CN108734186B

CN108734186B - Method, device and system for automatically quitting instant messaging session group

Info

Publication number: CN108734186B
Application number: CN201710254343.4A
Authority: CN
Inventors: 靳玉康
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2017-04-18
Filing date: 2017-04-18
Publication date: 2022-05-10
Anticipated expiration: 2037-04-18
Also published as: CN108734186A

Abstract

The application discloses a method, a device and a system for automatically quitting an instant messaging conversation group. Wherein, the method comprises the following steps: traversing at least one conversation group, and acquiring the user behavior characteristics of each user contained in the conversation group; acquiring the probability of each user exiting the conversation group according to the user behavior characteristics of each user contained in the conversation group; and determining whether to output prompt information for exiting the conversation group according to the probability of exiting the conversation group. The method and the device solve the technical problem that the group returning operation of the existing instant messaging tool is complex and influences the user experience effect.

Description

Method, device and system for automatically quitting instant messaging session group

Technical Field

The present application relates to the field of communications technologies, and in particular, to a method, an apparatus, and a system for automatically quitting an instant messaging session group.

Background

With the rapid development of internet technology, instant messaging has been developed into a comprehensive information platform integrating communication, information, entertainment, search, e-commerce, office collaboration, enterprise customer service, and the like. The user can send and receive messages with other computers or mobile phones which are already provided with corresponding client software through intelligent communication equipment such as computers or mobile phones which are provided with instant messaging software (such as QQ, WeChat, MSN and the like). In the use process of an instant messaging tool (for example, WeChat), especially in an enterprise instant messaging tool, a plurality of temporary communication groups are often established according to work needs, and as work progresses, a plurality of problems such as problem focusing, interface simplicity and the like are brought to more and more temporary communication groups.

The existing instant messaging tool mainly supports two ways of manually quitting the group or regularly breaking the group for quitting the temporary communication group. In the former, because the user needs to manually quit the group chat, the user operation experience is influenced, and in addition, when the user manually quits the group, the prompt of self group quitting can be displayed in the group, so that an embarrassing situation is brought to the user; the latter sets up the group life cycle, and the group can be automatic to be dispersed in a certain time, if need continue to communicate, need prolong the group life cycle or establish the crowd again, and this is great to the whole user of crowd influence.

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The embodiment of the invention provides a method, a device and a system for automatically quitting an instant messaging conversation group, which at least solve the technical problem that the user experience effect is influenced by complicated group quitting operation of the existing instant messaging tool.

According to an aspect of the embodiments of the present invention, there is provided a method for automatically exiting an instant messaging session group, including: traversing at least one conversation group, and acquiring the user behavior characteristics of each user contained in the conversation group; acquiring the probability of each user exiting the conversation group according to the user behavior characteristics of each user contained in the conversation group; and determining whether to output prompt information for exiting the conversation group according to the probability of exiting the conversation group.

According to another aspect of the embodiments of the present invention, there is also provided a system for automatically exiting an instant messaging session group, including: the server is used for providing a model file, wherein the model file prestores user behavior characteristics of the session group fed back by at least one client, and the user behavior characteristics of the session group comprise the user behavior characteristics of at least one user in the session group; and the client is communicated with the server and used for traversing at least one session group, acquiring the user behavior characteristics of each user contained in the session group, acquiring the probability of each user exiting the session group according to the user behavior characteristics of each user contained in the session group, and determining whether to output prompt information for exiting the session group according to the probability of exiting the session group.

According to another aspect of the embodiments of the present invention, there is also provided an apparatus for automatically exiting an instant messaging session group, including: the first acquisition module is used for traversing at least one conversation group and acquiring the user behavior characteristics of each user contained in the conversation group; the second acquisition module is used for acquiring the probability of each user exiting the conversation group according to the user behavior characteristics of each user contained in the conversation group; and the determining module is used for determining whether to output prompt information for exiting the conversation group according to the probability of exiting the conversation group.

According to another aspect of the embodiments of the present invention, there is also provided a method for exiting a group, including: acquiring user behavior characteristics of a plurality of users contained in a first group; acquiring the probability of at least one user exiting the first group according to the user behavior characteristics of the plurality of users; and determining whether to output prompt information for exiting the first group according to the probability.

According to another aspect of the embodiments of the present invention, there is also provided an apparatus for exiting a group, including: a first obtaining unit, configured to obtain user behavior characteristics of a plurality of users included in a first group; the second acquisition unit is used for acquiring the probability of at least one user exiting the first group according to the user behavior characteristics of the plurality of users; and the determining unit is used for determining whether to output prompt information for exiting the first group according to the probability.

According to another aspect of the embodiment of the present invention, a storage medium is further provided, where the storage medium includes a stored program, and when the program runs, a device on which the storage medium is located is controlled to perform any one of the above methods for automatically exiting an instant messaging session group.

According to another aspect of the embodiments of the present invention, there is further provided a processor, which is characterized in that the processor is configured to execute a program, where the program executes any one of the above-mentioned methods for automatically exiting an instant messaging session group.

According to another aspect of the embodiments of the present invention, there is also provided a system, including: a processor; and a memory coupled to the processor for providing instructions to the processor for processing the following processing steps: step 402, traversing at least one conversation group, and acquiring user behavior characteristics of each user included in the conversation group; step 404, obtaining the probability of each user exiting the conversation group according to the user behavior characteristics of each user included in the conversation group; and step 406, determining whether to output prompt information for exiting the conversation group according to the probability of exiting the conversation group.

In the embodiment of the invention, the user behavior characteristics of each user contained in the conversation group are obtained by traversing at least one conversation group; acquiring the probability of each user exiting the conversation group according to the user behavior characteristics of each user contained in the conversation group; according to the probability of exiting the conversation group, whether prompt information for exiting the conversation group is output or not is determined, the purpose that whether the user exits the conversation group is predicted according to the user behavior characteristics of the user in the conversation group or not is determined, and whether the user is prompted to execute the group exiting operation or not is achieved, so that the technical effects that the user executing the group exiting operation is simplified, the user experience is improved are achieved, and the technical problem that the user experience effect is influenced due to the fact that the group exiting operation of the existing instant messaging tool is complicated is solved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

fig. 1(a) is a schematic diagram of an alternative mobile phone version of a "WeChat" group chat list according to an embodiment of the present application;

fig. 1(b) is a schematic diagram of an alternative mobile phone version of "WeChat" group chat into a certain group according to the embodiment of the present application;

fig. 1(c) is an operation diagram of an optional mobile phone version of "WeChat" group chat to exit a group according to the embodiment of the present application;

fig. 2 is a schematic diagram of an alternative instant messaging network architecture according to an embodiment of the present application;

fig. 3 is a schematic diagram of a system for automatically exiting an instant messaging conversation group according to an embodiment of the present application;

fig. 4 is a flowchart of a method for automatically exiting an instant messaging session group according to an embodiment of the present application;

fig. 5 is a flowchart of an alternative method for automatically logging out of an instant messaging session group according to an embodiment of the present application;

FIG. 6 is a flow chart of an alternative method for automatically dropping out of an instant messaging session group according to an embodiment of the present application;

FIG. 7 is a flow chart of an alternative method for automatically dropping out of an instant messaging session group according to an embodiment of the present application;

FIG. 8 is a flow chart of an alternative method for automatically dropping out of an instant messaging session group according to an embodiment of the present application;

FIG. 9 is a flowchart of an alternative method for automatically dropping out of an instant messaging session group according to an embodiment of the present application;

fig. 10 is a flowchart of an alternative method for automatically logging out of an instant messaging session group according to an embodiment of the present application;

FIG. 11 is a flow chart of an alternative method for automatically dropping out of an instant messaging session group according to an embodiment of the present application;

FIG. 12 is a flow chart of an alternative method for automatically dropping out of an instant messaging session group according to an embodiment of the present application;

FIG. 13 is a flowchart of an alternative method for automatically dropping out of an instant messaging session group according to an embodiment of the present application;

FIG. 14 is a schematic diagram of an alternative data mapping according to an embodiment of the present application;

FIG. 15 is a flowchart of an alternative method for automatically dropping out of an instant messaging session group according to an embodiment of the present application;

FIG. 16 is a flow chart of an alternative method for automatically dropping out of an instant messaging session group according to an embodiment of the present application;

fig. 17 is a schematic diagram of an apparatus for automatically exiting an instant messaging session group according to an embodiment of the present application;

FIG. 18 is a flow chart of a method of exiting a cluster according to an embodiment of the present application;

FIG. 19 is a schematic diagram of an apparatus for exiting a cluster according to an embodiment of the present application; and

fig. 20 is a block diagram of a hardware configuration of a computer terminal according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

First, some terms or terms appearing in the description of the embodiments of the present application are applicable to the following explanations:

bayesian theorem, also known as Bayesian inference, was used in the 18 th century to solve the following problems in the English scholars Bayes (1702-1763): assuming that H1, H2 …, hn are mutually exclusive and constitute a complete event, knowing their probabilities P (hi),

i

1,2, …, n, it is now observed that an event a occurs randomly accompanied by H, 1, H, 2, …, H, n, and knowing the conditional probability P (a/H, i), P (H, i)/a) is solved.

Euclidean distance, also known as the euclidean metric, is a commonly used definition of distance, referring to the true distance between two points in an m-dimensional space, or the natural length of a vector (i.e., the distance of the point from the origin). The euclidean distance in two and three dimensions is the actual distance between two points.

The conversation group can be a group which is created in the instant communication tool and comprises a plurality of users, and can support a plurality of people to send voice, video, pictures or characters for conversation chat, such as a QQ group, a QQ discussion group, a WeChat group and the like.

The group state feature may be a feature used in the instant messaging software to characterize the state of each session group.

The user behavior characteristics are used for representing the behavior characteristics of each user in the conversation group, and the user behavior characteristics of each user can be obtained according to the group state characteristics of the conversation group.

Example 1

According to the embodiment of the present application, a system embodiment for automatically exiting an instant messaging conversation group is provided, and the embodiment can be applied to group management in various instant messaging tools based on internet communication, including but not limited to application scenarios such as a QQ group, a wechat group, an MSN group, and a QQ discussion group.

Instant Messaging (IM) is an internet-based terminal service that allows two or more people to communicate text messages, voice, and video instantly using a network. At present, instant messaging services support multi-party conversations, i.e., group chat. The inventor finds that, since anyone can establish a group, especially, a temporary conversation group such as a QQ discussion group, a WeChat temporary group, etc. which appear in recent years, it is faster and more convenient to create a group chat, and often a group is temporarily established in order to let people exchange some opinions or communicate some things (e.g., a time and place of a discussion party, etc.), so that more and more conversation groups are owned by users. Since many temporary groups may be used once and are not needed any more, or some temporary groups are forced to be pulled in, taking "WeChat" of mobile phone version as an example, fig. 1(a) is a schematic diagram of a "WeChat" group chat list of mobile phone version according to the embodiment of the present application, as shown in fig. 1(a), the group chat interface includes a plurality of groups such as "product department", "party discussion", "company headquarters", "college classmates", "Red envelope group" and "mobile phone purchase exchange". As can be seen from fig. 1(a), the group "party discussion" may be a temporary discussion group that the user establishes or joins for a certain party, and the group "mobile phone purchase communication" may be a group that the user joins at the stage of purchasing the mobile phone, for these temporarily established or temporarily joined groups, the group chat content may not be related to the user, and at this time, the user usually chooses to quit some useless groups in order to keep the communication interface simple.

