Conversation processing method and device, storage medium and program product

Abstract

The embodiment of the invention provides a dialogue processing method and device, a storage medium and a program product, relates to the technical field of communication, and can adapt to a current dialogue scene. The method comprises the steps of obtaining to-be-processed dialogue data; based on a dialogue object corresponding to the to-be-processed dialogue data, performing scene adaptation adjustment on the to-be-processed dialogue data to obtain recommended dialogue data; the scene adaptation adjustment comprises at least one of semantic adjustment and mood adjustment.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a conversation processing method, device, storage medium and program product. Background Art

[0002] In daily online communication, users often send messages with unclear expressions, inappropriate tone, and informal language, which reduces communication efficiency. Traditional methods can implement spelling check, auto-complete and other functions, but they cannot adapt to current conversation scenarios and therefore cannot meet users' growing conversation needs. Summary of the invention

[0003] The embodiments of the present disclosure provide a conversation processing method, device, storage medium, and program product, which can adapt to the current conversation scenario.

[0004] On the one hand, a conversation processing method is provided, comprising: obtaining conversation data to be processed; performing scene adaptation adjustment on the conversation data to be processed based on a conversation object corresponding to the conversation data to be processed to obtain recommended conversation data; the scene adaptation adjustment comprises at least one of the following: semantic adjustment and tone adjustment.

[0005] In yet another aspect, a conversation processing method is provided, comprising: in response to a conversation input instruction in a conversation interface, displaying conversation data to be processed in a conversation input box in the conversation interface;

[0006] In response to a scene adaptation adjustment instruction in a dialogue interface, target recommended dialogue data is displayed in a dialogue input box of the dialogue interface; wherein the target recommended dialogue data is obtained by performing scene adaptation adjustment on the dialogue data to be processed based on the dialogue object corresponding to the dialogue data to be processed; the scene adaptation adjustment includes at least one of the following: semantic adjustment, tone adjustment;

[0007] In response to a dialogue sending instruction in the dialogue interface, the target recommendation dialogue data in the dialogue input box is sent.

[0008] In another aspect, a dialog processing device is provided, comprising: an acquisition unit and an adjustment unit;

[0009] An acquisition unit, used for acquiring the conversation data to be processed;

[0010] The adjustment unit is used to perform scene adaptation adjustment on the dialogue data to be processed based on the dialogue object corresponding to the dialogue data to be processed to obtain recommended dialogue data; the scene adaptation adjustment includes at least one of the following: semantic adjustment and tone adjustment.

[0011] In yet another aspect, there is provided a conversation processing device, comprising: a display unit and a sending unit;

[0012] A display unit, configured to display the to-be-processed dialogue data in a dialogue input box in the dialogue interface in response to a dialogue input instruction in the dialogue interface;

[0013] The display unit is further configured to respond to a scene adaptation adjustment instruction in the dialogue interface and display the target recommended dialogue data in the dialogue input box of the dialogue interface; wherein the target recommended dialogue data is obtained by performing scene adaptation adjustment on the dialogue data to be processed based on the dialogue object corresponding to the dialogue data to be processed; the scene adaptation adjustment includes at least one of the following: semantic adjustment and tone adjustment;

[0014] A sending unit is used to send the target recommendation dialogue data in the dialogue input box in response to a dialogue sending instruction in the dialogue interface.

[0015] On the other hand, an electronic device is provided, comprising: a memory and a processor; the memory and the processor are coupled; the memory is used to store a computer program; and the processor implements the conversation processing method described in any of the above embodiments when executing the computer program.

[0016] On the other hand, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the dialog processing method described in any of the above embodiments is implemented.

[0017] On the other hand, a computer program product is provided, which includes computer program instructions, and when the computer program instructions are executed by a processor, the dialog processing method described in any of the above embodiments is implemented.

[0018] The disclosed embodiment discloses that the dialogue data to be processed can be obtained, and based on the dialogue object corresponding to the dialogue data to be processed, the dialogue data to be processed is subjected to scene adaptation adjustment, thereby obtaining recommended dialogue data. Since scene adaptation can achieve semantic adjustment and / or tone adjustment, so that the semantics of the dialogue data to be processed is clearer, and the tone is more adapted to the dialogue object, the recommended dialogue data can be better adapted to the current dialogue scene, and can better meet the needs of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present disclosure, the drawings required for use in some embodiments of the present disclosure will be briefly introduced below. Obviously, the drawings described below are only drawings of some embodiments of the present disclosure, and a person skilled in the art can also obtain other drawings based on these drawings.

