Message sending method and device, equipment and storage medium

Abstract

The invention provides a message sending method and device, equipment and a storage medium, and belongs to the field of artificial intelligence, and the method comprises the steps: obtaining session information inputted by a user in a current session group, and extracting context session summary information of the current session group based on a preset information extraction model; obtaining associated session groups of the current session group, and obtaining context session summary information of each associated session group; determining a target associated session group with similar session content according to the context session summary information of the current session group and the context session summary information of each associated session group; and synchronizing the session information to the target associated session group. The problem that it is difficult to determine the associated session group of the similar session is effectively solved, the session information synchronization efficiency and accuracy are greatly improved, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a message sending method, device, equipment and storage medium. Background Art

[0002] With the continuous development of instant messaging (IM) technology, more and more people are using various IM platforms to conduct social communication activities on the Internet. IM is no longer just a chat tool, it has developed into a comprehensive information platform that integrates communication, information, entertainment, search, e-commerce, office collaboration and corporate customer service.

[0003] At present, there are some problems with instant messaging in communication groups. For example, when discussing a design plan, relevant personnel will be pulled into a group to discuss the problem. As the communication and discussion deepen, some related issues only involve some people in the group, and the user will pull a new group to discuss related solution issues. As time goes by, there are more and more groups of "related issues", and it is difficult for users to determine the context and background content of the issues discussed in each group. When it is necessary to share messages to groups with multiple related issues, it is also difficult for users to determine the group to send to, resulting in a poor user experience. Summary of the invention

[0004] The main purpose of this application is to provide a message sending method, device, equipment and storage medium, aiming to improve the efficiency and accuracy of group message sending.

[0005] In a first aspect, the present application provides a method for sending a message, the method for sending a message comprising the following steps:

[0006] Acquire the conversation information input by the user in the current conversation group, and extract the context conversation summary information of the current conversation group based on a preset information extraction model;

[0007] Acquire the associated conversation groups of the current conversation group, and acquire context conversation summary information of each of the associated conversation groups;

[0008] Determining a target associated conversation group with similar conversation content according to the context conversation summary information of the current conversation group and the context conversation summary information of each associated conversation group;

[0009] The session information is synchronized to the target associated session group.

[0010] In a second aspect, the present application further provides a message sending device, the message sending device comprising an acquisition module, an extraction module, a determination module and an information synchronization module, wherein:

[0011] The acquisition module is used to acquire the session information input by the user in the current session group;

[0012] The extraction module is used to extract the contextual conversation summary information of the current conversation group based on a preset information extraction model;

[0013] The acquisition module is further used to acquire the associated conversation groups of the current conversation group, and acquire the context conversation summary information of each of the associated conversation groups;

[0014] The determining module is used to determine a target associated conversation group with similar conversation content according to the context conversation summary information of the current conversation group and the context conversation summary information of each associated conversation group;

[0015] The information synchronization module is used to synchronize the session information to the target associated session group.

[0016] In a third aspect, the present application also provides a terminal device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the message sending method as described above are implemented.

[0017] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the message sending method as described above are implemented.

[0018] The present application provides a message sending method, device, equipment and storage medium. The present application obtains the session information input by the user in the current session group, and extracts the context session overview information of the current session group based on a preset information extraction model; obtains the associated session groups of the current session group, and obtains the context session overview information of each associated session group; determines the target associated session group with similar session content according to the context session overview information of the current session group and the context session overview information of each associated session group; and synchronizes the session information to the target associated session group. In the present application, according to the context session overview information of each associated session group and the context session overview information of the current session group, the target associated session group with similar session content can be accurately determined, and the session information can be synchronized to the target associated session group, which effectively solves the problem of difficulty in determining the associated session group of similar sessions, greatly improves the efficiency and accuracy of session information synchronization, and improves the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 A flowchart of a message sending method provided in an embodiment of the present application;

[0021] Figure 2 for Figure 1 A schematic diagram of the sub-step flow chart of the message sending method in FIG.

