Method and device for sending reply information, equipment and medium

Abstract

The invention provides a reply information sending method and device, equipment and a medium, and relates to the technical field of artificial intelligence, in particular to the technical field of natural language processing and deep learning. According to the implementation scheme, reply information for dialogue information is determined based on the dialogue information from a user; determining a reply time interval based on the dialogue information and the reply information; and in response to determining that the time interval between the current moment and the sending moment of the dialogue information exceeds the reply time interval, sending the reply information to the user.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to the field of natural language processing and deep learning technology, and specifically to a method, device, electronic device, computer-readable storage medium and computer program product for sending reply information. Background Art

[0002] Artificial intelligence is a discipline that studies how to use computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0003] With the development of computer technology, the application of human-computer dialogue is becoming more and more extensive. By using computers to simulate real interpersonal dialogue, labor costs can be effectively saved.

[0004] The methods described in this section are not necessarily methods that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any method described in this section is considered to be prior art simply because it is included in this section. Similarly, unless otherwise indicated, the issues mentioned in this section should not be considered to have been recognized in any prior art. Summary of the invention

[0005] The present disclosure provides a method, device, electronic device, computer-readable storage medium, and computer program product for sending reply information.

[0006] According to one aspect of the present disclosure, a method for sending a reply message is provided, comprising: determining reply information for a conversation message based on conversation information from a user; determining a reply time interval based on the conversation information and the reply message; and sending the reply message to the user in response to determining that the time interval between a current moment and a moment when the conversation message is sent exceeds the reply time interval.

[0007] According to another aspect of the present disclosure, a device for sending a reply message is provided, comprising: a first determination unit, configured to determine reply information for a conversation message based on conversation information from a user; a second determination unit, configured to determine a reply time interval based on the conversation information and the reply message; and a sending unit, configured to send the reply message to the user in response to determining that the time interval between a current moment and the moment when the conversation message is sent exceeds the reply time interval.

[0008] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned method of sending reply information.

[0009] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned method for sending reply information.

[0010] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program can implement the above-mentioned method for sending reply information when executed by a processor.

[0011] According to one or more embodiments of the present disclosure, the timing of sending a reply message to a user may be determined more accurately, thereby improving user experience.

[0012] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0014] Figure 1 A schematic diagram showing an exemplary system in which the various methods described herein may be implemented according to an exemplary embodiment of the present disclosure;

[0015] Figure 2 A flow chart showing a method for sending reply information according to an exemplary embodiment of the present disclosure is shown;

[0016] Figure 3 A schematic diagram showing a training process of a generative language model according to an exemplary embodiment of the present disclosure is shown;

[0017] Figure 4 A structural block diagram of a device for sending reply information according to an exemplary embodiment of the present disclosure is shown;

[0018] Figure 5 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0019] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0020] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0021] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in this disclosure covers any one of the listed items and all possible combinations.

[0022] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0023] Figure 1 FIG. 1 is a schematic diagram of an exemplary system 100 in which various methods and apparatuses described herein may be implemented according to an embodiment of the present disclosure. Figure 1 , the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

[0024] In an embodiment of the present disclosure, the server 120 may run one or more services or software applications that enable the method of sending reply information to be executed.

[0025] In some embodiments, server 120 may also provide other services or software applications, which may include non-virtualized environments and virtualized environments. In some embodiments, these services may be provided as web-based services or cloud services, such as provided to users of client devices 101, 102, 103, 104, 105, and / or 106 under a software as a service (SaaS) model.

[0026] exist Figure 1 In the configuration shown, the server 120 may include one or more components that implement the functions performed by the server 120. These components may include software components, hardware components, or a combination thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 may in turn utilize one or more client applications to interact with the server 120 to utilize the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from the system 100. Therefore, Figure 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

[0027] The user may use client devices 101, 102, 103, 104, 105 and / or 106 to send conversation information or conversation data. The client device may provide an interface that enables the user of the client device to interact with the client device. The client device may also output information to the user via the interface. Figure 1 Only six client devices are depicted, but one skilled in the art will appreciate that the present disclosure may support any number of client devices.