[0020] Figure 1 A communication system architecture diagram provided for some embodiments of the present disclosure;

[0021] Figure 2 A flow chart of a method for processing a conversation provided in some embodiments of the present disclosure Figure 1 ;

[0022] Figure 3 A schematic diagram of a process of performing adjustment based on an adjustment level provided in some embodiments of the present disclosure;

[0023] Figure 4 A schematic diagram of a personalized adjustment process provided for some embodiments of the present disclosure;

[0024] Figure 5 A schematic diagram of a process for determining conversation data to be transmitted provided in some embodiments of the present disclosure;

[0025] Figure 6 A schematic diagram of a process for training a personalized dialogue model based on data to be transmitted provided in some embodiments of the present disclosure;

[0026] Figure 7 A schematic diagram of a different personalized dialogue model provided for some embodiments of the present disclosure;

[0027] Figure 8 A flowchart of another method for processing a conversation provided in some embodiments of the present disclosure;

[0028] Fig. 9 A schematic diagram of conversation data to be processed and target recommended conversation data provided in some embodiments of the present disclosure;

[0029] Fig.10 A schematic diagram of adjustment levels of different dialogue objects provided in some embodiments of the present disclosure;

[0030] Fig.11 A schematic diagram of a process of selecting a target recommendation dialogue from a recommendation dialogue interface provided by some embodiments of the present disclosure;

[0031] Fig.12 A schematic diagram of a recommendation dialogue interface provided in some embodiments of the present disclosure;

[0032] Fig.13 A schematic diagram of the structure of a communication device provided in some embodiments of the present disclosure;

[0033] Fig.14 A schematic diagram of the structure of another communication device provided in some embodiments of the present disclosure;

[0034] Fig.15 A schematic diagram of the structure of yet another communication device provided for some embodiments of the present disclosure. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the present disclosure to clearly and completely describe the technical solutions in the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0036] It should be noted that, in the present disclosure, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present disclosure should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0037] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0038] In the description of the present disclosure, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" means one or more, and "a plurality" means two or more.

[0039] In daily online communication, users often send messages with unclear expressions, inappropriate tone, and informal language, which reduces communication efficiency. Traditional methods can implement spelling check, auto-complete and other functions, but they cannot adapt to current conversation scenarios and therefore cannot meet users' growing conversation needs.

[0040] In this regard, the disclosed embodiment provides a conversation processing method, which can obtain conversation data to be processed, and based on the conversation object corresponding to the conversation data to be processed, perform scene adaptation adjustment on the conversation data to be processed, so as to obtain recommended conversation data. Since scene adaptation can achieve semantic adjustment and / or tone adjustment, so that the semantics of the conversation data to be processed is clearer, and the tone is more suitable for the conversation object, the recommended conversation data can be better adapted to the current conversation scene, and can better meet the needs of users.

[0041] The dialogue processing method provided by the embodiment of the present disclosure can be applied to systems of various communication formats. For example, the dialogue processing provided by the embodiment of the present disclosure can be applied to systems including, but not limited to, long term evolution (LTE) systems, various versions based on LTE evolution, fifth generation mobile communication technology (5G) systems, future mobile communication networks (such as 6G mobile communication networks), or multiple communication convergence systems. In addition, the dialogue processing method provided by the embodiment of the present disclosure can also be applied to future-oriented communication systems.

[0042] Exemplarily, the above-mentioned dialogue processing method can be applied to Figure 1 In the communication system, Figure 1 As shown, the communication system includes: a terminal 101 and a server 102.

[0043] Among them, the terminal 101 is connected to the server 102 for communication. Optionally, the terminal can be a smart watch, a tablet, a computer, etc., and can be connected to a communication network (such as 3 / 4 / 5G network, wireless fidelity (WI-FI), wired network, etc.). The server 102 can be a cloud server or a cloud service platform, providing powerful background support and computing capabilities.

