CN110581772B

CN110581772B - Instant messaging message interaction method and device and computer readable storage medium

Info

Publication number: CN110581772B
Application number: CN201910842445.7A
Authority: CN
Inventors: 陈姿
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2019-09-06
Filing date: 2019-09-06
Publication date: 2020-10-13
Anticipated expiration: 2039-09-06
Also published as: CN110581772A

Abstract

The embodiment of the invention discloses an instant messaging message interaction method, an instant messaging message interaction device and a computer readable storage medium. The scheme receives a session message of a target session group; performing scene analysis on the session message, and determining a preset session scene in which the target session group is located according to a scene analysis result; determining a target semantic analysis algorithm corresponding to a preset conversation scene, performing semantic analysis on the conversation message through the target semantic analysis algorithm, and generating a message to be replied according to a semantic analysis result; and sending the message to be replied to the target session group, determining a proper target semantic algorithm through different preset session scenes, performing semantic analysis on the session message based on the target semantic algorithm, generating the message to be replied matched with the session scene for interaction, better adjusting the chat atmosphere in the target session group, improving the interaction efficiency of instant messaging information and further improving the activity of the session group.

Description

Instant messaging message interaction method and device and computer readable storage medium

Technical Field

The invention relates to the technical field of communication, in particular to an instant messaging message interaction method, an instant messaging message interaction device and a computer-readable storage medium.

Background

With the increasing popularization of electronic products and various instant messaging software, people are willing to communicate through the instant messaging software more and more, the various instant messaging software has a group chat function, and in the same group, group members in each group can freely send group chat messages.

Users generally participate in a plurality of chat groups, discussion groups and the like in instant messaging software, but in some cases, a group may have an inactive chat atmosphere, or a phenomenon that a group member sends a group chat message but does not reply by any person, which causes a cold scene of the group, and further causes difficulty in maintaining the liveness of the group.

Disclosure of Invention

The embodiment of the invention provides an instant messaging message interaction method, an instant messaging message interaction device and a computer readable storage medium, and aims to improve the interaction efficiency of instant messaging messages.

The embodiment of the invention provides an interactive method of instant messaging messages, which comprises the following steps:

receiving a session message of a target session group;

performing scene analysis on the session message, and determining a preset session scene in which the target session group is located according to a scene analysis result;

determining a target semantic analysis algorithm corresponding to a preset conversation scene, performing semantic analysis on the conversation message through the target semantic analysis algorithm, and generating a message to be replied according to a semantic analysis result;

and sending the message to be replied to the target session group.

The embodiment of the present invention further provides an interactive device for instant messaging messages, including:

the first acquisition unit is used for receiving the session message of the target session group;

the scene analysis unit is used for carrying out scene analysis on the session message and determining a preset session scene in which the target session group is located according to a scene analysis result;

the semantic analysis unit is used for determining a target semantic analysis algorithm corresponding to a preset conversation scene, performing semantic analysis on the conversation message through the target semantic analysis algorithm, and generating a message to be replied according to a semantic analysis result;

and the message reply unit is used for sending the message to be replied to the target session group.

The embodiment of the present invention further provides a computer-readable storage medium, where multiple instructions are stored in the computer-readable storage medium, and the instructions are suitable for being loaded by a processor to execute any method for interacting an instant messaging message provided in the embodiment of the present invention.

The embodiment of the invention also provides a server, which comprises a processor and a memory, wherein the memory is provided with a computer program, and the processor executes any instant messaging message interaction method provided by the embodiment of the invention by calling the computer program.

The interactive scheme of the instant messaging message provided by the embodiment of the invention receives the session message of the target session group, performs scene analysis on the session message, determines the preset session scene of the target session group according to the scene analysis result, determines the target semantic analysis algorithm corresponding to the preset session scene, performs semantic analysis on the session message through the target semantic analysis algorithm, generates the message to be replied according to the semantic analysis result, and transmits the message to be replied to the target session group, so that the appropriate target semantic algorithm is determined through different preset session scenes, the session message is subjected to semantic analysis based on the target semantic algorithm, the message to be replied matched with the session scene is generated for interaction, the chat atmosphere in the target session group is better adjusted, and the interaction efficiency of the instant messaging message is improved, thereby improving the activity of the session group.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1a is an alternative structural diagram of a distributed system applied to a blockchain system according to an embodiment of the present invention;

FIG. 1b is an alternative block structure according to an embodiment of the present invention;

fig. 1c is a schematic view of a scenario of an instant messaging interactive system according to an embodiment of the present invention;

fig. 1d is a first flowchart of an interaction method for instant messaging messages according to an embodiment of the present invention;

fig. 1e is a schematic diagram of a first session interface in the method for interacting instant messaging messages according to the embodiment of the present invention;

fig. 1f is a schematic diagram of a second session interface in the method for interacting instant messaging messages according to the embodiment of the present invention;

fig. 2a is a second flow chart of an interaction method of instant messaging messages according to an embodiment of the present invention;

fig. 2b is a schematic third flow chart of an interaction method of an instant messaging message according to an embodiment of the present invention;

fig. 2c is a fourth flowchart illustrating an interaction method of instant messaging messages according to an embodiment of the present invention;

fig. 2d is a fifth flowchart illustrating an interaction method of instant messaging messages according to an embodiment of the present invention;

fig. 3a is a schematic diagram of a first structure of an instant messaging message interaction device according to an embodiment of the present invention;

fig. 3b is a schematic diagram of a second structure of an instant messaging message interaction device according to an embodiment of the present invention;

fig. 3c is a schematic diagram of a third structure of an instant messaging message interaction apparatus according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

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

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.

Artificial Intelligence (AI) is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human Intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. 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.

The artificial intelligence technology is a comprehensive subject and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

Among them, Natural Language Processing (NLP) is an important direction in the fields of computer science and artificial intelligence. It studies various theories and methods that enable efficient communication between humans and computers using natural language. Natural language processing is a science integrating linguistics, computer science and mathematics. Therefore, the research in this field will involve natural language, i.e. the language that people use everyday, so it is closely related to the research of linguistics. Natural language processing techniques typically include text processing, semantic understanding, machine translation, robotic question and answer, knowledge mapping, and the like.