At present, the session group in the existing instant messaging tool still needs to manually perform group quitting operation, and the group quitting operation steps are different for different operating systems and different instant messaging software. Taking WeChat as an example, table 1 shows the group drop operation steps of WeChat on Symbian, Android, iphone and Windows phone.

TABLE 1 WeChat out of group operation procedure on different operating systems

Operating system type	Group retirement operation
		Symbian	Wechat-group-option-delete and exit
Android	WeChat-group-click on top right multi-person head portrait-top right conversation operation-delete and exit
		iphone	WeChat-group-click on top right multi-person head portrait-delete and exit
Windows phone	WeChat-group-click on top right multi-person head portrait-click on bottom action bar-delete and exit

Still taking the iphone handset version "WeChat" shown in FIG. 1(a) as an example, if the user wants to exit the group "party discussion", the user needs to click "party discussion" first to enter the group, as shown in FIG. 1(b), click the head portrait of the upper right-hand person, pop up the chat information interface as shown in FIG. 1(c), and then click the "delete and exit" button, the group "party discussion" can be exited.

As can be seen from the above, the existing group quitting operations all require manual operations and at least one click operation, and if there are many temporary groups, the complicated group quitting operations greatly affect the user experience. On the other hand, since the user actively quits the group, the prompt message of "a certain quit group" is usually displayed on the group chat interface, which inevitably causes the embarrassment of the user in quitting the group.

Therefore, through research, the inventor provides a method which can automatically identify the behavior characteristics of a user in a certain group to judge whether the user needs to quit the group, and then prompt the user to execute a group quitting confirmation operation under the condition that the user needs to quit the group, so that the successful group quitting by one key is realized, the tedious operation of manually quitting the group in the traditional instant messaging tool is simplified, and the user experience effect is improved.

In an alternative application environment, fig. 2 shows an alternative instant messaging network architecture diagram, as shown in fig. 2, a server may be an application server for providing any instant messaging service (e.g., WeChat, QQ, etc.), and clients (N shown in fig. 2) may be terminal devices (e.g., mobile phones, computers, laptops, tablet computers, etc.) installed with instant messaging tools or capable of accessing the instant messaging service based on Web pages.

In one scenario, each client shown in fig. 2 may be installed with an instant chat tool, the instant chat tool (e.g., WeChat) may provide at least one session group (e.g., WeChat group), a plurality of clients belonging to the same session group may form an instant chat room, and the server may obtain a group session feature of each client in the instant chat room in real time. After a user logs in an instant chat tool (e.g., WeChat) on any client, the client starts to detect a group state characteristic of each session group in a current instant chat tool (e.g., WeChat) interface, and determines a probability of the user exiting each session group according to a behavior characteristic of each session group in the current instant chat tool interface, taking a WeChat group list shown in FIG. 1(a) as an example, the client detects the behavior characteristic of the user in each session group in real time or regularly, detects the behavior characteristic of the user in each session group after a period of time, finds that the user has not performed any session content in the session group of "party discussion" for a long period of time, and often exits the session group by other users, in this case, it can be determined that the user may want to exit the group of "party discussion", and at this time, the client can prompt the user whether to exit the group of "party discussion", and if the user confirms to quit, executing group quitting operation, otherwise, not executing the group quitting operation and recording the operation of the user. Optionally, the probability of each user exiting the conversation group can be calculated according to the collected user behavior characteristics of each user in the conversation group, and whether to prompt the user to exit the conversation group or not can be determined according to the probability of each user exiting the conversation group. An alternative is as follows:

for example, client 1 in FIG. 2 may initiate a user characteristic behavior that traverses all users in at least one locally currently open conversation group, and sends the obtained user behavior characteristics of each user included in each session group to the server, and likewise, the server may also receive the user behavior characteristics of all users in each session group fed back from other clients (e.g., client 2, client 3, …, client N), and the user behavior characteristics fed back from a plurality of clients in each conversation group are subjected to de-duplication processing, and updating the feature values of the group state features of each session group in the model file stored on the server, the model file pre-stores the user behavior characteristics of the session groups fed back from the plurality of clients, and the updated model file can also be provided for each client shown in fig. 2, so that each client determines the probability of the user exiting each session group.

It should be noted here that the software platform of each client may be, but is not limited to, operating system platforms such as Symbian, Android, iphone, and Windows phone; the hardware platform can be but is not limited to a computer, a notebook computer, a mobile phone, a tablet computer and other devices.

In the application scenario, fig. 3 is a schematic diagram of an optional system for automatically exiting an instant messaging session group according to an embodiment of the present application, and as shown in fig. 3, the system includes: a server 101 and a client 103.

The server 101 is configured to provide a model file, where the model file pre-stores user behavior characteristics of a session group fed back by at least one client, and the user behavior characteristics of the session group include user behavior characteristics of at least one user in the session group;

the client 103 is in communication with the server 101, and is configured to traverse at least one session group, obtain a user behavior feature of each user included in the session group, obtain a probability that each user exits the session group according to the user behavior feature of each user included in the session group, and determine whether to output prompt information for exiting the session group according to the probability of exiting the session group.

It should be noted that the client 103 may be any one of the N clients in the network architecture shown in fig. 2, and the instant messaging software installed on the client may include, but is not limited to, QQ, wechat, fash, MSN, and the like; the server may be an application server providing an instant messaging service, such as a QQ server, a wechat server, a messenger server, an MSN server, and the like. The client 103 can communicate with the server 101 through the internet, and obtain the model file stored on the server 101, because the model file includes the user behavior feature of at least one user in the session group fed back by at least one client, the client can obtain the user behavior feature of each user included in the session group by traversing the instant messaging software installed on the client or each session group in the Web-based instant messaging server interface, and obtain the probability of each user exiting the session group according to the user behavior feature of each user included in the session group, and finally determine whether to output the prompt information for exiting the session group to the user according to the probability of each user exiting the session group.

As can be seen from the above, in the scheme disclosed in embodiment 1 of the present application, the client 103 communicates with the server 101, and through the model file provided by the server 101, after traversing one or more conversation groups in the instant messaging software and acquiring the user behavior characteristics of each user in the conversation group, the client 103 acquires, from the server 101, the probability that each user in the conversation group exits the conversation group according to the user behavior characteristics of each user included in the conversation group, and then determines whether to output, to the user, prompt information for exiting the conversation group according to the probability that each user exits the conversation group.

It is easy to note that, since the client 103 can automatically obtain the user behavior characteristics of each user in the session group, when the session group of the user includes a plurality of users, the user does not need to manually perform a cumbersome group quitting operation to quit a certain group, the client 103 receives the user behavior characteristics of the server in the session group, calculates the probability that the user quits each session group, and outputs the prompt information of quitting the session group to the user when the probability meets the preset condition, so as to realize automatic group quitting. Therefore, by the scheme provided by the embodiment of the application, the probability that the user exits from the conversation group is predicted according to the user behavior characteristics of the user in the conversation group, so that whether the user is prompted to execute the group exiting operation is determined, and therefore the technical effects of simplifying the user to execute the group exiting operation and improving the user experience are achieved.

Therefore, the technical problem that the group quitting operation of the existing instant messaging tool is complicated and influences the user experience effect is solved by the scheme of the embodiment 1 provided by the application.

In order to enable the server 101 to obtain the user behavior characteristics of each user included in each session group in the instant chat tool, in an alternative embodiment, the client 103 may traverse at least one session group displayed in the client interface in real time or at regular time, obtain the user included in each session group, detect at least one group status characteristic of each user included in each session group, if it is detected that at least one group status characteristic of the user changes, obtain the user behavior characteristics of the user with the changed at least one group status characteristic in the session group, and send the user behavior characteristics of each session group in the client interface to the server 101.

Based on the above embodiment, before the client 103 detects at least one group state feature of each user included in the session group, the client 103 opens at least one session group of the application software in the client interface, collects the group state feature of each session group, and if an event that a user exits from any session group is detected, stores the group state feature of the user that has exited the event, and obtains the group state feature of the user that is not exiting the session group; the number of the conversation groups, the number of the historical chat messages of the conversation groups, the number of the chat participants of the conversation groups, the creating time of the conversation groups, the average number of the read messages in the conversation groups, the average number of the chat messages per person in the conversation groups, the maximum number of the chat messages in the conversation groups, the number of the top-positioned times of the conversation groups by the personnel in the conversation groups, the recent chat time of the conversation groups, the number of the participants in the recent chat time of the conversation groups and the number of the chat messages of the conversation groups.

Further, after obtaining the user behavior characteristics of each user included in the session group, the client 103 may calculate, according to a model file stored on the server 101, a probability that each user in the session group exits the session group, as an optional implementation manner, the client 103 reads the model file from the server 101, and performs probability calculation on the user behavior characteristics of each user included in the session group according to the user behavior characteristics recorded in the model file, to obtain the probability that each user exits the session group, where the model file stores in advance the user behavior characteristics of the session group fed back by at least one client, and the user behavior characteristics of the session group include the user behavior characteristics of at least one user in the session group.

As an optional embodiment, the user behavior characteristics of the user corresponding to the session group may be obtained according to a change of the group state characteristics of the session group, specifically, after the client 103 obtains at least one group state characteristic that has changed in the session group, the group state characteristic that is locally stored before the session group changes is updated, and the at least one group state characteristic of the session group whose group state characteristic has changed is mapped to the server 101, and after the server receives the at least one group state characteristic of the session group that has changed, the server modifies the group state characteristic before the session group changes in the server 101, and updates the user behavior characteristic of the at least one user in each session group that is pre-stored in the model file according to the updated group state characteristic.

In the foregoing embodiment, as a preferred implementation, after saving the group state feature of the user who has generated the exit event, obtaining the group state feature of each session group in the open state, the client 103 may further perform compression processing on the group state feature of each session group in the open state, and then transmit the compressed group state feature to the server, specifically, the client 103 may classify a plurality of session groups according to whether the exit event is generated in the session group in the open state, obtaining a first type sample and a second type sample, and calculate a euclidean distance between any two group state features in the first type sample, and select two group state features whose euclidean distance is smaller than a first predetermined threshold to perform first compression processing, so as to obtain a compressed third type sample, and at the same time, calculate a euclidean distance between any two group state features in the second type sample, selecting two group state characteristics with Euclidean distance smaller than a second preset threshold value to perform second compression processing to obtain a compressed fourth type sample; finally, the third type samples and the fourth type samples are transmitted to a server; the first type sample comprises a group state feature which is in an open state and a user sends out a quit session group, and the second type sample is a group state feature which is in an open state and does not quit the session group.

