CN112836503A

CN112836503A - Group processing method and device and computer equipment

Info

Publication number: CN112836503A
Application number: CN201911080489.7A
Authority: CN
Inventors: 葛佳欣
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2019-11-07
Filing date: 2019-11-07
Publication date: 2021-05-25
Anticipated expiration: 2039-11-07
Also published as: CN112836503B

Abstract

The application relates to a group processing method, a device and computer equipment, wherein the method comprises the following steps: acquiring interactive group messages in a social group; performing word segmentation processing on the group message to obtain word segments; selecting semantic representation word segments in the word segments; determining group chat subject information currently corresponding to the social group according to the semantic representation word fragments; and identifying the social group according to the group chat subject information. The scheme of the application can reduce the consumption of system resources.

Description

Group processing method and device and computer equipment

Technical Field

The invention relates to the technical field of computers and the field of social communication, in particular to a group processing method and device and computer equipment.

Background

With the rapid development of scientific technology and the continuous improvement of life rhythm, the online social platform is called as a social tool which is very mainstream in life. Users often establish or join social groups through online social platforms to quickly communicate and share information among the social groups.

Since there are usually many group messages in a social group, the group members usually need to browse through a large number of chat records to know what the group is discussing at present. However, in the process of browsing a large number of group chat records by a user, a certain degree of occupation is generated on system resources, and the system resources are consumed.

Disclosure of Invention

Therefore, it is necessary to provide a group processing method, an apparatus, a computer device, and a storage medium for solving the problem of system resource consumption caused by browsing group chat records in the conventional method.

A method of group treatment, the method comprising:

acquiring interactive group messages in a social group;

performing word segmentation processing on the group message to obtain word segments;

selecting semantic representation word segments in the word segments; the semantic representation word segment is a word segment capable of representing the semantics of the group message;

determining group chat subject information currently corresponding to the social group according to the semantic representation word fragments;

and identifying the social group according to the group chat subject information.

In one embodiment, the determining, according to the semantic representation word segment, group chat subject information to which the social group currently corresponds includes:

according to the semantic representation word segment, determining a group name for representing the current group chat subject;

the identifying the social group according to the group chat subject information includes:

replacing an initial group name of the social group with the determined group name.

In one embodiment, the performing word segmentation processing on the group message to obtain a word segment includes:

when the group message includes an intention group message for representing the group intention, then

Performing word segmentation processing on the intention group message to obtain word segments;

the determining, according to the semantic representation word segment, a group name for representing a current group chat subject matter includes:

and determining a group name for representing the clustering intention according to the semantic representation word segment.

In one embodiment, the determining a group name for characterizing a current group chat motif from the semantic characterization word fragments comprises:

carrying out semantic recombination on the semantic representation word fragments;

and generating a group name for representing the group chat subject according to the semantic information obtained by the reorganization.

In one embodiment, the social group is a first social group; the determining, according to the semantic representation word segment, a group name for representing a current group chat subject matter includes:

determining a second social group; the semantic representation word segment belongs to a high-frequency vocabulary in the group message of the second social group; the second social group is different from the first social group;

searching a group name corresponding to the second social group;

and determining the group name of the first social group according to the searched group name and used for representing the current group chat subject.

In one embodiment, the obtaining group messages interacted in a social group comprises:

when a group message for requesting recommendation of a group name is detected from group messages in a social group, acquiring an interactive group message from the social group; or the like, or, alternatively,

and acquiring interactive group messages in the social group according to a preset period.

In one embodiment, the replacing the initial group name of the social group with the determined group name comprises:

in the social group, returning a group name recommendation message comprising the determined group name;

when a recommendation enabling instruction for the group name recommendation message is received, the recommendation enabling instruction

Replacing an initial group name of the social group with a group name that is confirmed enabled by the enabling recommendation instruction.

In one embodiment, the identifying the social group according to the group chat subject information includes:

adding the group chat subject information to the social group as a subtitle;

returning the subtitles to the terminals corresponding to the group member identifications;

the subheading is used for indicating each terminal to display the subheading corresponding to the social group; the group member identifier is an identifier uniquely corresponding to each group member in the social group.

In one embodiment, the method further comprises:

obtaining marking results obtained by marking and marking time corresponding to each marking result;

sequencing the marking results according to the sequence of the corresponding marking time to obtain a marking result set with time sequence;

and returning the marking result set to a terminal corresponding to each group member identifier in the social group so as to indicate each terminal to correspondingly display the marking result set and the social group.

In one embodiment, the method further comprises:

obtaining a marking result obtained by marking;

acquiring marking time corresponding to each marking result;

correspondingly storing each marking result and the marking time in a block chain;

the obtaining of the marking result obtained by the identification and the marking time corresponding to each marking result includes:

and acquiring each marking result and the marking time corresponding to each marking result from the block chain.

In one embodiment, the selecting the semantic representation word segment comprises:

determining a heat value corresponding to each word segment;

determining the weight of each word segment according to the heat value; the weight is positively correlated with the heat value;

sequencing the word segments according to the sequence of the weights from big to small;

and selecting the word segments ordered at the previous preset order to obtain the semantic representation word segments.

A method of group treatment, the method comprising:

displaying a session interface of the social group;

presenting, in the conversation interface, group messages that interact in the social group;

when at least a part of the group message corresponds to group chat subject information, then

And identifying the social group in the conversation interface according to the group chat subject information.

In one embodiment, the identifying the social group in the session interface according to the group chat theme information includes:

when the group chat subject information is a group name, replacing the initial group name of the social group with the received group name in the session interface; or the like, or, alternatively,

and when the group chat subject information is a subtitle, displaying the subtitle corresponding to the social group in the session interface.

In one embodiment, when at least a portion of the group message corresponds to group chat subject information, then identifying the social group in the session interface in accordance with the group chat subject information comprises: and when the group message comprises an intention group message, identifying the group establishment intention information corresponding to the social group in the conversation interface according to the intention group message.

In one embodiment, according to the intention group message, identifying, in the conversation interface, the group intention information corresponding to the social group includes:

replacing, in the session interface, the initial group name of the social group with a group name that characterizes the intent to establish a group; and the group name representing the clustering intention is generated according to the intention group message.

In one embodiment, the group chat subject information is obtained by performing word segmentation processing on at least a part of group messages interacted in the social group and determining according to semantic representation word segments selected from word segments obtained by the word segmentation processing.

In one embodiment, the group name is obtained by semantically recombining the semantic representation word segments; and generating according to the semantic information obtained by the recombination.

In one embodiment, the social group is a first social group. And the group name is obtained by searching the group name corresponding to the second social group and is used for representing the current group chat subject of the first social group. A second social group is different from the first social group, and a semantic token word segment belongs to a high frequency vocabulary in a group message of the second social group.

In one embodiment, the group chat subject information is obtained by triggering word segmentation processing on group information interacted in a social group after detecting group information for requesting recommendation of a group name, and determining according to semantic representation word segments selected from word segments obtained by the word segmentation processing.

In one embodiment, when the group chat theme information is a group name, then replacing, in the session interface, the initial group name of the social group with the received group name comprises: displaying a group name recommendation message including a group name in a session interface; wherein the group name corresponds to at least a portion of the group message; and when a recommendation enabling instruction for the group name recommendation message is received, replacing the initial group name of the social group with the group name confirmed to be enabled by the recommendation enabling instruction.

In one embodiment, the method further comprises: acquiring a group name set or a subheading set with time sequence, and displaying the group name set or the subheading set with time sequence corresponding to a social group in a preset area in a session interface; the group name set or the subheading set is arranged according to the sequence of the marking time corresponding to the determined group name, or the group name set or the subheading set is arranged according to the sequence of the marking time corresponding to the determined subheading.