[0022] Figure 3 A schematic block diagram of a message sending device provided in an embodiment of the present application;

[0023] Figure 4 A schematic block diagram of a model training module provided in an embodiment of the present application;

[0024] Figure 5 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present application.

[0025] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0028] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0029] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0030] With the continuous development of instant messaging (IM) technology, more and more people are using various IM platforms to conduct social communication activities on the Internet. IM is no longer just a chat tool, it has developed into a comprehensive information platform that integrates communication, information, entertainment, search, e-commerce, office collaboration and corporate customer service.

[0031] At present, there are some problems with instant messaging in communication groups. For example, when discussing a design plan, relevant personnel will be pulled into a group to discuss the problem. As the communication and discussion deepen, some related issues only involve some people in the group, and the user will pull a new group to discuss related solution issues. As time goes by, there are more and more groups of "related issues", and it is difficult for users to determine the context and background content of the issues discussed in each group. When it is necessary to share messages to groups with multiple related issues, it is also difficult for users to determine the group to send to, resulting in a poor user experience.

[0032] To solve the above problems, embodiments of the present application provide a message sending method, apparatus, device and storage medium, wherein the message sending method includes: obtaining session information input by a user in a current session group, and extracting context session summary information of the current session group based on a preset information extraction model; obtaining associated session groups of the current session group, and obtaining context session summary information of each of the associated session groups; determining a target associated session group with similar session content according to the context session summary information of the current session group and the context session summary information of each of the associated session groups; and synchronizing the session information to the target associated session group.

[0033] Among them, the message sending method can be applied to a terminal device, which can be an electronic device such as a mobile phone, a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device.

[0034] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0035] Please refer to Figure 1 , Figure 1A flowchart of a message sending method provided in an embodiment of the present application.

[0036] like Figure 1 As shown, the message sending method includes steps S101 to S104.

[0037] Step S101: Acquire conversation information input by a user in a current conversation group, and extract context conversation summary information of the current conversation group based on a preset information extraction model.

[0038] The session information includes but is not limited to text, documents, pictures, videos, and link addresses, etc. The contextual session summary information is the topic discussed in the current session group. For example, the contextual session summary information in UI design may be "UI color selection", the contextual session summary information in the financial industry may be "how to reasonably increase the rate of return", and the contextual session summary information in the medical industry may be "how to improve the effect of drugs", etc.

[0039] In some embodiments, step S101 also includes steps S201 to S205.

[0040] Step S201: Acquire a sample data set, where the sample data set includes a plurality of sample data, each of which includes sample session information and annotated text session summary information corresponding to the sample session information.

[0041] The sample data set includes a plurality of sample data, each of which includes sample session information and annotated session overview information corresponding to the sample session information. The annotated session overview information is pre-set by the user based on each session group.

[0042] For example, in the medical industry, the contextual conversation summary information of a conversation group may be “how to develop a drug for treating a certain disease”, the contextual conversation summary information of a conversation group may be “how to improve the therapeutic effect of a certain drug”, and the contextual conversation summary information of a conversation group may be “how to reduce the cost of a certain drug”, etc.

[0043] In some embodiments, multiple sample session information is obtained, and the text session summary information marked in each sample session information is obtained, and each sample session information and various corresponding text session summary information are combined to obtain multiple sample session information.

[0044] Step S202: Select a sample data from the sample data set as target sample data.

[0045] A sample data is selected from the sample data set as the target sample data. The direction of the selection can be selected according to actual conditions, and the present invention does not make any specific limitation on this. For example, a sample data is randomly selected as the target sample data.

[0046] Step S203: input the sample conversation information in the target sample data into a preset neural network model to extract conversation overview, and obtain predicted conversation overview information.

[0047] Among them, the preset neural network model includes but is not limited to a convolutional neural network model, a recurrent neural network model and a recurrent convolutional neural network model. For example, an embodiment of the present invention is trained with a recurrent convolutional neural network model.

[0048] In some embodiments, the sample session information in the target sample data is input into a preset neural network model to extract the session summary, and the predicted session summary information is obtained. The sample session information is input into a preset neural network model to extract the session summary, and the predicted session summary information can be accurately obtained.