As a preferred embodiment, after the plurality of clients 103 transmit the third type samples and the fourth type samples to the server 101, the server 101 receives the third type samples and the fourth type samples from the plurality of clients, obtains a plurality of third type samples and a plurality of fourth type samples, calculates a euclidean distance between any two feature data in the plurality of third type samples, selects one of the two feature data with the euclidean distance smaller than a third predetermined threshold value for retention, calculates a euclidean distance between any two feature data in the fourth type samples, and selects one of the two feature data with the euclidean distance smaller than a fourth predetermined threshold value for retention; and counting the characteristic values of the sample data reserved in the plurality of third type samples, counting the characteristic values of the sample data reserved in the plurality of fourth type samples, and generating the model file.

It should be noted that the feature value is used to characterize the frequency of occurrence and the number of occurrences of the group state feature of each session group returned by the plurality of clients.

Optionally, before the server 101 counts the feature values of the sample data retained in the plurality of third type samples and the feature values of the sample data retained in the plurality of fourth type samples and generates the model file, the sample data retained in the plurality of third type samples and the sample data retained in the plurality of fourth type samples may be mapped to a predetermined data range respectively and the flag in the data range is marked.

In an alternative embodiment, a bayesian algorithm may be used to calculate the probability of each user exiting the conversation group, and specifically, the server 101 may obtain the feature value of the user behavior feature of each user displayed in the conversation window according to the feature value of the user behavior feature of the conversation group recorded in the model file, and perform calculation processing on the feature value of the user behavior feature of each user displayed in the conversation window by using the bayesian algorithm to obtain the probability of each user exiting each conversation group.

Specifically, in the process that the server 101 performs calculation processing on the feature value of the group state feature of each session group displayed in the client interface by using the bayesian algorithm to obtain the probability of opening each session group, the server 101 may distinguish the feature value of the group state feature of each session group displayed in the client interface, obtain the feature values of a plurality of first class group state features and the feature values of a plurality of second class group state features, perform calculation processing on the feature values of the plurality of first class group state features and the feature values of the plurality of second class group state features by using the bayesian algorithm to obtain a first probability that each session group is in an open state and generates a quit message, and a second probability that each session group is in an open state and does not generate a quit message; the first group state feature is used for representing that the conversation group is in an open state and generating an exit message, and the second group state feature is used for representing that the conversation group is in the open state and generating no exit message.

In an optional embodiment, the server 101 may be further configured to calculate, according to the first probability and the second probability corresponding to each session group, an exit priority in each session group where the same user exists, and rank, according to the exit priority, each session group to obtain an exit order for exiting each session group.

Example 2

According to the embodiment of the present application, an embodiment of a method for automatically quitting an instant messaging session group is further provided, and the method for automatically quitting an instant messaging session group provided in this embodiment may be applied to the system for automatically quitting an instant messaging session group provided in embodiment 1 of the present application, including but not limited to the application scenario described in embodiment 1 of the present application. It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.

Because the existing group quitting operation needs manual operation and at least one click operation needs to be executed, if a large number of temporary groups exist, the complex group quitting operation causes great influence on the user experience. The method for automatically quitting the instant messaging conversation group can automatically identify the user behavior characteristics of each conversation group in the instant messaging tool of the user, judge the probability of quitting each conversation group of the user, and further determine whether to prompt the user to execute the group quitting confirming operation or not according to the probability of quitting each conversation group of the user, and the user can successfully quit the group by one key only by executing the confirming operation by one click, so that the complex operation of manually quitting the group in the traditional instant messaging tool is simplified, and the user experience effect is improved.

Fig. 4 is a flowchart of a method for automatically exiting an instant messaging session group according to an embodiment of the present application, as shown in fig. 4, including the following steps:

step S402, traversing at least one conversation group, and acquiring the user behavior characteristics of each user in the conversation group.

Specifically, in the above step, the conversation group may be a group including a plurality of users created in an instant messaging tool, and may support multiple people to send voice, video, pictures or text to perform conversation and chat, for example, a QQ group, a QQ discussion group, a wechat group, or the like; the user behavior characteristics can be used for characterizing the behavior characteristics of each user in the conversation group, such as the number of times of actively initiating the conversation, the accumulated time of conducting the conversation, the number of times of being @ by other members, and the like. And traversing one or more conversation groups in real time or at regular time in the instant messaging software to acquire the user behavior characteristics of each user contained in each conversation group.

Optionally, the instant messenger may be, but is not limited to, an instant messenger such as QQ, wechat, fly message, MSN, etc.

Step S404, according to the user behavior characteristics of each user included in the conversation group, obtaining the probability that each user exits the conversation group.

Specifically, in the above step, the probability of exiting the conversation group may be obtained by the system through a certain mathematical model according to a large number of collected behavior characteristics of the user in the conversation group; after the user behavior characteristics of each user included in the session group are obtained, as an optional implementation scheme, a preset model may be called to obtain the probability that each user may exit the session group.

Step S406, determining whether to output the prompt information of exiting the conversation group according to the probability of exiting the conversation group.

Specifically, in the above step, the prompt information may be information for prompting the user to perform a group withdrawal confirmation operation, and after obtaining the probability that the user withdraws from the session group according to the user behavior characteristics of the user in the session group, it may be determined whether the probability that the user withdraws from the session group meets a preset condition, and if the probability meets the preset condition, the prompt information for prompting the user to withdraw from the session group is output; otherwise, no operation is performed.

It should be noted here that, in the process of obtaining the probability that the user exits from the conversation group according to at least one user behavior feature of the user in the conversation group, the more the user behavior features are considered, the more accurate the probability that each user in the conversation group exits from the conversation group is obtained.

In an alternative embodiment, taking "WeChat" of a mobile phone version as an example, fig. 1(a) is a schematic diagram of a "WeChat" group chat list of a mobile phone version according to an embodiment of the present application, and as shown in fig. 1(a), the group chat interface includes 6 session groups, which are "product department", "party discussion", "company headquarters", "college classmates of high school", "red package group", and "mobile phone purchase exchange", respectively. Assuming that the "mobile phone purchase communication" group is a group that a user joins one group when purchasing a mobile phone (3/20/2017) (2016, 10/1/2016), communicates with friends and shares some thoughts of purchasing a mobile phone, and then has no session in the session group, based on the scheme disclosed in the above steps S202 to S206, it can be predicted that the probability of the current user exiting the session group is high, and thus prompt information prompting the user whether to exit the session group can be output. For the "high school classmate" conversation group, it is assumed that the time when the user creates the group is (9/1/2000), the user has not performed a conversation in the conversation group in the last year, but it is detected that the user has a friend relationship with more than half of the group members in the conversation group, or is always @byother group members in the conversation group, and although the user has no conversation behavior in the last year of the conversation group, based on the scheme disclosed in the above steps S202 to S206, the probability that the current user exits the conversation group is predicted not to be too large, and thus, the user is not prompted to exit the prompt information of the conversation group.

As an optional implementation scheme, when the probability that each user in the conversation group exits the conversation group satisfies the probability of exiting the conversation group, outputting the prompt information of exiting the conversation group to the user may be information for the user to perform a one-key confirmation operation, and if the user wishes to exit the conversation group, only clicking a "confirmation" button displayed on the interface is needed, and the purpose of successfully exiting the conversation group by one key can be achieved; if the user does not wish to exit the conversation group, a "cancel" button displayed on the interface may be clicked, thereby taking the group fade operation.

As can be seen from the above, in the scheme disclosed in the foregoing embodiment 2 of the present application, the user behavior feature of each user in the session group is obtained in real time or at regular time by traversing one or more session groups in the instant messaging software, the probability that each user in the session group exits from the session group is obtained according to the user behavior feature of each user included in the session group, and then whether to output the prompt information for exiting from the session group to the user is determined according to the probability that each user exits from the session group.

It is easy to note that since the user behavior characteristics of each user in the session group are automatically obtained, in the case that the session group of the user includes a plurality of users, the user does not need to manually perform a cumbersome group quitting operation to quit a certain group, and the system can automatically predict a group that the user may want to quit from the plurality of session groups according to the automatically obtained user behavior characteristics of the user in the session group, so as to implement automatic group quitting. Therefore, by the scheme provided by the embodiment of the application, the probability that the user exits from the conversation group is predicted according to the user behavior characteristics of the user in the conversation group, so that whether the user is prompted to execute the group exiting operation is determined, and therefore the technical effects of simplifying the user to execute the group exiting operation and improving the user experience are achieved.

Therefore, the technical problem that the group quitting operation of the existing instant messaging tool is complicated and influences the user experience effect is solved by the scheme of the embodiment 2 provided by the application.

In an alternative embodiment, as shown in fig. 5, traversing at least one conversation group to obtain the user behavior feature of each user included in the conversation group may include the following steps:

step S502, traversing at least one conversation group displayed in a client interface in real time or regularly to acquire users contained in any conversation group, wherein the conversation group corresponds to a conversation window;

step S504, detect at least a kind of group status characteristic of each user included in the conversation group;

step S506, if it is detected that at least one group status feature of the user changes, acquiring a user behavior feature of the user in the session group, where the at least one group status feature changes.

Specifically, in the above steps, the client may be a smart device such as a computer, a notebook computer, a tablet computer, and a mobile phone, which is installed with software for instant messaging (e.g., QQ, wechat, messenger, MSN, etc.); the interface can be a chat interface of instant messaging software installed on a client, and can also be an instant messaging chat interface based on a Web version. The group status feature may be a feature used in the instant messaging software to characterize the status of each session group, and in an alternative embodiment, taking "WeChat" as an example, the group status feature of each session group in the client interface may include, but is not limited to: the number of people in the conversation group, the number of historical chat messages in the conversation group, the number of people in the conversation group participating in the conversation group, the creation time of the conversation group, the average number of people in the conversation group who are read, the average number of chat messages per person in the conversation group, the maximum number of chat messages in the conversation group, the number of times the conversation group is set to the top of people in the group, the recent chat time of the conversation group, the number of people in the recent chat time of the conversation group, and the number of chat messages in the conversation group. It should be noted that each conversation group may correspond to a conversation window, that is, a conversation window for performing group chat.

In an alternative embodiment, the group status characteristics may include, but are not limited to, the characteristics shown in Table 2.

TABLE 2 group status characteristics

Through the scheme disclosed by the embodiment, the aim of acquiring the user behavior characteristic of each user in the conversation group according to the conversation group state characteristic data is fulfilled.