The system related to the embodiment of the invention can be a distributed system formed by connecting a client, a plurality of nodes (any form of computing equipment in an access network, such as a server and a user terminal) through a network communication mode.

Taking a distributed system as an example of a blockchain system, referring to fig. 1a, fig. 1a is an optional structural schematic diagram of a blockchain system to which the distributed system 100 provided by the embodiment of the present invention is applied, where the blockchain system is formed by a plurality of nodes (computing devices in any form in an access network, such as servers and user terminals) and clients, and a Peer-to-Peer (P2P, Peerto Peer) network is formed between the nodes, and a P2P protocol is an application layer protocol operating on a Transmission Control Protocol (TCP). In a distributed system, any machine, such as a server or a terminal, can join to become a node, and the node comprises a hardware layer, a middle layer, an operating system layer and an application layer.

Referring to the functions of each node in the blockchain system shown in fig. 1a, the functions involved include:

1) routing, a basic function that a node has, is used to support communication between nodes.

Besides the routing function, the node may also have the following functions:

2) the application is used for being deployed in a block chain, realizing specific services according to actual service requirements, recording data related to the realization functions to form recording data, carrying a digital signature in the recording data to represent a source of task data, and sending the recording data to other nodes in the block chain system, so that the other nodes add the recording data to a temporary block when the source and integrity of the recording data are verified successfully.

For example, the services implemented by the application include:

2.1) wallet, for providing the function of transaction of electronic money, including initiating transaction (i.e. sending the transaction record of current transaction to other nodes in the blockchain system, after the other nodes are successfully verified, storing the record data of transaction in the temporary blocks of the blockchain as the response of confirming the transaction is valid; of course, the wallet also supports the querying of the remaining electronic money in the electronic money address;

and 2.2) sharing the account book, wherein the shared account book is used for providing functions of operations such as storage, query and modification of account data, record data of the operations on the account data are sent to other nodes in the block chain system, and after the other nodes verify the validity, the record data are stored in a temporary block as a response for acknowledging that the account data are valid, and confirmation can be sent to the node initiating the operations.

2.3) Intelligent contracts, computerized agreements, which can enforce the terms of a contract, implemented by codes deployed on a shared ledger for execution when certain conditions are met, for completing automated transactions according to actual business requirement codes, such as querying the logistics status of goods purchased by a buyer, transferring the buyer's electronic money to the merchant's address after the buyer signs for the goods; of course, smart contracts are not limited to executing contracts for trading, but may also execute contracts that process received information.

3) And the Block chain comprises a series of blocks (blocks) which are mutually connected according to the generated chronological order, new blocks cannot be removed once being added into the Block chain, and recorded data submitted by nodes in the Block chain system are recorded in the blocks.

Referring to fig. 1b, fig. 1b is an optional schematic diagram of a Block Structure (Block Structure) according to an embodiment of the present invention, where each Block includes a hash value of a transaction record (hash value of the Block) stored in the Block and a hash value of a previous Block, and the blocks are connected by the hash value to form a Block chain. The block may include information such as a time stamp at the time of block generation. A block chain (Blockchain), which is essentially a decentralized database, is a string of data blocks associated by using cryptography, and each data block contains related information for verifying the validity (anti-counterfeiting) of the information and generating a next block.

The embodiment of the invention provides an instant messaging message interaction method based on natural language processing, wherein an execution main body of the instant messaging message interaction method can be an instant messaging message interaction device provided by the embodiment of the invention or a server integrated with the instant messaging message interaction device, and the instant messaging message interaction device can be realized in a hardware or software mode. In some embodiments, the instant messaging interactive device or the server integrated with the instant messaging interactive device may be a node of the distributed system, wherein different conversation groups may correspond to different nodes, for example, the following reply database of the target conversation group may be stored in a block corresponding to the target conversation group in the block chain system.

Referring to fig. 1c, fig. 1c is a schematic view of a scenario of an instant messaging interactive system according to an embodiment of the present invention. The system comprises a user terminal and a server integrated with any instant messaging message interaction device provided by the embodiment of the invention. The user terminal is connected with the server through a wireless network or a wired network, the user participates in the conversation group through instant messaging software running on the user terminal, and the conversation messages sent by the members of the conversation group are sent to the user terminals of the members in the conversation group through the server. In the embodiment of the invention, the server receives the session message of the session group, performs scene analysis on the session message, determines the preset session scene in which the session group is positioned according to the analysis result, further performs semantic analysis on the session message by using a semantic analysis algorithm corresponding to the preset session scene, generates the message to be replied according to the semantic analysis result, and sends the message to be replied to the user terminals of the members of the session group, so that the chat atmosphere in the target session group is better adjusted, the interaction efficiency of instant messaging information is improved, and the liveness of the session group is further improved.

The user terminal can be a mobile phone, a tablet computer, a notebook computer and other devices. The server may be a single server or a server cluster composed of a plurality of servers. For example, in some embodiments, an application server and a semantic analysis server are included in a server cluster. The user terminal is directly communicated with the application server, the application server receives a session message sent by the user terminal and sends the session message to the semantic analysis server, the semantic analysis server performs semantic analysis on the session message and sends a semantic analysis result to the application server, and the application server generates a message to be replied according to the semantic analysis result.

The example of fig. 1c is only an example of a system architecture for implementing the embodiment of the present invention, and the embodiment of the present invention is not limited to the system architecture shown in fig. 1c, and various embodiments of the present invention are proposed based on the system architecture. In the present embodiment, a detailed description will be made from the perspective of a server integrated with an interactive device for instant messaging messages. It should be noted that the following description of the embodiments is not intended to limit the preferred order of the embodiments.

Referring to fig. 1d, fig. 1d is a first flowchart of an interaction method of instant messaging messages according to an embodiment of the present invention. The specific flow of the instant messaging message interaction method may be as follows:

101. a session message for a target session group is received.

The instant messaging message interaction method can be applied to conversation scenes in which at least two members participate in applications such as instant messaging application, social application, video community application and the like.

