CN116166893A - Interactive topic positioning and display method, device, equipment and storage medium - Google Patents

Abstract

This application discloses a method, device, device and storage medium for locating and displaying interactive topics, which relate to the field of computer technology and are used to improve the efficiency of locating interactive topics and protect the privacy of member objects participating in the interaction. The method includes: When the target object enters the target group, for the specified historical time period, the interactive behavior indicators corresponding to each candidate bucket associated with the target group are obtained; from each candidate bucket, it is determined that the interactive behavior indicator satisfies the topic heat peak condition At least one target bucket; for each target bucket in the at least one target bucket, based on the correlation between the interaction messages whose generation time is before the creation time of each target bucket, respectively determine the respective corresponding The starting point position of the interactive topic; based on the determined starting point positions, the target group operation interface corresponding to the target object is presented.

Description

Interactive topic positioning and display method, device, equipment and storage medium

technical field

The present application relates to the field of computer technology, and provides an interactive topic positioning and display method, device, equipment and storage medium.

Background technique

With the development of communication technology, the use of instant messaging applications is becoming more and more common. In instant messaging applications, there are scenarios where multiple member objects participate in the interaction, such as group chat scenarios. In this multi-member object participation scenario, once too many member objects participate, or the interaction If the rate is too high, it is very likely that a large number of historical interaction messages will be generated, and newly entered member objects need to spend a lot of time to check these historical interaction messages in order to learn the historical interaction content of other member objects.

At present, in order to assist member objects to quickly understand the interactive content, the topic corresponding to the historical interactive content may be located by an interactive topic identification method, thereby helping the member object to quickly understand the historical interactive content.

However, the current interactive topic recognition methods are usually implemented by analyzing texts using neural networks such as semantic recognition. Whether each interactive text belongs to the same topic. Obviously, this method needs to obtain the text content of the member object, which is easy to touch the privacy of the member object, and the text analysis through the neural network requires a large amount of calculation, which consumes a lot of resources and takes a long time, making the interaction The efficiency of topic identification is not high.

Contents of the invention

Embodiments of the present application provide a method, device, device, and storage medium for locating and displaying interactive topics, which are used to improve the efficiency of locating interactive topics and protect the privacy of member objects participating in the interaction.

On the one hand, a method for locating an interactive topic is provided, and the method includes:

When the target object enters the target group, for the specified historical time period, obtain the interactive behavior indicators corresponding to each candidate bucket associated with the target group, wherein each candidate bucket contains: In a sub-time period, the interactive messages generated by the target group;

From each of the candidate buckets, determine at least one target bucket whose interaction behavior index satisfies the topic popularity peak condition;

For each target bucket in the at least one target bucket, based on the correlation between the interaction messages whose generation time is before the creation time of each target bucket, respectively determine the respective corresponding The location of the starting point of the interactive topic;

Based on the determined starting point positions, a target group operation interface corresponding to the target object is presented.

On the one hand, a method for displaying interactive topics is provided, the method comprising:

In response to the trigger operation of the target object entering the target group, a target group operation interface corresponding to the target object is presented; wherein, the target group operation interface displays interactive messages generated by the target group within a historical time period ;

In response to a trigger operation on the topic jump control in the target group operation interface, jump to the starting point of the corresponding interactive topic in the historical time period for display.

In one aspect, an interactive topic locating device is provided, the device comprising:

The behavior indicator acquisition unit is used to acquire the interactive behavior indicators corresponding to each candidate bucket associated with the target group for a specified historical time period when the target object enters the target group, wherein each candidate bucket contains : an interactive message generated by the target group within a sub-time period in the historical time period;

A topic peak positioning unit, configured to determine at least one target bucket whose interactive behavior index satisfies the topic heat peak condition from the candidate buckets;

The starting point locating unit is configured to, for each target bucket in the at least one target bucket, determine the at least The starting point position of the interactive topic corresponding to each target bucket;

The interface presentation unit is configured to present the target group operation interface corresponding to the target object based on the determined starting point positions.

Optionally, the behavior index acquisition unit is also used for:

receiving at least one interactive message sent by the member objects in the target group;

If the time difference between the current moment and the end moment of the previous sub-time period is not greater than the bucketing time difference threshold, based on the interactive behavior index corresponding to the at least one interactive message, update the created candidate bucket, the most recently created The interactive behavior indicators of candidate buckets;

If the time difference is greater than the bucketing time difference threshold, create a candidate bucket, and update the interaction behavior indicator of the newly created candidate bucket based on the interaction behavior indicator corresponding to the at least one interactive message.

Optionally, the interactive behavior indicator is the number of interactive messages; the topic peak positioning unit is specifically used for:

Based on the number of interactive messages corresponding to each of the candidate buckets, determine the threshold of the number of interactive messages when the topic popularity peak condition is met in the historical time period;

For each of the candidate buckets, perform the following operations: for a candidate bucket, if the number of interactive messages corresponding to it is greater than the threshold of the number of interactive messages, determine the candidate bucket as the target bucket.

Optionally, the topic peak positioning unit is specifically used for:

Based on the number of interactive messages in each candidate bucket, determine the mean value of the number of interactive messages in each candidate bucket;

Based on the group business type of the target group, determine the topic peak coefficient corresponding to the target group;

Based on the mean value of the number of interactive messages and the peak coefficient of the topic, the threshold of the number of interactive messages is determined.

Optionally, the interactive behavior indicator is the number of member objects participating in the interaction; the topic peak positioning unit is specifically used for:

Determine the number of member objects that are not recorded in the last created candidate bucket among the member objects corresponding to the at least one interactive message;

On the basis of the number of member objects recorded in the last created candidate bucket, the number of unrecorded member objects is accumulated.

Optionally, the topic peak positioning unit is specifically used for:

Based on the number of member objects recorded in each candidate bucket, determine the threshold of the number of member objects when the topic heat peak condition is met in the historical time period;

For each of the candidate buckets, the following operations are respectively performed: for a candidate bucket, if the number of recorded member objects is greater than the threshold of the number of member objects, determine the candidate bucket as the target bucket.

Optionally, the interactive behavior index includes the number of interactive messages and the number of member objects; the topic peak positioning unit is specifically used for:

For each of the candidate buckets, perform the following operations:

For a candidate bucket, determine whether the corresponding interactive message quantity is greater than the interactive message quantity threshold;

If the number of interactive messages is greater than the threshold of the number of interactive messages, determine whether the number of recorded member objects is greater than the threshold of the number of member objects;

If the number of member objects is greater than the threshold of the number of member objects, determine a candidate bucket as the target bucket.

Optionally, the starting point positioning unit is specifically used for:

For each of the target buckets, perform the following operations:

For a target bucket, starting from the interaction message with the earliest generation time in the target bucket, determine the generation time of each interaction message one by one, and whether the time difference between the generation time of the previous interaction message and the generation time of the previous interaction message is greater than the generation time difference threshold , until a target interaction message with a time difference greater than the generation time difference threshold appears;

The target interaction message is determined as the starting point of the interaction topic corresponding to the one target bucket.

Optionally, the starting point positioning unit is specifically used for:

Determine the degree of overlap between the member objects corresponding to each interaction message between the target interaction message and the interaction message at the earliest generation time, and the member objects corresponding to the one target bucket;

If the coincidence degree is not less than the coincidence degree threshold, it is determined that the previous interaction message of the target interaction message is the starting point of the interaction topic corresponding to the one target bucket.

Optionally, the device also includes a topic merging unit, configured to:

For each determined starting point position, perform the following operations:

For a starting point location, if the interaction message between the starting point location and the corresponding first target bucket has covered the interaction message of the second target bucket, then the first target bucket and the first target bucket Merge interactive topics corresponding to the second target bucket.

Optionally, the interface presentation unit is also used for:

In response to the operation performed on the topic jump control in the target group operation interface, jump from the current interactive topic area to the starting point of other interactive topics for display.

In one aspect, an interactive topic display device is provided, the device comprising:

An operation interface switching unit, configured to present a target group operation interface corresponding to the target object in response to a trigger operation that the target object enters the target group; wherein, the target group operation interface displays the Interactive messages generated by target groups;

The topic jump unit is configured to jump to the starting point of the corresponding interactive topic in the historical time period for display in response to a trigger operation on the topic jump control in the target group operation interface.