[0044] In a possible implementation, the terminal 101 may obtain the conversation data to be processed input by the user, and based on the conversation object corresponding to the conversation data to be processed, perform scene adaptation adjustment on the conversation data to be processed to obtain recommended conversation data. Afterwards, the user may have a conversation with other users based on the recommended conversation data output by the electronic device.

[0045] In another possible implementation, the terminal 101 may obtain the conversation data to be processed input by the user. Afterwards, the terminal 101 may send the conversation data to be processed to the server 102. After receiving the conversation data to be processed, the server 102 may perform scene adaptation adjustment on the conversation data to be processed based on the conversation object corresponding to the conversation data to be processed, and obtain recommended conversation data. Then, the server 102 may send the recommended conversation data to the terminal 101, so that the user can have a conversation based on the recommended conversation data received by the terminal 101.

[0046] It should be noted that the terminal 101 and the server 102 may include: a processor (central processing unit, CPU), a memory (random access memory, RAM), a storage unit (Storage), a network interface, an operating system, and an artificial intelligence (artificial intelligence, AI) processing unit.

[0047] In some embodiments, the electronic device may include: a data encryption and storage module, a data transmission module, a natural language processing (NLP) processing module, and a personalized dialogue model module.

[0048] The data transmission module is used for transmitting the conversation data to be processed and the recommended conversation data between the terminal 101 and the server 102 .

[0049] The data encryption and storage module is used to encrypt and decrypt the transmitted data and store the data.

[0050] The NLP processing module is used to perform scene adaptation adjustments on the conversation data to be processed.

[0051] The personalized dialogue model module is used to make personalized adjustments to the dialogue data to be processed, and to fuse the personalized dialogue data with the recommended dialogue data to obtain personalized recommended dialogue data.

[0052] Exemplarily, the terminal encrypts the conversation data to be processed through the data encryption and storage module, and sends the encrypted data to the server through the data transmission module.

[0053] The server receives the encrypted data through the data transmission module and decrypts it. The server can process the data to be processed through the NLP processing module and the personalized dialogue model module to obtain personalized recommendation dialogue data. Afterwards, the server can send the encrypted personalized recommendation dialogue data to the terminal through the data transmission module and the data encryption and storage module.

[0054] The terminal obtains personalized recommendation conversation data through the data transmission module, data encryption and storage module.

[0055] In some embodiments, the terminal can be a device with wireless transceiver function, which can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it can also be deployed on the water surface (such as ships, etc.); it can also be deployed in the air (for example, on airplanes, balloons and satellites, etc.). The terminal can be a mobile phone, a tablet computer (Pad), a computer with wireless transceiver function, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc. The embodiments of the present application do not limit the application scenarios. A terminal may sometimes also be referred to as a user, user equipment (UE), access terminal, UE unit, UE station, mobile station, mobile station, remote station, remote terminal, mobile device, UE terminal, wireless communication equipment, UE agent or UE device, etc., but the embodiments of the present application are not limited to this.

[0056] It should be noted that Figure 1 This is just an exemplary framework diagram. Figure 3 The number of devices included in the Figure 1 In addition to the devices shown, the communication system may also include other devices, such as relay nodes, etc.

[0057] The application scenarios of the embodiments of the present disclosure are not limited. The system architecture and business scenarios described in the embodiments of the present disclosure are intended to more clearly illustrate the technical solutions of the embodiments of the present disclosure, and do not constitute a limitation on the technical solutions provided by the embodiments of the present disclosure. It is known to those skilled in the art that with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of the present disclosure are also applicable to similar technical problems.

[0058] The conversation processing method provided by the embodiment of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0059] The dialog processing method provided by the embodiment of the present disclosure can be applied to an electronic device, which can be Figure 1 A terminal 101 or a server 102 in the communication system shown. Figure 2 A flow chart showing a method for processing a dialogue Figure 1 ,like Figure 2 As shown, the dialogue processing method includes the following S201.

[0060] S201. The electronic device obtains conversation data to be processed.

[0061] Optionally, the conversation data to be processed may be text or voice data.

[0062] Taking the electronic device as a terminal as an example, when conducting an online conversation, the user can input the conversation data to be processed into the electronic device, for example, through the input box (or input method) of the electronic device. Alternatively, taking the electronic device as a server as an example, the user can input the conversation data to be processed into the terminal, and after determining that the data needs to be adjusted, send the conversation data to be processed to the electronic device.