[0028] Client devices 101, 102, 103, 104, 105 and / or 106 may include various categories of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptop computers), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, game systems, thin clients, various messaging devices, sensors or other sensing devices, etc. These computer devices may run various categories and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as GOOGLE Chrome OS); or include various mobile operating systems, such as MICROSOFT Windows Mobile OS, iOS, Windows Phone, Android. Portable handheld devices may include cellular phones, smart phones, tablet computers, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Game systems may include various handheld game devices, Internet-enabled game devices, etc. The client device is capable of executing a variety of different applications, such as various Internet-related applications, communication applications (eg, email applications), short message service (SMS) applications, and may use various communication protocols.

[0029] The network 110 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including but not limited to TCP / IP, SNA, IPX, etc. By way of example only, one or more networks 110 may be a local area network (LAN), an Ethernet-based network, a token ring, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0030] Server 120 may include one or more general purpose computers, dedicated server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running virtual operating systems, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain a server's virtual storage device). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0031] The computing units in the server 120 may run one or more operating systems including any of the above operating systems and any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and / or middle-tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0032] In some implementations, server 120 may include one or more applications to analyze and consolidate data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and 106. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and 106.

[0033] In some embodiments, the server 120 may be a server of a distributed system, or a server combined with a blockchain. The server 120 may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in a cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

[0034] The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. The databases 130 may reside in various locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The databases 130 may be of different categories. In some embodiments, the databases used by the server 120 may be, for example, relational databases. One or more of these databases may store, update, and retrieve data to and from the databases in response to commands.

[0035] In some embodiments, one or more of the databases 130 may also be used by applications to store application data. The databases used by the applications may be different categories of databases, such as a key-value store, an object store, or a conventional store backed by a file system.

[0036] Figure 1The system 100 may be configured and operated in various ways to enable the application of various methods and apparatuses described in the present disclosure.

[0037] In the related art, when a generative language model is applied to generate reply data based on user input data, the performance of the model is usually enhanced by manually annotating the corpus or adjusting the training method (such as optimizing the loss function or performing reinforcement learning) during the model training phase. In the application phase of the model, that is, the data generation process, the reply data is usually directly generated and sent based on the query data input by the user, without considering how to determine the appropriate time to send the reply information to the user.

[0038] Based on this, the present disclosure provides a method for sending a reply message. After determining the reply message based on the conversation information, the reply time interval is determined based on the conversation information and the reply message, and then the reply message is sent to the user based on the reply time interval, simulating a real manual conversation and improving the user experience.

[0039] Figure 2 FIG. 2 shows a flow chart of a method 200 for sending reply information according to an exemplary embodiment of the present disclosure. Figure 2 As shown, the method 200 includes:

[0040] Step S201: Determine reply information for the conversation information based on the conversation information from the user;

[0041] Step S202: determining a reply time interval based on the conversation information and the reply information; and

[0042] Step S203: In response to determining that the time interval between the current time and the time when the conversation message is sent exceeds the reply time interval, sending the reply message to the user.

[0043] By applying the above method 200, after determining the reply information based on the conversation information sent by the user, the reply time interval can be determined based on the conversation information and the reply information, and then the reply information can be sent to the user based on the reply time interval, simulating a real manual conversation and improving the user experience.

[0044] According to some embodiments, determining the reply time interval based on the conversation information and the reply information in step S202 includes: inputting the conversation information and the reply information into a reply time prediction model to obtain the reply time interval output by the reply time prediction model, wherein the reply time prediction model is trained using sample data labeled with reference reply time intervals, the sample data including sample conversation information and sample reply information. By using the trained reply time prediction model, the reply time interval can be determined more efficiently and accurately.