Optionally, a top jump control is displayed in the target group operation interface, and the top jump control is used to jump to the position of the first interactive message in the historical time period;

Then the device also includes a message jump unit for:

In response to the trigger operation performed on the top jump control, jump to the first interactive message position in the historical time period for display; and,

The topic jump control is displayed on the target group operation interface.

Optionally, the topic jump control is used to jump to the next interactive topic;

Then the topic jump unit is specifically used for:

In response to a trigger operation performed on the topic jump control, jump from the current interactive message position to the starting point of the next interactive topic for display.

Optionally, the topic jump control includes topic jump sub-controls for jumping to each interactive topic in the historical time period, and each topic jump sub-control corresponds to an interactive topic;

Then the topic jump unit is specifically used for:

In response to a trigger operation on the target topic jump sub-control in each topic jump sub-control, jump from the current interactive message position to the starting point of the interactive topic corresponding to the target topic jump sub-control for display.

Optionally, the device also includes a topic positioning unit, configured to:

For a specified historical time period, obtain the interactive behavior indicators corresponding to each candidate bucket associated with the target group, wherein each candidate bucket includes: within a sub-time period in the historical time period, the Interactive messages generated by target groups;

From each of the candidate buckets, determine at least one target bucket whose interaction behavior index satisfies the topic popularity peak condition;

For each target bucket in the at least one target bucket, based on the correlation between the interaction messages whose generation time is before the creation time of each target bucket, respectively determine the respective corresponding The location of the starting point of the interactive topic.

In one aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and operable on the processor, and the processor implements the steps of any one of the above methods when executing the computer program.

In one aspect, a computer storage medium is provided, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the steps of any one of the above methods are implemented.

In one aspect there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps of any one of the above-mentioned methods.

In the embodiment of this application, when the target object enters the target group, the interactive messages in the historical time period are divided into multiple candidate buckets according to each sub-time period, and the interactive behavior indicators of each candidate bucket are obtained through statistics, so that When the target object enters the target group, the target bucket that meets the peak heat condition of the topic can be determined from each candidate bucket based on the interactive behavior index. Each target bucket is the peak heat area of an interactive topic, and then passed The correlation of the interactive messages before each target bucket is used to locate the starting point of the interactive topic corresponding to each target bucket, so as to present the corresponding target group operation interface. It can be seen that by analyzing the interactive behavior in the group, there is no need to obtain the content of the interactive text, and the privacy of the member objects in the group will not be involved. Moreover, through the analysis of the interactive behavior, the amount of calculation is far less than the identification through the interactive text The method requires less computing resources, and can locate interactive topics more quickly.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the accompanying drawings that need to be used in the description of the embodiments or related technologies. Obviously, the accompanying drawings in the following description are only For the embodiment of the application, those skilled in the art can also obtain other drawings according to the provided drawings without making creative efforts.

FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the present application;

FIG. 2 is a schematic flow diagram of an interactive topic locating method provided in an embodiment of the present application;

FIG. 3 is a schematic flowchart of determining the threshold of the number of interactive messages provided by the embodiment of the present application;

FIG. 4 is a schematic flowchart of determining the threshold of the number of member objects provided by the embodiment of the present application;

FIG. 5 is a schematic flow diagram of determining target bucketing provided by the embodiment of the present application;

FIG. 6 is a schematic flow chart of counting interactive behavior indicators of candidate buckets provided by the embodiment of the present application;

FIG. 7 is a schematic flow diagram of a chat topic location process in a chat group provided by an embodiment of the present application;

FIG. 8 is a schematic flowchart of an interactive topic display method provided by an embodiment of the present application;

FIG. 9a and FIG. 9b are schematic display diagrams of the chat group page provided by the embodiment of the present application;

Fig. 10a and Fig. 10b are schematic diagrams of the effect of the interactive topic positioning method provided by the embodiment of the present application;

FIG. 11 is a schematic structural diagram of an interactive topic locating device provided by an embodiment of the present application;

FIG. 12 is a schematic structural diagram of an interactive topic display device provided by an embodiment of the present application;

FIG. 13 is a schematic structural diagram of a computer device provided by an embodiment of the present application.

Detailed ways

In order to make the purpose, technical solutions and advantages of the application clearer, the technical solutions in the embodiments of the application will be clearly and completely described below in conjunction with the drawings in the embodiments of the application. Obviously, the described embodiments are only It is a part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application. In the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined arbitrarily with each other. Also, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

In order to facilitate the understanding of the technical solutions provided by the embodiments of the present application, some key terms used in the embodiments of the present application are first explained here:

Group: Consists of multiple member objects, such as group chats, live broadcasts, or games where multiple people participate. Taking group chat as an example, each member object can send an interactive message in the group, and the interactive message sent by it will be forwarded to all member objects in the group, and all member objects can view it.

Interactive message: refers to the message triggered by the member object in the group through interactive behavior. Taking group chat as an example, the interactive message can refer to the group chat message sent by the member object, which can include text, link and picture, etc. Taking a live broadcast as an example, members who enter the live broadcast room can also interact in the live broadcast room to trigger interactive messages, such as comments, likes, or other interactive behaviors in the live broadcast room.

Bucketing: According to a certain duration, the interactive messages sent by the member objects in the group are grouped, and each group is a bucketing. Taking group chat as an example, a bucket can be created every 10 minutes, and a bucket includes all interactive messages generated within every 10 minutes.

Topic popularity peak: In the interaction in a multi-member object participation group, there is usually one or more popularity peak periods around an interactive topic. During this popularity peak period, there may be more participants or more interactive behaviors.

The following briefly introduces the design idea of the embodiment of the present application.

In instant messaging applications, there are scenarios where multiple member objects participate in the interaction, such as group chat scenarios. In order to assist member objects to quickly understand the interactive content, the method of interactive topic identification can be used to locate the topic corresponding to the historical interactive content, thereby helping Member objects provide a quick overview of the content of historical interactions.

However, the current method of interactive topic recognition is usually implemented by analyzing the text using a neural network such as semantic recognition. This method needs to obtain the text content of the member object, which is easy to touch the privacy of the member object, and is carried out through the neural network. Text analysis requires a large amount of calculation, which consumes a lot of resources and takes a long time, which makes the efficiency of interactive topic identification not high. In addition, in the process of text interaction, the text may be scattered in multiple interactive messages, which makes it difficult for the semantic recognition algorithm to recognize such scattered sentences, so there are recognition errors. Moreover, semantic recognition only supports text messages, and it is difficult for semantic recognition algorithms to recognize more meaningful sentences. Emoticons, links, etc., are usually not recognized by semantic recognition algorithms.

Considering that when the core topic of group chat appears, the number of participants and the volume of messages will increase sharply in a unit time. Through this phenomenon, the core topic can be located.

In view of this, the embodiment of the present application provides an object-based retrieval method. In this method, by directly analyzing the interactive behavior, it is separated from the text analysis and avoids the need to carry out various information forms such as text, pictures, emoticons, and links. However, for the positioning of interactive topics, there is a simpler implementation method, and the effect is ideal.

Specifically, when the target object enters the target group, the interactive messages in the historical time period are divided into multiple candidate buckets according to each sub-time period, and the interactive behavior indicators of each candidate bucket are obtained through statistics, so that the target When the object enters the target group, the target bucket that satisfies the peak heat condition of the topic can be determined from each candidate bucket based on the interactive behavior indicators. Each target bucket is the peak heat area of an interactive topic, and then through each The relevance of the interactive messages before the target bucket is used to locate the starting point of the interactive topic corresponding to each target bucket, so as to present the corresponding target group operation interface. It can be seen that by analyzing the interactive behavior in the group, there is no need to obtain the content of the interactive text, and the privacy of the member objects in the group will not be involved. Moreover, through the analysis of the interactive behavior, the amount of calculation is far less than the identification through the interactive text The method requires less computing resources, and can locate interactive topics more quickly.

The following briefly introduces the applicable application scenarios of the technical solutions of the embodiments of the present application. It should be noted that the application scenarios described below are only used to illustrate the embodiments of the present application and not limit them. In the specific implementation process, the technical solutions provided by the embodiments of the present application can be flexibly applied according to actual needs.