[0063] S202: The electronic device performs scene adaptation adjustment on the conversation data to be processed based on the conversation object corresponding to the conversation data to be processed, and obtains recommended conversation data.

[0064] Among them, the scene adaptation adjustment includes at least one of the following: semantic adjustment and tone adjustment.

[0065] In addition to obtaining the dialogue data to be processed, the electronic device can also obtain the dialogue object corresponding to the dialogue data to be processed. Since different dialogue objects correspond to different dialogue scenarios, the tone and semantic requirements of the dialogue data are also different during the dialogue. In this case, the electronic device can make scene adaptation adjustments to the data to be processed (for example, through AI processing) based on the dialogue object corresponding to the dialogue data to be processed, so that the semantics of the recommended dialogue data obtained are clearer and the tone is more adaptable to the current dialogue object, so that the recommended dialogue data can better meet the current dialogue scenario and better meet the needs of users. In addition, it can also provide users with communication efficiency and communication quality, and reduce communication costs.

[0066] In the case where the electronic device is a server, the electronic device also needs to send the obtained recommended conversation data to the terminal so that the user can have a conversation based on the recommended conversation data.

[0067] In a possible implementation, when the electronic device is a server, when the terminal sends the conversation data to be processed to the electronic device, and when the electronic device sends the recommended conversation data to the terminal, the conversation data can be encrypted, and the encrypted data is transmitted through the network interface, thereby improving the security of the data and protecting the privacy of the user. In addition, when the electronic device stores the user data such as the conversation data to be processed and the recommended conversation data, it can also encrypt and store the data to ensure the security and privacy of the data. In addition, the electronic device can also perform security audits and mobile monitoring regularly to further improve the security of the system.

[0068] The application scenarios of the embodiments of the present disclosure may include the following:

[0069] In daily communication, the dialogue partner can be family members, friends, etc. It can help users organize sentences, correct spelling errors, and provide appropriate vocabulary suggestions to make communication smoother. It also provides personalized expression suggestions based on the situation, enhances the interactive experience, and avoids misunderstandings caused by inappropriate wording.

[0070] When communicating in the workplace, the person you are talking to can be a colleague, a leader, etc. This can make the tone more formal and appropriate, and ensure semantic accuracy and professionalism.

[0071] In business communication, the dialogue partners can be customers, users, etc. The semantics are more accurate and clear, and the tone is more formal and appropriate, which can improve customer satisfaction.

[0072] In another possible implementation, the to-be-processed dialog data is input by the user based on an input method. The disclosed embodiment can be integrated into a plug-in or integrated as a function into an input method or a smart keyboard, thereby improving adaptability.

[0073] In another possible implementation, the electronic device can perform not only scene adaptation adjustment but also translation of the conversation data to be processed, thereby better meeting user needs.

[0074] In some embodiments, in combination Figure 2 ,like Figure 3 As shown, in the above S202, the electronic device performs scene adaptation adjustment on the conversation data to be processed based on the conversation object corresponding to the conversation data to be processed, including:

[0075] S301. The electronic device obtains an adjustment level of a dialogue partner.

[0076] One dialog object corresponds to one adjustment level, and the adjustment levels corresponding to multiple dialog objects may be the same. Optionally, when the electronic device is a server, the terminal may carry the adjustment level of the dialog object when sending the dialog data to be processed to the electronic device. Alternatively, the electronic device may pre-store the adjustment level corresponding to each dialog.

[0077] Since different dialogue objects have different requirements for the semantics and tone of dialogue data, the electronic device has different adjustment degrees for the dialogue data to be processed for different dialogue objects. In this case, the electronic device can obtain the adjustment level of the dialogue object and determine the adjustment degree of the dialogue data to be processed based on the adjustment level of the dialogue object.

[0078] S302: The electronic device performs scene adaptation adjustment on the dialogue data to be processed based on the adjustment level of the dialogue object.

[0079] After obtaining the adjustment level of the dialogue object, the electronic device can perform scene adaptation adjustment on the dialogue data to be processed based on the adjustment level. Different adjustment levels correspond to different degrees of scene adaptation adjustment. For example, when the dialogue object is a leader or a customer, the adjustment level can be higher, and the semantics of the recommended dialogue data obtained after adjustment are clearer, the tone is more formal, etc., so as to better meet the current scene. In this way, scenes corresponding to various dialogue objects can be met, and the needs of users can be better met.