Instant messaging refers to a communication mode of instantly sending and receiving messages through the internet. The instant messaging software refers to an application program with an instant messaging function, such as WeChat, QQ and the like. When chatting is performed by using a chat tool, two parties of the chat need to log in and start a chat device on a human-computer interface and then input chat information, and a user terminal sends the chat information to the other party so as to enable the two parties to perform chat activities, wherein the chat information (namely, session information) input by the two parties of the chat can be information in various formats such as text information, audio information and/or audio information, picture information and the like.

The conversation group refers to a set of a plurality of member users performing instant messaging. In the embodiment of the application, the target session group can only comprise two members, and when two members exist, the two members can be a one-to-one session or a chat group with two members; the target session group may also have three or more group members, for example, a chat group in WeChat, a chat group or discussion group in QQ, and some chat groups in social software such as microblog, etc., which may all be used as the target session group.

The target conversation group is a conversation group serving as an analysis object, and the server detects conversation messages sent by all members in the target conversation group in real time. It is to be understood that the conversation message as the analysis object may be one or more pieces. For example, each time the server receives a session message, the server performs scene analysis on the session message to determine a session scene of the target session group. For another example, the server performs a scene analysis on n consecutive session messages received, so as to perform a scene analysis on a combination of a session message and a context message of the session message, so as to determine a session scene of the target session group. For another example, the server performs scene analysis on a plurality of received session messages within a continuous preset time duration (e.g., 1-10 minutes), and when the server receives a session message, acquires a plurality of session messages (i.e., the previous messages of the currently received session message) within the preset time duration before the session message is sent, and performs scene analysis on the session message and the previous messages thereof.

In an embodiment, a control of "add chat robot" may be provided for a user on a chat interface of an instant messaging software client, please refer to fig. 1e, where fig. 1e is a schematic view of a first session interface in an interaction method of instant messaging messages provided in an embodiment of the present invention. The chat robot can detect scenes in the conversation group and judge whether to send some atmosphere adjusting messages. When the user adds the chat robot in the chat scene based on the control, the chat robot can participate in the conversation, and each member in the current conversation group can receive the prompt information that the chat robot is added in the conversation group. Next, the server starts to detect and analyze the session messages of the session group in real time. Moreover, for different types of data contained in the session message, a corresponding data analysis method may be adopted, for example, if the session message is text data, a text analysis algorithm is adopted to analyze the session message; if the session message contains data such as pictures and videos, the pictures or the video data can be identified by adopting an image identification related algorithm; if the conversation message contains audio data, the audio data can be analyzed by adopting a voice recognition algorithm. If the conversation message contains the chat expression, the emotion meaning corresponding to the chat label can be determined for analysis.

102. And performing scene analysis on the session message, and determining a preset session scene where the target session group is located according to a scene analysis result.

103. And determining a target semantic analysis algorithm corresponding to the preset conversation scene, performing semantic analysis on the conversation message through the target semantic analysis algorithm, and generating a message to be replied according to a semantic analysis result.

The preset conversation scenes can be various, and for different conversation scenes, the server adopts different semantic analysis algorithms to carry out semantic analysis on the conversation messages. For example, the association relationship between a preset session scene and a semantic analysis algorithm is preset in the server, and a matching semantic analysis algorithm is adopted for different session scenes. For example, the first preset session scene is a cold field scene, and the corresponding semantic analysis algorithm is an intention identification algorithm; the second preset session scene is a recall scene, and the corresponding semantic analysis algorithm is a keyword matching algorithm, and the like. After analyzing the conversation message, the server generates a message to be replied, which is matched with the current conversation scene of the conversation group, so as to adjust the chat atmosphere of the conversation group.

In some embodiments, the step of performing scene analysis on the session message and determining the preset session scene in which the target session group is located according to the scene analysis result may include: detecting whether the conversation message contains a first keyword or not; and when the conversation message is detected to contain the first keyword and the reply message is not received within the preset time interval of receiving the conversation message, judging that the target conversation group is in a first preset conversation scene.

The steps of determining a target semantic analysis algorithm corresponding to a preset conversation scene, performing semantic analysis on the conversation message through the target semantic analysis algorithm, and generating a message to be replied according to a semantic analysis result may include: when the target session group is in a first preset session scene, taking an intention recognition algorithm as a target semantic analysis algorithm; and identifying the conversation intention of the conversation message according to an intention identification algorithm, and generating the message to be replied corresponding to the conversation intention.

In this embodiment, whether the target session group is in the first preset session scenario is determined by detecting whether the session message includes a preset first keyword. For example, the first preset session scene is a cold scene, and a plurality of first keywords are defined in advance to form a first keyword set, where the first keywords are specific characters, words, symbols, and the like that can reflect that the session may be cold. For example, the first keyword may be "with or without people", "together", "i think", "do", "big", "how", "are? "etc. constitute the first set of keywords. The server detects whether the session message can be matched with the first keyword or not after receiving the session message, if so, then detects the reply condition of other members except the member sending the session message in the target group, and when detecting that the reply of other members in the target session group to the session message is not received within a preset time interval after receiving the session message, judges that a cold field appears in the target session group, namely, judges that the target session group is in a first preset session scene.

When the server detects that the target session group is located in a first preset session scene, determining a semantic analysis algorithm corresponding to the first preset session scene as a target semantic analysis algorithm from the corresponding relationship between the session scene and the semantic analysis algorithm. In the embodiment, when the target conversation group is in the first preset conversation scene, the intention recognition algorithm is used as the target semantic analysis algorithm to recognize the conversation intention of the conversation message, and then the message to be replied is generated according to the conversation intention. There are various embodiments of the intention recognition algorithm, which will be described below by way of example.

For example, a pre-trained intent recognition model is used to recognize conversational intent of conversational messages. Specifically, if the session message is text data, extracting keywords of the text data as text features, converting the text features into word vectors according to a word vector model, and inputting the word vectors into a pre-trained intention recognition model to obtain corresponding intention labels. The intention identification model is a classification model and represents the relationship between the user characteristic matrix and the intention label. For example, the intention recognition model may be obtained by training a classification algorithm such as a convolutional neural network, a BP neural network (Back Propagation) or an SVM (Support vector machine) algorithm. The method comprises the steps of training a pre-constructed classification model by using a sample word vector and an intention label added to the sample word vector in advance to obtain an intention identification model.