The solutions provided by the embodiments of the present application can be applied to most interactive scenarios involving multi-member objects, such as group chat, live broadcast, or game scenarios. As shown in FIG. 1 , it is a schematic diagram of an application scenario provided by the embodiment of the present application. In this scenario, multiple terminal devices 101 and servers 102 may be included.

The terminal device 101 may be, for example, a mobile phone, a tablet computer (PAD), a notebook computer, a desktop computer, a smart TV, a smart vehicle-mounted device, and a smart wearable device. The terminal device 101 may be installed with a group interaction application capable of participation by multiple member objects, such as an instant messaging application, a live broadcast application, or a game application. Understandably so. The application involved in the embodiment of the present application may be a software client, or a client such as a web page or a small program, and the server is a background server corresponding to the software, web page, or small program, etc., and the specific type of the client is not limited.

The server 102 may be a background server corresponding to the group interaction application installed on the terminal device 101, which may provide background services for multi-member objects participating in the interaction in the same group. For example, it can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or it can provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, intermediate Cloud servers for basic cloud computing services such as software services, domain name services, security services, content distribution network (Content Delivery Network, CDN), and big data and artificial intelligence platforms, but are not limited thereto.

The method steps in this embodiment of the present application may be executed by the terminal device 101 or by the server 102 . Taking execution of the terminal device 101 as an example, the terminal device 101 may include one or more processors, memories, and interactive I/O interfaces, and the like. Wherein, the memory of the terminal device 101 may store program instructions of the interactive topic locating method provided by the embodiment of the present application, and these program instructions can be used to implement the steps of the interactive topic locating method provided by the embodiment of the present application when executed by the processor.

Specifically, for a target object, when the member objects in the group perform interactive behaviors, the target object will also receive interactive messages. In order to facilitate the positioning of subsequent interactive topics, it can be divided according to time periods. The received interaction messages are managed in buckets, and when the target object enters the group (such as opening the interface of the group), it can be determined from each candidate bucket based on the interactive behavior indicators of each candidate bucket The target bucket of the topic heat peak condition, each target bucket is the heat peak area of an interactive topic, and then locate the interaction corresponding to each target bucket through the correlation of the interaction messages before each target bucket The starting point of the topic to present the corresponding target group operation interface.

Taking the interactive scenario as a group chat scene as an example, multiple users use their own instant messaging accounts to conduct group chats in their group A. Taking user 1 as an example, when user 1 does not open the interface of group A , the chat process in group A can also be continuous, that is, if other users in the group are sending chat messages, user 1 will still receive chat messages, and during this process, it can be carried out according to the time period Divide, manage the received chat messages in buckets, and when user 1 enters group A, it will divide the unread interactive messages according to the interactive behavior indicators such as the number of messages in each chat message or the number of participating users, etc. Select the chat topic peak areas from the chat message buckets, and trace back the chat messages based on these chat topic peak areas to locate the starting point of each chat topic, and then provide users with shortcuts to jump topics and quickly enter each chat topic. Chat topics, browse chat messages.

Each terminal device 101 and the server 102 can be directly or indirectly connected through one or more networks 103 . The network 103 may be a wired network or a wireless network. For example, the wireless network may be a mobile cellular network, or may be a Wireless-Fidelity (Wireless-Fidelity, WIFI) network, or other possible networks. Examples are not limited to this.

In a possible application scenario, relevant data (such as interactive topics and interactive message hash values, etc.) and model parameters involved in the embodiments of the present application may be stored using cloud storage technology. Cloud storage is a new concept extended and developed from the concept of cloud computing. Distributed cloud storage system refers to a large number of different types of storage in the network through functions such as cluster application, grid technology and distributed storage file system. Devices (or storage nodes) work together through application software or application interfaces to jointly provide a storage system with data storage and service access functions.

In a possible application scenario, in order to reduce communication delay, servers 102 can be deployed in various regions, or for load balancing, different servers 102 can serve terminal devices 101 in different regions, for example, terminal devices 101 Located at location a, it establishes a communication connection with the server 102 at service location a. The terminal device 101 is located at location b, and establishes a communication connection with the server 102 at service location b. Multiple servers 102 form a data sharing system, and data sharing is realized through blockchain. shared.

For each server 102 in the data sharing system, there is a node identification corresponding to the server 102, and each server 102 in the data sharing system can store node identifications of other servers 102 in the data sharing system, so that subsequent The node identification of the server 102 broadcasts the generated block to other servers 102 in the data sharing system. Each server 102 may maintain a node identification list, and the name of the server 102 and the node identification are correspondingly stored in the node identification list. Wherein, the node identifier may be an Internet protocol (Internet Protocol, IP) address and any other information that can be used to identify the node.

Of course, the method provided in the embodiment of the present application is not limited to the application scenario shown in FIG. 1 , and can also be used in other possible application scenarios, which is not limited by the embodiment of the present application. The functions that can be realized by each device in the application scenario shown in FIG. 1 will be described together in subsequent method embodiments, and will not be repeated here.

The method flow provided in each embodiment of the present application can be executed by the server 102 or the terminal device 101 in FIG. 1 , or can be executed jointly by the server 102 and the terminal device 101. Here, the execution by the terminal device 101 is mainly used as an example for introduction. .

Referring to FIG. 2 , it is a schematic flow chart of the interactive topic locating method provided by the embodiment of the present application.

Step 201: When the target object enters the target group, for the specified historical time period, obtain the interactive behavior indicators corresponding to each candidate bucket associated with the target group, wherein each candidate bucket includes: in the historical time period Interaction messages generated by the target group within a sub-time period.

In the embodiment of the present application, each group can include multiple member objects, and each member object can also belong to multiple groups. For the convenience of description, here is a specific group, that is, the above-mentioned target group as an example. Introduction, when a member object belongs to multiple groups, the process performed by each group may be similar, so please refer to the subsequent introduction.

In one embodiment, the target object entering the target group may refer to the process of opening the operation interface of the target group, that is, the target object has joined the target group and has become a member object in the target group, then the target object can Enter the operation interface of the target group to view the interactive messages sent by other member objects, and also perform interactive operations to send interactive messages to other member objects.

In another implementation manner, the target object entering the target group may also refer to the target object joining the target group, that is, the target object joins the target group through any way of adding groups, and becomes a member object of the target group.

In practical applications, the specified historical time period may refer to the time period between the last time the target object left the operation interface of the target group and the current moment, then the interactive messages in the historical time period are essentially the unread messages of the target object. Interactive messages; or, the specified historical time period can also refer to any time period after the target object joined the target group; or, the specified historical time period can also be a specified period of time before the target object joined the target group . Of course, the specified historical time period may also be any time period specified by the target object, which is not limited in this embodiment of the present application.

In the embodiment of this application, each candidate bucket contains interactive messages generated by the target group in a sub-time period in the historical time period, and each candidate bucket corresponds to a sub-time period, and the duration of different sub-time periods can be the same. It can also be different. In addition, the duration of the sub-time period can also be set according to actual needs. Taking the same duration of each sub-time period as an example, the duration of the sub-time period can be set to 10 minutes, that is, a candidate bucket is created every 10 minutes, and each Candidate buckets are used to record interactive messages generated within every 10 minutes. Certainly, the duration of the sub-time period may also be other possible values, which is not limited in this embodiment of the present application.

In the embodiment of the present application, the interactive behavior index is a quantitative index parameter of the interactive message generated by the interactive behavior in the candidate bucket, which can be used to represent the degree of hotness of topic discussion in a candidate bucket. For example, the interactive behavior indicator can be the number of interactive messages. When the number of interactive messages in a candidate bucket is larger, it indicates that the candidate bucket is a topic peak area of an interactive topic. On the contrary, when a candidate bucket has The smaller the number of interactive messages, the lower the probability that the candidate bucket is the topic peak area of an interactive topic; or, the action behavior index can also be the number of member objects participating in the interaction, when the member objects participating in the interaction in a candidate bucket The larger the number of objects, the higher the probability that the candidate bucket is a topic peak area of an interactive topic. The probability of the topic peak area of the interactive topic is lower. Certainly, the interactive behavior index may be other possible quantitative indexes, which is not limited in this embodiment of the present application.