[0049] Step S204: Determine whether the preset neural network model converges according to the predicted session overview information and the session overview information annotated in the target sample data.

[0050] In some embodiments, the loss value of the preset neural network model is determined based on the predicted conversation overview information and the text conversation overview information annotated in the target sample data; if the loss value is less than or equal to the preset loss value, it is determined that the preset neural network model has converged; if the loss value is greater than the preset loss value, it is determined that the preset neural network model has not converged. Among them, the preset loss value can be set according to actual conditions, and the embodiment of the present invention does not make specific limitations on this. For example, the preset loss value can be set to 0.002. According to the loss value of the preset neural network model, it is possible to accurately know whether the model has converged, which greatly improves the efficiency and accuracy of model training.

[0051] In some embodiments, the method of determining the loss value of the preset neural network model according to the predicted conversation summary information and the text conversation summary information marked in the target sample data can be: calculating the cosine similarity between the predicted conversation summary information and the text conversation summary information marked in the target sample data; and determining the loss value of the preset neural network model according to the cosine similarity. By calculating the cosine similarity between the predicted conversation summary information and the text conversation summary information marked in the target sample data, the loss value of the preset neural network model can be accurately determined.

[0052] In some embodiments, based on the cosine similarity, the loss value of the preset neural network model can be determined by subtracting the cosine similarity from the unit 1 to obtain a similarity difference, and determining the similarity difference as the loss value of the preset neural network model.

[0053] Step S205: If the preset neural network model has not converged, the model parameters of the preset neural network model are updated, and the step of selecting a sample data from the sample data set as the target sample data is returned to execute until the preset neural network model converges to obtain an information extraction model.

[0054] In some embodiments, if the preset neural network model has not converged, the model parameters of the preset neural network model are updated, and the loop execution is returned to select a sample data from the sample data set as the target sample data; the sample session information in the target sample data is input into the preset neural network model to extract the session overview to obtain the predicted session overview information; according to the predicted session overview information and the session overview information marked in the target sample data, the step of determining whether the preset neural network model has converged is performed until the preset neural network model converges to obtain the information extraction model. By cyclically training the preset neural model, the information extraction model can be accurately obtained.

[0055] In some embodiments, all the conversation information in the current conversation group is input into a preset information extraction model to extract the context conversation summary information, so as to obtain the context conversation summary information of the current conversation group.

[0056] Step S102: Acquire the associated conversation groups of the current conversation group, and acquire context conversation summary information of each of the associated conversation groups.

[0057] The associated conversation group is a preset associated conversation group, and the associated conversation group can be set according to actual conditions, which is not specifically limited in the embodiment of the present invention.

[0058] For example, when designing UI interaction for a financial app, conversation group 1, conversation group 2, conversation group 3, and conversation group 4 are established, wherein conversation group 1 is used to discuss "UI interaction design", conversation group 2 is used to discuss "front-end system design", conversation group 3 is used to discuss "back-end system design", and conversation group 4 is used to discuss "UI design copyright". When the current conversation group is conversation group 2, conversation group 1, conversation group 3, and conversation group 4 are associated conversation groups of conversation group 2.

[0059] In some embodiments, the associated conversation groups of the current conversation group are obtained to obtain at least one associated conversation group, and the conversation information of each conversation group is respectively input into the information extraction model to extract the context conversation summary information to obtain the context conversation summary information of each associated conversation group. By extracting the summary information of the conversation information of the conversation group by the information extraction model, the context conversation summary information of each associated conversation group can be accurately obtained, which greatly improves the efficiency and accuracy of conversation information synchronization.

[0060] Step S103: determining a target associated conversation group with similar conversation content according to the context conversation summary information of the current conversation group and the context conversation summary information of each associated conversation group.

[0061] The target associated conversation group is an associated conversation group with similar conversation topics.