In one embodiment, obtaining a set of group names or subheading sets with temporal ordering comprises: and acquiring a group name set or a subheading set with time sequence from the blockchain.

A group treatment apparatus, the apparatus comprising:

the acquisition module is used for acquiring interactive group messages in the social group;

the main subject determining module is used for carrying out word segmentation processing on the group message to obtain word segments; selecting semantic representation word segments in the word segments; the semantic representation word segment is a word segment capable of representing the semantics of the group message; determining group chat subject information currently corresponding to the social group according to the semantic representation word fragments;

and the marking module is used for identifying the social group according to the group chat subject information.

A group treatment apparatus, the apparatus comprising:

the display module is used for displaying a conversation interface of the social group; presenting, in the conversation interface, group messages that interact in the social group;

a marking module, configured to identify the social group in the session interface according to the group chat subject information when at least a portion of the group message corresponds to the group chat subject information.

A computer device comprising a memory and a processor, the memory having stored therein a computer program that, when executed by the processor, causes the processor to perform the steps of the group processing method according to embodiments of the present application.

A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, causes the processor to perform the steps of a group processing method as described in embodiments of the present application.

According to the group processing method, the group processing device, the computer equipment and the storage medium, the group information interacted in the social group is subjected to word segmentation processing, semantic representation word segments are selected and the like, semantic analysis is carried out, the group chat subject information currently corresponding to the social group is obtained, and then the social group is marked according to the group chat subject information obtained through analysis. Therefore, the group members can know the current group chat subject of the social group only by looking up the mark according to the group chat subject information, and do not need to know the group chat subject by browsing a large number of group chat records, so that the consumption of system resources caused by browsing a large number of group chat records is saved.

Drawings

FIG. 1 is a diagram of an embodiment of a group processing method;

FIG. 2 is a diagram illustrating an exemplary group processing method according to another embodiment;

FIG. 3 is a flow diagram illustrating a group processing method according to one embodiment;

FIGS. 4-5 are schematic diagrams of interfaces for replacing group names in one embodiment;

FIG. 6 is a simplified diagram of a process for group name recommendation in one embodiment;

FIGS. 7-8 are schematic diagrams of interfaces for adding subtitles in one embodiment;

FIG. 9 is a flowchart illustrating a group processing method according to another embodiment;

FIG. 10 is a timing diagram of a group processing method in one embodiment;

FIG. 11 is a block diagram of a group processing device in one embodiment;

FIG. 12 is a block diagram of a group processing device in another embodiment;

FIG. 13 is a block diagram of a computer device in one embodiment;

fig. 14 is a block diagram of a computer device in another embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

Fig. 1 is a diagram illustrating an application scenario of the group processing method according to an embodiment. Referring to fig. 1, the application scenario includes at least one terminal 110 and a server 120. Each terminal 110 establishes a communication connection with the server 120. The terminal 110 has social software running therein that enables group communication. The terminal 110 may be a smart television, a smart speaker, a desktop computer, or a mobile terminal, and the mobile terminal may include at least one of a mobile phone, a tablet computer, a notebook computer, a personal digital assistant, a wearable device, and the like. The server 120 may be implemented as a stand-alone server or as a server cluster of multiple physical servers.

It can be understood that the group member identifiers respectively logged in each terminal 110 form a social group, and communication between the groups can be realized by forwarding the group message through the server 120. That is, each terminal 110 may send a group message to the server 120. The server 120 may receive the group message and forward the group message sent by one of the terminals 110 to the other terminals 110 to enable inter-group communication.

The server 120 may obtain group messages interacted in the social group; performing word segmentation processing on the group message to obtain word segments; selecting semantic representation word segments in the word segments; the semantic representation word segment is a word segment capable of representing the semantics of the group message. The server 120 may determine, according to the semantic representation word segment, group chat subject information currently corresponding to the social group; and identifying the social group according to the group chat subject information. Further, the server 120 may also return a tagging result obtained by identifying the social group to each terminal 110, so as to instruct each terminal 110 to correspondingly present the tagging result with the social group.

Fig. 2 is a diagram illustrating an application scenario of the group processing method in another embodiment. Referring to fig. 2, the application scenario includes at least one terminal 210, a social platform server 220, and a naming server 230. Wherein, a network connection is established between every two of the terminal 210, the social platform server 220 and the naming server 230. It is understood that a server equivalent to server 120 in FIG. 1 may include a social platform server 220 and a naming server 230.

In one embodiment, the social platform server 220 may include at least one of a social network server and an instant messaging server.

Likewise, the terminals 210 send group messages to the social platform server 220, and the social platform server 220 forwards the group messages to other terminals 210 to enable group communication. In addition, the social platform server 220 may also send group messages that interact in the social group to the naming server 230. The naming server 230 may perform word segmentation on the group message to obtain word segments; and selecting semantic representation word segments in the word segments. The naming server 230 may determine, according to the semantic representation word segment, group chat subject information currently corresponding to the social group; and identifying the social group according to the group chat subject information.

It is understood that the naming server 230 may directly identify the social group according to the group chat subject information, and then directly return the marking result obtained by the identification to each terminal 210, so as to instruct the terminal 210 to correspondingly present the marking result and the social group. The naming server 230 may also return the group chat theme information to the social platform server 220, the social platform server 220 identifies the social group according to the group chat theme information, and then the social platform server 220 returns the tagging result to each terminal 210 to instruct the terminal 210 to correspondingly display the tagging result and the social group.

It is understood that either server 120 or naming server 230 can belong to an artificial intelligence server.

Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making. It is understood that the server 120 or the naming server 230 can automatically understand the core subject content of the current group chat by executing the group processing method in the embodiments of the present application, which is equivalent to understanding the group chat subject in a manner similar to human intelligence, and belongs to an artificial intelligence server.

FIG. 3 is a flowchart illustrating a group processing method according to an embodiment. The group processing method in this embodiment can be applied to a computer device, and is mainly illustrated by the server 120 in fig. 1. Referring to fig. 3, the method specifically includes the following steps:

s302, obtaining interactive group information in the social group.

The social group is a group which comprises a plurality of group members and realizes social communication.

It is understood that an interactive group message refers to a group message sent and/or received by each group member in a social group in the social group.

In one embodiment, the social group may include at least one of an instant messaging group, a social network group, and the like. The instant messaging group is a group established based on instant messaging application. For example, the group of QQ (instant messenger application developed by Tencent) and the group of WeChat (an application provided by Tencent in 2011, 1, 21) that provides instant messenger service for an intelligent terminal. The social network group is a group established based on a social network application. Such as groups created based on social networking applications such as blogs or microblogs.

It is to be appreciated that social communication between groups can be achieved whether the groups are instant messaging groups or social network groups.

It is noted that the social group may include at least one of a traditional social group and a group in which multiple people chat. The traditional social group refers to a social group which is traditionally managed mainly by a group owner and an administrator. For example, in a conventional QQ group, the QQ group is broken up after the group is broken down. Compared with the traditional social group, the group chatting by multiple persons weakens the authority of the group owner and the administrator, reduces the dependence on the group owner and the administrator, and still exists after the group owner exits the group. For example, the wechat group (or the QQ group created by initiating a group chat) belongs to a group for a multi-person chat, and the wechat group (or the QQ group) still exists after the group is handed off.

In one embodiment, a computer device may retrieve a group message sent in a social group within a preset length of time prior to a current time. For example, the preset duration is 30 minutes, and the computer device may obtain the group message interacted in the social group in the previous 30 minutes.