In one embodiment, when the target object enters the target group, the interactive messages in the historical time period can be counted according to the duration of the sub-time period, and each sub-time period corresponds to a candidate bucket, so as to obtain each candidate bucket Corresponding interactive behavior indicators.

In another implementation, the interactive behavior indicators of each candidate bucket can also be counted in advance and stored, then when the target object enters the target group, the interactive behavior of each candidate bucket can be read from the local storage index.

Step 202: From each candidate bucket, determine at least one target bucket whose interaction behavior index satisfies the peak condition of topic popularity.

In the embodiment of this application, the target bucketing meets the topic heat peak condition, that is, the target bucketing is equivalent to the topic peak area of an interactive topic, which can be judged by the interactive behavior indicators. The following will introduce different interactive behavior indicators respectively. .

(1) The interactive behavior indicator is the number of interactive messages

When the interactive behavior indicator is the number of interactive messages, the topic popularity peak condition can be set as the number of interactive messages in candidate buckets must be greater than the threshold of the number of interactive messages.

In an implementation manner, the threshold of the number of interactive messages may be set to a larger fixed value, that is, if the number of interactive messages corresponding to a candidate bucket exceeds the set fixed value, the candidate bucket is considered to meet the topic popularity peak condition.

For example, the peak popularity condition of a topic can be set to be that the number of interactive messages exceeds 200, then when the number of interactive messages in a candidate bucket exceeds 200, the candidate bucket can be determined as the target bucket.

In another implementation manner, the specific value of the interactive message quantity threshold may be adjusted according to the specific interactive message quantity of each candidate bucket, so that the topic peak area in the historical time period can be more flexibly determined. Specifically, based on the number of interactive messages corresponding to each candidate bucket, determine the threshold of the number of interactive messages in the historical time period when the topic heat peak condition is met, that is, first determine how many interactive messages are defined as the topic heat peak conditions.

Referring to FIG. 3 , it is a schematic flowchart of determining the threshold of the number of interactive messages.

S30: Based on the number of interactive messages in each candidate bucket, determine an average value of the number of interactive messages in each candidate bucket.

For example, X candidate buckets are recorded in the historical time period, and the corresponding numbers of interactive messages are respectively M1, M2, M3, ..., Mx, then the average number of interactive messages N can be:

S31: Based on the group business type of the target group, determine a topic peak coefficient corresponding to the target group.

In the embodiment of this application, considering the groups of different business types, the difference in the number of interactive messages is relatively large, so it is possible to consider the business type and assign different topic peak systems to different groups, so as to more accurately locate different businesses The position of the interactive topic in the group of the type.

S32: Determine the threshold value of the number of interactive messages based on the mean value of the number of interactive messages and the peak coefficient of the topic.

Specifically, the threshold of the number of interactive messages may be, for example, the product of the mean value of the number of interactive messages and the peak coefficient of the topic, that is, the threshold N' of the number of interactive messages may be expressed as follows:

N'=N*Y

Wherein, Y is a topic peak coefficient, for example, it may take a value of 300%, and it is adjusted according to actual services.

After determining the threshold of the number of interactive messages, for each candidate bucket, when the number of interactive messages corresponding to a candidate bucket is greater than the threshold of the number of interactive messages, the candidate bucket is determined to be the target bucket, that is, the candidate bucket is defined as the peak area of discussion for a topic.

(2) The interactive behavior indicator is the number of member objects participating in the interaction

When the interactive behavior indicator is the number of member objects, the topic popularity peak condition can be set as the number of member objects in the candidate bucket must be greater than the threshold of the number of member objects.

In an implementation manner, the threshold of the number of member objects can be set to a larger fixed value, that is, if the number of member objects corresponding to a candidate bucket exceeds the set fixed value, the candidate bucket is considered to meet the topic popularity peak condition.

For example, the topic popularity peak condition can be set as the number of member objects exceeds 5, then when the number of member objects in a candidate bucket exceeds 5, the candidate bucket can be determined as the target bucket.

In another implementation manner, the specific value of the threshold of the number of member objects may be adjusted according to the number of specific member objects of each candidate bucket, so that the topic peak area in the historical time period can be more flexibly determined. Specifically, based on the number of member objects corresponding to each candidate bucket, determine the threshold of the number of member objects when the topic heat peak condition is met in the historical time period, that is, first determine how many member objects are defined as the topic heat peak conditions.

Referring to FIG. 4 , it is a schematic flowchart of determining the threshold of the number of member objects.

S40: Based on the number of member objects in each candidate bucket, determine an average value of the number of member objects in each candidate bucket.

For example, X candidate buckets are recorded in the historical time period, and the number of member objects corresponding to each is P1, P2, P3, ..., Px, then the mean value Z of the number of member objects can be:

S41: Based on the group service type of the target group, determine a topic peak coefficient corresponding to the target group.

S42: Determine the threshold of the number of member objects based on the mean value of the number of member objects and the peak coefficient of the topic.

Specifically, the threshold of the number of member objects can be, for example, the product of the mean value of the number of member objects and the peak coefficient of the topic, that is, the threshold Z' of the number of member objects can be expressed as follows:

Z'=Z*Y

After determining the threshold of the number of member objects, for each candidate bucket, when the number of member objects corresponding to a candidate bucket is greater than the threshold of the number of member objects, the candidate bucket is determined to be the target bucket, that is, the candidate bucket is defined as the peak area of discussion for a topic.

(3) Interactive behavior indicators include the number of interactive messages and the number of member objects

In the embodiment of the present application, the topic peak condition can be set based on various parameters to improve the accuracy of determining the topic peak area.

Specifically, the target bucket can be determined on the basis of the number of interactive messages, and the number of member objects can be used as a verification. When both are satisfied, it is determined that a bucket is indeed a topic peak area.

Referring to FIG. 5 , it is a schematic flow diagram of determining target bucketing. Here, a candidate bucket A is taken as an example to introduce the process of determining whether the candidate bucket A is a target bucket.

S50: For candidate bucket A, determine whether the number of interactive messages corresponding to it is greater than a threshold for the number of interactive messages.

S51: If the number of interactive messages is greater than the threshold of the number of interactive messages, that is, the determination result of step S50 is Yes, determine whether the number of member objects recorded in the candidate bucket A is greater than the threshold of the number of member objects.

S52: If the number of member objects is greater than the threshold of the number of member objects, that is, the determination result of step S51 is Yes, determine the candidate bucket A as the target bucket.

S53: If the number of interactive messages is not greater than the threshold of the number of interactive messages, or if the number of member objects is not greater than the threshold of the number of member objects, that is, the determination result of step S50 or step S51 is No, determine that the candidate bucket A is not the target bucket.

Step 203: For each target bucket in at least one target bucket, based on the correlation between the interaction messages whose generation time is before the creation time of each target bucket, respectively determine the interaction topics corresponding to at least one target bucket The starting point position.

In the embodiment of the present application, since the determination process of the starting point position of each target bucket is similar, one target bucket is taken as an example for introduction here.

In one embodiment, for the target bucket B, starting from the interaction message with the earliest generation time in the target bucket B, the time difference between the generation time of each interaction message and the generation time of the previous interaction message is determined one by one Whether it is greater than the generation time difference threshold, until a target interaction message with a time difference greater than the generation time difference threshold appears, and then determine the previous interaction message of the target interaction message as the starting point position of the interaction topic corresponding to a target bucket.

That is to say, starting from the first interactive message in the target bucket B, go back to the previous message, if the time difference between the previous interactive message and the first interactive message is not greater than the generation time difference threshold, continue to select the previous interactive message The previous interactive message is determined until a target interactive message with a time difference greater than the generation time difference threshold appears.

The above-mentioned at least one target bucket can be used to determine the target interaction message in the above-mentioned manner.

In a specific application, the generation time difference threshold can be adjusted according to experimental results, for example, it can be 10 minutes, and of course, it can also be other possible values, which are not limited in this embodiment of the present application.

In another implementation manner, after the target interaction message is determined in the above manner, it may also be verified whether the previous interaction topic matches the target bucket B by verifying the coincidence degree of the member objects.

Specifically, it is possible to determine the degree of overlap between the member objects corresponding to each interaction message between the target interaction message and the first interaction message of the target bucket B, and the member objects corresponding to the target bucket B, if the coincidence degree is not less than The overlapping degree threshold determines that the previous interactive message of the target interactive message is the starting point of the interactive topic corresponding to the target bucket B.