Based on the foregoing embodiment, after obtaining the user behavior feature of the user whose at least one group state feature changes in the session group, in an alternative embodiment, as shown in fig. 6, obtaining the probability that each user exits from the session group according to the user behavior feature of each user included in the session group may include the following steps:

step S602, reading a model file, wherein the model file pre-stores user behavior characteristics of a conversation group fed back by at least one client, and the user behavior characteristics of the conversation group comprise the user behavior characteristics of at least one user in the conversation group;

step S604, carrying out probability calculation on the user behavior characteristics of each user contained in the conversation group according to the user behavior characteristics recorded in the model file to obtain the probability of each user exiting the conversation group.

Specifically, in the above step, the model file may be a file provided by the server and containing group state features of each session group in which each client performs a group session through the instant messaging software, and feature values of the group state features; the characteristic value may be a frequency of occurrence of a group state characteristic of each session group fed back to the server by at least one client, and the like. In the process of detecting one or more group state characteristics of each session group displayed in an instant messaging software interface of a client in real time or at regular time, if at least one group state characteristic of any session group in the current interface is detected to be changed, reading a model file from a server, and performing probability calculation on the user behavior characteristics of each user contained in each session group according to the model file to obtain the probability that each user may exit the session group.

As an alternative implementation, the probability of exiting the conversation group may include two types, one is the probability that the user confirms exiting the conversation group after being prompted to exit the conversation group, that is, the probability of exiting the conversation group; one is to prompt the user to leave the conversation group and then the user does not leave the conversation group, i.e. the probability of negatively leaving the conversation group.

In an alternative embodiment, as shown in fig. 7, if it is detected that at least one group status feature of the user changes, acquiring the user behavior feature of the user with the changed at least one group status feature in the conversation group may include the following steps:

step S702, acquiring at least one group state characteristic changed in the conversation group;

step S704, updating the locally stored group state characteristics before the session group changes;

step S706, mapping at least one group state feature of the session group with the changed group state feature to a server, and modifying the group state feature before the session group in the server changes;

step S708, updating the user behavior characteristics of at least one user in each session group pre-saved in the model file according to the updated group state characteristics.

Specifically, in the above step, the server may be configured to store a model file including a group state feature and a feature value of each session group in a chat interface of the instant messaging software; under the condition that at least one group state feature of each session group displayed in a client interface is detected to be changed, the client updates the group state feature of the session group locally stored before the session group is changed according to the changed at least one group state feature in the session group, at least one group state feature of the session group with the changed group state feature is mapped to the server when the client is timed or the client is closed and quit, the server modifies the group state feature before the session group is changed in the server after receiving the at least one group state feature of the session group with the changed group state feature, and updates the feature value of each user behavior feature in the session group pre-stored in the model file according to the updated group state feature, wherein the feature value comprises one of the following values: frequency of occurrence, number of occurrences of group status features.

By the embodiment, the server side obtains the group state characteristics of each session group of each client side in real time or at regular time, and the model file is updated.

Based on the foregoing embodiment, after updating the user behavior feature of at least one user in the session group pre-stored in the model file on the server according to the updated group state feature, in an alternative embodiment, as shown in fig. 8, performing probability calculation on the user behavior feature of each user included in the session group according to the user behavior feature value recorded in the model file to obtain the probability that each user exits the session group, may include the following steps:

step S802, according to the characteristic value of the user behavior characteristic of the conversation group recorded in the model file, acquiring the characteristic value of the user behavior characteristic of each user displayed in the conversation window;

step S804, a Bayesian algorithm is used for calculating the characteristic value of the user behavior characteristic of each user displayed in the conversation window, and the probability that each user exits each conversation group is obtained.

Specifically, in the above step, since the model file stored in the server records the user behavior feature of each user in each session group on each client and the feature value of each user behavior feature, in the process of performing probability calculation on the user behavior feature of each user included in the session group by using the user behavior feature recorded in the model file, the feature value of the user behavior feature of each user displayed in the group session window may be obtained according to the feature value of the user behavior feature recorded in the model file read from the server, and the feature value of the user behavior feature of each user displayed in the session window may be calculated by using the bayesian algorithm, so as to obtain the probability that each user exits each session group.

In an alternative embodiment, as shown in fig. 9, before detecting at least one group status feature of each user included in the conversation group, the method may further include the following steps:

step S902, opening at least one session group of the application software in a client interface, and collecting group state characteristics of each session group;

step S904, if detecting that any session group has a user exit event, storing the group state characteristics of the user having the exit event to obtain the group state characteristics of the users not exiting the session group;

wherein the group status characteristics include at least one of: the number of people in the conversation group, the number of historical chat messages in the conversation group, the number of people in the conversation group participating in the conversation group, the creation time of the conversation group, the average number of people in the conversation group who are read, the average number of chat messages per person in the conversation group, the maximum number of chat messages in the conversation group, the number of times the conversation group is set to the top of people in the group, the recent chat time of the conversation group, the number of people in the recent chat time of the conversation group, and the number of chat messages in the conversation group.

Specifically, in the above step, a local feature storage module is provided at each client, and is configured to store group state features of each session group in the client chat interface, and when a user opens one or more session groups of the application software in the client interface, the client may collect the group state features of each session group in real time, and when a session event occurs in any one session group in the client interface is detected, the local feature storage module stores the group state features of the session group in which the exit event occurs, so as to obtain the group state features of each session group in the open state.

By the embodiment, the purpose of acquiring the group state characteristics of each session group of the client in real time is achieved.

In an alternative embodiment, as shown in fig. 10, after saving the group status feature of the user who has generated the exit event and obtaining the group status feature of each session group in the open state, the method may further include the following steps:

step S102, compressing the group state characteristics of each session group in the open state and transmitting the compressed group state characteristics to a server, wherein the step S comprises the following steps:

step S102a, classifying the multiple conversation groups according to whether an exit event is generated in the conversation groups in the open state, to obtain a first type sample and a second type sample, wherein the first type sample includes a group state feature that is in the open state and that a user issues an exit from the conversation group, and the second type sample is a group state feature that is in the open state and that does not exit from the conversation group;

step S102b, calculating the Euclidean distance between any two group state features in the first type sample, and selecting two group state features with the Euclidean distance smaller than a first preset threshold value to perform first compression processing to obtain a compressed third type sample;

step S102c, calculating the Euclidean distance between any two group state characteristics in the second type sample, and selecting two group state characteristics with the Euclidean distance smaller than a second preset threshold value to perform second compression processing to obtain a compressed fourth type sample;

step S102d, the third type samples and the fourth type samples are transmitted to the server.

Specifically, in the above step, after the client stores the group state feature of the session group in which the session event has occurred, the client compresses the group state feature of each session group in the open state and transmits the compressed group state feature to the server. In an alternative embodiment, the group state feature data of each session group may be classified according to whether the user opens the session group and performs the session group quitting operation, so as to obtain a first type sample in which the session group is in an open state and the user performs the session group quitting operation, and a second type sample in which the session group is in an open state and the user does not perform the session group quitting operation. Respectively calculating Euclidean distances between any two group characteristics aiming at the first type samples and the second type samples, randomly selecting one group characteristic when the distance between any two group characteristics is smaller than a preset threshold value, thereby realizing the compression of group state characteristic data, respectively obtaining third type samples and fourth type samples after the first type samples and the second type samples are compressed, and transmitting the third type samples and the fourth type samples to a server.

It should be noted that, taking the first type sample as an example, assuming that the first type sample includes n conversation groups, each group state feature corresponds to n conversation groups, and thus each group state feature has n feature values, and the distance between two group state features (a and B) can be expressed as the following equation:

wherein x is_AkA feature value, x, representing a group status feature A of the kth session group_BkA feature value representing a group state feature B of the kth session group; the group state features A and B are two n-dimensional vectors a (x)_A1，x_A2，…x_An) And b (x)_B1，x_B2，…x_Bn)。

By the embodiment, the group state characteristic data of the client is compressed and then sent to the server, so that the transmission rate is improved, and the network flow cost is reduced.

In an alternative embodiment, as shown in fig. 11, after the third type samples and the fourth type samples are transmitted to the server, the method may further include the following steps:

step S112, the server receives the third type samples and the fourth type samples from the plurality of clients to obtain a plurality of third type samples and a plurality of fourth type samples;

step S114, calculating the Euclidean distance between any two feature data in a plurality of third type samples, selecting one of the two feature data with the Euclidean distance smaller than a third preset threshold value for reservation, calculating the Euclidean distance between any two feature data in a fourth type sample, and selecting one of the two feature data with the Euclidean distance smaller than a fourth preset threshold value for reservation;

step S116, counting the characteristic values of the sample data retained in the plurality of third type samples, and counting the characteristic values of the sample data retained in the plurality of fourth type samples, thereby generating a model file.

Specifically, in the above step, the server may obtain the third type sample and the fourth type sample at regular time, in an optional embodiment, the fixed time may be one day, the server receives a plurality of third type sample data and a plurality of fourth type sample data from a plurality of clients, calculates euclidean distances between any two pieces of group state feature data for data in the plurality of third type samples and data in the plurality of fourth type samples, respectively, and randomly selects a certain piece of group state feature to be retained if the distance between any two pieces of group state feature data is smaller than a predetermined threshold, and counts feature values such as occurrence frequencies or occurrence times of group state features in the compressed third type sample and fourth type sample, generates a model file according to the group state features and their corresponding feature values, and stores the model file in the server for the clients to update at regular time.

By the embodiment, the group state characteristic data from each client at the server side is compressed, so that the aim of saving storage space is fulfilled.

In an optional embodiment, the feature values are used to characterize the occurrence frequency and the occurrence frequency of the group state feature of each session group returned by the plurality of clients, where before the feature values of the sample data retained in the plurality of third type samples are counted, the feature values of the sample data retained in the plurality of fourth type samples are counted, and the model file is generated, as shown in fig. 12, the method may further include the following steps:

step S122, mapping the sample data retained in the third type samples and the sample data retained in the fourth type samples to a predetermined data range, and marking the data range.

Specifically, in the above step, since all the group state features are data statistics values, and the number of statistics values is various, which increases the complexity of the offline training, in an alternative embodiment, the data may be mapped, the data range is defined as 0 to MAX, the interval is 10, that is, there are MAX/10 intervals, the interval flag is from 0 to (MAX/10-1), and the feature values in the group state features are replaced by the interval flags.

In an alternative embodiment, fig. 13 is a schematic diagram of an alternative data mapping according to an embodiment of the present application; as shown in fig. 13, if MAX is 20 and the interval is 10, the number of intervals is 2, and the interval flag is 0 or 1, the value between 0 and 9 is replaced with 0, and the value between 10 and 19 is replaced with 1.

Through the embodiment, the complexity of off-line training is reduced.

In an alternative embodiment, as shown in fig. 14, the calculating the feature value of the group state feature of each conversation group displayed in the client interface by using the bayesian algorithm to obtain the probability of opening each conversation group may include the following steps:

step S142, distinguishing a characteristic value of a group state characteristic of each session group displayed in a client interface, and acquiring characteristic values of a plurality of first group state characteristics and characteristic values of a plurality of second group state characteristics, wherein the first group state characteristics are used for representing that the session groups are in an open state and generating exit messages, and the second group state characteristics are used for representing that the session groups are in the open state and generating no exit messages;

step S144, using a bayesian algorithm to respectively perform calculation processing on the feature values of the plurality of first class group state features and the feature values of the plurality of second class group state features, so as to obtain a first probability that each session group is in an open state and generates a quit message, and a second probability that each session group is in the open state and does not generate the quit message.