[0062] In some embodiments, the contextual conversation summary information of the current conversation group and the contextual conversation summary information of each associated conversation group are similarly calculated to obtain the similarity between the current conversation group and each associated conversation group; the associated conversation group whose similarity is greater than or equal to the preset similarity is determined as the target associated conversation group. The preset similarity can be set according to actual conditions, and the embodiment of the present invention does not specifically limit this. For example, the preset similarity can be set to 0.8. By calculating the similarity between the contextual conversation summary information of the current conversation group and the contextual conversation summary information of each associated conversation group, the similarity between the current conversation group and each associated conversation group can be accurately determined, and then based on the similarity, the target associated conversation group with similar conversation content can be accurately determined, which greatly improves the efficiency and accuracy of conversation information synchronization.

[0063] It should be noted that the method for calculating the similarity between the contextual conversation summary information of the current conversation group and the contextual conversation summary information of each associated conversation group can be selected according to actual conditions, and the embodiment of the present invention does not specifically limit this. For example, the method for calculating the similarity can be cosine similarity.

[0064] For example, for conversation group 1, conversation group 2, conversation group 3, conversation group 4, and conversation group 5, the similarity between the context conversation summary information of the current conversation group and the context conversation summary information of conversation group 1 is 0.6; the similarity between the context conversation summary information of the current conversation group and the context conversation summary information of conversation group 2 is 0.9; the similarity between the context conversation summary information of the current conversation group and the context conversation summary information of conversation group 3 is 0.95; the similarity between the context conversation summary information of the current conversation group and the context conversation summary information of conversation group 4 is 0.4; the similarity between the context conversation summary information of the current conversation group and the context conversation summary information of conversation group 5 is 0.85. If the preset similarity is 0.8, conversation group 2, conversation group 3, and conversation group 5 are determined as target conversation groups.

[0065] Step S104: synchronizing the session information to the target associated session group.

[0066] In some embodiments, the credibility information of the target associated conversation group is obtained; when the target associated conversation group is determined to be a credible conversation group according to the credibility information, the conversation information is synchronized to the target associated conversation group. By obtaining the credibility information of the target associated conversation group, identity authentication is performed based on the credibility information to improve the security of the conversation information.

[0067] In some embodiments, the credibility information of the target associated conversation group is obtained; when the target associated conversation group is determined to be an untrusted conversation group according to the credibility information, the target associated conversation group is added to a blacklist. When the target associated conversation group is an untrusted conversation group, the target associated conversation group is added to the blacklist, which greatly improves the security of the conversation information.

[0068] It should be noted that the credibility information can be set according to actual conditions, and the embodiment of the present invention does not specifically limit this. For example, the credibility information can be a session group tag. If the session group carries a trusted session group tag, the target association group is determined to be a trusted target session association group.

[0069] In some embodiments, the message sending method is applied to a terminal device, which includes a display screen, the display screen displays a conversation interface of an application, and the overview preview bar of each conversation group in the conversation interface displays the chat summary information of the conversation group. The conversation group selected by the user is obtained, and the selected conversation group is determined as a target associated conversation group; the conversation information is synchronized to the target associated conversation group. By displaying the chat summary information of the conversation group in the overview preview bar of each associated conversation group on the display screen, the subject of each conversation group can be effectively presented to the user, so that the user can determine the target conversation group for message synchronization, which greatly improves the efficiency and accuracy of message synchronization.

[0070] The message sending method provided in the above embodiment obtains the session information input by the user in the current session group, and extracts the context session overview information of the current session group based on the preset information extraction model; obtains the associated session groups of the current session group, and obtains the context session overview information of each associated session group; determines the target associated session group with similar session content according to the context session overview information of the current session group and the context session overview information of each associated session group; and synchronizes the session information to the target associated session group. In the present application, according to the context session overview information of each associated session group and the context session overview information of the current session group, the target associated session group with similar session content can be accurately determined, and the session information can be synchronized to the target associated session group, which effectively solves the problem of difficulty in determining the associated session group of similar sessions, greatly improves the efficiency and accuracy of session information synchronization, and improves the user experience.