In another embodiment, the computer device may also detect an interaction frequency of the group messages in the social group, and obtain the group messages in the social group that satisfy the preset interaction frequency.

It will be appreciated that the frequency of interaction of group messages corresponds to the frequency of chat conversations among the group members. The interaction frequency of the group message meeting the preset interaction frequency in the social group is greater than or equal to the preset interaction frequency, which is equivalent to the content discussed by the group member in the social group. And subsequent semantic analysis processing is carried out on the group messages meeting the preset interaction frequency, so that the chat subject in the current group can be accurately analyzed.

It is understood that the computer device may actively execute step S302, or may trigger to execute step S302 after receiving the trigger operation. It is understood that the user may directly trigger the corresponding control to input the operation. The user may also trigger the step S302 by sending a group message for triggering the step S302 to be executed in the social group, for example, by sending a group message requesting recommendation in the social group to trigger the step S302 to be executed.

In one embodiment, step S302 includes: and acquiring interactive group messages in the social group according to a preset period. That is, the computer device actively acquires the group message interacted in the social group according to a preset period.

S304, performing word segmentation processing on the group message to obtain word segments.

Specifically, the computer device may perform word segmentation Processing on the group message by using Natural Language Processing (NLP) technology to obtain word segments. The word segment refers to a word obtained after word segmentation. For example, after the group message of "i love in china" is participated, the obtained "i", "love" and "china" belong to word fragments.

It is understood that the computer device may perform the word segmentation process on all or part of the acquired group message.

In one embodiment, when the group message includes an intention group message representing a group intention, the intention group message may be subjected to word segmentation to obtain a word segment.

The group building intention refers to the purpose or intention of establishing a social group. The intention group message refers to a group message for representing the group establishment intention. For example, group messages such as "we organize big family together … … for the purpose" or "we are mainly going to solve the problem" all belong to intention group messages.

It can be understood that, when the group message includes the intention group message, the computer device may perform word segmentation only on the intention group message to obtain word segments, and execute steps S306-310 according to the obtained word segments to mark the group intention for the social group, so that the group members all know the intention established by the social group to improve the efficiency of joining the group chat.

In other embodiments, the computer device may also perform word segmentation on all the obtained group messages, and execute steps S306-310 to mark recent group chat subjects for the social group, so that the group members know the topic discussed by the recent group chat to better join the group chat.

S306, selecting semantic representation word segments in the word segments.

The semantic representation word segment is a word segment capable of representing the semantics of the group message. The semantic representation word segment is at least one.

In one embodiment, the semantic token fragments may be a high-heat vocabulary. The high heat degree means that the heat degree value of the semantic representation word segment is greater than or equal to a preset heat degree threshold value. It is understood that the high-heat vocabulary is a more popular, focused, and widely used vocabulary at the present time.

In one embodiment, the step S306 of selecting the semantic representation word segment includes: determining a heat value corresponding to each word segment; determining the weight of each word segment according to the heat value; the weight is positively correlated with the heat value; sequencing the word segments according to the sequence of the weights from big to small; and selecting the word segments ordered at the previous preset order to obtain the semantic representation word segments.

In one embodiment, the computer device may determine a corresponding heat value for each word segment within a preset time.

In other embodiments, the computer device may determine the weight of each word segment in conjunction with the time dimension influencing factors in addition to considering the heat value.

For example, if the yesterday heat value of the word segment a is higher than the heat value of the word segment B, but the present heat value of the word segment a is lower than the heat value of the word segment B, it may be determined that the weight of the word segment a is greater than the weight of the word segment B, or based on assigning a higher influence coefficient to the today heat value, the yesterday heat value influence coefficient is assigned a lower influence coefficient, and further, each heat value is weighted and summed according to the corresponding influence coefficient, so as to obtain the final corresponding weight of each word segment. Or, the heat values corresponding to the word segments in different time periods may be ranked based on the time dimension, and the weight corresponding to each word segment may be determined according to the heat value of each word segment in the time period closest to the current time. It is understood that selecting the semantic representation word segment based on the weight determined in this way enables generating group chat subject information that best fits the social group at the current time period according to the semantic representation word segment.

In one embodiment, the heat value corresponding to each word segment is determined according to at least one of the following data: the corresponding word frequency of the word segment in a preset time period; the number of times that the word segment is discussed by different group members in the social group within a preset time period; the number of different social groups of the word segment is discussed within a preset time period.

In other embodiments, the computer device may also select the semantically characterized word fragments directly from the word frequency. Specifically, the computer device may select word segments with a word frequency greater than or equal to a preset word frequency threshold to obtain semantic representation word segments.

And S308, determining group chat subject information currently corresponding to the social group according to the semantic representation word fragments.

The meaning, meaning or purpose of the subject matter is defined as the main meaning, meaning or purpose. The group chat detail information is information for expressing the content of the group chat detail. A group chat subject, i.e. a group chat topic, corresponds to a topic where a group message mainly surrounds the discussion.

In one embodiment, the group chat theme information may include a group name for characterizing the group chat theme. That is, the group chat theme is embodied in the form of a group name.

It is to be appreciated that the computer device can generate a group name for characterizing a group chat motif from the semantic representation word segment. The computer device can also search a group name which is matched with the semantic representation word segment and used for representing the group chat subject from a preset group name library according to the semantic representation word segment. The group name library is a collection of group names stored in advance.

In another embodiment, the group chat motif information may further include a subtitle for characterizing the group chat motif. That is, the group chat subject is embodied in the form of a subheading without changing the group name.

The subtitle is a supplementary explanation of the group chat subject. That is, the subtitle is used to supplement the explanation of the group chat subject with respect to the explanation of the social group by the group name.

And S310, identifying a social group according to the group chat subject information.

In one embodiment, the computer device may add a tag to a social group that characterizes a group chat motif without changing the original information of the social group. For example, the computer device may add a subtitle representing a group chat theme to the social group in the form of a subtitle without changing original information of the social group.

In another embodiment, the computer device may also modify existing information characterizing an identity of the social group into group chat motif information to identify the social group. The existing information for characterizing the identity may be a group name. The computer device may modify the group name into group chat motif information to tag the social group.

It can be understood that after the social group is identified according to the group chat subject information, the group members can see the marked group chat subject after entering a session interface of the social group, and then can conveniently and quickly know the subject content of the current group chat, thereby improving the efficiency of joining the group chat.

Further, the computer device may send the marking result obtained by the identification to the terminal corresponding to each group member identification, so that each terminal displays the marking result corresponding to the social group. It is to be understood that the tagging result may be a group name for characterizing the group chat topic or a subheading for characterizing the group chat topic.

It should be noted that the computer device may repeatedly execute steps S302 to S310, so as to determine the group chat subject information currently corresponding to the social group in real time, so as to mark the current group chat subject in real time.

It is understood that the computer device may directly identify the social group according to the group chat subject information, and the computer device may also return recommendation information including the group chat subject information to the terminal. And after a recommendation enabling instruction for the recommendation information is received, identifying the social group according to the group chat subject information.

In one embodiment, the computer device may return the recommendation information to the terminal by way of the prompt message. In another embodiment, the computer device may also return recommendation information including group chat subject information in the social group. That is, the computer device may return the recommendation information in a group message.

In one embodiment, the computer device may prompt the user for current group chat motif information by voice.

According to the group processing method, the group information sent within the preset time before the current time is subjected to word segmentation processing, semantic representation word segments are selected, semantic analysis is carried out, the group chat subject information corresponding to the social group at present is obtained, and then the social group is marked according to the group chat subject information obtained through analysis. Therefore, the group members can know the current group chat subject of the social group only by looking up the mark according to the group chat subject information, and do not need to know the group chat subject by browsing a large number of group chat records, so that the consumption of system resources caused by browsing a large number of group chat records is saved.