[0045] In some examples, the reply time prediction model can be constructed based on various structural types of neural network models, such as a ResNet network. In this example, the reply time prediction model can be obtained by supervised training using sample corpus, and the sample corpus used to train the reply time prediction model includes sample conversation information and sample reply information annotated with reference reply time intervals. During the training process, the sample conversation information and sample reply information can be input into the initial reply time prediction model to obtain the predicted reply time interval, and the loss value is calculated based on the predicted reply time interval and the reference reply time interval, and then the parameters of the reply time prediction model are adjusted based on the loss value.

[0046] According to some embodiments, the sample data is obtained in the following manner: obtaining historical conversation data of a sample user, wherein the historical conversation data includes a plurality of historical conversation information and a plurality of historical reply information arranged in an interlaced manner; and determining the sample data based on the adjacent first historical conversation information and the first historical reply information in the historical conversation data, wherein the reference reply time interval annotated with the sample data is determined based on the time interval between the sending time of the first historical conversation information and the sending time of the first historical reply information. By using the user's historical conversation data to train the reply time prediction model, the trained reply time prediction model can learn the reply habits of the sample user, and then more realistically simulate interpersonal conversations based on the prediction results of the reply time prediction model in the process of conducting intelligent conversations with the user, thereby improving the user experience.

[0047] In some examples, the historical conversation data of the sample user may be a set of text message sequences, each of which includes the sender, text content, and sending time of the message, for example, in the following form:

[0048] Person A: content xxx, time t0;

[0049] Person B: content yyy, time t1;

[0050] Person A: content zzz, time t2;

[0051] Character B: Content mmm, time t3.

[0052] For the above-mentioned historical conversation data, adjacent text information belonging to two conversation characters can be extracted as a set of first historical conversation information and first historical reply information, and the reply time interval can be determined based on the respective times of the first historical conversation information and the first historical reply information to serve as annotation supervision information for the sample corpus.

[0053] According to some embodiments, determining reply information for the dialogue information based on the dialogue information from the user in step S201 includes: sending the dialogue information to a generative language model to obtain the reply information output by the generative language model. By using the generative language model to obtain the reply information corresponding to the dialogue information, the natural language processing capability of the generative language model can be effectively utilized to more efficiently obtain high-quality reply information.

[0054] In some examples, the generative language model used to generate reply information based on input information has end-to-end characteristics, and can directly generate reply information based on conversation information in the form of natural language text. In some examples, the reply information can be in the form of natural language text, or it can be multimodal information, for example, it can include documents and picture content. In some examples, the generative language model can adopt an N-layer Transformer network structure with an encoder (Encoder) and a decoder (Decoder), or a unified pre-trained language model (Unified pre-trained LanguageModel, UniLM) network structure. It is understandable that the deep learning model can also be a neural network model of other network structures, which is not limited here. In some examples, the generative language model can be trained using a large-scale sample corpus, and then a language model with stronger natural language processing performance can be obtained to improve the generation quality of the reply information.

[0055] In some examples, the generative language model can be based on the GraphRAG model (Graph-based Retrieval-Augmented Generation). The GraphRAG model combines the retrieval-augmented generation technology of the knowledge graph and the large language model, combining the knowledge graph and the retriever to ensure more accurate information retrieval, and then using the generator based on the large language model to output more accurate response information.

[0056] According to some embodiments, the generative language model is obtained by fine-tuning the historical conversation data of the sample user. By fine-tuning the language model using the historical conversation data of the user, the trained generative language model can learn the conversation habits and language expressions of the sample user, and then can more realistically simulate the interpersonal conversation of the sample user in the intelligent conversation process, thereby improving the user experience.

[0057] In some examples, training instructions for inputting into the generative language model can be constructed based on the historical conversation data of the sample user. Referring to the example described above, when the historical conversation data of the sample user is a text message sequence consisting of text messages including the sender, text content, and sending time, training task description information can be added on this basis and then sent to the generative language model.

[0058] In this example, the historical conversation data of the sample user are all natural language texts, and the generative language model is also used to receive and generate natural language texts. In this case, the task description information can be a preset natural language text segment or template to indicate the existence of the historical conversation of the sample user in the input data. The task description information can be, for example, "Please speak to the learning dialogue character A according to the following dialogue data __". By filling the historical conversation data into the template, the generative language model can be instructed to learn the dialogue features of the dialogue characters, and based on this, imitate the dialogue character A to simulate interpersonal conversation.