[0071] See also Figure 3 , Figure 3 A schematic block diagram of a message sending device provided in an embodiment of the present application.

[0072] like Figure 3 As shown, the message sending device 300 includes an acquisition module 310, an extraction module 320, a determination module 330 and an information synchronization module 340, wherein:

[0073] The acquisition module 310 is used to acquire the session information input by the user in the current session group;

[0074] The extraction module 320 is used to extract the contextual conversation summary information of the current conversation group based on a preset information extraction model;

[0075] The acquisition module 310 is further configured to acquire the associated conversation groups of the current conversation group, and acquire the context conversation summary information of each of the associated conversation groups;

[0076] The determining module 330 is used to determine a target associated conversation group with similar conversation content according to the context conversation summary information of the current conversation group and the context conversation summary information of each associated conversation group;

[0077] The information synchronization module 340 is used to synchronize the session information to the target associated session group.

[0078] In some embodiments, the determining module 330 is further configured to:

[0079] performing similarity calculation on the contextual conversation summary information of the current conversation group and the contextual conversation summary information of each of the associated conversation groups to obtain similarities between the current conversation group and each of the associated conversation groups;

[0080] The associated conversation group whose similarity is greater than or equal to the preset similarity is determined as the target associated conversation group.

[0081] In some embodiments, the information synchronization module 340 is further used to:

[0082] Acquiring the credibility information of the target associated conversation group;

[0083] When it is determined according to the credibility information that the target associated conversation group is a trusted conversation group, the conversation information is synchronized to the target associated conversation group.

[0084] In some embodiments, Figure 4 As shown, the model training module 400 includes an acquisition module 410, an extraction module 420, a determination module 430 and an update module 440, wherein:

[0085] The acquisition module 410 is used to acquire a sample data set, where the sample data set includes a plurality of sample data, each of which includes sample session information and annotated session summary information corresponding to the sample session information;

[0086] The acquisition module 410 is further used to select a sample data from the sample data set as target sample data;

[0087] The extraction module 420 is further used to input the sample conversation information in the target sample data into a preset neural network model to extract the conversation summary, so as to obtain the predicted conversation summary information;

[0088] The determination module 430 is used to determine whether the preset neural network model converges according to the predicted session overview information and the session overview information marked in the target sample data;

[0089] The updating module 440 is used to update the model parameters of the preset neural network model if the preset neural network model has not converged, and return to execute the step of selecting a sample data from the sample data set as the target sample data until the preset neural network model converges to obtain the information extraction model.

[0090] In some embodiments, the determining module 430 is further configured to:

[0091] Determining a loss value of the preset neural network model according to the predicted conversation summary information and the text conversation summary information annotated in the target sample data;

[0092] If the loss value is less than or equal to the preset loss value, determining that the preset neural network model has converged;

[0093] If the loss value is greater than the preset loss value, it is determined that the preset neural network model has not converged.

[0094] In some embodiments, the determining module 430 is further configured to:

[0095] Calculating the cosine similarity between the predicted conversation summary information and the text conversation summary information annotated in the target sample data;

[0096] According to the cosine similarity, a loss value of the preset neural network model is determined.

[0097] In some embodiments, the message sending device 300 is further used to:

[0098] Acquire a conversation group selected by a user, and determine the selected conversation group as a target associated conversation group;

[0099] The session information is synchronized to the target associated session group.

[0100] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-mentioned message sending device can refer to the corresponding process in the aforementioned message sending method embodiment, and will not be repeated here.

[0101] See also Figure 5 , Figure 5 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present application.

[0102] like Figure 5 As shown, the terminal device 500 includes a processor 502 and a memory 503 connected via a system bus 501, wherein the memory 503 may include a storage medium and an internal memory.

[0103] The storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any message sending method.

[0104] The processor 502 is used to provide computing and control capabilities to support the operation of the entire terminal device.

[0105] The internal memory provides an environment for the operation of the computer program in the storage medium. When the computer program is executed by the processor, the processor can execute any message sending method.