[0080] As an example, the adjustment level (also called AI assistance level) can range from 0 to 1, and is divided into 11 levels. Each level corresponds to a different degree of adjustment. The higher the level, the higher the degree of adjustment. For example:

[0081] Level 0: No processing is performed on the conversation data to be processed, that is, no AI processing is required.

[0082] Level 0.1-0.3: spelling correction and basic grammar checking, which can be adapted to daily casual chats. For example, at level 0.2, the dialogue data to be processed is "I am late", and the recommended dialogue data is "I am late again today".

[0083] Level 0.4-0.6: Correction of typos, basic grammar check and revision suggestions, optimization of sentence structure to make logic clearer, tone adjustment, vocabulary replacement (i.e. replacement of more appropriate vocabulary), suitable for communication with colleagues, customers, etc. For example, at level 0.5, the dialogue data to be processed is "I am late today", and the recommended dialogue data is "I am late today, sorry".

[0084] Level 0.7-1: Correction of typos, basic grammar check and revision suggestions, optimization of sentence structure to make logic clearer, tone adjustment, vocabulary replacement (i.e. replacement of more appropriate vocabulary), format adjustment, and personalized adjustment, suitable for very formal communication occasions with leaders, important customers, etc. For example, at level 0.8, the dialogue data to be processed is "I am late today", and the recommended dialogue data is "I am late today, I am very sorry". For example, at level 1, the dialogue data to be processed is "I am late today", and the recommended dialogue data is "I am very sorry, I was late today due to traffic reasons, which caused inconvenience to your work, please forgive me".

[0085] In one possible implementation, the electronic device performs scene adaptation adjustment on the conversation data to be processed based on natural language processing (NLP) technology.

[0086] The electronic device can perform sentiment analysis, context understanding, semantic analysis, lexical analysis, etc. on the processed dialogue data based on NLP technology, and make adjustments based on the content obtained from the analysis, so that the adjusted data semantics are clearer and the tone is more suitable for the current scene. Optionally, the electronic device can perform word segmentation on the text to be processed to obtain multiple words, one word corresponding to one part of speech. Afterwards, the electronic device can make scene adaptation adjustments to the text to be processed based on the parts of speech of multiple words.

[0087] In some embodiments, in combination Figure 2 ,like Figure 4 As shown, the method provided by the embodiment of the present disclosure also includes:

[0088] S401. The electronic device performs personalized adjustment on the dialogue data to be processed by using a personalized dialogue model to obtain personalized dialogue data.

[0089] Among them, the personalized dialogue model is a model obtained based on the user's historical dialogue data.

[0090] Through machine learning algorithms, the user's historical conversation data can be used as training data to train a personalized conversation model. In this way, the personalized conversation data adjusted by the personalized conversation model can meet the user's personalized needs, such as meeting the user's habits and language style, and can better meet the user's needs, and can also help users improve communication efficiency and quality.

[0091] S402: The electronic device fuses the recommended conversation data and the personalized conversation data to generate personalized recommended conversation data.

[0092] In some implementations, after determining the recommended conversation data, the electronic device may output the recommended conversation data to the user, so that the user can have a conversation based on the recommended conversation data. Alternatively, the electronic device may perform data fusion on the recommended conversation data and the personalized conversation data, so that the obtained personalized recommended conversation data has clear semantics, a tone that is more suitable for the current scene, and is more in line with the personalized needs of the user, thereby better meeting the needs of the user.

[0093] In some embodiments, in combination Figure 4 ,like Figure 5 As shown, the recommended conversation data or personalized conversation data is multiple, and the method provided by the embodiment of the present disclosure also includes:

[0094] S501. The electronic device determines target recommended conversation data from a plurality of recommended conversation data or a plurality of personalized recommended conversation data in response to a selection operation triggered by a user.

[0095] The target recommended conversation data is used to determine the conversation data to be transmitted, and the conversation data to be transmitted is the target recommended conversation data or data obtained after adjusting the target recommended conversation data.