For example, if the overlap threshold is set to 50%, the member objects corresponding to each interaction message between the target interaction message and the first interaction message in target bucket B are member objects 2 to 4, and the member objects corresponding to target bucket B are For member objects 2 to 5, there are 3 overlapping member objects, and the coincidence degree is not less than 50%, then it is determined that the target interaction message is indeed the starting point of the interaction topic corresponding to the target bucket B, otherwise you can start from the target interaction message Backtracking, determine the interactive message whose coincidence degree satisfies the condition, and use it as the starting point position.

In the embodiment of this application, it is also considered that an interactive topic may be divided into multiple topic slices, that is to say, multiple target buckets may belong to the same interactive topic, then these topics can be merge.

Specifically, after determining the starting point position, if the interaction message between the starting point position and the corresponding first target bucket has covered the interaction message of the second target bucket, then the first target bucket and the second target bucket The target buckets should belong to the same interactive topic, then the interactive topics corresponding to the first target bucket and the second target bucket can be merged.

Of course, in practical applications, if the coincidence degree of the starting point position with the interaction message between the corresponding first target bucket and the interaction message with the second target bucket exceeds a certain threshold, it can also be considered that the first target bucket The bucket and the second target bucket should belong to the same interactive topic, and the interactive topics corresponding to the first target bucket and the second target bucket can also be merged.

Step 204: Present the target group operation interface corresponding to the target object based on the determined starting point positions.

In the embodiment of the present application, after the starting point position of each interactive topic is determined, after the target object enters the target group, a corresponding topic prompt can be performed.

In an implementation manner, relevant information of each interactive topic may be directly displayed on the target group operation interface, for example, the starting point position of each interactive topic may be displayed.

In one embodiment, after the target object enters the target group, a jump control that jumps to the interactive message whose generation time is the longest from the current time can be displayed, and when jumping to the top through the jump control, then The topic jump control can be displayed, and in response to the operation on the topic jump control in the target group operation interface, jump from the current interactive topic area to the starting point of other interactive topics for display. For example, the topic jump control can be used to jump to the starting point of the next topic, and after the control, jump to the starting point of the next interactive topic at the current position for display.

In the embodiment of the present application, before obtaining the interactive behavior indicators, the interactive behavior indicators can be counted while receiving the interactive messages, as shown in Figure 6, which is a schematic flow chart of counting the interactive behavior indicators of candidate buckets, and the process can be It is performed before the above step 201, which may specifically include the following steps S1-S4.

S60: Receive at least one interactive message sent by member objects in the target group.

In the embodiment of this application, when there is an interaction between member objects in the target group, the server will send the corresponding interaction message to the client corresponding to each member object in the target group, and the client will then will receive these interactive messages.

S61: Determine whether the time difference between the current moment and the end moment of the previous sub-time period is not greater than the bucketing time difference threshold.

S62: If the time difference between the current moment and the end moment of the previous sub-time period is not greater than the bucketing time difference threshold, that is, the determination result of step S2 is no, update the created interactive behavior index based on at least one interactive message Among the candidate buckets of , the interaction behavior indicator of the last created candidate bucket.

Taking 10 minutes per sub-time period as an example, the received messages are accumulated and counted according to one candidate bucket every 10 minutes in the target group. Then, when at least one of the above interaction messages is received, it is necessary to determine which candidate bucket it needs to be accumulated into, so as to determine whether the time difference between the current moment and the end moment of the previous sub-time period is not greater than the bucketing time difference threshold, That is, it is judged whether the duration of the current bucket (the candidate bucket created last time) exceeds 10 minutes.

Specifically, if it does not exceed 10 minutes, the accumulation is still performed in the last created candidate bucket, that is, the interaction behavior indicator corresponding to at least one interactive message, and the interaction behavior indicator of the last created candidate bucket is updated.

In one embodiment, when the interactive behavior indicator is the number of interactive messages, if the cumulative number of interactive messages in the last created candidate bucket is A, and the number of at least one interactive message is B, then based on the original number A The accumulative quantity B is to update the accumulative message quantity of the last created candidate bucket to A+B.

In another embodiment, when the interaction behavior indicator is the number of member objects participating in the interaction, when updating the interaction behavior indicator of the last created candidate bucket, it is necessary to determine the corresponding Among the member objects, the number of unrecorded member objects in the last created candidate bucket, so that the number of unrecorded member objects is accumulated on the basis of the number of recorded member objects in the last created candidate bucket.

For example, if the cumulative number of member objects in the last created candidate bucket is 3, that is, member objects 1 to 3, if at least one of the above interactive messages is sent by member object 3, and the last created candidate bucket has been recorded member object 3, that is to say, the number of unrecorded member objects should be zero, and the cumulative number of member objects in the candidate bucket created last time is still 3; sent, and the last created candidate bucket does not record member objects 4 and 5, that is, the number of unrecorded member objects should be 2, then based on the cumulative number of member objects of the last created candidate bucket 3 , the cumulative quantity is 2, that is, the cumulative number of member objects is updated to 5.

Furthermore, when the end moment of each sub-period is reached and the bucketing statistics are completed, the interaction behavior index of the candidate bucket can be obtained. For example, the candidate bucket is bucket 1, and the corresponding number of interactive messages is M1. analogy.

It should be noted that when the target object enters the target group, the statistics of the interaction behavior indicator of the last candidate bucket is suspended to obtain the interaction behavior indicator of the candidate bucket.

S63: If the time difference is greater than the bucket time difference threshold, that is, the determination result of step S2 is Yes, create a candidate bucket, and update the interaction behavior indicator of the newly created candidate bucket based on the interaction behavior indicator corresponding to at least one interactive message.

Specifically, if the duration of the current bucket exceeds 10 minutes, a new candidate bucket needs to be created, and then the interaction behavior indicator corresponding to at least one interactive message is used to update the interaction behavior indicator of the newly created candidate bucket. The update method is the same as above The latest created candidate buckets are updated in the same manner, so details will not be repeated here.

In the following, the technical solution of the present application will be introduced with specific embodiments, the group is specifically a chat group, and the interactive behavior indicator is specifically the number of chat messages as an example. Referring to FIG. 7 , it is a schematic flowchart of a process of locating a chat topic in a chat group.

S70: the server sends the chat message to the client.

S71: The client performs statistics on the number of chat messages according to buckets.

Specifically, the client performs cumulative statistics of the chat messages in the current bucket 1. When the chat message exceeds the first chat message in the current bucket 1 by 10 minutes, create a new bucket 2, and so on. At the end of each bucket statistics, the total number of chat messages accumulated in the bucket is counted. For example, the number of chat messages in bucket 1 shown in FIG. 7 is M1, the number of chat messages in bucket 2 is M2, and so on.

It should be noted that the bucketing time period shown in Figure 7, such as the time period of bucket 1 is 9:00-9:03, because there are chat messages in this time period, and there are no other messages in the group. Chat messages are generated, but the statistics are still based on the upper limit of 10 minutes for each bucket. Similarly, if there are no new unread chat messages between 9:03 and 10:15, the statistics can be stopped. Until an unread chat message is triggered, it can also save device resources and avoid excessive processing pressure on the device.

S72: When the user enters the chat, calculate the average number of chat messages.

Specifically, when the user enters the chat, the statistics of the last bucket x is suspended, and the number of existing chat messages is recorded as the number of chat messages changed into buckets, that is, Mx shown in FIG. 7 . At the same time, calculate the average number of chat messages in all buckets based on the number of recorded chat messages in each bucket:

S73: Determine the peak of the topic based on the average number of chat messages.

Specifically, the number of chat messages M1-Mx in each bucket is compared with N in sequence, and if Mx/N>Y, then the bucket is defined as a peak area of topic discussion.

S74: Locate the starting point of the chat topic.

Specifically, in the above determination results, multiple eligible buckets may be obtained, all of which are marked as topic peak areas. Furthermore, for each eligible sub-bucket, take the first chat message A1 in the sub-bucket, and go back to the previous chat message one by one, if the time difference between the last chat message A1-1 and this chat message A1 is < Q minutes , then take the previous chat message A1-1 and continue to compare with the previous chat message A1-2 until the time difference between A1-X and A1-X+1 > Q minutes, then A1-X is judged as the start of the chat topic starting position.

