that news pushed to users is time-sensitive.

Further, different message push intervals may be set for different users, for example, according to the user quality of each user, the corresponding message push interval is respectively set, wherein the user quality includes at least the activity level of the corresponding user. The activity can include active time (can be accurate to the hour level, such as 9-10 am), active frequency (daily/week/month several active), the longer the user's active time, the higher the frequency of active, the corresponding correspondence The higher the activity of the user, the better the quality of the corresponding user. Therefore, for users with better user quality, a shorter message push interval can be set, thereby improving the click conversion rate of the push message, and for the user with poor user quality, You can set a longer message push interval to prevent message pushes from affecting the user experience too frequently.

Of course, for the sake of simple implementation, the same message push interval can be set for all users. For example, the same message push interval can be set for all users for 30 minutes.

When the preset message push interval arrives, the message push is performed based on the user's message push list, wherein the message push list includes a plurality of messages to be pushed to the application in a specific order.

In this embodiment, each user has a corresponding message push list, and the message push is performed based on the user's message push list, so that personalized and accurate push for the user can be implemented.

And, in each user's message push list, there are a plurality of messages to be pushed to the user, and the messages are arranged in a specific order in the list, so as to be pushed based on the message push list to the corresponding user, based on The specific order is to push the message to the corresponding user, so that when the user accurately pushes the message, the priority of the message push can be further reflected.

For example, the specific order may be in the order of descending order according to the predicted click conversion rate of the message (the predicted click conversion rate is the probability that the user opens or browses the message after the predicted message is pushed to the user), so that the predicted click conversion rate is higher. The messages are sorted first, so that they can be pushed to the user first, which improves the user's actual click conversion rate and brings a better user experience.

Specifically, in this embodiment, the message push list of the user may be obtained according to the method shown in FIG. 3, including: steps S3100-S3200.

Step S3100: Construct a message library, where the message library includes all messages to be pushed;

Specifically, the message library can be constructed by acquiring a message conforming to the push purpose by using webpage crawling, message clustering, automatic content generation, and the like.

For example, the message to be pushed is news, and the news that meets the requirements of heat or timeliness can be obtained through the method of web crawling and news clustering, thereby constructing a corresponding message library.

It should be understood that the construction of the message library in this embodiment may be continuous, and each time a new message to be pushed is acquired, it is added to the message library to implement continuous construction of the message library. For example, the original three news items {n1, n2, n3} in the message library, when crawling through the web page to a new time-sensitive news content n4, the message library is updated to {n1, n2, n3, n4}.

Step S3200: Extract user characteristics for each user, and select a message that matches the message feature from the message library, and then sort the selected messages in descending order according to the corresponding predicted click conversion rate to generate Corresponding to the user's message push list.

The user feature is representative information related to the browsing information of the user. Specifically, the feature of the user includes at least one of historical behavior information, activity, interest classification label, location information, and device information of the user. The historical behavior information may include browsing history, push history (received push message), click history (push message that has been opened), keyword information (browsing keywords, weights corresponding to keywords, etc.); The activity level may include an active time (which may be accurate to an hour level, such as 9-10 am), an active frequency (daily/week/month multiple active); the interest classification label is a classification label of the user's browsing interest, and may Including classification categories (sports, entertainment, hilarity, etc.) and degree classification (severe, moderate, light, etc.); the location information is the user location (can be accurate to latitude and longitude or country / administrative district / street / house number or iconic Building or the like) or a movement trajectory of the user within a predetermined time period, etc., the device information may include software information (information of the device used by the user) Software version broadcast platform or receive push message client version, etc.) and hardware information (device model, operating system information equipment, network equipment, etc.).

The message feature is representative information related to the message. Specifically, the message feature is at least one of message classification information, keyword information, and quality evaluation information, where the message classification information may be a classification topic of the message. For example, sports, entertainment, funny, etc., can also be further subdivided, such as sports can be subdivided into football, basketball, tennis, etc.; keyword information can be based on a series of message content extraction The keyword that can represent the feature of the message content may further include a corresponding keyword weight; the quality evaluation information may include a historical click conversion rate of the message, a historical user evaluation of the message, and a quality score obtained by evaluating the quality content model based on the message content. Wait.