[0106] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the terminal device to which the scheme of the present application is applied. The specific terminal device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0107] It should be understood that the processor 502 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0108] In one embodiment, the processor 502 is used to run a computer program stored in the memory to implement the following steps:

[0109] Acquire the conversation information input by the user in the current conversation group, and extract the context conversation summary information of the current conversation group based on a preset information extraction model;

[0110] Acquire the associated conversation groups of the current conversation group, and acquire context conversation summary information of each of the associated conversation groups;

[0111] Determining a target associated conversation group with similar conversation content according to the context conversation summary information of the current conversation group and the context conversation summary information of each associated conversation group;

[0112] The session information is synchronized to the target associated session group.

[0113] In one embodiment, when the processor 502 determines the target associated conversation group with similar conversation content according to the context conversation summary information of the current conversation group and the context conversation summary information of each associated conversation group, it is configured to implement:

[0114] performing similarity calculation on the contextual conversation summary information of the current conversation group and the contextual conversation summary information of each of the associated conversation groups to obtain similarities between the current conversation group and each of the associated conversation groups;

[0115] The associated conversation group whose similarity is greater than or equal to the preset similarity is determined as the target associated conversation group.

[0116] In one embodiment, when implementing the synchronizing the session information to the target associated session group, the processor 502 is configured to implement:

[0117] Acquiring the credibility information of the target associated conversation group;

[0118] When it is determined according to the credibility information that the target associated conversation group is a trusted conversation group, the conversation information is synchronized to the target associated conversation group.

[0119] In one embodiment, before implementing the extracting the contextual conversation summary information of the current conversation group based on the preset information extraction model, the processor 502 is further configured to implement:

[0120] Acquire a sample data set, the sample data set comprising a plurality of sample data, each of the sample data comprising sample session information and annotated session summary information corresponding to the sample session information;

[0121] Selecting a sample data from the sample data set as target sample data;

[0122] Inputting the sample conversation information in the target sample data into a preset neural network model to extract conversation overview, and obtaining predicted conversation overview information;

[0123] Determining whether the preset neural network model converges according to the predicted session summary information and the session summary information annotated in the target sample data;

[0124] If the preset neural network model has not converged, the model parameters of the preset neural network model are updated, and the step of selecting a sample data from the sample data set as the target sample data is returned to execute until the preset neural network model converges to obtain an information extraction model.

[0125] In one embodiment, when the processor 502 determines whether the preset neural network model converges according to the predicted session summary information and the text session summary information annotated in the target sample data, it is configured to implement:

[0126] Determining a loss value of the preset neural network model according to the predicted conversation summary information and the text conversation summary information annotated in the target sample data;

[0127] If the loss value is less than or equal to the preset loss value, determining that the preset neural network model has converged;

[0128] If the loss value is greater than the preset loss value, it is determined that the preset neural network model has not converged.

[0129] In one embodiment, when the processor 502 determines the loss value of the preset neural network model according to the predicted session summary information and the text session summary information annotated in the target sample data, it is used to implement:

[0130] Calculating the cosine similarity between the predicted conversation summary information and the text conversation summary information annotated in the target sample data;

[0131] According to the cosine similarity, a loss value of the preset neural network model is determined.

[0132] In one embodiment, the invention is applied to a terminal device, the terminal device includes a display screen, the display screen displays a session interface of an application, and an overview preview bar of each session group in the session interface displays chat summary information of the session group, and the processor 502 is further configured to implement:

[0133] Acquire a conversation group selected by a user, and determine the selected conversation group as a target associated conversation group;

[0134] The session information is synchronized to the target associated session group.

[0135] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the terminal device described above can refer to the corresponding process in the aforementioned message sending method embodiment, and will not be repeated here.

[0136] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the various embodiments of the message sending method of the present application.

[0137] The computer-readable storage medium may be an internal storage unit of the terminal device described in the foregoing embodiment, such as a hard disk or memory of the terminal device. The computer-readable storage medium may be non-volatile or volatile. The computer-readable storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc., equipped on the terminal device.