Specifically, in the above steps, after the client obtains the feature value of the group state feature of each session group displayed in the client interface according to the feature value of the group state feature recorded in the model file returned by the server, dividing the characteristic value of the group state characteristic of each session group displayed in the client interface into a characteristic value of a first group state characteristic of the session group in an open state and generating an exit message and a characteristic value of a second group state characteristic of the session group in the open state and generating no exit message, and respectively calculating the characteristic values of the first group state characteristic and the second group state characteristic by using a Bayesian algorithm to obtain a first probability of each session group in the open state and generating the exit message and a second probability of each session group in the open state and generating no exit message.

Through the embodiment, the client obtains the probability that each conversation group in the client chat interface is opened by the user through calculation according to the model file returned by the server.

In an alternative embodiment, as shown in fig. 15, sorting all the conversation groups according to the probability of each user exiting each conversation group to obtain the exiting order of exiting each conversation group may include the following steps:

step S152, calculating exit priority of each conversation group with the same user according to the first probability and the second probability corresponding to each conversation group;

step S154, sort each session group according to the exit priority, and obtain the exit order of exiting each session group.

Specifically, in the above steps, after the client calculates the first probability and the second probability of each session group by using the bayesian algorithm according to the model file, the priority order of the processed session groups can be obtained through a certain algorithm, and the session groups in the client chat interface are sorted according to the priority of each session group to obtain the exit order of exiting each session group.

By the embodiment, the chat behaviors of a large number of users and the advantages of big data are utilized, the conversation priority in the instant chat software is sequenced, and the intelligence of the chat software is improved.

Fig. 16 is a schematic diagram illustrating a general flow of an optional automatic instant messaging conversation group quitting scheme according to an embodiment of the present application, where as shown in fig. 16, the scheme for automatically quitting an instant messaging conversation group mainly includes two parts, an offline feature data collection training module and an online prediction module. The off-line characteristic data collection training module is mainly responsible for collecting user behavior characteristics from the client, storing and training the off-line characteristics, the on-line prediction module is mainly responsible for periodically traversing all user groups and predicting according to the Userfeature of the user groups, and when the user needs to quit the user groups, the user is informed to perform group quitting operation confirmation.

As an alternative embodiment, in the case where the collected characteristics are the user behavior characteristics shown in table 1, the user behavior characteristics may be defined as follows:

we define Datai ═ { Flag, UserFeaturei }, where Datai denotes the ith record, where the value of Flag is 0 or 1, 1 denotes that the user manually quits, 0 denotes that the user does not quit the group, and UserFeature denotes the feature of the user in the group. And when the user manually exits each time, the server records the behavior, stores the Data and sets the flag of the Data of the user exiting the group to 1. As the training model needs positive and negative samples, the active group of the user is randomly selected, the Userfeature of the user is counted, and Flag is set to be 0.

In the training stage, an SVM is used for data training, and a model file generated by training is synchronized to a real-time prediction module.

As an alternative embodiment, the real-time online prediction function may be implemented by the following codes:

according to the scheme disclosed by the embodiment of the application, the group quitting operation of the user is predicted by utilizing the group quitting behavior of the user, and the group quitting operation is automatically carried out for the user. And the manual operation of a user is avoided, and the interface is kept simple. And performing group action prediction based on an algorithm aiming at each group behavior of a single user, and judging whether the user needs to exit the group. The application has the advantages that: 1. the group withdrawing is not required to be carried out manually by a user, and great convenience is realized; 2. and the group quitting judgment is carried out aiming at a single user, and other users in the group are not influenced.

Alternatively, as an expanded embodiment, other classifiers may be used instead of SVMs.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art will recognize that the embodiments described in this specification are preferred embodiments and that acts or modules referred to are not necessarily required for this application.

Through the above description of the embodiments, those skilled in the art can clearly understand that the method for automatically exiting an instant messaging conversation group according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method of the embodiments of the present application.

Example 3

According to an embodiment of the present application, there is further provided an apparatus embodiment for implementing the method for automatically quitting an instant messaging session group, where fig. 17 is a schematic diagram of an apparatus for automatically quitting an instant messaging session group according to an embodiment of the present application, and as shown in fig. 17, the apparatus includes: a first acquisition module 171, a second acquisition module 173, and a determination module 175.

The first obtaining module 171 is configured to traverse at least one session group, and obtain a user behavior feature of each user included in the session group;

a second obtaining module 173, configured to obtain, according to the user behavior feature of each user included in the session group, a probability that each user exits the session group;

the determining module 175 is configured to determine whether to output a prompt message for exiting the conversation group according to the probability of exiting the conversation group.

It should be noted here that the first acquiring module 171, the second acquiring module 173 and the determining module 175 correspond to steps S402 to S406 in embodiment 2, and the modules are the same as the corresponding steps in the implementation example and application scenarios, but are not limited to the disclosure in embodiment 2. It should be noted that the modules described above as part of an apparatus may be implemented in a computer system such as a set of computer-executable instructions.

As can be seen from the above, in the scheme disclosed in the foregoing embodiment 3 of the present application, the first obtaining module 171 traverses one or more session groups in the instant messaging software, obtains the user behavior feature of each user in the session group in real time or at regular time, obtains the probability that each user in the session group exits from the session group according to the user behavior feature of each user included in the session group through the second obtaining module 173, and finally the determining module 175 determines whether to output the prompt information for exiting from the session group to the user according to the probability that each user exits from the session group.

It is easy to note that since the user behavior feature of each user in the session group is automatically obtained, in a case that the session group of the user includes a plurality of users, the user does not need to manually perform a cumbersome group quitting operation to quit a certain group, the first obtaining module 171 may automatically obtain the user behavior feature of the user in the session group, and the second obtaining module 173 may obtain the probability that the user quits each session group according to the user behavior feature of the user in the session group obtained by the first obtaining module 171, so that the determining module 175 may determine whether to output prompt information for quitting the session group to the user according to the probability that the user quits each session group. Therefore, by the scheme provided by the embodiment of the application, the probability that the user exits from the conversation group is predicted according to the user behavior characteristics of the user in the conversation group, so that whether the user is prompted to execute the group exiting operation is determined, and therefore the technical effects of simplifying the user to execute the group exiting operation and improving the user experience are achieved.

Therefore, the technical problem that the group quitting operation of the existing instant messaging tool is complicated and influences the user experience effect is solved by the scheme of the embodiment 3 provided by the application.

In an alternative embodiment, as shown in fig. 17, the first obtaining module includes: the third acquisition module is used for traversing at least one conversation group displayed in the client interface in real time or at regular time and acquiring users contained in any one conversation group, wherein the conversation group corresponds to one conversation window; the detection module is used for detecting at least one group state characteristic of each user contained in the conversation group; and the fourth obtaining module is used for obtaining the user behavior characteristics of the user with the changed at least one group state characteristic in the conversation group if the change of the at least one group state characteristic of the user is detected.

It should be noted here that the third acquiring module, the detecting module and the fourth acquiring module correspond to steps S502 to S506 in embodiment 2, and the modules are the same as the corresponding steps in the implementation example and application scenarios, but are not limited to the disclosure in embodiment 2. It should be noted that the modules described above as part of an apparatus may be implemented in a computer system such as a set of computer-executable instructions.

In an optional embodiment, the second obtaining module includes: the reading module is used for reading the model file, wherein the model file pre-stores the user behavior characteristics of the session group fed back by at least one client, and the user behavior characteristics of the session group comprise the user behavior characteristics of at least one user in the session group; and the first calculation module is used for performing probability calculation on the user behavior characteristics of each user contained in the conversation group according to the user behavior characteristics recorded in the model file to obtain the probability of each user exiting the conversation group.

It should be noted here that the above reading module and the first calculating module correspond to steps S602 to S604 in embodiment 2, and the above modules are the same as the examples and application scenarios realized by the corresponding steps, but are not limited to the disclosure of embodiment 2. It should be noted that the modules described above as part of an apparatus may be implemented in a computer system such as a set of computer-executable instructions.

In an optional embodiment, the fourth obtaining module includes: a fifth obtaining module, configured to obtain at least one group state feature that changes in the session group; the first updating module is used for updating the locally stored group state characteristics before the conversation group changes; the modification module is used for mapping at least one group state feature of the session group with the changed group state feature to the server and modifying the group state feature before the session group in the server changes; and the second updating module is used for updating the user behavior characteristics of at least one user in each conversation group pre-stored in the model file according to the updated group state characteristics.

It should be noted here that the fifth acquiring module, the first updating module, the modifying module and the second updating module correspond to steps S702 to S708 in embodiment 2, and the modules are the same as the corresponding steps in the implementation example and application scenario, but are not limited to the disclosure in embodiment 2. It should be noted that the modules described above as part of the apparatus may be implemented in a computer system such as a set of computer executable instructions.

In an optional embodiment, the first calculating module includes: a sixth obtaining module, configured to obtain, according to the feature value of the user behavior feature of the session group recorded in the model file, a feature value of the user behavior feature of each user displayed in the session window; and the second calculation module is used for calculating and processing the characteristic value of the user behavior characteristic of each user displayed in the conversation window by using a Bayesian algorithm to obtain the probability of each user exiting each conversation group.

It should be noted here that the sixth acquiring module and the second calculating module correspond to steps S802 to S804 in embodiment 2, and the modules are the same as the examples and application scenarios realized by the corresponding steps, but are not limited to the disclosure in embodiment 2. It should be noted that the modules described above as part of an apparatus may be implemented in a computer system such as a set of computer-executable instructions.

In an optional embodiment, the apparatus further comprises: the collection module is used for opening at least one session group of the application software in the client interface and collecting the group state characteristics of each session group; the storage module is used for storing the group state characteristics of the users who have quitted the event if the event that the users quit from any session group is detected, and obtaining the group state characteristics of the users who are not quitted the session group; the number of people in the conversation group, the number of historical chat messages in the conversation group, the number of chat people in the conversation group, the creating time of the conversation group, the average number of people reading messages in the conversation group, the average number of chat messages per person in the conversation group, the maximum number of chat messages in the conversation group, the number of times that the conversation group is set by people in the group, the recent chat time of the conversation group, the number of people participating in the recent chat time of the conversation group and the number of chat messages in the conversation group.

It should be noted here that the above collection module and storage module correspond to steps S902 to S904 in embodiment 2, and the above modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure of embodiment 2. It should be noted that the modules described above as part of an apparatus may be implemented in a computer system such as a set of computer-executable instructions.