[0059] In some examples, the historical conversation data of the sample user can be preprocessed after being obtained. For example, the historical conversation data can be segmented based on the conversation time information of each group of text information to obtain multiple different conversation segments, and the time interval between conversation information or reply information in each conversation segment does not exceed a preset time threshold. In this way, the historical conversation data of the sample user can be segmented into different conversation scenes to avoid the influence of unrelated conversation content on the model training effect.

[0060] According to some embodiments, the historical conversation data includes a plurality of historical conversation information and a plurality of historical reply information arranged in an interlaced manner, and the fine-tuning training process of the generative language model includes: determining an emotion label for each historical reply information in the historical conversation data, wherein the emotion label for each historical reply information indicates an emotion feature of the historical reply information; and determining a training instruction for the generative language model based on the emotion label for the historical conversation data and each historical reply information. By adding emotion labels to the sample conversation data, the generative language model can learn the conversation features of the sample user based on the emotion labels during the training process, so as to more accurately imitate the sample user to have a conversation.

[0061] In some examples, the step of determining the sentiment label of each historical reply information in the historical conversation data may be implemented in the following manner: first, each historical reply information may be encoded to obtain a text feature vector corresponding to each historical reply information. In this step, an encoder based on a Transformer model may be used for embedding encoding to map the text content of the historical reply information to a semantic vector space.

[0062] In this example, the emotion tag feature vectors of different emotion tags may be stored in the database in advance. It is understandable that the training process of the embedding encoder can be implemented based on various conventional training methods, as long as the mapping between the input text and the semantic vector space can be achieved. In one example, the emotion tag database may be a key-value pair database, that is, the emotion tag feature vector is used as the key and the emotion tag is used as the value. In this case, the corresponding emotion tag can be queried conveniently and efficiently based on the emotion tag feature vector.

[0063] After obtaining the text feature vector corresponding to the historical reply information, the text feature vector can be compared with the emotion tag feature vector of the stored emotion tag. For example, the similarity between the vectors can be determined by calculating the distance between the vectors in the semantic vector space, and then the emotion tag corresponding to the historical reply information can be determined based on one or more emotion tag feature vectors that are most similar (closest to) the text feature vector.

[0064] As mentioned above, the training instructions for inputting the generative language model can be constructed based on the historical conversation data of the sample user. In this example, the training instructions for inputting the generative language model can also be constructed based on the historical conversation data of the sample user and the sentiment tags of the historical reply information.

[0065] In one example, the task description information in the training instruction can be: Please learn the conversation character A to speak according to the following conversation data __, pay attention to the emotional label information in the conversation data, and learn the emotional characteristics of the conversation based on the emotional label. By filling the emotional labels of historical conversation data and historical reply information into the template, the generative language model can be instructed to learn the emotional characteristics of the conversation characters in the conversation, and imitate the conversation character A based on this to simulate interpersonal conversation.

[0066] Figure 3 FIG. 1 is a schematic diagram showing a training process of a generative language model according to an exemplary embodiment of the present disclosure. Figure 3 As shown, the corpus collection service 310 can be used to collect historical conversation data of sample users, and the corpus processing service 320 can generate training instructions for input into the language model based on the historical conversation data of the sample users, and then pass the training instructions to the generative language model 330, so that the generative language model 330 can learn the conversation characteristics of the sample users, and then use the trained generative language model 330 to imitate the sample users to conduct intelligent conversations.

[0067] In this example, the corpus processing service 320 can also generate sample conversation information and sample reply information annotated with reference reply time intervals based on the historical conversation data of the sample user, and train the reply time prediction model 340 based on this, so that the reply time prediction model 340 can learn the reply speed characteristics of the sample user, and then the trained reply time prediction model 340 can be used to imitate the sample user to conduct intelligent conversations.