[0096] In one implementation, when the electronic device is a terminal, after determining a plurality of recommended conversation data or a plurality of personalized recommended conversation data, the electronic device may output the plurality of recommended conversation data or a plurality of personalized recommended conversation data to the user. Afterwards, the user may select a recommended conversation data or a personalized recommended conversation data from the plurality of recommended conversation data or a plurality of personalized recommended conversation data as the target recommended conversation data to be transmitted, that is, the conversation data to be transmitted is the target recommended conversation data.

[0097] Alternatively, after the user selects a recommended conversation data or personalized recommended conversation data from multiple recommended conversation data or multiple personalized recommended conversation data as the target recommended conversation data, the target recommended conversation data can be adjusted to obtain the conversation data to be transmitted. Subsequently, the electronic device can send the conversation data to be transmitted to the conversation object. In this way, the user can have more choices, thereby better meeting the user's needs.

[0098] In some embodiments, in combination Figure 5 ,like Figure 6 As shown, the method provided by the embodiment of the present disclosure also includes:

[0099] S601: The electronic device obtains conversation data to be transmitted.

[0100] In one implementation, after determining the conversation data to be transmitted, the electronic device may reacquire the conversation data to be transmitted that has been sent.

[0101] S602: The electronic device trains a personalized conversation model based on the conversation data to be transmitted.

[0102] Among them, the personalized dialogue model is a model obtained based on the user's historical dialogue data.

[0103] Since the conversation data to be transmitted is the target recommended conversation data selected by the user, or is obtained by adjusting the target recommended conversation data, it can better meet the needs of the user. Therefore, the electronic device can continue to train the personalized conversation model based on the conversation data to be transmitted, so that the personalized conversation model can better adjust the personalized conversation for the user and improve the user's satisfaction.

[0104] As an example, Figure 7 A schematic diagram of a different personalized dialogue model is shown. Figure 7As shown in the figure, the data sent by the conversation object is "Have you eaten? What did you eat today?", and the conversation data to be processed is "I ate in the company cafeteria". For the trained initial personalized conversation model, the recommended conversation data generated is "I ate at the company today". After the personalized conversation model is trained multiple times based on the conversation data to be transmitted, the recommended conversation data generated is "I ate. I ate at the company today".

[0105] As another example, taking the electronic device as a server as an example, the following will be described through multiple steps.

[0106] Step 1: The user inputs the conversation data to be processed.

[0107] The user inputs text or voice information through a terminal (such as a computer, keyboard or voice input). The terminal preliminarily formats the conversation data to be processed and converts it into a standardized data structure.

[0108] Step 2: Data encryption and transmission.

[0109] The terminal encrypts the conversation data to be processed after the preliminary formatting, and sends the data to the electronic device through the network interface.

[0110] Step 3: Data reception and decryption.

[0111] The electronic device receives the encrypted and preliminarily formatted conversation data to be processed, decrypts and restores it to the conversation data to be processed, and then stores the conversation data to be processed in a temporary memory.

[0112] Step 4: Adjust the scene to suit your needs.

[0113] The electronic device uses NLP technology to perform grammatical analysis, tone analysis, emotion recognition, etc. on the conversation data to be processed, and uses deep learning to analyze the structure, vocabulary, tone, etc. of the conversation data to be processed to obtain recommended conversation data.

[0114] Step 5: The electronic device processes the conversation data to be processed based on the personalized conversation model to obtain personalized conversation data.

[0115] Step 6: Generate personalized recommendation conversation data.

[0116] The recommendation conversation data and the personalized recommendation conversation data are integrated to obtain the personalized recommendation conversation data.

[0117] Step 7: Data encryption and return.

[0118] The electronic device encrypts the personalized recommendation conversation data and sends the encrypted data to the terminal.

[0119] Step 8: Output personalized recommendation conversation data.

[0120] The terminal receives the encrypted personalized recommendation conversation data and decrypts it. After that, the decrypted data is displayed to the user, who can send it only or send it after modification. In addition, the data sent by the user can continue to be used for personalized model training.

[0121] The following is another implementation of the embodiment of the present disclosure. Figure 8 A flow chart showing a method for processing a dialogue Figure 2 ,like Figure 8 As shown, the dialogue processing method includes:

[0122] S801. The electronic device displays the dialogue data to be processed in the dialogue input box in the dialogue interface in response to the dialogue input instruction in the dialogue interface.