In the method shown in FIG. 3, after extracting a user feature for each user, a message matching the message feature with the user feature is selected from the message library, and then the selected message is converted according to the corresponding predicted click. The rate is sorted in descending order to generate a message push list for the corresponding user.

The predicted click conversion rate is a probability that the user opens or browses the message after the message is pushed to the user in advance, and can be calculated by the degree of matching of the message feature of the message with the user feature.

In a specific example, it is assumed that the users to be pushed are A and B, and the user characteristics of the extracted A are: entertainment heavy users, prefer to open the client every day at 10 am, in the first-line city; the user characteristics of the extracted B are: sports heavy Users, prefer to open the client every day at 5 pm;

There are four news items in the message library {n1, n2, n3, n4}, where n1 is entertainment news, n2 is sports news, n3 is funny news, n4 is tennis news, and statistics show that you have viewed entertainment. The user of news n1 also browsed the funny news n3. Therefore, for user A, the message characteristics selected from the message library match the user characteristics are n1 and n3, and for user B, the message characteristics selected from the message library The messages matching their user characteristics are n2 and n4;

For user A, n1 is entertainment news, n3 is n1 related news, n1 message feature matches user A's user feature, and the corresponding predicted click conversion rate is higher. Therefore, user A's message push list is [n1,n3];

For user B, n4 is tennis news, n2 is sports news, n4 message feature matches user B's user feature, and the corresponding predicted click conversion rate is higher. Therefore, user A's message push list is [ N4, n2].

As described above, the construction of the message library may be continuous. Therefore, the method shown in FIG. 3 in this embodiment may further include the following steps:

When a message to be pushed is added to the message library, the user whose user feature matches the message feature of the newly added message is determined to be an update user;

Adding the newly added message to the message push list of the update user, and sorting all the messages included in the message push list in descending order according to the corresponding predicted click conversion rate, and updating the message push list of the corresponding user.

For example, in the above example, when the football news n5 is added in the message library, the user feature of the user B matches the message feature of the n5, and the user B is determined to be the update user, and n5 is added to the message push list of the user B, the user B's original message push list is [n4, n2], n5 is football news, compared with sports news n2, tennis news n4, n5 message features and user B's user features match more, the corresponding forecast The click conversion rate is higher. Therefore, n4, n2, and n5 are sorted in descending order according to the predicted click conversion rate, and the message push list of the updated user B is [n5, n4, n2].

Therefore, when the user pushes the message push list to push the message, the message with the higher predicted click conversion rate can be preferentially pushed to the user, thereby improving the actual click conversion rate of the user and bringing a better user experience.

The method for obtaining a message push list of a user in the embodiment has been described above with reference to FIG. The step of performing the message push based on the user's message push list may be specifically as shown in FIG. 4, including: steps S2101-S2102.

Step S2101: Performing a descending order according to the user quality of each user to determine a user push order.

Step S2102: Perform message pushing to the user according to the corresponding message push list in sequence according to the user push order.

The user quality includes at least the activity level of the corresponding user, and the activity level is defined in the foregoing, and details are not described herein again. The higher the user's activity, the better the quality of the corresponding user. The user push order is determined in descending order of the user quality, so that the user with high user quality is preferentially pushed by the user to push the message, thereby improving the user experience.

Specifically, when the user pushes the message according to the corresponding push list in the user push order, the message to be pushed included in the corresponding message list may be pushed by the user according to the user push order, for example, the message push of the user A. The list is [n1, n3], the message push list of user B is [n5, n4, n2], the user quality of user A is better than the user quality of user B, and the message n1, n3 can be pushed to user A, and then the user B pushes the message n5, n4, n2; according to the user push order, the message to be pushed in the corresponding message list is pushed one by one according to the user, for example, in the above example, after the user A pushes the message n1, the user B pushes the message n5. Then, the user A pushes the message n3, and then pushes the user B to n4 and n2.