Wherein, Q is set according to the experimental effect, for example, it is set to 10 minutes.

Similarly, when the interactive behavior indicator is the number of members participating in the group chat, the process of locating the interactive topic is similar to the above process, so please refer to the description in the above part, and will not repeat it here. In addition, different groups can use the above-mentioned process to locate the interactive topic in the group.

In the embodiment of the present application, according to the above-mentioned embodiment process, the position of each interactive topic in the group can be located, such as the positioning of the chat topic in the above-mentioned chat group, and then the position of each interactive topic can be obtained according to the positioning. position to display the group page.

Referring to FIG. 8 , it is a schematic flowchart of an interactive topic display method provided by the embodiment of the present application.

Step 801: In response to the trigger operation of the target object entering the target group, present the target group operation interface corresponding to the target object; wherein, the target group operation interface displays interactive messages generated by the target group within a historical time period.

Specifically, the trigger operation for entering the target group may be, for example, clicking the icon of the target group in the interactive application; or, when a notification message is displayed that the target group has a new interactive message, click the notification message to enter, of course, it may also be Other trigger modes are adopted, which is not limited in this embodiment of the present application.

Step 802: In response to the trigger operation on the top jump control, jump to the position of the first interactive message in the historical time period for display, and display the topic jump control in the target group operation interface.

After entering the target group, since there are many unread interactive messages, in order to facilitate the user to read from the beginning, a shortcut to quickly jump to the first interactive message can be provided to the user, that is, on the target group operation interface Display the top jump control, which can be used to jump to the first interactive message position in the historical time period, and then operate on it, you can quickly jump.

It should be noted that step 802 is not a mandatory step, that is, after entering the operation interface of the target group, the topic jump control may also be directly displayed on the interface.

Step 803: In response to the trigger operation on the topic jump control in the target group operation interface, jump to the starting point of the corresponding interactive topic in the historical time period for display.

Taking group chat as an example, see FIGS. 9a and 9b , which are schematic diagrams showing a chat group page. When users have a lot of group chat messages, by locating the core topics in the group, users can quickly jump, thereby facilitating users to better digest chat messages. When the user enters the chat group, the group interface as shown in Figure 9a can be displayed, the group interface includes a top jump control, and after operating the top jump control, it can jump to the dimension message Display at the top, that is, switch to the group interface shown in Figure 9b, which includes a topic jump control, which is used to jump to the identified topic, such as the starting point of the next topic, so that Users quickly jump to chat topics.

In one embodiment, as shown in FIG. 9b, the topic jump control can be used to jump to the next interactive topic, and after the trigger operation is performed on the topic jump control, it can respond to the trigger operation from the current Interactive message position, jump to the starting point of the next interactive topic for display.

In another embodiment, the topic jump control may also include topic jump sub-controls for jumping to each interactive topic in the historical time period, and each topic jump sub-control corresponds to an interactive topic, and you can jump to as needed Go to any interactive topic, and then respond to the trigger operation on the target topic jump sub-control in each topic jump sub-control, jump from the current interactive message position to the start of the interactive topic corresponding to the target topic jump sub-control The starting position is displayed.

Of course, in practical applications, other methods can also be used to display the identified topics, such as directly displaying the located chat topic area on the group page, and the user chooses to jump. In addition, the embodiments of the present application do not limit the display positions and display styles of the above-mentioned controls.

In the embodiment of the present application, the process of locating the position of the starting point of each interactive topic can be described in the above method for locating the interactive topic, and will not be repeated here.

To sum up, in the embodiment of this application, by directly analyzing the interactive behavior, it is separated from the text analysis and avoids the identification problems caused by various message forms such as text, pictures, emoticons, and links. As far as topic positioning is concerned, there is a simpler way to achieve it, and the effect is ideal. Referring to FIG. 10 a and FIG. 10 b , it is a schematic diagram of the effect of the method for locating an interactive topic in the embodiment of the present application.

Referring to Figure 10a, it is a schematic diagram of the effect of a group chat with chat topics, wherein the solid line graph represents the change in the number of messages in a group chat, and the broken line graph represents the change in the number of participating users in the group chat, The effect diagram in Figure 10a is obtained by bucketing according to 10 minutes, and the average number of messages is 7.8. Generally speaking, these group chats are usually group chats based on interests, such as pet groups or food groups, etc. Through the interactive topic positioning method of the embodiment of this application, topics with high participation of members in the group can be effectively located, as shown in the figure Topics 1-4 in 10a have significantly higher data (number of messages or user participation) than other time periods, high positioning accuracy, and high error acceptability.

Referring to Figure 10b, it is a schematic diagram of the effect of group chats with relatively few topics, such as marketing groups, shopping groups, etc. It can be seen that the characteristics of this group chat are obvious, and the number of users who send chat messages is basically fixed, and usually If there are fixed people, and the number of chat messages is also regular, most non-topic content can also be better filtered out through the interactive topic positioning method of the embodiment of the present application.

Please refer to Fig. 11, based on the same inventive concept, the embodiment of the present application also provides an interactive topic locating device 110, which includes:

The behavior indicator acquisition unit 1101 is configured to acquire the interactive behavior indicators corresponding to each candidate bucket associated with the target group for a specified historical time period when the target object enters the target group, wherein each candidate bucket contains: In a sub-time period in the historical time period, interactive messages generated by the target group;

Topic peak positioning unit 1102, configured to determine at least one target bucket whose interaction behavior index satisfies the topic heat peak condition from each candidate bucket;

The starting point locating unit 1103 is configured to, for each target bucket in at least one target bucket, determine the respective The starting point position of the corresponding interactive topic;

The interface presentation unit 1104 is configured to present the target group operation interface corresponding to the target object based on the determined starting point positions.

Optionally, the behavior index acquisition unit 1101 is also used for:

receiving at least one interactive message sent by the member objects in the target group;

If the time difference between the current moment and the end moment of the previous sub-time period is not greater than the bucketing time difference threshold, based on the interaction behavior indicator corresponding to at least one interactive message, update the candidate created last time among the created candidate buckets Bucketed interaction behavior indicators;

If the time difference is greater than the bucket time difference threshold, create a candidate bucket, and update the interaction behavior indicator of the newly created candidate bucket based on the interaction behavior indicator corresponding to at least one interactive message.

Optionally, the interactive behavior indicator is the number of interactive messages; the topic peak location unit 1102 is specifically used for:

Based on the number of interactive messages corresponding to each candidate bucket, determine the threshold of the number of interactive messages when the topic popularity peak condition is met in the historical time period;

For each candidate bucket, perform the following operations: For a candidate bucket, if the number of interactive messages corresponding to it is greater than the threshold of the number of interactive messages, determine a candidate bucket as the target bucket.

Optionally, the topic peak location unit 1102 is specifically used for:

Based on the number of interactive messages in each candidate bucket, determine the mean value of the number of interactive messages in each candidate bucket;

Based on the group business type of the target group, determine the topic peak coefficient corresponding to the target group;

Based on the mean value of the number of interactive messages and the peak coefficient of the topic, the threshold of the number of interactive messages is determined.

Optionally, the interactive behavior indicator is the number of member objects participating in the interaction; the topic peak positioning unit 1102 is specifically used for:

Determine the number of member objects that are not recorded in the last created candidate bucket among the member objects corresponding to at least one interactive message;

Based on the number of member objects recorded in the last created candidate bucket, add the number of unrecorded member objects.

Optionally, the topic peak location unit 1102 is specifically used for:

Based on the number of member objects recorded in each candidate bucket, determine the threshold of the number of member objects when the topic popularity peak condition is met in the historical time period;

For each candidate bucket, perform the following operations: For a candidate bucket, if the number of recorded member objects is greater than the threshold of the number of member objects, determine a candidate bucket as the target bucket.

Optionally, the interactive behavior index includes the number of interactive messages and the number of member objects; the topic peak location unit 1102 is specifically used for:

For each candidate bucket, perform the following operations:

For a candidate bucket, determine whether the corresponding interactive message quantity is greater than the interactive message quantity threshold;

If the number of interactive messages is greater than the threshold of the number of interactive messages, it is determined whether the number of recorded member objects is greater than the threshold of the number of member objects;

If the number of member objects is greater than the threshold of the number of member objects, determine a candidate bucket as the target bucket.