In addition, the group members can know the current group chat subject without browsing a large number of group chat records, so that the group chat efficiency of the user and the group chat joining efficiency are greatly improved. Meanwhile, under the condition that the user can conveniently know the group chat subject, the conversion rate of the group chat can be improved, namely, the utilization rate of the user is improved.

Moreover, the social group can be marked according to the group chat subject information, so that the user can be more pertinently added into the group chat, the accuracy of the group chat is improved, and unnecessary group messages sent by the user in unnecessary group chat are avoided, and unnecessary occupation of system resources is avoided.

In one embodiment, step S308 includes: and determining a group name for representing the current group chat subject according to the semantic representation word segment. In this embodiment, step S310 includes: replacing an initial group name of the social group with the determined group name.

The initial group name refers to a group name before replacement. The initial group name is not limited to a default group name at the time of group establishment, but refers to a group name before replacement with a group name that does not indicate the subject of the current group chat.

The semantic representation word segment can be a high-heat vocabulary in a preset time period. Such as high frequency words.

It is to be appreciated that the computer device can generate a group name for characterizing the current group chat subject directly from the semantic representation word segment. The computer device may also look up existing group names from the group name library that match the semantic token fragments. The computer device may replace the initial group name of the social group with the determined group name.

In one embodiment, a computer device may input semantically characterizing word fragments into a pre-trained group name generation model and output a group name for characterizing group chat topics. The group name generation model is a machine learning model which is obtained by taking a sample vocabulary and a sample group name as sample data in advance and training through an iterative model and is used for generating the group name. It can be understood that the group name generation model generates the group name according to the semantic representation word segment in the group message, so that the generated group name is related to the information expressed by the semantic representation word segment, and the group chat subject can be embodied.

In one embodiment, determining a group name for characterizing a current group chat motif from the semantic characterization word fragments comprises: carrying out semantic recombination on the semantic representation word fragments; and generating a group name for representing the group chat subject according to the semantic information obtained by the reorganization.

Specifically, the computer device may perform semantic recognition on the semantic representation word segments through a natural language processing technique (NLP technique), perform semantic reorganization on the semantic representation word segments after semantic understanding is performed, and generate a group name for representing the group chat subject according to semantic information obtained through the reorganization.

For ease of understanding, the following examples are now provided.

For example, if semantic representation word segments composed of forward semantics such as "idol a", "like", "i super-loving idol a" are mentioned in a group message of a social group, these semantic representation word segments may be semantically recombined to obtain semantic information such as "like idol a". Then, a group name such as "i love idol a ac group" or "idol a fan exchange meeting" that meets the current time semantics may be generated based on such semantic information, and the initial group name of the social group is changed to "i love idol a ac group" or "idol a fan exchange meeting". Therefore, all group members can quickly know the current discussion idol A in the social group according to the replaced group name, and can quickly join in group chat.

For another example, semantic representation word segments of a certain mobile phone product, such as semantic representation word segments of "H make ×," camera ", and" performance ", are mentioned in a social group message many times, and these semantic representation word segments can be semantically recombined to obtain semantic information of" discussing H make ×, "mobile phone camera performance", and then a group name of "H make ×," mobile phone camera performance discussion "can be generated based on the semantic information to replace the initial group name. Therefore, the group members can quickly know the performance of the mobile phone camera of the brand H and the model at present, and can quickly join in group chat.

It can be understood that, when performing semantic reorganization, intent analysis may be performed on the semantic representation word segments of the conventional screen-brushing to obtain corresponding intent information, and then the intent information of the semantic representation word segments of the conventional screen-brushing and the remaining semantic representation word segments (the semantic representation word segments other than the semantic representation word segments of the conventional screen-brushing) are subjected to semantic reorganization to obtain the reorganized semantic information. Further, a group name for representing a group chat topic is generated based on the reconstructed semantic information.

For example, in group chat, group member a sends my college of today, koshiqing, and a plurality of subsequent users send words of conventional screen brushing in the group, such as congratulatory words like "666", "congratulatory happiness", "like", and "stick". Then, the intention information of the semantic representation word segments which are regularly brushed is semantically recombined with the remaining semantic representation word segments to obtain recombined semantic information which is congratulatory university on study A, and further, the group name of the congratulatory university on study A can be obtained to replace the initial group name. Therefore, the group members can quickly know the current affairs of the Qinghua university in the discussion group member A, and can quickly join in the group chat.

Fig. 4 to 5 are schematic diagrams of interfaces for replacing a group name in one embodiment. FIG. 4 is a conversation interface between social group alternate group names. As can be seen from fig. 4, avatar a through avatar D represent group members a through D, respectively. The initial group name is "relative group". The group member A sends 'I am of Qinghua university' in the 'relative group', and other group members in the relative group send congratulatory phrases such as 'congratulations', 'praise' and 'stick' in a dispute. Then, a group name of "congratulatory group member a college on qinghua university" may be generated by the group processing method in the embodiment of the present application to indicate that the congratulatory group member a college on qinghua university is currently in the group. That is, the group name of "relative group" may be replaced with the group name of "congratulatory university" to obtain the session interface shown in fig. 5.

According to the group processing method, the group information interacted in the social group is subjected to word segmentation processing, semantic representation word fragments are selected and the like, semantic analysis is carried out, the group name which is currently corresponding to the social group and used for representing the group chat subject is obtained, and then the group name is replaced by the group name. Therefore, the group members can know the current group chat theme of the social group only by looking up the group chat theme according to the group name, and do not need to know the group chat theme by browsing a large number of group chat records, so that the consumption of system resources caused by browsing a large number of group chat records is saved.

In addition, because the group members can know the current group chat subject in real time without browsing a large number of group chat records, the group chat efficiency of the users and the group chat joining efficiency are greatly improved. Meanwhile, under the condition that the user can conveniently know the group chat subject, the conversion rate of the group chat can be improved, namely, the utilization rate of the user is improved.

Then, because the current group chat subject is marked by the group name, the user can be more pertinently added into the group chat, thereby improving the accuracy of the group chat, and avoiding the user from sending unnecessary group messages in unnecessary group chat, thereby avoiding unnecessary occupation of system resources.

Finally, the group name is a common headache for the user, and the group name used for representing the group chat subject is automatically determined by analyzing the group information through artificial intelligence, so that the group naming difficulty can be reduced, and the group naming efficiency is improved.

In one embodiment, the method further comprises: obtaining marking results obtained by marking and marking time corresponding to each marking result; sequencing the marking results according to the sequence of the corresponding marking time to obtain a marking result set with time sequence; and returning the marking result set to the terminal corresponding to each group member identifier in the social group so as to indicate each terminal to correspondingly display the marking result set and the social group.

It is to be understood that, when the group chat theme information is a group name for characterizing the group chat theme, the tagging result is the determined group name. And marking time corresponding to the marking result, namely the time point when the initial group name is replaced by the determined group name.

And when the group chat subject information is a subheading for representing the group chat subject, marking the result as the subheading. And marking time corresponding to the marking result is the time point when the subtitle is added to the social group.

The time-ordered marked result set corresponds to a group chat subject marked on a group chat timeline, and is used to represent a group chat subject that changes in time dimension. Therefore, the user who misses the group chat or enters the group chat later can be helped to efficiently and quickly know the change of the forward group chat theme, so that the user is familiar with the process of the group chat topic and the efficiency of joining the group chat is improved. And the efficiency of acquiring the group chat message is improved. In addition, the important information quantity compared with the forward group chat can be obtained without turning over a large number of group chat records, and the consumption of system resources is saved.