In a specific message push scenario, there is usually a situation where the user pushing the message is offline, for example, the user does not open the client that provides the message push service. Therefore, the step of the user-based message push list for message push includes:

When the user is online, the user is sequentially pushed to the predetermined number of messages in the corresponding message push list;

When the user is offline, the first message in the corresponding message push list is pushed to the user.

Wherein, the predetermined number is a value selected according to engineering experience or a simulation experiment, and may be set to 2, for example.

For example, user A's message push list is [n1, n3], user B's message push list is [n5, n4, n2], assuming user A is online, user B is offline, and user A and user B have the same message push interval. , so when the message push interval arrives:

User A will push messages n1 and n3. After pushing, user A's message push list is empty, and when new information is added in the message library, a new message push list will be triggered to push the message subsequently;

For user B, only message n5 will be pushed. After pushing, user B's message push list will delete n5 to [n4, n2], and then when the message library adds new information, the updated message push list will be triggered. When the push interval is pushed, the message list is sorted to the first message. For example, when the message push interval is reached again, the message push list is still the first order of the message n4, then the message n4 will be pushed to the user B.

By distinguishing users from online or offline message push, the efficiency of message push can be further improved.

Step 2200: Detect a message push status of the user according to a preset coverage detection interval to determine an unpush user that does not open the push message, to re-trigger the message push to the unpushed user.

The coverage detection interval is a time interval for detecting a message push state of all users. In a specific implementation, the corresponding coverage detection interval may be preset according to a specific message push scenario. For example, for an application scenario with a high coverage requirement, a shorter coverage detection interval may be set.

When the preset coverage detection interval arrives, the message push status of all users is detected. Specifically, the message push status of the user may be obtained from the client that provides the message push service used by the user, for example, through a private or public communication protocol. The corresponding interface is obtained from the client, and the message push state includes at least whether the user opens the push message, and more specifically, at least whether the user opens the latest push message.

Further, the coverage detection interval of the user may be separately set according to the user classification of each user, and the user classification is obtained according to the user quality division.

The user quality includes at least the activity of the corresponding user. The specific meaning of the activity is described in the foregoing and will not be described here. The higher the user's activity is, the better the user quality is. Therefore, the user can be classified according to the user's quality. For example, the user is divided into two categories by a predetermined monthly activity threshold. For users whose monthly activity is greater than the monthly activity threshold. It is considered that the monthly user with better user quality can set the detection coverage interval to be shorter, so as to quickly determine the unpushed user of the detected user who has not opened the push message, for example, 3 hours; and for the monthly activity is not greater than The user with the monthly activity threshold is considered to be a monthly user with normal user quality. The detection coverage interval can be set longer to avoid frequent detection and reduce efficiency, for example, 5 hours.

According to the detected message push status of the user, it is determined that the unpushed user who has not opened the push message can re-trigger the message push to the unpushed user to improve the coverage of the message push. Specifically, the step of re-triggering the message push to the unpushed user may be similar to step S2100 of implementing message push as described in the foregoing. In an example, the step of re-triggering the message push to the unpushed user may be as shown in FIG. 5, including: steps S2201-S2202.

Step 2201: Perform descending order according to user quality of each of the unpushed users to determine a user re-push order;

Step S2202: Re-push the interval according to the preset message, and sequentially push the message to the unpushed user based on the corresponding message push list according to the user re-pushing order.

The user quality includes at least the activity level of the corresponding user. The specific meaning of the activity level is described in the foregoing. It is not described here. The higher the user activity, the better the corresponding user quality. The user re-pushing order is determined according to the descending order of the unpushed user quality, so that the unpushed user with higher user quality is preferentially pushed to push the message, thereby improving the user experience.

In addition, the message re-push interval is a time interval for re-pushing a message to the unpushed user. Similar to the message push interval in the preceding text, the message re-push interval can be set according to the user quality of the unpushed user, so that the user quality is high. The user's message re-push interval is shorter to enhance the user experience, and the same message re-push interval can be set for all unpushed users for the purpose of simple implementation.