If the conversation message is a voice message, the voice message can be converted into text data, and then keywords are extracted from the text data to serve as text features.

For another example, the corresponding relationship between the corpus text and the dialog intention is preset. The server identifies each piece of session text data in the session message, and if the session text data contains a preset corpus text, determines a conversation intention corresponding to the corpus text as the conversation intention of the session text data. For example, if the conversation message shows the sentence "go to the dining bar together", the message can be directly identified as the intention of "engagement to eat"; if the conversation text data does not contain any preset corpus text, inputting the conversation text data into a pre-established intention recognition model, calculating the distribution probability of the conversation text on each intention label, and taking the intention with the maximum distribution probability as the intention corresponding to the conversation message.

After recognizing the dialog intention, a message to reply corresponding to the dialog intention is generated, for example, a conversation message is "want to go to eating nearby, have or not together? If the server recognizes that the conversation is intended to recommend eating based on the message, it may query some nearby dining places, generate a reply message based on the dining places, and send the chat robot to the conversation group as the sender of the message, for example, generate a message to be replied: please refer to fig. 1f, which is a schematic diagram of a second session interface in the interaction method of the instant messaging message provided by the embodiment of the present invention, and simultaneously, other members can be reminded to view the message to activate the chat atmosphere in the target session group.

As another example, the session message is "what good movies have been recently? If the server identifies that the conversation intention is a recommended movie according to the message, the server can inquire the movie currently in the showing period, select a movie with a higher user score from the movies, and send movie information or a ticket purchasing page to the target conversation group.

Or, in other embodiments, some multimedia data, such as pictures, videos and the like, sent by each member in the target conversation group may also be recorded, a multimedia file with commemorative significance is generated, the commemorative file is sent to a chat group, such as a classmate group, a work group, a relatives and friends group and the like, when the members in the group go out, travel, a party and the like together, the taken pictures of the trip are shared in the group, the server may record the pictures and information of time, place and the like, generate a commemorative atlas for storage, and after one year, the chatting robot is used as a sender of messages, the commemorative atlas is sent to the chat group, and a message of' how we remember one year ago is attached. Alternatively, when it is recognized from the session message that there is a member in the chat group who is talking and mentions the trip, the commemorative album may be sent to the chat group by using the chat robot as the sender of the message, and a message "do here" may be attached. Alternatively, in some embodiments, the generated memorial album may be uploaded to a group file for sharing to group members, who may view at any time.

Specifically, it can be realized in the following manner. In some embodiments, after the step of "receiving a session message of a target session group", the method may further include: if the session message contains multimedia data, acquiring portrait information of each member in a target session group, wherein at least two members in the target session group are provided; performing portrait recognition on the multimedia data based on the portrait information; when the member of the session group is identified in the multimedia data, acquiring a context message which is associated with the session message and belongs to the multimedia data; and generating a multimedia file according to the session message and the context message, and storing the multimedia file in association with the target session group.

In this embodiment, the server performs real-time detection on the session message of the target session group, and when detecting that the session message contains multimedia data, analyzes the multimedia data. Next, taking multimedia data as an example of a picture, it can be understood that when the multimedia data is a video, an image frame in the video can be used as an analysis object.

The method comprises the steps of obtaining portrait information of each member in a target group, wherein the portrait information can be human face features, for example, a server can analyze self-portrait shared by sharing platforms such as head portraits, photo albums or friend circles of the members in the group in advance, obtain images containing the head portraits of users, and extract the human face features from the images for storage. If the session message contains multimedia data, the server acquires the face characteristics of each member in the target session group, carries out portrait recognition on the image in the session data according to the face characteristics, and generates a multimedia file by combining the multimedia message related to the session message in the context message of the session message when recognizing that the image contains the portrait of the member in the target group. For example, the group members share various taken travel pictures in the group, the server recognizes the pictures and generates an album, and information such as a travel place and travel time is recorded in the album. For another example, in a meeting activity, the group members take videos and share the videos in the group, the server combines the videos into a video collection, and meanwhile information such as a meeting place, a meeting theme and meeting time is added to a video picture.

In some embodiments, before the step of obtaining the context message associated with the session message and belonging to the multimedia data, the method may further comprise:

when the multimedia data is identified to contain the members of the conversation group, calculating the matching degree between the conversation message and the members of the conversation group according to the identification result; and when the matching degree meets a preset condition, acquiring the context message which is associated with the session message and belongs to the multimedia data.

In this embodiment, in order to improve the accuracy of recording the multimedia data, when the multimedia data includes a member of the session group, the matching degree between the session message and the member of the session group is determined according to the recognition result, for example, the ratio of the number of the group members included in the image to the total number of the group members is calculated, the ratio is used as the matching degree, if the matching degree is greater than a preset threshold, for example, 0.5, it is determined that the matching degree meets a preset condition, and at this time, the server performs acquiring the context message which is associated with the session message and belongs to the multimedia data.

Wherein, after storing the multimedia file in association with the target session group, the server further comprises: acquiring time information and position information corresponding to the session message; and adding the time information and the position information as a group of keywords to a preset keyword set corresponding to the target session group.

Taking the group member holding the party event as an example, the server may determine the time of the party event according to the sending time of the session message, determine the location information of the party event according to the context message of the session message, and the like, and the server adds the time information and the location information as a set of second keywords to a preset keyword set corresponding to the target session group. The server records a preset keyword set for each session group, wherein each set of second keywords in the preset keyword set corresponds to a multimedia file. The preset keyword set is used for matching the session message to judge whether the multimedia file needs to be shared in the session group.

Next, how the server shares the multimedia files will be described.

As an embodiment, in some embodiments, the step of performing scene analysis on the session message and determining the preset session scene in which the target session group is located according to the scene analysis result may include:

detecting whether the conversation message contains a keyword of a preset type; and if so, judging that the target session group is in a second preset session scene.