[0123] The user can input the dialogue data to be processed in the dialogue interface of the electronic device, and the electronic device can generate a dialogue input instruction. Afterwards, the electronic device can respond to the dialogue input instruction in the dialogue interface and display the dialogue data to be processed for input in the dialogue input box of the dialogue interface.

[0124] S802: The electronic device displays target recommended dialogue data in a dialogue input box of the dialogue interface in response to a scene adaptation adjustment instruction in the dialogue interface.

[0125] Among them, the target recommended dialogue data is obtained after the dialogue data to be processed is subjected to scene adaptation adjustment based on the dialogue object corresponding to the dialogue data to be processed; the scene adaptation adjustment includes at least one of the following: semantic adjustment and tone adjustment.

[0126] When the user wants to perform scene adaptation adjustment on the dialogue data to be processed, the user can trigger the scene adaptation adjustment control on the dialogue interface to generate a scene adaptation adjustment instruction. Afterwards, the electronic device can respond to the scene adaptation adjustment instruction and perform scene adaptation adjustment on the dialogue data to be processed to obtain target recommended dialogue data. Afterwards, the electronic device can display the target recommended dialogue data in the dialogue input box of the dialogue interface.

[0127] For example, Fig. 9 A schematic diagram of the dialogue data to be processed and the target recommended dialogue data is shown. Fig. 9 As shown, the dialogue object is Hu A, the data sent is "Have you eaten? What did you eat for lunch today?", and the dialogue data to be processed is "I ate in the company cafeteria". Then, the target recommended dialogue data after scene adaptation adjustment of the dialogue data to be processed is "I have eaten. I ate in the company cafeteria today", and it is displayed in the dialogue input box.

[0128] S803: The electronic device sends the target recommended dialogue data in the dialogue input box in response to the dialogue sending instruction in the dialogue interface.

[0129] After determining the target recommended conversation data, the user can trigger the conversation sending control on the conversation interface to generate a conversation sending instruction. Afterwards, the electronic device can respond to the conversation sending instruction and send the target recommended conversation data to the conversation object. In this way, the semantics of the target recommended conversation data adjusted through scene adaptation are clearer, and the tone is more adaptable to the current scene, thereby meeting the needs of users.

[0130] In one possible manner, the electronic device adjusts the scene adjustment configuration of the dialogue object in the dialogue interface to the scene adjustment configuration indicated by the configuration instruction in response to the configuration instruction in the dialogue interface, and the scene adjustment configuration includes an adjustment level. Since the scene adaptation adjustment is adjusted based on the dialogue object, different dialogue objects correspond to different adjustment levels. In this case, the user can trigger the configuration control in the dialogue interface to generate the configuration instruction. Afterwards, the electronic device can adjust the scene adjustment configuration of the dialogue object in response to the configuration instruction in the dialogue interface, such as adjusting the adjustment level of the dialogue object. In this way, the recommended dialogue data obtained can be adapted to different scenes and objects, so as to better meet user needs.

[0131] For example, Fig.10 A schematic diagram showing the adjustment levels of different dialogue objects is shown. Fig.10 As shown, the two dialogue objects are Aunt Li and Mom. Aunt Li's adjustment level is 0.4, and Mom's adjustment level is 0.2. The two dialogue objects send the same dialogue "Have you eaten well recently? What did you eat for lunch?", and the dialogue data to be processed is "Eat in the company cafeteria". Since the adjustment levels of the two dialogue objects are different, the target recommendation dialogue data displayed in the dialogue input box in the dialogue interface is also different. The target recommendation dialogue data displayed in the dialogue input box corresponding to Aunt Li is "Aunt Li, eat in the company cafeteria for lunch", and the target recommendation dialogue data displayed in the dialogue input box corresponding to Mom is "Mom, eat in the company cafeteria, don't worry". Optionally, the configuration control can be a slider, and the user can configure the adjustment level on the slider in the dialogue interface corresponding to each dialogue object.

[0132] In some embodiments, in combination Figure 8 ,like Fig.11 As shown, in the above S802, the electronic device displays the target recommended dialogue data in the dialogue input box of the dialogue interface in response to the scene adaptation adjustment instruction in the dialogue interface, including:

[0133] S1101. The electronic device displays a recommendation dialogue interface in response to a scene adaptation adjustment instruction in the dialogue interface.