In one embodiment, the method further comprises: obtaining a marking result obtained by marking; acquiring marking time corresponding to each marking result; and correspondingly storing each marking result and the marking time in a block chain. In this embodiment, the obtaining of the marking result obtained by performing the identification and the marking time corresponding to each marking result includes: and acquiring each marking result and the marking time corresponding to each marking result from the block chain.

The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism and an encryption algorithm. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product services layer, and an application services layer.

The block chain underlying platform can comprise processing modules such as user management, basic service, intelligent contract and operation monitoring. The user management module is responsible for identity information management of all blockchain participants, and comprises public and private key generation maintenance (account management), key management, user real identity and blockchain address corresponding relation maintenance (authority management) and the like, and under the authorization condition, the user management module supervises and audits the transaction condition of certain real identities and provides rule configuration (wind control audit) of risk control; the basic service module is deployed on all block chain node equipment and used for verifying the validity of the service request, recording the service request to storage after consensus on the valid request is completed, for a new service request, the basic service firstly performs interface adaptation analysis and authentication processing (interface adaptation), then encrypts service information (consensus management) through a consensus algorithm, transmits the service information to a shared account (network communication) completely and consistently after encryption, and performs recording and storage; the intelligent contract module is responsible for registering and issuing contracts, triggering the contracts and executing the contracts, developers can define contract logics through a certain programming language, issue the contract logics to a block chain (contract registration), call keys or other event triggering and executing according to the logics of contract clauses, complete the contract logics and simultaneously provide the function of upgrading and canceling the contracts; the operation monitoring module is mainly responsible for deployment, configuration modification, contract setting, cloud adaptation in the product release process and visual output of real-time states in product operation, such as: alarm, monitoring network conditions, monitoring node equipment health status, and the like.

The platform product service layer provides basic capability and an implementation framework of typical application, and developers can complete block chain implementation of business logic based on the basic capability and the characteristics of the superposed business. The application service layer provides the application service based on the block chain scheme for the business participants to use.

For the embodiment of the application, the marking result and the corresponding marking time are stored in the block chain, so that the block chain can be prevented from being tampered. Then, each marking result and corresponding marking time can be obtained from the block chain, and then each marking result is sequenced according to the sequence of the corresponding marking time, so as to obtain a marking result set with time sequence. It is understood that since tamper resistance is possible, the accuracy can be improved based on the marking result obtained from the block chain and the marking time generated set of the marking results.

In one embodiment, the step S304 performs word segmentation processing on the group message, and obtaining the word segment includes: and when the group message comprises an intention group message representing the group building intention, performing word segmentation on the intention group message to obtain word segments. In this embodiment, determining, according to the semantic representation word segment, a group name for representing the current group chat subject includes: and determining a group name for representing the clustering intention according to the semantic representation word segment.

Specifically, when the intent group message is included in the group message, the computer device may perform word segmentation processing only on the intent group message to obtain a word segment. And then, selecting semantic representation word segments in the word segments, wherein the selected semantic representation word segments are semantic representation word segments representing the clustering intention. The computer device may determine a group name for characterizing the clustering intent from the semantic token word segments characterizing the clustering intent. Further, the computer device may replace the initial group name with a group name that characterizes the intent to crowd.

In one embodiment, when the computer device is a social platform server, the intention group message may be sent to a naming server, and the naming server performs asynchronous processing on the intention group message to perform semantic recognition on the intention group message, and performs word segmentation on the intention group message to obtain a word segment. The naming server can select semantic representation word segments from the word segments, and then generate group names for representing the clustering intents according to the semantic representation word segments. It is understood that the computer device may input the semantic representation word segments into the group name generation model to output the group names, or perform semantic reorganization on the semantic representation word segments to generate the group names, or search the group names matching the semantic representation word segments from the group name library.

In one embodiment, the computer device may perform semantic matching on the word segments obtained by word segmentation with a preset mass word segmentation library to identify semantic representation word segments therefrom. It is to be understood that the semantic representation word segment corresponds to a group chat topic tag, and the computer device may determine a group name for representing the group intent by using the identified semantic representation word segment as the group chat topic tag.

In one embodiment, the initial group name may be a default group name for group creation.

The default group name in the clustering process is the group name distributed according to the default initial clustering naming rule. For example, the group name obtained from the name combination of the group members during the group building is the default group name. It can be understood that the scheme in this embodiment is applicable to a use scenario in which a user establishes a group but does not define a group name by self, and in this scenario, a group name used for representing an establishment intention may be automatically generated according to an intention group message based on the scheme in this embodiment, so as to replace the default group name.

In the embodiment, the group name according with the group building intention can be automatically generated without manually modifying the group name by the user, so that the automatic modification of the group name in the first chat process is realized, the group naming efficiency is greatly improved, and the naming accuracy is also ensured. In addition, the group name which is automatically generated and used for representing the group intention can enable the group members to quickly know the group intention, so that the group members can quickly join the group chat.

In one embodiment, the social group is a first social group. In this embodiment, determining, according to the semantic representation word segment, a group name for representing the current group chat subject includes: determining a second social group; the semantic representation word segments belong to high-frequency words in the group messages of the second social group; searching a group name corresponding to the second social group; and determining the group name of the first social group according to the searched group name and used for characterizing the current group chat subject.

Wherein the second social group is different from the first social group. The high-frequency vocabulary refers to vocabulary with the occurrence frequency meeting a preset high-frequency condition in the group message of the second social group. The high frequency condition may be that the frequency of occurrence is greater than or equal to a preset frequency threshold. The second social group is at least one.

It should be noted that the occurrence frequency of the semantic term segment in the group message refers to the occurrence frequency of the semantic term segment itself and the synonyms and/or near-synonyms of the semantic term segment in the group message. For example, if the semantic token segment is "won," it may be determined that "won is a high-frequency word in the group message of the social group a when the occurrence frequency of" won is greater than or equal to the preset frequency threshold in the group message, and the synonym and/or the synonym of "won is greater than or equal to the preset frequency threshold.

Specifically, the computer device may search for a semantic representation word segment, find an appearance frequency in a group message different from a social group of the first social group, and determine that the semantic representation word segment belongs to a high-frequency vocabulary in the group message of the social group when the appearance frequency in the social group meets a preset high-frequency condition.

In one embodiment, when the semantic representation word segment belongs to a high-frequency vocabulary in the group messages of the plurality of social groups, the plurality of social groups are all determined as the second social group. The computer device may search for group names corresponding to the plurality of second social groups, and return a set of the searched group names to the terminal. The user may select a group name from the set of group names, and the computer device may determine the selected group name as the group name of the first social group and used to characterize the current group chat subject matter.

In another embodiment, when the semantic representation word segment belongs to a high frequency vocabulary in the group message of the plurality of social groups, the computer device may select the social group with the highest frequency of occurrence from the plurality of social groups as the second social group. In this way, the computer device may directly use the group name of the second social group as the group name of the first social group and used to characterize the current group chat subject. The computer device may replace the initial group name with the group name for characterizing the current group chat theme, or may generate a recommendation message to be sent to the terminal, and when the user enables the recommended group name based on the terminal, replace the initial group name with the group name for characterizing the current group chat theme.

For example, in the group message of the first social group, words such as "royal glory" and "thrill battlefield" have the highest frequency and belong to semantic representation word segments. Suppose that 327 similar high-frequency words of the semantic representation word segment hit the social group a, which indicates that the semantic representation word segment is a high-frequency word in the group message of the social group a. The social group a is the second social group, and if the group name is "eat chicken good for tonight", the group name can be recommended to the user. For another example, assuming that the semantic representation word segments belong to high-frequency words in a plurality of social groups, the plurality of social groups may be the second social group, and the corresponding group names may be obtained, respectively, and assuming that the group names are "people are on the tower", "open black together", or "eat chicken in great profits this night", the set of the group names (i.e., the group name recommendation list) may be recommended to the user. The user may select the group name that the user wants to enable, and then replace the initial group name with the selected group name.