[0138] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0139] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0140] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0141] It should also be understood that the term "and / or" used in the present specification refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0142] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments. The above description is only a specific implementation mode of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application.

Claims

1. A message sending method, characterized in that: include: Acquire the conversation information input by the user in the current conversation group, and extract the context conversation summary information of the current conversation group based on a preset information extraction model; Acquire the associated conversation groups of the current conversation group, and acquire context conversation summary information of each of the associated conversation groups; Determining a target associated conversation group with similar conversation content according to the context conversation summary information of the current conversation group and the context conversation summary information of each associated conversation group; The session information is synchronized to the target associated session group.

2. The message sending method according to claim 1, characterized in that: The determining, according to the contextual session summary information of the current session group and the contextual session summary information of each of the associated session groups, a target associated session group having similar session contents includes: performing similarity calculation on the contextual conversation summary information of the current conversation group and the contextual conversation summary information of each of the associated conversation groups to obtain similarities between the current conversation group and each of the associated conversation groups; The associated conversation group whose similarity is greater than or equal to the preset similarity is determined as the target associated conversation group.

3. The message sending method according to claim 1, characterized in that: The synchronizing the session information to the target associated session group includes: Acquiring the credibility information of the target associated conversation group; When it is determined according to the credibility information that the target associated conversation group is a trusted conversation group, the conversation information is synchronized to the target associated conversation group.

4. The message sending method according to claim 1, characterized in that: Before extracting the contextual conversation summary information of the current conversation group based on a preset information extraction model, the method further includes: Acquire a sample data set, the sample data set comprising a plurality of sample data, each of the sample data comprising sample session information and annotated session summary information corresponding to the sample session information; Selecting a sample data from the sample data set as target sample data; Inputting the sample conversation information in the target sample data into a preset neural network model to extract conversation overview, and obtaining predicted conversation overview information; Determining whether the preset neural network model converges according to the predicted session summary information and the session summary information annotated in the target sample data; If the preset neural network model has not converged, the model parameters of the preset neural network model are updated, and the step of selecting a sample data from the sample data set as the target sample data is returned to execute until the preset neural network model converges to obtain an information extraction model.

5. The message sending method according to claim 4, characterized in that: The determining whether the preset neural network model converges according to the predicted conversation summary information and the text conversation summary information annotated in the target sample data includes: Determining a loss value of the preset neural network model according to the predicted conversation summary information and the text conversation summary information annotated in the target sample data; If the loss value is less than or equal to the preset loss value, determining that the preset neural network model has converged; If the loss value is greater than the preset loss value, it is determined that the preset neural network model has not converged.

6. The message sending method according to claim 5, characterized in that: The determining the loss value of the preset neural network model according to the predicted conversation summary information and the text conversation summary information marked in the target sample data includes: Calculating the cosine similarity between the predicted conversation summary information and the text conversation summary information annotated in the target sample data; According to the cosine similarity, a loss value of the preset neural network model is determined.

7. The message sending method according to any one of claims 1 to 6, characterized in that: Applied to a terminal device, the terminal device includes a display screen, the display screen displays a session interface of an application, and an overview preview bar of each session group in the session interface displays chat summary information of the session group, the method further includes: Acquire a conversation group selected by a user, and determine the selected conversation group as a target associated conversation group; The session information is synchronized to the target associated session group.

8. A message sending device, characterized in that: The message sending device includes an acquisition module, an extraction module, a determination module and an information synchronization module, wherein: The acquisition module is used to acquire the session information input by the user in the current session group; The extraction module is used to extract the contextual conversation summary information of the current conversation group based on a preset information extraction model; The acquisition module is further used to acquire the associated conversation groups of the current conversation group, and acquire the context conversation summary information of each of the associated conversation groups; The determining module is used to determine a target associated conversation group with similar conversation content according to the context conversation summary information of the current conversation group and the context conversation summary information of each associated conversation group; The information synchronization module is used to synchronize the session information to the target associated session group.

9. A terminal device, characterized in that: The terminal device includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the message sending method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the message sending method according to any one of claims 1 to 7 are implemented.

Images