The steps of determining a target semantic analysis algorithm corresponding to a preset conversation scene, performing semantic analysis on the conversation message through the target semantic analysis algorithm, and generating a message to be replied according to a semantic analysis result may include:

when the target session group is in a second preset session scene, taking a keyword matching algorithm as a target semantic analysis algorithm; determining a target keyword matched with the session message from a preset keyword set according to a keyword matching algorithm; and acquiring a multimedia file corresponding to the target keyword, and generating a message to be replied based on the multimedia file.

In this embodiment, after receiving the session message, the server obtains a preset keyword set corresponding to the target session group, and detects whether the current session message includes a preset type of keyword, where the preset type of keyword may be a keyword indicating a time and a place, for example, if a group member initiates a session message "recall that we are still in a party a half year ago" in a chat group, the server may calculate a party time according to the current time and the "half year ago" according to the information, and determine a party place according to session content, that is, the server may determine whether the session message includes a preset type of keyword according to whether time information and location information can be obtained from the session message. And if the time information and the position information can be obtained from the session message at the same time, judging that the target session group is in a second preset session scene, wherein the second preset session scene is a recall scene.

At this time, a keyword matching algorithm is used as a target semantic analysis algorithm, that is, a preset keyword set is matched with time information and position information obtained from a session message, if a group of second keywords is matched, the group of second keywords is used as target keywords, a multimedia file corresponding to the target keywords is obtained according to a mapping relation between the target keywords and the multimedia file, and a message to be replied is generated based on the multimedia file. For example, if a group member initiates a session message in a chat group, that is, "think that we are gathering together at a place half a year ago", the server may find a relevant album or video of the gathering, generate a message to be replied based on the found relevant album or video, and send the message to the chat group by the chat robot to activate the chat atmosphere in the target session group.

As another embodiment, after the step of "storing the multimedia file in association with the target session group", the method may further include: acquiring time information corresponding to the multimedia file, and determining a target date corresponding to the multimedia file according to a preset reminding mechanism; and when the target date is reached, generating a message to be replied based on the multimedia file, and sending the message to be replied to the target session group.

In this embodiment, the generated multimedia file may be stored, and the multimedia file may be sent to the session group at a specific time thereafter, for example, the recording time of the multimedia file is 2018, month 1 and year 8, and the preset reminding mechanism is reminding once after half a year and after one year, and then the target dates corresponding to the multimedia file are determined to be 2019, month 2 and month 1 and 2019, month 8 and month 1, and when the server detects that the system time reaches the above two dates, the image or video set recorded at the time of the last party may be collected at an appropriate time period within the date, and a message to be replied is generated and sent to the session group.

In some embodiments, when it is detected that a new member joins the target session group according to the session data, it may be determined that the target session group is in a third preset session scene, where the third preset session scene is a new people joining scene, some response messages marked as welcome may be acquired from the response database, and the chat robot is sent to the target session group as a sender of the messages.

104. And sending the message to be replied to the target session group.

After the server acquires the message to be replied, the chat robot is used as a message sender, and the message to be replied is sent to the target session group.

In some embodiments, the step of generating the message to be replied according to the semantic analysis result may include: acquiring a style label of a target session group, and acquiring response data corresponding to the style label from a response database; and generating a message to be replied according to the semantic analysis result and the response data, and sending the message to be replied to the target session group.

Since different groups may have different conversation styles, the server may obtain the conversation style labels corresponding to the conversation groups, such as "quadratic", "cynical", "formal", "family", etc., by self-learning the historical conversation messages in the groups. For example, for a target session group, the server records its historical session messages, e.g., collects the historical session messages of the target session group; and performing semantic analysis on the historical conversation messages to generate style labels of the target conversation group.

For example, the server records the last three months of chat records of the target session group or all historical chat records, and performs semantic analysis on the recorded historical session records, wherein the server extracts the keywords in the historical chat records, converts the keywords into word vectors according to a word vector model, inputs the word vectors into a pre-trained style recognition model to obtain corresponding style labels, and stores the style labels in association with the target session group. The style recognition model can be obtained by training a classification model by using pre-collected sample keywords and style labels.

Or, in other embodiments, a plurality of style tags are preset, each style tag corresponds to one answer data set, and the answer data set includes words representing a conversation style corresponding to the style tag. When the message to be replied is generated according to the semantic analysis result, the response data corresponding to the style label of the conversation group can be obtained, and the content to be replied is combined with the response data to generate the message to be replied. For example, if a group member prefers "soga" to represent "originally so", the session group may be marked as preferring two-dimensional or Japanese style, the server queries the meaning corresponding to "soga", and then the "originally so" is directly replaced by "soga" if it needs to be answered. The chat robot of the conversation group is more intelligent and personalized, the conversation style of the group can be approached during chat, and the user experience is improved.

In some embodiments, after receiving the session message of the target session group, the method may further include: detecting whether the conversation message contains words representing the membership, if so, determining at least two members corresponding to the words representing the membership according to the conversation message and the conversation message, marking the relationships of the at least two members, such as lovers, friends, families, company associates and the like, and storing the relationships in a server.

For example, a user name floret sending session "@ air-mother, you remember to call me", is matched to "mother" in the relational lexicon. Wherein, the relation lexicon contains vocabularies representing membership, such as 'dad', 'mom', 'tertiary', 'brother', 'friend', 'wife' and the like; here, the relation between the relation of the relation "mom" and the corresponding user @ by the conversation person can be matched by inquiring that the gender of the floret is female, the relation is marked as "air" as mom, "floret" as daughter, and the relation between the member "air" and the member "floret" as mother and daughter. After the membership in the conversation group is determined, the type of the group, such as a family group, a relatives-friends group or a work group, can be determined according to the membership, and then the conversation style of the group is obtained according to the type of the group.

In particular implementation, the present application is not limited by the execution sequence of the described steps, and some steps may be performed in other sequences or simultaneously without conflict.