It is understood that the computer device may directly look up the group name corresponding to the second social group from the social platform server.

In other embodiments, the group name of each social group in the social platform may be pre-stored in the blockchain, and then the computer device may look up the group name corresponding to the second social group from the blockchain. Therefore, the searched group name can be ensured not to be falsified, and the group name of the current group chat subject can be represented. In the above embodiment, the group name recommendation is performed by using the background group name library, and the group name of the second social group of the high-frequency vocabulary to which the semantic representation word segment belongs is recommended, because the semantic representation word segment also belongs to the high-frequency vocabulary in the second social group, to a certain extent, the group name of the second social group has strong correlation with the semantic representation word segment, and the characteristic represented by the semantic representation word segment can be embodied to a great extent. Therefore, the group name of the second social group is recommended, and the group naming efficiency and naming accuracy are improved. Moreover, based on the group name of the second social group, the group members can quickly know the current group chat subject, the efficiency of joining the group chat is improved, and the waste of system resources caused by browsing the group chat records is avoided. In addition, the group name of the second social group is recommended, accurate information sharing is achieved, and the diversity of group naming is improved.

In one embodiment, the computer device may perform step S302 after being triggered to turn on the group name recommendation function.

In one embodiment, a control for turning on or off the group name recommendation function may be displayed in the group setting interface of the terminal. The user can perform triggering operation on the control to trigger the computer equipment to start or close the group name recommendation function. In another embodiment, the user may also perform a preset trigger action through an interface of the terminal to trigger the computer device to turn on or off the group name recommendation function. The user can also do a remote preset action instead of the interface of the terminal, and the terminal informs the computer equipment after detecting the preset action of the user so as to trigger the computer equipment to start or close the group name recommendation function.

In one embodiment, obtaining group messages interacted in a social group comprises: when a group message for requesting recommendation of a group name is detected from group messages in the social group, an interactive group message is acquired from the social group.

The message content of the group message for requesting recommendation of the group name comprises keywords of the recommendation of the group name. For example, the group message "please recommend a group name bar" is a group message for requesting recommendation of a group name.

Specifically, the user may transmit a group message for requesting recommendation of a group name in a social group through the terminal. When detecting a group message for requesting recommendation of a group name, the computer device triggers the start of a group name recommendation function to execute a step of acquiring the group message sent within a preset time before the current time from the social group and subsequent steps.

It will be appreciated that the group members may also request to turn off the group name recommendation function by sending a group message in the social group. The computer device may then turn off the function of recommending group names after receiving the group message.

In the above embodiment, by simply sending the group message, control of turning on or off the group name recommendation can be achieved, and compared with the case where a separate access to the group setting interface is required for setting, the operation is greatly simplified, and the efficiency is improved. In addition, the group name recommending function is controlled to be turned on or off by sending the group message, so that the use of the group name recommending function is transparent, and the group members can know the turning on or off of the function through the group message, thereby improving the rationality and effectiveness of group management.

In one embodiment, replacing the initial group name of the social group with the determined group name comprises: in the social group, returning a group name recommendation message comprising the determined group name; and when a recommendation enabling instruction for the group name recommendation message is received, replacing the initial group name of the social group with the group name confirmed to be enabled by the recommendation enabling instruction.

The group name recommendation message refers to a group message whose message content includes a recommended group name. I.e. the recommended group name, is a component of the substantive message content of the group name recommendation message. The instruction to enable recommendation is an instruction to enable a recommended group name. The enabled group name is confirmed to be the group name to be enabled specified by the enabled recommending instruction.

Specifically, the computer device may return the group name recommendation message to the terminal corresponding to the group member identifier through the social group. Each terminal may present the group name recommendation message. The user can confirm whether the recommended group name is enabled or not for the group name recommendation message, and when the recommended group name is confirmed to be enabled, a recommendation enabling instruction for the group name recommendation message is generated and sent to the computer device. The computer device may then replace the initial group name of the social group with the group name that was confirmed enabled by the enable recommendation instruction.

For ease of understanding, this is now exemplified. Return messages from the group steward in the social group: "i recommend for you 'eat chicken good girls this evening' group name, ask for whether to start? When the user clicks on the enabled group name, the initial group name is changed to the group name "eat chicken good girls this evening".

It will be appreciated that when the recommended group name is one, then the initial group name may be replaced directly with the recommended group name. When the recommended group name is multiple, the user may select the confirmed enabled group name from the set of recommended group names, and further generate an enabled recommendation instruction. The computer device may then replace the initial group name of the social group with the selected confirmed enabled group name.

It will be appreciated that when the deny enable instruction is received, the initial group name of the social group is kept unchanged. It is to be understood that the deny enable instruction refers to an instruction to deny enablement of the recommended group name.

FIG. 6 is a simplified diagram of a flow of group name recommendations in one embodiment. Referring to fig. 6, upon receiving a group name recommendation message, it is determined whether a recommended new group name is enabled, and if so, the enabled group name is determined and the group name of the social group is changed to the enabled group name. If the enablement of the recommended group name is denied, then this is done, i.e., the initial group name of the social group is kept unchanged.

In the embodiment, the group name recommendation message including the determined group name is returned in the social group, so that the group members can know the recommended group name through the group message, the group name recommendation can be transparent and convenient, and the recommendation efficiency is improved. In addition, after the recommendation enabling instruction for the group name recommendation message is received, the initial group name of the social group is replaced by the group name confirmed to be enabled by the recommendation enabling instruction, and the accuracy of group name replacement is improved.

In one embodiment, identifying the social group according to the group chat theme information comprises: adding the group chat subject information to the social group as a subtitle; returning the subtitles to the terminals corresponding to the group member identifications; the subheading is used for indicating each terminal to display the subheading corresponding to the social group; the group member identifier is an identifier uniquely corresponding to each group member in the social group.

In particular, the computer device may not change the current initial group name of the social group, but add group chat motif information to the social group as a subtitle to tag the social group. The computer device may return the subtitles to the terminals corresponding to the group member identifications. The terminal, upon receiving the subheading, may present the subheading corresponding to the social group.

In one embodiment, the subtitle is used to refer to that the terminal correspondingly shows the subtitle at a preset position below a group name of a session interface (i.e., a group chat window) of a social group, or at a preset area of the session interface.

It is understood that in the embodiment, the original information of the social group is not changed, and the annotation about the group chat subject is provided for the user in the form of a subtitle. The subheading does not affect the group name and other logical settings of the social group during the change process.

For ease of understanding, this is now exemplified. For example, the group ". 16 level softworker 3 shifts of university", group messages of recent chats, after semantic analysis, are mainly recommended as topics (i.e. group chat subject information) around next shift commission. At this time, a subheading of "shift committee recommendation" is added to the group, so that students who open a group chat can immediately understand the topic of discussion. For another example, the group "2 shifts from southern mountain kindergarten", the recent chat message is mainly about the topic of parent notification through semantic analysis, and after the semantic is recognized, a subtitle "2 shifts from southern mountain kindergarten parent notification" is added to the group. And enabling parents who subsequently open the group chat to immediately understand the theme of the current group chat discussion.