In an optional embodiment, the apparatus further comprises: a processing module, configured to compress the group state features of each session group in an open state and transmit the compressed group state features to a server, where the processing module includes: the classification module is used for classifying the plurality of conversation groups according to whether exit events are generated in the conversation groups in the open state or not to obtain a first class sample and a second class sample, wherein the first class sample comprises the group state characteristics which are in the open state and are sent by a user to exit the conversation groups, and the second class sample is the group state characteristics which are in the open state and do not exit the conversation groups; the third calculation module is used for calculating the Euclidean distance between any two group state features in the first type of sample, and selecting two group state features with the Euclidean distance smaller than a first preset threshold value to perform first compression processing to obtain a compressed third type of sample; the fourth calculation module is used for calculating the Euclidean distance between any two group state features in the second type sample, and selecting two group state features with the Euclidean distance smaller than a second preset threshold value to perform second compression processing to obtain a compressed fourth type sample; and the transmission module is used for transmitting the third type samples and the fourth type samples to the server.

It should be noted here that the processing module, the classifying module, the third calculating module, the fourth calculating module and the transmitting module correspond to steps S102, S102a to S102d in embodiment 2, and the modules are the same as the examples and application scenarios realized by the corresponding steps, but are not limited to the contents disclosed in embodiment 2. It should be noted that the modules described above as part of an apparatus may be implemented in a computer system such as a set of computer-executable instructions.

In an optional embodiment, the apparatus further comprises: the receiving module is used for receiving the third type samples and the fourth type samples from the plurality of clients by the server to obtain a plurality of third type samples and a plurality of fourth type samples; the fifth calculation module is used for calculating the Euclidean distance between any two feature data in the multiple third type samples, selecting one of the two feature data with the Euclidean distance smaller than a third preset threshold value to be reserved, calculating the Euclidean distance between any two feature data in the fourth type samples, and selecting one of the two feature data with the Euclidean distance smaller than a fourth preset threshold value to be reserved; and the statistical module is used for counting the characteristic values of the sample data reserved in the third type samples, counting the characteristic values of the sample data reserved in the fourth type samples and generating the model file.

It should be noted here that the receiving module, the fifth calculating module and the counting module correspond to steps S112 to S116 in embodiment 2, and the modules are the same as the examples and application scenarios realized by the corresponding steps, but are not limited to the disclosure of embodiment 2. It should be noted that the modules described above as part of an apparatus may be implemented in a computer system such as a set of computer-executable instructions.

In an optional embodiment, the feature value is used to characterize the frequency of occurrence and the number of occurrences of the group state feature of each session group returned by the plurality of clients, where the apparatus and method further include: and the mapping module is used for mapping the sample data reserved in the third type samples and the sample data reserved in the fourth type samples to a preset data range respectively and marking the marks in the data range.

It should be noted here that the mapping module corresponds to step S122 in embodiment 2, and the modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure of embodiment 2. It should be noted that the modules described above as part of an apparatus may be implemented in a computer system such as a set of computer-executable instructions.

In an alternative embodiment, the second calculation module comprises: the system comprises a dividing module, a judging module and a display module, wherein the dividing module is used for distinguishing a characteristic value of a group state characteristic of each conversation group displayed in a client interface, and acquiring characteristic values of a plurality of first group state characteristics and characteristic values of a plurality of second group state characteristics, the first group state characteristics are used for representing that the conversation group is in an open state and generating an exit message, and the second group state characteristics are used for representing that the conversation group is in the open state and generating no exit message; and the sixth calculation module is used for calculating and processing the characteristic values of the plurality of first class group state characteristics and the characteristic values of the plurality of second class group state characteristics by using a Bayesian algorithm to obtain a first probability that each conversation group is in an open state and generates an exit message and a second probability that each conversation group is in the open state and does not generate the exit message.

It should be noted here that the above dividing module and the sixth calculating module correspond to steps S142 to S144 in embodiment 2, and the above modules are the same as the examples and application scenarios realized by the corresponding steps, but are not limited to the disclosure of embodiment 2. It should be noted that the modules described above as part of an apparatus may be implemented in a computer system such as a set of computer-executable instructions.

In an optional embodiment, the apparatus further comprises: the sixth calculating module is used for calculating the exit priority of each conversation group with the same user according to the first probability and the second probability corresponding to each conversation group; and the sequencing module is used for sequencing each conversation group according to the quit priority to obtain a quit sequence quitting each conversation group.

It should be noted here that the sixth calculating module and the sorting module correspond to steps S152 to S154 in embodiment 2, and the modules are the same as the examples and application scenarios realized by the corresponding steps, but are not limited to the disclosure of embodiment 2. It should be noted that the modules described above as part of an apparatus may be implemented in a computer system such as a set of computer-executable instructions.

Example 4

According to the embodiment of the present application, an embodiment of a method for exiting a group is further provided, and the method for exiting a group provided in this embodiment may be applied to group management in various instant messaging tools based on internet communication, including but not limited to application scenarios such as a QQ group, a wechat group, an MSN group, a QQ discussion group, and a mail group. It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.

Fig. 18 is a flowchart of a method for exiting a cluster according to an embodiment of the present application, as shown in fig. 18, including the following steps:

s182, obtaining user behavior characteristics of a plurality of users included in the first group.

Specifically, in the above step, the first group may be a group of any communication tools, including an instant communication group (e.g., a QQ group, a QQ discussion group, a wechat group, etc.) and a non-instant communication group (e.g., a mail group, etc.); since each group contains a plurality of users, the user behavior characteristics of each user in the group can be monitored in real time for a group, and the user behavior characteristics include but are not limited to: the time the user is engaged in the session, the user's exit from the group, the group is masked, etc.

S184, according to the user behavior characteristics of the users, obtaining the probability that at least one user exits the first group.

After the user behavior characteristics of the plurality of users in the group are obtained, the probability that each user in the group exits the first group is obtained according to the user behavior characteristics of the plurality of users.

And S186, determining whether to output prompt information for exiting the first group according to the probability.

Specifically, in the above step, after the probability that each user in the group exits the group is obtained, whether to output the prompt information for exiting the group to the user is determined according to the probability that the user exits the group. For example, when more than 50% of users in the group exit the group, it can be determined that the probability of the user exiting the group is high, and thus the user can be prompted to exit the group.

As can be seen from the above, in the scheme disclosed in embodiment 4 of the present application, the user behavior feature of at least one user in a certain group in the communication software is detected in real time or at regular time, the probability that each user in the group exits from the group is obtained according to the user behavior features of a plurality of users in the group, and then whether to output the prompt information for exiting from the group to the user is determined according to the probability that each user exits from the group, so that the purpose of predicting the probability that the user exits from the group according to the user behavior features of a large number of users in the group to determine whether to prompt the user to execute the group exit operation is achieved, thereby simplifying the user to execute the group exit operation and improving the technical effect of user experience.

Therefore, the technical problem that the group quitting operation of the existing instant messaging tool is complicated and influences the user experience effect is solved by the scheme of the embodiment 4 provided by the application.

As an alternative embodiment, the first group may be an instant messaging group. Instant messaging groups include, but are not limited to: QQ groups, QQ discussion groups, WeChat groups, etc.

In another alternative embodiment, the first group may be a mail group. Mail groups include, but are not limited to, a gmail mailbox, 163 mailboxes, 126 mailboxes, and the like.

Example 5

According to an embodiment of the present application, there is further provided an apparatus embodiment for implementing the method for exiting a group in embodiment 4, including but not limited to the application scenario of embodiment 4. Fig. 19 is a schematic diagram of an apparatus for exiting a cluster according to an embodiment of the present application, as shown in fig. 19, the apparatus includes: a first acquisition unit 191, a second acquisition unit 193, and a determination unit 195.

The first obtaining unit 191 is configured to obtain user behavior characteristics of a plurality of users included in a first group;

a second obtaining unit 193, configured to obtain, according to user behavior characteristics of multiple users, a probability that at least one user exits the first group;

the determining unit 195 is configured to determine whether to output a prompt to exit the first group according to the probability.

It should be noted here that the first acquiring unit 191, the second acquiring unit 193, and the determining unit 195 correspond to steps S182 to S186 in embodiment 4, and the modules are the same as the corresponding steps in the implementation example and application scenarios, but are not limited to the disclosure in embodiment 4. It should be noted that the modules described above as part of an apparatus may be implemented in a computer system such as a set of computer-executable instructions.

As can be seen from the above, in the solution disclosed in embodiment 5 of the present application, the first obtaining unit 191 detects the user behavior feature of at least one user in a group in the communication software in real time or at regular time, the second obtaining unit 193 obtains the probability that each user in the group exits the group according to the user behavior features of a plurality of users in the group, and the determining unit 195 determines whether to output the prompt information for exiting the group to the user according to the probability that each user exits the group, so as to predict the probability that the user exits the group according to the user behavior features of a large number of users in the group, so as to determine whether to prompt the user to execute the group exit operation, thereby simplifying the user to execute the group exit operation, and improving the technical effect of user experience.

Therefore, the technical problem that the group quitting operation of the existing instant messaging tool is complicated and influences the user experience effect is solved by the scheme of the embodiment 5 provided by the application.

As an alternative embodiment, the first group may be an instant messaging group or a mail group.

Example 6

The embodiment of the application can provide a computer terminal, and the computer terminal can be any one computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal may also be replaced with a terminal device such as a mobile terminal.

Optionally, in this embodiment, the computer terminal may be located in at least one access device of a plurality of network devices of a computer network.

Fig. 20 shows a block diagram of a hardware configuration of a computer terminal. As shown in fig. 20, computer terminal 20 may include one or more (shown as 202a, 202b, … …, 202 n) processors 202 (processor 202 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 204 for storing data, and a transmission device 206 for communication functions. Besides, the method can also comprise the following steps: a display, an input/output interface (I/O interface), a Universal Serial Bus (USB) port (which may be included as one of the ports of the I/O interface), a network interface, a power source, and/or a camera. It will be understood by those skilled in the art that the structure shown in fig. 20 is only an illustration and is not intended to limit the structure of the electronic device. For example, the computer terminal 20 may also include more or fewer components than shown in FIG. 20, or have a different configuration than shown in FIG. 20.

It should be noted that the one or more processors 202 and/or other data processing circuitry described above may be referred to generally herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part in software, hardware, firmware, or any combination thereof. Further, the data processing circuit may be a single stand-alone processing module, or incorporated in whole or in part into any of the other elements in the computer terminal 20. As referred to in the embodiments of the application, the data processing circuit acts as a processor control (e.g. selection of a variable resistance termination path connected to the interface).

The processor 202 may invoke the memory-stored information and the application program via the transmission means to perform the following steps: acquiring a selected path in a map; generating a dynamic image of the path according to the road condition information of the selected path, wherein the dynamic image of the path is an image which dynamically moves from a starting position to an end position along the path; a dynamic image of the route is displayed in the map.