From the above, the instant messaging message interaction method provided in the embodiments of the present invention receives a session message of a target session group, performs scene analysis on the session message, determines a preset session scene in which the target session group is located according to a scene analysis result, determines a target semantic analysis algorithm corresponding to the preset session scene, performs semantic analysis on the session message through the target semantic analysis algorithm, generates a message to be replied according to a semantic analysis result, and sends the message to be replied to the target session group, thereby determining a suitable target semantic algorithm through different preset session scenes, performs semantic analysis on the session message based on the target semantic algorithm, generates a message to be replied matching the session scene, interacts with the message to be replied, better adjusts a chat atmosphere in the target session group, and improves the interaction efficiency of the instant messaging message, thereby improving the activity of the session group.

The method according to the preceding embodiment is illustrated in further detail below by way of example.

Referring to fig. 2a and fig. 2b, fig. 2a is a second flow chart of an interaction method of an instant messaging message according to an embodiment of the present invention, and fig. 2b is a third flow chart of the interaction method of the instant messaging message according to the embodiment of the present invention. The method comprises the following steps:

201. a session message for a target session group is received.

The user sends the session message in the target session group through the user terminal, and the server detects and analyzes the session message of the session group in real time.

202. And if the session message contains multimedia data, acquiring the portrait information of each member in the target session group.

203. And performing portrait recognition on the multimedia data based on the portrait information.

When the session message is detected to contain multimedia data, such as pictures and videos, the portrait information of each member in the target group is obtained, wherein the portrait information can be face features, and the server carries out portrait recognition on the images in the session data according to the face features.

204. And when the multimedia data contains the members of the session group, calculating the matching degree between the session message and the members of the session group according to the identification result.

When the figure of the members in the target group is identified in the image, calculating the proportion of the number of the group members in the image to the total number of the group members, and taking the proportion as the matching degree.

205. And when the matching degree meets a preset condition, acquiring the context message which is associated with the session message and belongs to the multimedia data.

206. And generating a multimedia file according to the session message and the context message, and storing the multimedia file in association with the target session group.

When the number of the group members contained in the image accounts for more than half of the total number of the group members, the matching degree meets a preset condition, and the server acquires the context message which is associated with the session message and belongs to the multimedia data. And generating the multimedia file. For example, the group members share the taken pictures of a plurality of group members in the group, the server recognizes the pictures, generates an album, and stores the album in association with the target conversation group.

207. Acquiring time information corresponding to the multimedia file, and determining a target date corresponding to the multimedia file according to a preset reminding mechanism.

208. And when the target date is reached, generating a message to be replied based on the multimedia file, and sending the message to be replied to the target session group.

The server stores the generated multimedia file, and sends the multimedia file to the session group at a specific time thereafter, for example, the recording time of the multimedia file is 2018, month 1 and year 8, and a preset reminding mechanism is that reminding is performed once after half a year and once after a year, and then target dates corresponding to the multimedia file are determined to be 2019, month 2 and day 1 and 2019, month 8 and day 1, and when the server detects that the system time reaches the above two dates, images or videos recorded at the last party can be collected at a proper time period within the dates, and a message to be replied is generated and sent to the session group.

In view of the above, the instant messaging message interaction method provided in the embodiments of the present invention records some multimedia data sent by each member in the target conversation group, generates a multimedia file with commemorative significance, and sends the commemorative file to the conversation group on some commemorative days or in a recall chat atmosphere, so as to adjust the chat atmosphere in the target conversation group and improve the liveness of the group.

Referring to fig. 2c and fig. 2d, fig. 2c is a fourth flowchart illustrating an interaction method of an instant messaging message according to an embodiment of the present invention, and fig. 2d is a fifth flowchart illustrating the interaction method of the instant messaging message according to the embodiment of the present invention. The method comprises the following steps:

211. a session message for a target session group is received.

212. Whether the conversation message contains the first keyword is detected.

In this embodiment, a user sends a session message in a target session group through a user terminal, and a server performs real-time detection and analysis on the session message of the session group, specifically, the server determines whether the target session group may be in a cold scene by detecting whether the session message includes a preset first keyword, for example, the first keyword may be "without person", "together", "i want", "do", "big", "how", "what", "can be" or? "etc. can embody a particular word, symbol, etc. that may be cold in the conversation.

213. When the conversation message is detected to contain the first keyword, whether a reply message is received within a preset time interval of receiving the conversation message is judged.

If the server detects that the session message can be matched with the first keyword, the server detects the reply condition of other members except the member sending the session message in the target group, and when the server detects that the reply of other members in the target session group to the session message is not received within a preset time interval after the session message is received, the server judges that a cold spot appears in the target session group and needs to adjust the chat atmosphere.

214. If not, recognizing the dialogue intention of the dialogue message according to an intention recognition algorithm.

For example, text data in the conversation message is acquired, keywords of the text data are extracted as text features, the text features are converted into word vectors according to a word vector model, and the word vectors are input into a pre-trained intention recognition model to obtain corresponding conversation intents.

For example, the conversation message is "want to eat nearby, have or not together? ", the server recognizes from the conversation message that the conversation is intended to recommend eating. As another example, the session message is "what good movies have been recently? The server recognizes from the message that the session intention is to recommend a movie. Determining the content to be replied according to the conversation intention, for example, the conversation intention is to recommend eating, some dining places nearby can be used as the content to be replied, the conversation intention is to recommend a movie, and movie information or a ticket purchasing page and the like can be used as the content to be replied.

215. And acquiring the style label of the target session group, and acquiring response data corresponding to the style label from a response database.

216. And generating a message to be replied according to the conversation intention and the response data.

The server may self-learn the historical conversation messages in the group to obtain the conversation style labels corresponding to the conversation group, such as "two-dimensional", "cyny", "official", "family", etc. After the style tag is determined, words matched with the conversation intention are searched from a response data set corresponding to the style tag, and a message to be replied is generated according to the searched words and the content to be replied.

217. And sending the message to be replied to the target session group.

And taking the chat robot as a sender of the message, sending the message to be replied to the target session group, and simultaneously reminding other members to check the message so as to activate the chat atmosphere in the target session group.

In order to implement the above method, an embodiment of the present invention further provides an instant messaging message interaction apparatus, where the instant messaging message interaction apparatus may be specifically integrated in a terminal device, such as a mobile phone, a tablet computer, and the like.