Fig. 7 to 8 are schematic diagrams of interfaces for adding subtitles in one embodiment. Fig. 7 is a group chat interface before adding subtitles. Referring to fig. 7, the group name is ". x. university grade 16 softworker 3 shifts". Previously, the group members discussed mainly things in the group that new scholars, so the subheading 702 was "Notification of New scholars". Recently, the group members mainly discuss the next shift commission recommendation list, so that a new subheading 802 "shift commission recommendation" can be generated according to the scheme of the embodiment of the application to replace the previous subheading "new school issue notice". That is, the interface diagram after replacing the subtitle shown in fig. 8 is obtained.

In the embodiment, the group chat subject information is marked as the subtitle, so that the current group chat subject is embodied without influencing the original information of the social group, a user can quickly know the group chat subject, and the efficiency of joining the group chat is improved. In addition, the original logic is not changed in a subheading mode, and the efficiency is improved.

As shown in fig. 9, in an embodiment, a group processing method is provided, and the method is mainly used for the example of applying to the terminal shown in fig. 1. The method specifically comprises the following steps:

s902, displaying a session interface of the social group.

S904, the group message interacted in the social group is displayed in the session interface.

And S906, when at least one part of the group message corresponds to the group chat subject information, identifying the social group in the conversation interface according to the group chat subject information.

The fact that at least a part of the group messages correspond to the group chat subject information means that at least a part of the group messages exist in the displayed group messages and can represent the group chat subject. It can be understood that, after the server determines the group chat subject information according to the at least part of the group messages, the group chat subject information is returned to the terminal, and the returned group chat subject information corresponds to the at least part of the group messages. The terminal may then identify the social group in the conversation interface in accordance with group chat motif information corresponding to at least a portion of the group message.

In one embodiment, the identifying the social group in the session interface according to the group chat theme information in step S904 includes: when the group chat subject information is a group name, replacing the initial group name of the social group with the received group name in the session interface; or, when the group chat subject information is the subheading, displaying the subheading corresponding to the social group in the session interface.

Referring to fig. 4 to 5, the server analyzes the interactive group message, generates a group name 'congratulatory survey a college of qinghua' representing the subject of the group chat, and returns it to the terminal. The terminal may replace the initial group name "relative group" with a new group name "congratulatory a college of council of japan". As can be seen from fig. 5, the group name "congratulatory a to be college of qinghua" is identical to the subject of the group chat represented by the group message displayed on the session interface, i.e. corresponds to the group message.

Referring to fig. 7 to 8, the server analyzes the interactive group message and returns the group chat subject information "shift commission recommendation" to the terminal in the form of a subtitle. The terminal may then replace the original subtitle "new schdule start notice" with the new subtitle "shift committee notice". As can be seen from fig. 8, the group name "shift commission recommendation" is the same as the group chat substance represented by the group message displayed on the session interface, i.e., corresponds to the group message.

According to the group processing method, the group members can know the current group chat subject of the social group only by looking up the marks according to the group chat subject information, and do not need to know the group chat subject by browsing a large number of group chat records, so that consumption of system resources caused by browsing a large number of group chat records is saved.

FIG. 10 is a timing diagram of a group processing method in one embodiment. Referring to fig. 10, the sequence diagram includes a plurality of terminals, an instant messaging server, and a naming server. The method specifically comprises the following steps:

1) each terminal sends a group message to the instant messaging server through the social group.

The terminal is a terminal in which the group member identifier of the social group logs in.

2) When the group message comprises the intention group message for representing the group building intention, the instant communication server sends the intention group message to the naming server.

3) The naming server carries out word segmentation processing on the intention group message to obtain word fragments; selecting semantic representation word segments in the word segments; and determining a group name for representing the clustering intention according to the semantic representation word segment.

4) The naming server sends a group name for representing the clustering intention to each terminal to instruct each terminal to change the group name into the group name for representing the clustering intention.

5) The terminal sends a group message for requesting recommendation of the group name to the instant messaging server so as to start the function of recommending the group name.

6) The instant communication server acquires the interactive group message from the social group and sends the acquired group message to the naming server.

7) The naming server carries out word segmentation processing on the group message to obtain word segments; and selecting semantic representation word segments in the word segments.

8) When the group chat subject is marked by the group name mode, the naming server determines the group name for representing the group chat subject according to the semantic representation word segment.

9) And the naming server sends a group name recommendation message comprising the determined group name to each terminal in the social group.

10) And after receiving the recommendation starting instruction, each terminal updates the current group name into the recommended group name.

11) When the group chat subject is marked in the form of the subheading, the naming server generates group chat subject information according to the semantic representation word segment, and adds the group chat subject information to the social group as the subheading.

12) The naming server returns the subtitles to the terminals.

13) And after receiving the recommendation enabling instruction, each terminal displays the subtitle corresponding to the social group.

14) And the naming server sorts the updated group names or subheadings according to the sequence of the corresponding marking time to obtain a group name set or subheading set with time sequence.

15) And the naming server returns the group name set or the subheading set with the time sequence to each terminal.

16) And each terminal displays the group name set or the subheading set with time sequence in a preset area corresponding to the social group.

As shown in fig. 11, in one embodiment, a group processing apparatus 1100 is provided and disposed in a server. The apparatus 1100 comprises: an acquisition module 1102, a subject determination module 1104, and a marking module 1106, wherein:

an obtaining module 1102 is configured to obtain a group message interacted in a social group.

A subject determination module 1104, configured to perform word segmentation processing on the group message to obtain word segments; selecting semantic representation word segments in the word segments; and determining group chat subject information currently corresponding to the social group according to the semantic representation word fragments.

A tagging module 1106 configured to identify the social group according to the group chat subject information.

In one embodiment, the substance determining module 1104 is further configured to determine a group name for characterizing the current group chat substance according to the semantic representation word segment; the tagging module 1106 is also for replacing an initial group name of the social group with the determined group name.

In one embodiment, the theme determination module 1104 is further configured to, when the group message includes an intention group message representing a group intention, perform word segmentation on the intention group message to obtain a word segment. The subject matter determination module 1104 is further configured to determine a group name for characterizing the clustering intent according to the semantic representation word segment.

In one embodiment, the subject matter determination module 1104 is further configured to semantically recombine the semantic token fragments; and generating a group name for representing the group chat subject according to the semantic information obtained by the reorganization.

In one embodiment, the social group is a first social group. The subject determination module 1104 is further for determining a second social group; the semantic representation word segment belongs to a high-frequency vocabulary in the group message of the second social group; the second social group is different from the first social group; searching a group name corresponding to the second social group; and determining the group name of the first social group according to the searched group name and used for representing the current group chat subject.

In one embodiment, the obtaining module 1102 is further configured to, when a group message requesting recommendation of a group name is detected from a social group, obtain an interactive group message from the social group; or acquiring interactive group messages in the social group according to a preset period.

In one embodiment, the tagging module 1106 is further configured to return a group name recommendation message including the determined group name in the social group; and when a recommendation enabling instruction for the group name recommendation message is received, replacing the initial group name of the social group with the group name confirmed to be enabled by the recommendation enabling instruction.

In one embodiment, the tagging module 1106 is further configured to add the group chat subject information to the social group as a subtitle; returning the subtitles to the terminals corresponding to the group member identifications; the subheading is used for indicating each terminal to display the subheading corresponding to the social group; the group member identifier is an identifier uniquely corresponding to each group member in the social group.

In one embodiment, the marking module 1106 is further configured to obtain marking results obtained by performing the identification and marking time corresponding to each of the marking results; sequencing the marking results according to the sequence of the corresponding marking time to obtain a marking result set with time sequence; and returning the marking result set to a terminal corresponding to each group member identifier in the social group so as to indicate each terminal to correspondingly display the marking result set and the social group.