Optionally, the starting point positioning unit 1103 is specifically used for:

For each target bucket, perform the following operations:

For a target bucket, starting from the interaction message with the earliest generation time in a target bucket, determine whether the time difference between the generation time of each interaction message and the generation time of the previous interaction message is greater than the generation time difference threshold, until Until the target interaction message with a time difference greater than the time difference threshold appears;

The target interactive message is determined as the starting point position of the interactive topic corresponding to a target bucket.

Optionally, the starting point positioning unit 1103 is specifically used for:

Determine the overlap between the member objects corresponding to each interactive message between the target interactive message and the earliest interactive message at the generation time, and the member objects corresponding to a target bucket;

If the coincidence degree is not less than the coincidence degree threshold, it is determined that an interaction message preceding the target interaction message is the starting point of an interaction topic corresponding to a target bucket.

Optionally, the device also includes a topic merging unit 1105, configured to:

For each determined starting point position, perform the following operations:

For a starting point position, if the interaction message between a starting point position and the corresponding first target bucket has covered the interaction message of the second target bucket, then the first target bucket and the second target bucket Corresponding interactive topics are merged.

Through the above device, it is possible to analyze the interactive behavior in the group, so that there is no need to obtain the content of the interactive text, and the privacy of the member objects in the group will not be involved, and, through the analysis of the interactive behavior, the amount of calculation is much smaller than that through the interactive The method of text recognition requires less computing resources, and can locate interactive topics more quickly.

The device can be used to execute the methods shown in the various embodiments of the present application. Therefore, for the functions that can be realized by the functional modules of the device, etc., reference can be made to the descriptions of the foregoing embodiments, and details will not be repeated here.

Please refer to Fig. 12, based on the same inventive concept, the embodiment of the present application also provides an interactive topic display device 120, which can be, for example, the above-mentioned terminal device, which includes:

The operation interface switching unit 1201 is configured to present the target group operation interface corresponding to the target object in response to the trigger operation of the target object entering the target group; wherein, the target group operation interface displays information generated by the target group within a historical time period. interactive news;

The topic jump unit 1202 is configured to jump to the starting point of the corresponding interactive topic in the historical time period for display in response to a trigger operation on the topic jump control in the target group operation interface.

Optionally, a top jump control is displayed on the target group operation interface, and the top jump control is used to jump to the position of the first interactive message in the historical time period;

Then the device also includes a message jump unit 1203, configured to:

In response to a trigger operation on the top jump control, jump to the first interactive message position in the historical time period for display; and,

Display the topic jump control in the target group operation interface.

Optionally, the topic jump control is used to jump to the next interactive topic;

Then the topic jump unit 1202 is specifically used for:

In response to a trigger operation on the topic jump control, jump from the current interactive message position to the starting point of the next interactive topic for display.

Optionally, the topic jump control includes topic jump sub-controls for jumping to each interactive topic in the historical time period, and each topic jump sub-control corresponds to an interactive topic;

Then the topic jump unit 1202 is specifically used for:

In response to a trigger operation performed on the target topic jump sub-control in each topic jump sub-control, jump from the current interactive message position to the starting point of the interactive topic corresponding to the target topic jump sub-control for display.

Optionally, the device also includes a topic locating unit 1204, configured to:

For the specified historical time period, obtain the interaction behavior indicators corresponding to each candidate bucket associated with the target group, where each candidate bucket contains: the interaction generated by the target group in a sub-time period in the historical time period information;

From each candidate bucket, determine at least one target bucket whose interaction behavior index satisfies the topic heat peak condition;

For each target bucket in the at least one target bucket, based on the correlation between the interaction messages whose generation time is before the creation time of each target bucket, respectively determine the starting point position of the interactive topic corresponding to the at least one target bucket .

Through the above-mentioned device, users can be provided with operable controls for quickly jumping topics, and after the user performs operations, they can quickly jump topics, and quickly browse the content of each interactive topic, and exclude those that do not belong to interactive topics. content, realize quick browsing of historical unread messages, and improve user experience.

In addition, by analyzing the interactive behavior in the group, there is no need to obtain the content of the interactive text, and the privacy of the member objects in the group will not be involved, and, through the analysis of the interactive behavior, the amount of calculation is far less than the identification through the interactive text The method requires less computing resources, and can locate interactive topics more quickly.

The device can be used to execute the methods shown in the various embodiments of the present application. Therefore, for the functions that can be realized by the functional modules of the device, etc., reference can be made to the descriptions of the foregoing embodiments, and details will not be repeated here.

Please refer to FIG. 13 , based on the same technical concept, the embodiment of the present application also provides a computer device 130, which may be the terminal device or server shown in FIG. 1, and the computer device 130 may include a memory 1301 and a processor 1302.

The memory 1301 is used for storing computer programs executed by the processor 1302 . The memory 1301 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function, etc.; the data storage area may store data created according to the use of the computer device, etc. The processor 1302 may be a central processing unit (central processing unit, CPU), or a digital processing unit or the like. The specific connection medium between the memory 1301 and the processor 1302 is not limited in this embodiment of the present application. In the embodiment of the present application, in FIG. 13, the memory 1301 and the processor 1302 are connected through the bus 1303. The bus 1303 is represented by a thick line in FIG. As far as possible. The bus 1303 can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used in FIG. 13 , but it does not mean that there is only one bus or one type of bus.

The memory 1301 can be a volatile memory (volatile memory), such as a random-access memory (random-access memory, RAM); the memory 1301 can also be a non-volatile memory (non-volatile memory), such as a read-only memory, flash memory (flash memory), hard disk (hard disk drive, HDD) or solid-state drive (solid-state drive, SSD), or the memory 1301 can be used to carry or store desired program codes in the form of instructions or data structures and can be used by the computer Any other medium accessed, but not limited to. The memory 1301 may be a combination of the above-mentioned memories.

The processor 1302 is configured to execute the method executed by the device in each embodiment of the present application when calling the computer program stored in the memory 1301.

In some possible implementations, various aspects of the method provided in this application can also be implemented in the form of a program product, which includes program code. When the program product is run on a computer device, the program code is used to The computer device is made to execute the steps in the methods described above in this specification according to various exemplary implementations of the present application. For example, the computer device may execute the methods performed by the devices in the various embodiments of the present application.

The program product may reside on any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: electrical connection with one or more conductors, portable disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

While preferred embodiments of the present application have been described, additional changes and modifications to these embodiments can be made by those skilled in the art once the basic inventive concept is appreciated. Therefore, the appended claims are intended to be construed to cover the preferred embodiment and all changes and modifications which fall within the scope of the application.

Obviously, those skilled in the art can make various changes and modifications to the application without departing from the spirit and scope of the application. In this way, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims (20)