[0068] By combining the generative language model 330 and the reply time prediction model 340, it is possible to determine the reply information based on the conversation information sent by the user, and to determine the reply time interval (i.e., determine the appropriate time to reply) based on the conversation information and the reply information, so as to more accurately simulate real interpersonal conversations and enhance the user experience of intelligent conversation products.

[0069] According to one aspect of the present disclosure, a device for sending reply information is also provided. Figure 4 FIG. 4 shows a structural block diagram of a device 400 for sending reply information according to an exemplary embodiment of the present disclosure. Figure 4 As shown, the device 400 includes:

[0070] The first determining unit 401 is configured to determine reply information for the conversation information based on the conversation information from the user;

[0071] A second determining unit 402 is configured to determine a reply time interval based on the conversation information and the reply information; and

[0072] The sending unit 403 is configured to send the reply information to the user in response to determining that the time interval between the current time and the time when the conversation information is sent exceeds the reply time interval.

[0073] According to some embodiments, the second determination unit 402 is configured to: input the conversation information and the reply information into a reply time prediction model to obtain the reply time interval output by the reply time prediction model, wherein the reply time prediction model is trained using sample data marked with reference reply time intervals, and the sample data includes sample conversation information and sample reply information.

[0074] According to some embodiments, the sample data is determined using a sample data generation unit, the sample data generation unit comprising: an acquisition subunit configured to acquire historical conversation data of a sample user, wherein the historical conversation data comprises a plurality of historical conversation messages and a plurality of historical reply messages arranged in an interlaced manner; and a first determination subunit configured to determine the sample data based on adjacent first historical conversation messages and first historical reply messages in the historical conversation data, wherein a reference reply time interval marked with the sample data is determined based on a time interval between a sending moment of the first historical conversation message and a sending moment of the first historical reply message.

[0075] According to some embodiments, the first determining unit 401 is configured to: send the dialogue information to a generative language model to obtain the reply information output by the generative language model.

[0076] According to some embodiments, the generative language model is obtained by fine-tuning and training using historical conversation data of sample users.

[0077] According to some embodiments, the historical conversation data includes a plurality of historical conversation information and a plurality of historical reply information arranged in an interlaced manner, and the generative language model is obtained by fine-tuning training using a training unit, and the training unit includes: a second determination subunit, configured to determine the emotion label of each historical reply information in the historical conversation data, wherein the emotion label of each historical reply information indicates the emotion feature of the historical reply information; and a third determination subunit, configured to determine the training instructions for the generative language model based on the historical conversation data and the emotion label of each historical reply information.

[0078] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0079] According to another aspect of the present disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned method of sending reply information.

[0080] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is further provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned method for sending reply information.

[0081] According to another aspect of the present disclosure, a computer program product is also provided, including a computer program, wherein the computer program implements the above-mentioned method for sending reply information when executed by a processor.

[0082] refer to Figure 5 , a block diagram of an electronic device 500 that can be used as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0083] like Figure 5 As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0084] Multiple components in the device 500 are connected to the I / O interface 505, including: an input unit 506, an output unit 507, a storage unit 508, and a communication unit 509. The input unit 506 can be any type of device that can input information to the device 500. The input unit 506 can receive input digital or character information and generate key signal input related to user settings and / or function control of the electronic device, and can include but is not limited to a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and / or a remote controller. The output unit 507 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 508 can include but is not limited to a disk, an optical disk. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0085] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as a method for sending a reply message. For example, in some embodiments, the method for sending a reply message may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the method for sending the reply message described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to execute the method for sending the reply message in any other appropriate manner (e.g., by means of firmware).

[0086] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0087] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0088] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0089] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0090] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0091] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0092] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0093] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but only by the claims after authorization and their equivalent scope. Various elements in the embodiments or examples can be omitted or replaced by their equivalent elements. In addition, each step can be performed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples can be combined in various ways. It is important that with the evolution of technology, many elements described herein can be replaced by equivalent elements that appear after the present disclosure.