In one embodiment, the subject determination module 1104 is further configured to determine a heat value corresponding to each of the word segments; determining the weight of each word segment according to the heat value; the weight is positively correlated with the heat value; sequencing the word segments according to the sequence of the weights from big to small; and selecting the word segments ordered at the previous preset order to obtain the semantic representation word segments.

As shown in fig. 12, in one embodiment, there is provided a group processing apparatus 1200 applied to a terminal, the apparatus 1200 including: a presentation module 1202 and a marking module 1204, wherein:

a display module 1202, configured to display a session interface of a social group; presenting, in the conversation interface, group messages that interact in the social group.

A marking module 1204, configured to identify the social group in the session interface according to the group chat subject information when at least a portion of the group message corresponds to the group chat subject information.

In one embodiment, the tagging module 1204 is further configured to replace the initial group name of the social group with the received group name in the session interface when the group chat theme information is a group name; or when the group chat subject information is a subheading, displaying the subheading corresponding to the social group in the session interface.

In one embodiment, the tagging module 1204 is further configured to, when the group message includes an intention group message, identify, according to the intention group message, the group intention information corresponding to the social group in the session interface.

In one embodiment, the tagging module 1204 is further configured to replace, in the conversation interface, the initial group name of the social group with a group name that characterizes the intent to group; and the group name representing the clustering intention is generated according to the intention group message.

In one embodiment, the group chat subject information is obtained by triggering word segmentation processing on a group message which is sent in a preset time before the current time in a social group after detecting a group message for requesting recommendation of a group name, and determining according to a semantic representation word segment selected from word segments obtained by the word segmentation processing.

In one embodiment, the tagging module 1204 is further configured to present a group name recommendation message including the group name in the conversation interface; wherein the group name corresponds to at least a portion of the group message; and when a recommendation enabling instruction for the group name recommendation message is received, replacing the initial group name of the social group with the group name confirmed to be enabled by the recommendation enabling instruction.

In one embodiment, the tagging module 1204 is further configured to obtain a chronological group name set or a chronological subtitle set, and display the chronological group name set or the subtitle set in a preset area in the conversation interface corresponding to the social group. The group name set or the subheading set is arranged according to the sequence of the marking time corresponding to the determined group name, or the group name set or the subheading set is arranged according to the sequence of the marking time corresponding to the determined subheading.

FIG. 13 is a block diagram of a computer device in one embodiment. Referring to FIG. 13, the computer device may be the server 120 of FIG. 1. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device may store an operating system and a computer program. The computer program, when executed, causes a processor to perform a group processing method. The processor of the computer device is used for providing calculation and control capability and supporting the operation of the whole computer device. The internal memory may store a computer program that, when executed by the processor, causes the processor to perform a group processing method. The network interface of the computer device is used for network communication.

Those skilled in the art will appreciate that the architecture shown in fig. 13 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, the group processing apparatus or the data transmission apparatus provided in the present application may be implemented in the form of a computer program that can be run on a computer device as shown in fig. 13, and the nonvolatile storage medium of the computer device may store the respective program modules constituting the group processing apparatus or the data transmission apparatus. Such as acquisition module 1102, subject determination module 1104, and tagging module 1106 shown in fig. 11. The computer program composed of the respective program modules is used for causing the computer device to execute the steps in the group processing method of the embodiments of the present application described in the present specification.

For example, the computer device may obtain the group message interacted with in the social group through the obtaining module 1102 in the group processing apparatus 1100 shown in fig. 11. The computer device can perform word segmentation processing on the group message through the subject determination module 1104 to obtain word segments; selecting semantic representation word segments in the word segments; the semantic representation word segment is a word segment capable of representing the semantics of the group message; and determining group chat subject information currently corresponding to the social group according to the semantic representation word fragments. The computer device can identify the social group by tagging module 1106 according to the group chat subject information.

FIG. 14 is a diagram showing an internal configuration of a computer device according to an embodiment. Referring to fig. 14, the computer device may be the terminal 110 of fig. 1. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device may store an operating system and a computer program. The computer program, when executed, causes a processor to perform a group processing method. The processor of the computer device is used for providing calculation and control capability and supporting the operation of the whole computer device. The internal memory may store a computer program that, when executed by the processor, causes the processor to perform a group processing method. The network interface of the computer device is used for network communication. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer equipment can be a touch layer covered on a display screen, a key, a track ball or a touch pad arranged on a terminal shell, an external keyboard, a touch pad or a mouse and the like. The computer device may be a personal computer, a smart speaker, a mobile terminal or a vehicle-mounted device, and the mobile terminal includes at least one of a mobile phone, a tablet computer, a personal digital assistant or a wearable device.

Those skilled in the art will appreciate that the architecture shown in fig. 14 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, the group processing apparatus provided in the present application may be implemented in a form of a computer program, the computer program may be executed on a computer device as shown in fig. 14, and the non-volatile storage medium of the computer device may store various program modules constituting the group processing apparatus, such as the presentation module 1202 and the marking module 1204 shown in fig. 12. The computer program composed of the program modules is used for causing the computer device to execute the steps in the group processing method according to the embodiments of the present application described in the present specification, for example, the computer device may display a conversation interface of a social group through a display module 1202 in the group processing apparatus 1200 shown in fig. 12; presenting, in the conversation interface, group messages that interact in the social group. The computer device can identify the social group in the session interface according to the group chat theme information when at least a portion of the group message corresponds to the group chat theme information via tagging module 1204.

In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the group processing method described above. Here, the steps of the group processing method may be steps in the group processing methods of the above embodiments.

In one embodiment, a computer-readable storage medium is provided, in which a computer program is stored, which, when executed by a processor, causes the processor to carry out the steps of the group processing method described above. Here, the steps of the group processing method may be steps in the group processing methods of the above embodiments.

It should be noted that "first" and "second" in the embodiments of the present application are used only for distinction, and are not used for limitation in terms of size, order, dependency, and the like.

It should be understood that although the steps in the embodiments of the present application are not necessarily performed in the order indicated by the step numbers. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in various embodiments may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least some of the sub-steps or stages of other steps.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A method of group treatment, the method comprising:

acquiring interactive group messages in a social group;

2. The method of claim 1, wherein the determining group chat subject information to which the social group currently corresponds according to the semantic representation word segment comprises:

3. The method of claim 2, wherein the performing word segmentation on the group message to obtain word segments comprises:

4. The method of claim 2, wherein determining a group name for characterizing a current group chat motif from the semantic characterization word segments comprises:

5. The method of claim 2, wherein the social group is a first social group; the determining, according to the semantic representation word segment, a group name for representing a current group chat subject matter includes:

searching a group name corresponding to the second social group;

6. The method of claim 2, wherein obtaining group messages interacted in a social group comprises:

7. The method of any of claims 2-6, wherein replacing the initial group name of the social group with the determined group name comprises:

8. The method of any one of claims 1 to 6, wherein the identifying the social group according to the group chat theme information comprises:

adding the group chat subject information to the social group as a subtitle;

9. The method according to any one of claims 1 to 6, further comprising:

10. The method of claim 9, further comprising:

obtaining a marking result obtained by marking;

acquiring marking time corresponding to each marking result;

11. The method according to any one of claims 1 to 6, wherein the selecting the semantic representation word segment comprises:

determining a heat value corresponding to each word segment;

12. A method of group treatment, the method comprising:

displaying a session interface of the social group;

13. The method of claim 12, wherein the identifying the social group in the session interface in accordance with the group chat theme information comprises:

14. A group processing apparatus, comprising:

15. A computer arrangement comprising a memory and a processor, the memory having stored therein a computer program which, when executed by the processor, causes the processor to carry out the steps of the method of any one of claims 1 to 13.