1. An interactive topic location method, characterized in that the method comprises: When the target object enters the target group, for the specified historical time period, obtain the interactive behavior indicators corresponding to each candidate bucket associated with the target group, wherein each candidate bucket contains: In a sub-time period, the interactive messages generated by the target group; From each of the candidate buckets, determine at least one target bucket whose interaction behavior index satisfies the topic popularity peak condition; For each target bucket in the at least one target bucket, based on the correlation between the interaction messages whose generation time is before the creation time of each target bucket, respectively determine the respective corresponding The location of the starting point of the interactive topic; Based on the determined starting point positions, a target group operation interface corresponding to the target object is presented. 2. The method according to claim 1, characterized in that, when the target object enters the target group, for the specified historical time period, before obtaining the respective interactive behavior indicators corresponding to each candidate bucket associated with the target group , the method also includes: receiving at least one interactive message sent by the member objects in the target group; If the time difference between the current moment and the end moment of the previous sub-time period is not greater than the bucketing time difference threshold, based on the interactive behavior index corresponding to the at least one interactive message, update the created candidate bucket, the most recently created The interactive behavior indicators of candidate buckets; If the time difference is greater than the bucketing time difference threshold, create a candidate bucket, and update the interaction behavior indicator of the newly created candidate bucket based on the interaction behavior indicator corresponding to the at least one interactive message. 3. The method according to claim 2, wherein the interactive behavior indicator is the number of interactive messages; Then, from each of the candidate buckets, determine at least one target bucket whose interactive behavior index satisfies the peak condition of topic popularity, including: Based on the number of interactive messages corresponding to each of the candidate buckets, determine the threshold of the number of interactive messages when the topic popularity peak condition is met in the historical time period; For each of the candidate buckets, perform the following operations: for a candidate bucket, if the number of interactive messages corresponding to it is greater than the threshold of the number of interactive messages, determine the candidate bucket as the target bucket. 4. The method according to claim 3, characterized in that, based on the number of interactive messages corresponding to each of the candidate buckets, determine the threshold of the number of interactive messages in the historical time period when the topic popularity peak condition is met, include: Based on the number of interactive messages in each candidate bucket, determine the mean value of the number of interactive messages in each candidate bucket; Based on the group business type of the target group, determine the topic peak coefficient corresponding to the target group; Based on the mean value of the number of interactive messages and the peak coefficient of the topic, the threshold of the number of interactive messages is determined. 5. The method according to claim 2, wherein the interactive behavior index is the number of member objects participating in the interaction; Based on the interactive behavior index corresponding to the at least one interactive message, update the interactive behavior index of the last created candidate bucket among the created candidate buckets, including: Determine the number of member objects that are not recorded in the last created candidate bucket among the member objects corresponding to the at least one interactive message; On the basis of the number of member objects recorded in the last created candidate bucket, the number of unrecorded member objects is accumulated. 6. The method according to claim 5, wherein, from the candidate buckets, at least one target bucket whose interactive behavior index satisfies the topic heat peak condition is determined, comprising: Based on the number of member objects recorded in each candidate bucket, determine the threshold of the number of member objects when the topic heat peak condition is met in the historical time period; For each of the candidate buckets, the following operations are respectively performed: for a candidate bucket, if the number of recorded member objects is greater than the threshold of the number of member objects, determine the candidate bucket as the target bucket. 7. The method according to claim 1, wherein the interactive behavior indicators include the number of interactive messages and the number of member objects; Then, from each of the candidate buckets, determine at least one target bucket whose interactive behavior index satisfies the peak condition of topic popularity, including: For each of the candidate buckets, perform the following operations: For a candidate bucket, determine whether the corresponding interactive message quantity is greater than the interactive message quantity threshold; If the number of interactive messages is greater than the threshold of the number of interactive messages, determine whether the number of recorded member objects is greater than the threshold of the number of member objects; If the number of member objects is greater than the threshold of the number of member objects, determine a candidate bucket as the target bucket. 8. The method according to any one of claims 1-7, characterized in that, for each target bucket in the at least one target bucket, based on each interaction whose generation time is before the creation time of each target bucket The correlation between the messages respectively determines the starting point position of the interactive topic corresponding to the at least one target bucket, including: For each of the target buckets, perform the following operations: For a target bucket, starting from the interaction message with the earliest generation time in the target bucket, determine the generation time of each interaction message one by one, and whether the time difference between the generation time of the previous interaction message and the generation time of the previous interaction message is greater than the generation time difference threshold , until a target interaction message with a time difference greater than the generation time difference threshold appears; The target interaction message is determined as the starting point of the interaction topic corresponding to the one target bucket. 9. The method according to claim 8, wherein determining the previous interactive message of the target interactive message as the starting point position of the interactive topic corresponding to the one target bucket includes: Determine the degree of overlap between the member objects corresponding to each interaction message between the target interaction message and the interaction message at the earliest generation time, and the member objects corresponding to the one target bucket; If the coincidence degree is not less than the coincidence degree threshold, it is determined that the previous interaction message of the target interaction message is the starting point of the interaction topic corresponding to the one target bucket. 10. The method according to any one of claims 1-7, wherein, for each target bucket in the at least one target bucket, based on each target bucket whose generation time is before the creation time of each target bucket For the correlation between interactive messages, after determining the starting point positions of the interactive topics corresponding to the at least one target bucket respectively, the method further includes: For each determined starting point position, perform the following operations: For a starting point location, if the interaction message between the starting point location and the corresponding first target bucket has covered the interaction message of the second target bucket, then the first target bucket and the first target bucket Merge interactive topics corresponding to the second target bucket. 11. An interactive topic display method, characterized in that the method comprises: In response to the trigger operation of the target object entering the target group, a target group operation interface corresponding to the target object is presented; wherein, the target group operation interface displays interactive messages generated by the target group within a historical time period ; In response to a trigger operation on the topic jump control in the target group operation interface, jump to the starting point of the corresponding interactive topic in the historical time period for display. 12. The method according to claim 11, wherein a top jump control is displayed in the target group operation interface, and the top jump control is used to jump to the first item in the historical time period interactive message location; Then, before displaying the starting point position of the corresponding interactive topic in the historical time period in response to the trigger operation performed on the topic jump control in the target group operation interface, the method further includes: In response to the trigger operation performed on the top jump control, jump to the first interactive message position in the historical time period for display; and, The topic jump control is displayed on the target group operation interface. 13. The method according to claim 11, wherein the topic jump control is used to jump to the next interactive topic; Then, in response to the trigger operation performed on the topic jump control in the target group operation interface, jump to the starting point position of the corresponding interactive topic in the historical time period for display, including: In response to a trigger operation performed on the topic jump control, jump from the current interactive message position to the starting point of the next interactive topic for display. 14. The method according to claim 11, wherein the topic jump control includes a topic jump sub-control for jumping to each interactive topic in the historical time period, and each topic jump sub-control corresponds to an interactive topic; Then, in response to the trigger operation performed on the topic jump control in the target group operation interface, jump to the starting point position of the corresponding interactive topic in the historical time period for display, including: In response to a trigger operation on the target topic jump sub-control in each topic jump sub-control, jump from the current interactive message position to the starting point of the interactive topic corresponding to the target topic jump sub-control for display. 15. The method according to any one of claims 11-14, characterized in that, in response to a trigger operation performed on the topic jump control in the target group operation interface, jump to the corresponding topic within the historical time period. Before displaying the starting point position of the interactive topic, the method further includes: For a specified historical time period, obtain the interactive behavior indicators corresponding to each candidate bucket associated with the target group, wherein each candidate bucket includes: within a sub-time period in the historical time period, the Interactive messages generated by target groups; From each of the candidate buckets, determine at least one target bucket whose interaction behavior index satisfies the topic popularity peak condition; For each target bucket in the at least one target bucket, based on the correlation between the interaction messages whose generation time is before the creation time of each target bucket, respectively determine the respective corresponding The location of the starting point of the interactive topic. 16. An interactive topic locating device, characterized in that the device comprises: The behavior indicator acquisition unit is used to acquire the interactive behavior indicators corresponding to each candidate bucket associated with the target group for a specified historical time period when the target object enters the target group, wherein each candidate bucket contains : an interactive message generated by the target group within a sub-time period in the historical time period; A topic peak positioning unit, configured to determine at least one target bucket whose interactive behavior index satisfies the topic heat peak condition from the candidate buckets; The starting point locating unit is configured to, for each target bucket in the at least one target bucket, determine the at least The starting point position of the interactive topic corresponding to each target bucket; The interface presentation unit is configured to present the target group operation interface corresponding to the target object based on the determined starting point positions. 17. An interactive topic display device, characterized in that the device comprises: An operation interface switching unit, configured to present a target group operation interface corresponding to the target object in response to a trigger operation that the target object enters the target group; wherein, the target group operation interface displays the Interactive messages generated by target groups; The topic jump unit is configured to jump to the starting point of the corresponding interactive topic in the historical time period for display in response to a trigger operation on the topic jump control in the target group operation interface. 18. A computer device comprising a memory, a processor and a computer program stored on the memory and operable on the processor, characterized in that, The steps of the method described in any one of claims 1-10 or 11-15 are realized when the processor executes the computer program. 19. A computer storage medium on which computer program instructions are stored, characterized in that, When the computer program instructions are executed by the processor, the steps of the method described in any one of claims 1-10 or 11-15 are implemented. 20. A computer program product comprising computer program instructions, characterized in that, When the computer program instructions are executed by the processor, the steps of the method described in any one of claims 1-10 or 11-15 are implemented.

Images