For example, if the coverage detection interval is 5 hours, it is found that 40% of users have not opened the push message after the detection, that is, 40% of the unpushed users exist, and among the unpushed users, there are users A and B, and the user A has excellent user quality. For user B, user A's current message push list is [n7, n6], user B's current message push list is [n8], and the same message re-push for user A and user B:

For user A, it is found that the previous push message n3 is not opened. When the message re-push interval arrives, although the message n9 is added in the message library, the message feature of n9 does not match the user feature of user A, and the message is pushed to user A. N7, after which the message push list is updated [n6];

For user B, it is found that the previous push message n5 is not opened. When the message re-push interval arrives, the message n9 is added in the message library, the message feature of message n9 matches the user feature of user B, and the predicted click conversion rate of message n9 Higher than the message n8 in the message push list of the user B, the message push list of the user B is updated to [n9, n8], after the user A pushes the message n7, the message n9 is pushed to the user B, and thereafter the message push list is updated [n8] ].

By analogy, when the next coverage detection interval arrives, the user's message push status will be re-detected to determine that the user has not been pushed, and the push message will be re-triggered for the unpushed user until the message push covers all users, thus effectively improving message push. Overall coverage.

<example>

The message pushing method provided in this embodiment is further described below with reference to FIG. 6, which specifically includes steps S601-S608.

In step S601, the message library is continuously constructed, as shown in step S3100 in FIG. 3, and details are not described herein again.

In step S602, the message push list of the user is obtained. Specifically, as shown in step S3100 of FIG. 3, the user feature is extracted for each user, and a message matching the message feature with the user feature is selected from the message library, and then the message is The selected message is arranged in descending order according to the corresponding predicted click conversion rate to generate a message push list of the corresponding user, and details are not described herein again;

Step S603, it is determined whether the current time has reached the message push interval, if the message push interval is reached, go to step S604, otherwise, go back to step S601;

Step S604, the message is pushed according to the user's message push list, which may be specifically shown in FIG. 4, and details are not described herein again.

Step S605, it is determined whether the current time has reached the coverage detection interval, if the coverage detection interval is reached, go to step S606, otherwise, go to step S603;

Step S606, detecting the user's message push status to determine whether there is an unpushed user, if there is no push user, go to step S607, otherwise, go to step S601;

In step S607, the push-forwarding of the user is not triggered, and the information may be pushed as shown in FIG. 5, and details are not described herein again.

In step S608, it is determined whether the message push service needs to be closed, and if so, the process ends, otherwise, the process returns to step S601.

It should be understood that this example only schematically shows the flow of the specific implementation of the message pushing method provided in this embodiment. By this example, those skilled in the art may perform the purpose of simple or other non-technical factors. , other examples obtained by swapping or substituting the steps in the specific implementation.

According to the above example, the user pushes the message based on the message push list of the user according to the message push interval, and detects the user's message push status according to the coverage detection interval to determine that the user is not pushed, and then pushes the message back to the untriggered user to implement the differentiated user. The accurate push of the message, and effectively improve the overall coverage of message push.

<device>

In this embodiment, a message pushing device 7000 is further provided. As shown in FIG. 7, the message pushing unit 7100 includes a message pushing unit 7100 and a message re-pushing unit 7200. Optionally, the message library building unit 7300 and the message pushing list generating unit 7400 are further included. It is used to implement any method for pushing a message in this embodiment, and details are not described herein again.

The message pushing device 7000 includes:

The message pushing unit 7100 performs message push based on the message push list of the user according to a preset message pushing interval.

The message push list includes a plurality of messages to be pushed to the corresponding user in a specific order;

The message re-pushing unit 7200 is configured to detect a message push state of the user according to the preset coverage detection interval to determine an unpush user that does not open the push message, to re-trigger the message push to the un-pushed user.