The memory 204 may be used to store software programs and modules of application software, such as program instructions/data storage devices corresponding to the method for automatically exiting an instant messaging session group in the embodiment of the present application, and the processor 202 executes various functional applications and data processing by running the software programs and modules stored in the memory 204, that is, implementing the above-mentioned method for automatically exiting an instant messaging session group of an application program. Memory 204 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 204 may further include memory located remotely from the processor 202, which may be connected to the computer terminal 20 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission means 206 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal 20. In one example, the transmission device 206 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device 206 can be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.

The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with the user interface of the computer terminal 20.

It should be noted here that in some alternative embodiments, the computer terminal 20 shown in fig. 20 described above may include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that fig. 20 is only one example of a particular specific example and is intended to illustrate the types of components that may be present in the computer terminal 20 described above.

In this embodiment, the computer terminal 20 may execute the program code of the following steps in the method for automatically quitting the instant messaging session group of the application program: traversing at least one conversation group, and acquiring the user behavior characteristics of each user contained in the conversation group; acquiring the probability of each user exiting the conversation group according to the user behavior characteristics of each user contained in the conversation group; and determining whether to output prompt information for exiting the conversation group according to the probability of exiting the conversation group.

The processor can call the information and application program stored in the memory through the transmission device to execute the following steps: traversing at least one conversation group, and acquiring the user behavior characteristics of each user contained in the conversation group; acquiring the probability of each user exiting the conversation group according to the user behavior characteristics of each user contained in the conversation group; and determining whether to output prompt information for exiting the conversation group according to the probability of exiting the conversation group.

Optionally, the processor may further execute the program code of the following steps: traversing at least one conversation group displayed in a client interface in real time or at regular time to obtain users contained in any conversation group, wherein the conversation group corresponds to a conversation window; detecting at least one group state characteristic of each user contained in a conversation group; and if the change of at least one group state characteristic of the user is detected, acquiring the user behavior characteristic of the user with the change of at least one group state characteristic in the conversation group.

Optionally, the processor may further execute the program code of the following steps: reading a model file, wherein the model file pre-stores user behavior characteristics of a conversation group fed back by at least one client, and the user behavior characteristics of the conversation group comprise the user behavior characteristics of at least one user in the conversation group; and performing probability calculation on the user behavior characteristics of each user contained in the conversation group according to the user behavior characteristics recorded in the model file to obtain the probability of each user exiting the conversation group.

Optionally, the processor may further execute the program code of the following steps: acquiring at least one group state characteristic which is changed in a conversation group; updating locally stored group state characteristics before the session group changes; mapping at least one group state feature of the session group with the changed group state feature to a server, and modifying the group state feature of the session group in the server before the session group is changed; and updating the user behavior characteristics of at least one user in each conversation group pre-saved in the model file according to the updated group state characteristics.

Optionally, the processor may further execute the program code of the following steps: acquiring a characteristic value of the user behavior characteristic of each user displayed in a conversation window according to the characteristic value of the user behavior characteristic of the conversation group recorded in the model file; and calculating the characteristic value of the user behavior characteristic of each user displayed in the conversation window by using a Bayesian algorithm to obtain the probability of each user exiting each conversation group.

Optionally, the processor may further execute the program code of the following steps: opening at least one session group of application software in a client interface, and collecting group state characteristics of each session group; if the event that the user exits from any session group is detected, the group state characteristics of the user who exits the event are stored, and the group state characteristics of the user who does not exit the session group are obtained; the number of people in the conversation group, the number of historical chat messages in the conversation group, the number of chat people in the conversation group, the creating time of the conversation group, the average number of people reading messages in the conversation group, the average number of chat messages per person in the conversation group, the maximum number of chat messages in the conversation group, the number of times that the conversation group is set by people in the group, the recent chat time of the conversation group, the number of people participating in the recent chat time of the conversation group and the number of chat messages in the conversation group.

Optionally, the processor may further execute the program code of the following steps: classifying a plurality of conversation groups according to whether exit events are generated in the conversation groups in the open state or not to obtain a first type sample and a second type sample, wherein the first type sample comprises group state characteristics which are in the open state and enable a user to send out exit conversation groups, and the second type sample is the group state characteristics which are in the open state and do not exit the conversation groups; calculating the Euclidean distance between any two group state features in the first type sample, and selecting two group state features with the Euclidean distance smaller than a first preset threshold value to perform first compression processing to obtain a compressed third type sample; calculating the Euclidean distance between any two group state characteristics in the second type sample, and selecting two group state characteristics of which the Euclidean distance is smaller than a second preset threshold value to perform second compression processing to obtain a compressed fourth type sample; and transmitting the third type samples and the fourth type samples to a server.

Optionally, the processor may further execute the program code of the following steps: the server receives a third type sample and a fourth type sample from a plurality of clients to obtain a plurality of third type samples and a plurality of fourth type samples; calculating the Euclidean distance between any two feature data in a plurality of third type samples, selecting one of the two feature data with the Euclidean distance smaller than a third preset threshold value for reservation, calculating the Euclidean distance between any two feature data in a fourth type sample, and selecting one of the two feature data with the Euclidean distance smaller than a fourth preset threshold value for reservation; and counting the characteristic values of the sample data reserved in the plurality of third type samples, counting the characteristic values of the sample data reserved in the plurality of fourth type samples, and generating the model file.

Optionally, the processor may further execute the program code of the following steps: and mapping the sample data retained in the plurality of third type samples and the sample data retained in the plurality of fourth type samples to a predetermined data range respectively, and marking the marks in the data range.

Optionally, the processor may further execute the program code of the following steps: distinguishing a characteristic value of a group state characteristic of each session group displayed in a client interface, and acquiring characteristic values of a plurality of first group state characteristics and characteristic values of a plurality of second group state characteristics, wherein the first group state characteristics are used for representing that the session groups are in an open state and generating exit messages, and the second group state characteristics are used for representing that the session groups are in the open state and generating no exit messages; and respectively calculating the characteristic values of the plurality of first class group state characteristics and the characteristic values of the plurality of second class group state characteristics by using a Bayesian algorithm to obtain a first probability that each conversation group is in an open state and generates an exit message and a second probability that each conversation group is in the open state and does not generate the exit message.

Optionally, the processor may further execute the program code of the following steps: calculating the exit priority of each conversation group with the same user according to the first probability and the second probability corresponding to each conversation group; and sequencing each conversation group according to the quit priority to obtain the quit sequence of quitting each conversation group.

It can be understood by those skilled in the art that the structure shown in fig. 20 is only an illustration, and the computer terminal may also be a terminal device such as a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palmtop computer, a Mobile Internet Device (MID), a PAD, and the like. Fig. 20 is a diagram illustrating a structure of the electronic device. For example, the computer terminal 20 may also include more or fewer components (e.g., network interfaces, display devices, etc.) than shown in FIG. 20, or have a different configuration than shown in FIG. 20.

Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by a program instructing hardware associated with the terminal device, where the program may be stored in a computer-readable storage medium, and the storage medium may include: flash disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.

Example 7

Embodiments of the present application also provide a storage medium. Optionally, in this embodiment, the storage medium may be configured to store program codes executed by the method for automatically quitting an instant messaging session group provided in the second embodiment.

Optionally, in this embodiment, the storage medium may be located in any one of computer terminals in a computer terminal group in a computer network, or in any one of mobile terminals in a mobile terminal group.

Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: traversing at least one conversation group, and acquiring the user behavior characteristics of each user contained in the conversation group; acquiring the probability of each user exiting the conversation group according to the user behavior characteristics of each user contained in the conversation group; and determining whether to output prompt information for exiting the conversation group according to the probability of exiting the conversation group.

Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: traversing at least one conversation group displayed in a client interface in real time or regularly to obtain users contained in any conversation group, wherein the conversation group corresponds to a conversation window; detecting at least one group state characteristic of each user contained in a conversation group; and if the change of at least one group state characteristic of the user is detected, acquiring the user behavior characteristic of the user with the change of at least one group state characteristic in the conversation group.

Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: reading a model file, wherein the model file pre-stores user behavior characteristics of a conversation group fed back by at least one client, and the user behavior characteristics of the conversation group comprise the user behavior characteristics of at least one user in the conversation group; and performing probability calculation on the user behavior characteristics of each user contained in the conversation group according to the user behavior characteristics recorded in the model file to obtain the probability of each user exiting the conversation group.

Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: acquiring at least one group state characteristic which is changed in a conversation group; updating locally stored group state characteristics before session group changes; mapping at least one group state feature of the session group with the changed group state feature to a server, and modifying the group state feature of the session group in the server before the session group is changed; and updating the user behavior characteristics of at least one user in each conversation group pre-saved in the model file according to the updated group state characteristics.

Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: acquiring a characteristic value of the user behavior characteristic of each user displayed in a conversation window according to the characteristic value of the user behavior characteristic of the conversation group recorded in the model file; and calculating the characteristic value of the user behavior characteristic of each user displayed in the conversation window by using a Bayesian algorithm to obtain the probability of each user exiting each conversation group.

Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: opening at least one session group of application software in a client interface, and collecting group state characteristics of each session group; if the event that the user exits from any session group is detected, the group state characteristics of the user who exits the event are stored, and the group state characteristics of the user who does not exit the session group are obtained; the number of people in the conversation group, the number of historical chat messages in the conversation group, the number of chat people in the conversation group, the creating time of the conversation group, the average number of people reading messages in the conversation group, the average number of chat messages per person in the conversation group, the maximum number of chat messages in the conversation group, the number of times that the conversation group is set by people in the group, the recent chat time of the conversation group, the number of people participating in the recent chat time of the conversation group and the number of chat messages in the conversation group.

Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: classifying a plurality of conversation groups according to whether exit events are generated in the conversation groups in the open state or not to obtain a first type sample and a second type sample, wherein the first type sample comprises group state characteristics which are in the open state and enable a user to send out exit conversation groups, and the second type sample is the group state characteristics which are in the open state and do not exit the conversation groups; calculating the Euclidean distance between any two group state features in the first type sample, and selecting two group state features with the Euclidean distance smaller than a first preset threshold value to perform first compression processing to obtain a compressed third type sample; calculating the Euclidean distance between any two group state features in the second type sample, and selecting two group state features with the Euclidean distance smaller than a second preset threshold value to perform second compression processing to obtain a compressed fourth type sample; and transmitting the third type samples and the fourth type samples to a server.

Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: the server receives a third type sample and a fourth type sample from a plurality of clients to obtain a plurality of third type samples and a plurality of fourth type samples; calculating the Euclidean distance between any two feature data in a plurality of third type samples, selecting one of the two feature data with the Euclidean distance smaller than a third preset threshold value for reservation, calculating the Euclidean distance between any two feature data in a fourth type sample, and selecting one of the two feature data with the Euclidean distance smaller than a fourth preset threshold value for reservation; and counting the characteristic values of the sample data reserved in the plurality of third type samples, counting the characteristic values of the sample data reserved in the plurality of fourth type samples, and generating the model file.

Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: and mapping the sample data retained in the plurality of third type samples and the sample data retained in the plurality of fourth type samples to a predetermined data range respectively, and marking the marks in the data range.

Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: distinguishing a characteristic value of a group state characteristic of each session group displayed in a client interface, and acquiring characteristic values of a plurality of first group state characteristics and characteristic values of a plurality of second group state characteristics, wherein the first group state characteristics are used for representing that the session groups are in an open state and generate exit messages, and the second group state characteristics are used for representing that the session groups are in the open state and do not generate the exit messages; and respectively calculating the characteristic values of the plurality of first class group state characteristics and the characteristic values of the plurality of second class group state characteristics by using a Bayesian algorithm to obtain a first probability that each conversation group is in an open state and generates an exit message and a second probability that each conversation group is in the open state and does not generate the exit message.

Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: calculating the exit priority of each conversation group with the same user according to the first probability and the second probability corresponding to each conversation group; and sequencing each conversation group according to the quit priority to obtain the quit sequence of quitting each conversation group.

Example 8

Embodiments of the present application further provide a system, comprising: a processor and a memory, wherein the memory is coupled to the process for providing instructions to the processor for processing the following process steps:

step 402, traversing at least one conversation group, and acquiring user behavior characteristics of each user included in the conversation group;

step 404, obtaining the probability of each user exiting the conversation group according to the user behavior characteristics of each user included in the conversation group;

and step 406, determining whether to output prompt information for exiting the conversation group according to the probability of exiting the conversation group. . Optionally, in this embodiment, the storage medium may be configured to store program codes executed by the method for automatically quitting an instant messaging session group provided in the second embodiment.

It should be noted that the scenarios applied in steps S402 to S406 include, but are not limited to, the disclosure in embodiment two of the present application.

The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.

In the above embodiments of the present application, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.

Claims

1. A system for automatically exiting an instant messaging session group, comprising:

the server is used for providing a model file, wherein the model file pre-stores user behavior characteristics of a session group fed back by at least one client, and the user behavior characteristics of the session group comprise the user behavior characteristics of at least one user in the session group;

the client is communicated with the server and used for traversing at least one session group, acquiring the user behavior characteristics of each user contained in the session group according to the group state characteristics of the session group, acquiring the probability of each user exiting the session group according to the user behavior characteristics of each user contained in the session group, and determining whether to output prompt information for exiting the session group according to the probability of exiting the session group.

2. A method for automatically exiting an instant messaging session group, comprising:

traversing at least one conversation group, and acquiring user behavior characteristics of each user included in the conversation group according to the group state characteristics of the conversation group;

acquiring the probability of each user exiting the conversation group according to the user behavior characteristics of each user contained in the conversation group;

and determining whether to output prompt information for exiting the conversation group according to the probability of exiting the conversation group.

3. The method of claim 2, wherein traversing at least one conversation group to obtain the user behavior characteristics of each user included in the conversation group comprises:

traversing at least one conversation group displayed in a client interface in real time or regularly to obtain users contained in any conversation group, wherein the conversation group corresponds to a conversation window;

detecting at least one group state feature of each user included in the conversation group;

and if the change of at least one group state characteristic of the user is detected, acquiring the user behavior characteristic of the user with the change of the at least one group state characteristic in the conversation group.

4. The method according to claim 3, wherein obtaining the probability of each user exiting the conversation group according to the user behavior characteristics of each user included in the conversation group comprises:

reading a model file, wherein the model file pre-stores user behavior characteristics of a session group fed back by at least one client, and the user behavior characteristics of the session group comprise the user behavior characteristics of at least one user in the session group;

and performing probability calculation on the user behavior characteristics of each user contained in the conversation group according to the user behavior characteristics recorded in the model file to obtain the probability of each user exiting the conversation group.

5. The method of claim 4, wherein if it is detected that at least one group status feature of the user changes, acquiring the user behavior feature of the user with the changed at least one group status feature in the conversation group, comprises:

acquiring at least one group state feature which is changed in the session group;

updating locally stored group status characteristics prior to the session group change;

mapping at least one group state feature of the session group with the changed group state feature to a server, and modifying the group state feature before the session group is changed in the server;

and updating the user behavior characteristics of at least one user in each conversation group pre-stored in the model file according to the updated group state characteristics.

6. The method according to claim 5, wherein performing probability calculation on the user behavior feature of each user included in the conversation group according to the user behavior feature value recorded in the model file to obtain a probability that each user exits the conversation group comprises:

acquiring the characteristic value of the user behavior characteristic of each user displayed in the conversation window according to the characteristic value of the user behavior characteristic of the conversation group recorded in the model file;

and calculating the characteristic value of the user behavior characteristic of each user displayed in the conversation window by using a Bayesian algorithm to obtain the probability of each user exiting each conversation group.

7. The method of claim 6, wherein prior to detecting at least one group status characteristic of each user included in the conversation group, the method further comprises:

opening at least one session group of application software in the client interface, and collecting group state characteristics of each session group;

if the event that the user exits from any session group is detected, the group state characteristics of the user who exits the event are stored, and the group state characteristics of the user who does not exit the session group are obtained;

wherein the group status features include at least one of: the number of people in the conversation group, the number of historical chat messages in the conversation group, the number of people in the conversation group participating in the conversation group, the creation time of the conversation group, the average number of people in the conversation group who are read, the average number of chat messages per person in the conversation group, the maximum number of chat messages in the conversation group, the number of times the conversation group is set to the top of people in the group, the recent chat time of the conversation group, the number of people in the recent chat time of the conversation group, and the number of chat messages in the conversation group.

8. The method of claim 7, wherein after saving the group status feature of the user having the exit event, obtaining the group status feature of each session group in the open state, the method further comprises:

compressing the group state characteristics of each session group in the open state and transmitting the compressed group state characteristics to the server, wherein the step comprises the following steps:

classifying the at least one conversation group according to whether an exit event is generated in the conversation group in the open state or not to obtain a first type sample and a second type sample, wherein the first type sample comprises a group state feature which is in the open state and is used for a user to exit the conversation group, and the second type sample is a group state feature which is in the open state and is not used for exiting the conversation group;

calculating the Euclidean distance between any two group state features in the first type sample, and selecting two group state features with the Euclidean distance smaller than a first preset threshold value to perform first compression processing to obtain a compressed third type sample;

calculating the Euclidean distance between any two group state features in the second type sample, and selecting two group state features of which the Euclidean distance is smaller than a second preset threshold value to perform second compression processing to obtain a compressed fourth type sample;

transmitting the third type of sample and the fourth type of sample to the server.

9. The method of claim 8, wherein after transmitting the third type of sample and the fourth type of sample to the server, the method further comprises:

the server receives a third type sample and a fourth type sample from a plurality of clients to obtain a plurality of third type samples and a plurality of fourth type samples;

calculating the Euclidean distance between any two feature data in the plurality of third type samples, selecting one of the two feature data with the Euclidean distance smaller than a third preset threshold value for reservation, calculating the Euclidean distance between any two feature data in the fourth type samples, and selecting one of the two feature data with the Euclidean distance smaller than a fourth preset threshold value for reservation;

and counting the characteristic values of the sample data retained in the plurality of third type samples, counting the characteristic values of the sample data retained in the plurality of fourth type samples, and generating the model file.

10. The method according to claim 9, wherein the feature values are used to characterize the occurrence frequency and occurrence number of the group state features of each session group returned by the plurality of clients, and wherein before counting the feature values of the sample data retained in the plurality of third type samples and counting the feature values of the sample data retained in the plurality of fourth type samples, the method further comprises:

and mapping the sample data retained in the plurality of third type samples and the sample data retained in the plurality of fourth type samples to a predetermined data range respectively, and marking the marks in the data range.

11. The method according to any one of claims 6 to 10, wherein the calculating the feature value of the group state feature of each session group displayed in the client interface by using a bayesian algorithm to obtain the probability of each user exiting each session group comprises:

distinguishing a characteristic value of a group state characteristic of each session group displayed in the client interface, and acquiring characteristic values of a plurality of first group state characteristics and characteristic values of a plurality of second group state characteristics, wherein the first group state characteristics are used for representing that each session group is in an open state and generates an exit message, and the second group state characteristics are used for representing that each session group is in the open state and does not generate the exit message;

and respectively calculating the characteristic values of the plurality of first class group state characteristics and the characteristic values of the plurality of second class group state characteristics by using the Bayesian algorithm to obtain a first probability that each session group is in an open state and generates an exit message and a second probability that each session group is in the open state and does not generate the exit message.

12. The method of claim 11, wherein ranking all conversation groups according to the probability of each user exiting each conversation group, and obtaining an exiting order for exiting each conversation group comprises:

calculating the exit priority of each conversation group with the same user according to the first probability and the second probability corresponding to each conversation group;

and sequencing each conversation group according to the quit priority to obtain a quit sequence for quitting each conversation group.

13. An apparatus for automatically exiting an instant messaging session group, comprising:

the first acquisition module is used for traversing at least one conversation group and acquiring the user behavior characteristics of each user contained in the conversation group according to the group state characteristics of the conversation group;

the second acquisition module is used for acquiring the probability of each user exiting the conversation group according to the user behavior characteristics of each user contained in the conversation group;

and the determining module is used for determining whether to output prompt information for exiting the conversation group according to the probability for exiting the conversation group.

14. A method of exiting a cluster, comprising:

according to the group state characteristics of the first group, acquiring user behavior characteristics of a plurality of users contained in the first group;

acquiring the probability of at least one user exiting the first group according to the user behavior characteristics of the plurality of users;

and determining whether to output prompt information for exiting the first group or not according to the probability.

15. The method of claim 14, wherein the first group is an instant messaging group.

16. The method of claim 14, wherein the first group is a mail group.

17. An apparatus for exiting a cluster, comprising:

the first acquisition unit is used for acquiring user behavior characteristics of a plurality of users contained in a first group according to the group state characteristics of the first group;

the second obtaining unit is used for obtaining the probability that at least one user exits the first group according to the user behavior characteristics of the plurality of users;

and the determining unit is used for determining whether to output prompt information for exiting the first group or not according to the probability.

18. A storage medium, comprising a stored program, wherein the program, when executed, controls a device on which the storage medium is located to perform the method for automatically exiting an instant messaging session group according to any one of claims 2 to 12.

19. A processor, characterized in that the processor is configured to run a program, wherein the program when running performs the method of automatically exiting an instant messaging session group according to any one of claims 2 to 12.

20. An electronic device, comprising:

a processor; and

a memory coupled to the processor for providing instructions to the processor for processing the following processing steps:

step S402, traversing at least one conversation group, and acquiring the user behavior characteristics of each user included in the conversation group according to the group state characteristics of the conversation group;

step S404, obtaining the probability of each user exiting the conversation group according to the user behavior characteristics of each user contained in the conversation group;

step S406, determining whether to output prompt information for exiting the conversation group according to the probability of exiting the conversation group.