For example, please refer to fig. 3a, fig. 3a is a first structural diagram of an instant messaging message interaction device according to an embodiment of the present invention. The interactive device of the instant messaging message may include a first obtaining unit 301, a scene analyzing unit 302, a semantic analyzing unit 303, and a message replying unit 304, as follows:

a first obtaining unit 301, configured to receive a session message of a target session group;

a scene analysis unit 302, configured to perform scene analysis on the session message, and determine a preset session scene in which the target session group is located according to a scene analysis result;

a semantic analysis unit 303, configured to determine a target semantic analysis algorithm corresponding to a preset conversation scene, perform semantic analysis on the conversation message through the target semantic analysis algorithm, and generate a message to be replied according to a semantic analysis result;

a message replying unit 304, configured to send the message to be replied to the target session group.

Referring to fig. 3b, fig. 3b is a schematic diagram illustrating a second structure of an instant messaging message interaction device according to an embodiment of the present invention. In some embodiments, the scene analysis unit 302 is further configured to: detecting whether the session message contains a first keyword or not;

when the conversation message is detected to contain the first keyword and no reply message is received within a preset time interval of receiving the conversation message, judging that the target conversation group is in a first preset conversation scene;

the semantic analysis unit 303 includes:

a first analyzing subunit 3031, configured to, when the target session group is in a first preset session scenario, use an intention identifying algorithm as a target semantic analysis algorithm;

and the second analysis subunit 3032 is used for identifying the dialogue intention of the dialogue message according to the intention identification algorithm and generating the message to be replied corresponding to the dialogue intention.

In some embodiments, the scene analysis unit 302 is further configured to:

detecting whether the session message contains a keyword of a preset type;

if yes, judging that the target session group is in a second preset session scene;

the semantic analysis unit 303 is further configured to: when the target session group is in a second preset session scene, taking a keyword matching algorithm as a target semantic analysis algorithm;

determining a target keyword matched with the session message from a preset keyword set according to the keyword matching algorithm;

and acquiring a multimedia file corresponding to the target keyword, and generating a message to be replied based on the multimedia file.

Referring to fig. 3c, fig. 3c is a schematic diagram illustrating a third structure of an instant messaging message interaction device according to an embodiment of the present invention. In some embodiments, the instant messaging message interaction device may further include:

a second obtaining unit 305, configured to obtain portrait information of each member in the target session group if the session message includes multimedia data, where at least two members in the target session group are present;

a portrait recognition unit 306, configured to perform portrait recognition on the multimedia data based on the portrait information;

the second obtaining unit 305 is further configured to: when the multimedia data is identified to contain the members of the session group, acquiring a context message which is associated with the session message and belongs to the multimedia data;

a file generating unit 307, configured to generate a multimedia file according to the session message and the context message, and store the multimedia file in association with the target session group.

In some embodiments, the portrait recognition unit 306 is further configured to: when the multimedia data is identified to contain the members of the session group, calculating the matching degree between the session message and the members of the session group according to the identification result;

and when the matching degree meets a preset condition, acquiring the context message which is associated with the session message and belongs to the multimedia data.

In some embodiments, the instant messaging message interaction device may further include:

the keyword storage unit is used for acquiring time information and position information corresponding to the session message;

and adding the time information and the position information as a group of keywords to a preset keyword set corresponding to the target session group.

In some embodiments, the message reply unit 304 is further configured to:

acquiring time information corresponding to the multimedia file, and determining a target date corresponding to the multimedia file according to a preset reminding mechanism;

and when the target date is reached, generating a message to be replied based on the multimedia file, and sending the message to be replied to the target session group.

In some embodiments, the message reply unit 304 is further configured to:

acquiring a style label of the target session group, and acquiring response data corresponding to the style label from a response database;

and generating a message to be replied according to a semantic analysis result and the response data, and sending the message to be replied to the target session group.

the style identification unit is used for collecting historical conversation messages of the target conversation group;

and performing semantic analysis on the historical conversation message to generate a style label of the target conversation group.

In a specific implementation, the above units may be implemented as independent entities, or may be combined arbitrarily to be implemented as the same or several entities, and the specific implementation of the above units may refer to the foregoing method embodiments, which are not described herein again.

It should be noted that the instant messaging message interaction apparatus provided in the embodiment of the present invention and the instant messaging message interaction method in the above embodiment belong to the same concept, and any method provided in the instant messaging message interaction method embodiment may be run on the instant messaging message interaction apparatus.

In the instant messaging message interaction device provided by the embodiment of the present invention, the first obtaining unit 301 receives a session message of a target session group, the scene analyzing unit 302 performs scene analysis on the session message, determines a preset session scene in which the target session group is located according to a scene analysis result, and determines a target semantic analysis algorithm corresponding to the preset session scene, the semantic analyzing unit 303 performs semantic analysis on the session message through the target semantic analysis algorithm, generates a message to be replied according to a semantic analysis result, the message replying unit 304 sends the message to be replied to the target session group, thereby determining a suitable target semantic algorithm through different preset session scenes, performs semantic analysis on the session message based on the target semantic algorithm, generates a message to be replied matching with the session scene, performs interaction on the message to be replied, and better adjusts a chat atmosphere in the target session group, the interaction efficiency of the instant messaging information is improved, and the activity of the session group is further improved.

Fig. 4 shows a schematic structural diagram of an electronic device according to an embodiment of the present invention, where fig. 4 is a schematic structural diagram of the electronic device according to an embodiment of the present invention. Specifically, the method comprises the following steps:

the electronic device may include components such as a processor 401 of one or more processing cores, memory 402 of one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will appreciate that the electronic device configuration shown in fig. 4 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components. Wherein:

the processor 401 is a control center of the electronic device, connects various parts of the whole electronic device by various interfaces and lines, performs various functions of the electronic device and processes data by running or executing software programs and/or modules stored in the memory 402 and calling data stored in the memory 402, thereby performing overall monitoring of the electronic device. Optionally, processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 401.

The memory 402 may be used to store software programs and modules, and the processor 401 executes various functional applications and data processing by operating the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the electronic device, and the like. Further, the memory 402 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 access to the memory 402.