Optionally, the message pushing device 7000 further includes:

a message library building unit 7100, configured to construct a message library, where the message library includes all messages to be pushed;

The message push list generating unit 7200 is configured to extract a user feature for each user, and select a message that matches the message feature from the message library, and then select the converted message according to the corresponding predicted click conversion rate. Sorting in descending order to generate a message push list corresponding to the user;

The user feature includes at least one of historical behavior information, activity, interest classification label, location information, and device information of the user.

The message feature includes at least one of message classification information, keyword information, and quality evaluation information.

Those skilled in the art will appreciate that the message push device 7000 can be implemented in a variety of ways. For example, the message push device 7000 can be implemented by an instruction configuration processor. For example, the instructions can be stored in the ROM, and when the device is booted, the instructions are read from the ROM into the programmable device to implement the message push device 7000. For example, message push device 7000 can be cured into a dedicated device (eg, an ASIC). The message push device 7000 can be divided into mutually independent units, or they can be implemented together. The message push device 7000 may be implemented by one of the various implementations described above, or may be implemented by a combination of two or more of the various implementations described above.

<programmable device>

In this embodiment, there is also provided a programmable device comprising a memory and a processor, the memory for storing instructions for controlling the processor to perform to perform message push provided in the embodiment method. In a specific example, the programmable device may be the server 1100 as shown in FIG.

The embodiments of the present invention have been described above with reference to the accompanying drawings and examples. According to the present embodiment, a message push method, device, and programmable device are provided, and a message is pushed to a user based on a message push list of a user according to a message push interval, and After detecting the message push state of the user according to the coverage detection interval, it is determined that the user is not pushed by the push user, and the push message is re-triggered by the untriggered user, so that the accurate push of the message is differentiated, and the overall coverage of the message push can be effectively improved.

The invention can be a system, method and/or computer program product. The computer program product can comprise a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement various aspects of the present invention.

The computer readable storage medium can be a tangible device that can hold and store the instructions used by the instruction execution device. The computer readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer readable storage media include: portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM) Or flash memory), static random access memory (SRAM), portable compact disk read only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical encoding device, for example, with instructions stored thereon A raised structure in the hole card or groove, and any suitable combination of the above. A computer readable storage medium as used herein is not to be interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (eg, a light pulse through a fiber optic cable), or through a wire The electrical signal transmitted.

The computer readable program instructions described herein can be downloaded from a computer readable storage medium to various computing/processing devices or downloaded to an external computer or external storage device over a network, such as the Internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and/or edge servers. A network adapter card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in each computing/processing device .

Computer program instructions for performing the operations of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine related instructions, microcode, firmware instructions, state setting data, or in one or more programming languages. Source code or object code written in any combination, including object oriented programming languages such as Smalltalk, C++, etc., as well as conventional procedural programming languages such as the "C" language or similar programming languages. The computer readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer, partly on the remote computer, or entirely on the remote computer or server. carried out. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or wide area network (WAN), or can be connected to an external computer (eg, using an Internet service provider to access the Internet) connection). In some embodiments, the customized electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), can be customized by utilizing state information of computer readable program instructions. Computer readable program instructions are executed to implement various aspects of the present invention.

Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowcharts and/or block diagrams can be implemented by computer readable program instructions.

The computer readable program instructions can be provided to a general purpose computer, a special purpose computer, or a processor of other programmable data processing apparatus to produce a machine such that when executed by a processor of a computer or other programmable data processing apparatus Means for implementing the functions/acts specified in one or more of the blocks of the flowcharts and/or block diagrams. The computer readable program instructions can also be stored in a computer readable storage medium that causes the computer, programmable data processing device, and/or other device to operate in a particular manner, such that the computer readable medium storing the instructions includes An article of manufacture that includes instructions for implementing various aspects of the functions/acts recited in one or more of the flowcharts.