Claims

1. A method for sending a reply message, comprising: Determining reply information for the conversation information based on the conversation information from the user; Determining a reply time interval based on the conversation information and the reply information; as well as In response to determining that the time interval between the current time and the time when the conversation information is sent exceeds the reply time interval, the reply information is sent to the user.

2. The method of claim 1, wherein: The determining the reply time interval based on the conversation information and the reply information includes: The conversation information and the reply information are input into a reply time prediction model to obtain the reply time interval output by the reply time prediction model, wherein the reply time prediction model is trained using sample data annotated with reference reply time intervals, and the sample data includes sample conversation information and sample reply information.

3. The method of claim 2, wherein: The sample data is obtained in the following way: Acquiring historical conversation data of a sample user, wherein the historical conversation data includes a plurality of historical conversation information and a plurality of historical reply information arranged in an alternating manner; and The sample data is determined based on adjacent first historical conversation information and first historical reply information in the historical conversation data, wherein a reference reply time interval marked on the sample data is determined based on the time interval between the sending time of the first historical conversation information and the sending time of the first historical reply information.

4. The method of claim 1, wherein: The determining, based on the conversation information from the user, reply information to the conversation information includes: The dialogue information is sent to a generative language model to obtain the reply information output by the generative language model.

5. The method of claim 4, wherein: The generative language model is obtained by fine-tuning and training using historical conversation data of sample users.

6. The method of claim 5, wherein: The historical conversation data includes a plurality of historical conversation information and a plurality of historical reply information arranged in an interlaced manner, and the fine-tuning training process of the generative language model includes: Determining an emotion tag of each historical reply information in the historical conversation data, wherein the emotion tag of each historical reply information indicates an emotion feature of the historical reply information; and Based on the historical conversation data and the sentiment label of each historical reply information, a training instruction for the generative language model is determined.

7. A device for sending a reply message, comprising: A first determining unit is configured to determine reply information for the conversation information based on the conversation information from the user; A second determining unit is configured to determine a reply time interval based on the conversation information and the reply information; as well as The sending unit is configured to send the reply information to the user in response to determining that the time interval between the current time and the time when the conversation information is sent exceeds the reply time interval.

8. The device according to claim 7, wherein: The second determining unit is configured to: The conversation information and the reply information are input into a reply time prediction model to obtain the reply time interval output by the reply time prediction model, wherein the reply time prediction model is trained using sample data annotated with reference reply time intervals, and the sample data includes sample conversation information and sample reply information.

9. The device of claim 8, wherein: The sample data is determined by a sample data generating unit, and the sample data generating unit includes: an acquisition subunit, configured to acquire historical conversation data of a sample user, wherein the historical conversation data includes a plurality of historical conversation information and a plurality of historical reply information arranged in an interlaced manner; and The first determination subunit is configured to determine the sample data based on adjacent first historical conversation information and first historical reply information in the historical conversation data, wherein a reference reply time interval marked on the sample data is determined based on a time interval between a sending moment of the first historical conversation information and a sending moment of the first historical reply information.

10. The device according to claim 7, wherein: The first determining unit is configured to: The dialogue information is sent to a generative language model to obtain the reply information output by the generative language model.

11. The device of claim 10, wherein: The generative language model is obtained by fine-tuning and training using historical conversation data of sample users.

12. The device of claim 11, wherein: The historical conversation data includes a plurality of historical conversation information and a plurality of historical reply information arranged in an interlaced manner. The generative language model is obtained by fine-tuning training using a training unit, and the training unit includes: A second determining subunit is configured to determine an emotion tag of each historical reply information in the historical conversation data, wherein the emotion tag of each historical reply information indicates an emotion feature of the historical reply information; and The third determination subunit is configured to determine a training instruction for the generative language model based on the historical conversation data and the sentiment label of each historical reply information.

13. An electronic device comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; in The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to make a computer execute the method according to any one of claims 1-6.

15. A computer program product comprising a computer program, wherein: The computer program implements the method according to any one of claims 1 to 6 when executed by a processor.

Images