The electronic device further comprises a power supply 403 for supplying power to the various components, and preferably, the power supply 403 is logically connected to the processor 401 through a power management system, so that functions of managing charging, discharging, and power consumption are realized through the power management system. The power supply 403 may also include any component of one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.

The electronic device may further include an input unit 404, and the input unit 404 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

Although not shown, the electronic device may further include a display unit and the like, which are not described in detail herein. Specifically, in this embodiment, the processor 401 in the electronic device loads the executable file corresponding to the process of one or more application programs into the memory 402 according to the following instructions, and the processor 401 runs the application program stored in the memory 402, thereby implementing various functions as follows:

receiving a session message of a target session group;

and sending the message to be replied to the target session group.

It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.

As described above, the electronic device according to the embodiment of the present invention receives a session message of a target session group, performing scene analysis on the session message, determining a preset session scene in which the target session group is located according to a scene analysis result, determining a target semantic analysis algorithm corresponding to the preset session scene, performing semantic analysis on the session message through the target semantic analysis algorithm, generating a message to be replied according to the semantic analysis result, sending the message to be replied to the target session group, so as to, the method comprises the steps of determining a proper target semantic algorithm through different preset conversation scenes, carrying out semantic analysis on conversation messages based on the target semantic algorithm, generating messages to be replied matched with the conversation scenes for interaction, better adjusting the chat atmosphere in the target conversation group, improving the interaction efficiency of instant messaging information and further improving the activity of the conversation group.

To this end, an embodiment of the present invention provides a storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute any one of the instant messaging message interaction methods provided by the embodiments of the present invention. For example, the instructions may perform:

receiving a session message of a target session group;

and sending the message to be replied to the target session group.

The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.

Wherein the storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.

Since the instructions stored in the storage medium can execute any instant messaging message interaction method provided by the embodiment of the present invention, beneficial effects that can be achieved by any instant messaging message interaction method provided by the embodiment of the present invention can be achieved, which are detailed in the foregoing embodiments and will not be described herein again. The interaction method, device and storage medium for instant messaging messages provided by the embodiments of the present invention are described in detail above, and a specific example is applied in the present disclosure to explain the principle and implementation manner of the present invention, and the description of the above embodiments is only used to help understanding the method and core ideas of the present invention; meanwhile, for those skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. An interactive method of instant messaging messages, comprising:

receiving a session message of a target session group;

when detecting that the session message contains a first keyword and a reply message is not received within a preset time interval of receiving the session message, judging that the target session group is in a first preset session scene, and using an intention recognition algorithm as a target semantic analysis algorithm;

when detecting that the session message contains a keyword of a preset type, judging that the target session group is in a second preset session scene, and using a keyword matching algorithm as a target semantic analysis algorithm;

performing semantic analysis on the session message through the target semantic analysis algorithm, and generating a message to be replied according to a semantic analysis result;

and sending the message to be replied to the target session group.

2. The method for interacting instant messaging messages according to claim 1, wherein the step of performing semantic analysis on the conversation message through the target semantic analysis algorithm and generating the message to be replied according to the semantic analysis result comprises:

when the target conversation group is in a first preset conversation scene, recognizing the conversation intention of the conversation message according to the intention recognition algorithm, and generating a message to be replied corresponding to the conversation intention.

3. The method for interacting instant messaging messages according to claim 1, wherein the step of performing semantic analysis on the conversation message through the target semantic analysis algorithm and generating the message to be replied according to the semantic analysis result comprises:

when the target conversation group is in a second preset conversation scene, determining a target keyword matched with the conversation message from a preset keyword set according to the keyword matching algorithm;

4. The method for interacting instant messaging messages according to claim 1, wherein the step of receiving the session message of the target session group is followed by further comprising:

if the session message contains multimedia data, acquiring portrait information of each member in the target session group, wherein at least two members in the target session group are provided;

performing portrait recognition on the multimedia data based on the portrait information;

when the multimedia data is identified to contain the members of the session group, acquiring a context message which is associated with the session message and belongs to the multimedia data;

and generating a multimedia file according to the session message and the context message, and storing the multimedia file in association with the target session group.

5. The method for interacting with instant messaging messages according to claim 4, wherein the step of obtaining the context message associated with the session message and belonging to the multimedia data is preceded by the steps of:

when the multimedia data is identified to contain the members of the session group, calculating the matching degree between the session message and the members of the session group according to the identification result;

6. The method for instant messaging message interaction according to claim 4, wherein the step of storing the multimedia file in association with the target session group further comprises:

acquiring time information and position information corresponding to the session message;

7. The method for instant messaging message interaction according to claim 4, wherein the step of storing the multimedia file in association with the target session group further comprises:

8. The method according to any one of claims 1 to 7, wherein the step of generating the message to be replied according to the semantic analysis result comprises:

acquiring a style label of the target session group, and acquiring response data corresponding to the style label from a response database, wherein the response database is stored in a block corresponding to the target session group in a block chain system;

9. An instant messaging message interaction device, comprising:

the scene analysis unit is used for judging that the target session group is in a first preset session scene when detecting that the session message contains a first keyword and a reply message is not received within a preset time interval of receiving the session message, and judging that the target session group is in a second preset session scene when detecting that the session message contains a preset type of keyword;

the semantic analysis unit is used for taking an intention recognition algorithm as a target semantic analysis algorithm when the target conversation group is in a first preset conversation scene, taking a keyword matching algorithm as a target semantic analysis algorithm when the target conversation group is in a second preset conversation scene, performing semantic analysis on the conversation message through the target semantic analysis algorithm, and generating a message to be replied according to a semantic analysis result;

10. A computer-readable storage medium storing instructions adapted to be loaded by a processor to perform the method of interacting with instant messaging messages according to any one of claims 1 to 8.

11. An electronic device, comprising a processor and a memory, wherein the memory stores an application program, and the processor executes the application program stored in the memory to execute the instant messaging message interaction method according to any one of claims 1 to 8.

12. A server, characterized in that the server comprises a processor and a memory, the memory stores a computer program, and the processor executes the instant messaging message interaction method according to any one of claims 1 to 8 by calling the computer program.