The computer readable program instructions can also be loaded onto a computer, other programmable data processing device, or other device to perform a series of operational steps on a computer, other programmable data processing device or other device to produce a computer-implemented process. Thus, instructions executed on a computer, other programmable data processing apparatus, or other device implement the functions/acts recited in one or more of the flowcharts and/or block diagrams.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the invention. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a portion of an instruction that includes one or more components for implementing the specified logical functions. Executable instructions. In some alternative implementations, the functions noted in the blocks may also occur in a different order than those illustrated in the drawings. For example, two consecutive blocks may be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts, can be implemented in a dedicated hardware-based system that performs the specified function or function. Or it can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are equivalent.

The embodiments of the present invention have been described above, and the foregoing description is illustrative, not limiting, and not limited to the disclosed embodiments. Numerous modifications and changes will be apparent to those skilled in the art without departing from the scope of the invention. The choice of terms used herein is intended to best explain the principles, practical applications, or technical improvements in the various embodiments of the embodiments, or to enable those of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the invention is defined by the appended claims.

Claims (10)

A message pushing method, comprising: Pushing a message based on a user's message push list according to a preset message push interval, The message push list includes a plurality of messages to be pushed to the corresponding user in a specific order; According to the preset coverage detection interval, the message push status of the user is detected to determine that the unpushed user who has not opened the push message to re-trigger the message push to the unpushed user. The method according to claim 1, wherein the step of pushing the message based on the user-based message push list comprises: Descending the user quality according to the user quality of each user to determine the user push order, The user quality includes at least an activity level of the corresponding user; And according to the user pushing order, sequentially pushing the message to the user based on the corresponding message pushing list. The method according to claim 1 or 2, wherein the step of pushing the message based on the user-based message push list comprises: When the user is online, the user is sequentially pushed to the predetermined number of messages in the corresponding message push list; When the user is offline, the first message in the corresponding message push list is pushed to the user. A method according to any one of claims 1 to 3, characterized in that: Setting corresponding message push intervals according to user quality of each user; and / or According to the user classification of each user, the coverage detection interval of the user is separately set, and the user classification is obtained according to the user quality division. The user quality includes at least the activity of the corresponding user. The method according to any one of claims 1 to 4, wherein the step of retriving the message push to the unpushed user comprises: Descending the user quality according to the quality of each of the unpushed users to determine the user re-push order, The user quality includes at least an activity level of the corresponding user; Retrieving the interval according to the preset message, and sequentially pushing the message to the unpushed user based on the corresponding message push list according to the user re-pushing order. The method of any of claims 1-5, further comprising: Constructing a message library, the message library containing all messages to be pushed; Extracting a user feature for each user, and selecting a message that matches the message feature from the message library, and then sorting the selected message in descending order according to the corresponding predicted click conversion rate to generate a corresponding user. Message push list The user feature includes at least one of historical behavior information, activity, interest classification label, location information, and device information of the user. The message feature includes at least one of message classification information, keyword information, and quality evaluation information. A method according to any one of claims 1 to 6, wherein When a message to be pushed is added to the message library, the user whose user feature matches the message feature of the newly added message is determined to be an update user; Adding the newly added message to the message push list of the update user, and sorting all the messages included in the message push list in descending order according to the corresponding predicted click conversion rate, and updating the message push list of the corresponding user. A message pushing device comprising: The message pushing unit performs message pushing based on the user's message push list according to a preset message pushing interval. The message push list includes a plurality of messages to be pushed to the corresponding user in a specific order; And a message re-pushing unit, configured to detect a message push state of the user according to the preset coverage detection interval, to determine an unpush user that does not open the push message, to re-trigger the message push to the un-push user. The message pushing device of claim 8, further comprising: a message library building unit, configured to construct a message library, where the message library includes all messages to be pushed; a message push list generating unit, configured to extract a user feature for each user, and select a message that the message feature matches the user feature from the message library, and then perform the selected message according to the corresponding predicted click conversion rate. Sorting in descending order to generate a message push list corresponding to the user; The user feature includes at least one of historical behavior information, activity, interest classification label, location information, and device information of the user. The message feature includes at least one of message classification information, keyword information, and quality evaluation information. A programmable device, comprising: a memory and a processor, the memory for storing instructions for controlling the processor to operate to perform the method of any of claims 1-7 Methods.

Images