[0134] Among them, the recommended dialogue interface includes at least one recommended dialogue data, and the recommended dialogue data is obtained after the dialogue data to be processed is adapted to the scene based on the dialogue object corresponding to the dialogue data to be processed.

[0135] After the dialog data to be processed is subjected to scene adaptation adjustment, a plurality of recommended dialog data can be obtained. The electronic device can display a plurality of recommended dialog data on the recommended dialog interface for the user to select, thereby providing the user with more choices to better meet the user's needs.

[0136] S1102: The electronic device displays the selected target recommendation dialogue data in the dialogue input box of the dialogue interface in response to the selection instruction in the recommendation dialogue interface.

[0137] The user selects one recommended conversation data from multiple recommended conversation data displayed on the recommended conversation interface as the target recommended conversation data, and displays it in the conversation input box corresponding to the conversation object, so that the user can directly send the target recommended conversation data in the input box, or modify it and send it.

[0138] For example, Fig.12 A schematic diagram of a recommendation dialogue interface is shown. Fig.10 As shown, taking the electronic device as the terminal as an example, the data sent by the dialogue object is "Why didn't you come to today's meeting?", and the dialogue data to be processed is "I'm late." The user can choose to trigger the scene adaptation adjustment control (i.e., the button with AI written on it) of the dialogue input box to generate a scene adaptation adjustment instruction to implement the recommended dialogue interface. Multiple recommended dialogue data are displayed in the recommended dialogue interface. The user can select one from the multiple recommended dialogue data as the target recommended dialogue data, and the selected target recommended dialogue data is displayed in the dialogue input box.

[0139] In a possible implementation, after the electronic device obtains a piece of recommended conversation data, it directly displays the recommended conversation data in the user input box, thereby eliminating the need for selection through the recommended conversation interface.

[0140] It is understandable that, in order to implement the above functions, the dialogue processing device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the algorithm steps of each example described in the embodiments of the present disclosure, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present disclosure.

[0141] The disclosed embodiment can divide the dialogue processing device into functional modules according to the above method embodiment. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one functional module. The above integrated module can be implemented in the form of hardware or software. It should be noted that the division of modules in the disclosed embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation. The following is an example of dividing each functional module corresponding to each function.

[0142] Fig.13 is a schematic diagram of the structure of a communication device provided by an embodiment of the present disclosure, and the communication device can execute the conversation processing method provided by the above method embodiment. Fig.13 As shown, the communication device includes: an acquisition unit 1301 and an adjustment unit 1302.

[0143] The acquisition unit 1301 is used to acquire the conversation data to be processed.

[0144] The adjustment unit 1302 is used to perform scene adaptation adjustment on the dialogue data to be processed based on the dialogue object corresponding to the dialogue data to be processed to obtain recommended dialogue data; the scene adaptation adjustment includes at least one of the following: semantic adjustment and tone adjustment.

[0145] In a possible implementation, the adjustment unit 1302 is specifically configured to: obtain an adjustment level of the dialogue object; and perform the scene adaptation adjustment on the dialogue data to be processed based on the adjustment level of the dialogue object.

[0146] In a possible implementation, the adjustment unit 1302 is specifically configured to perform scene adaptation adjustment on the dialogue data to be processed based on natural language processing (NLP) technology.

[0147] In a possible implementation, the adjustment unit 1302 is further configured to perform personalized adjustment on the to-be-processed conversation data through a personalized conversation model to obtain personalized conversation data, wherein the personalized conversation model is a model obtained based on historical conversation data of the user;

[0148] In a possible implementation, the device further includes: a determination unit 1303. The determination unit 1303 is configured to determine target recommended conversation data from multiple recommended conversation data or multiple personalized recommended conversation data in response to a selection operation triggered by a user; the target recommended conversation data is used to determine conversation data to be transmitted, and the conversation data to be transmitted is the target recommended conversation data or data obtained after adjusting the target recommended conversation data.

[0149] In a possible implementation, the device further includes: a training unit 1304. The acquisition unit 1301 is further configured to acquire the conversation data to be transmitted.

[0150] The training unit 1304 is used to train a personalized dialogue model based on the dialogue data to be transmitted, where the personalized dialogue model is a model obtained based on the user's historical dialogue data.

[0151] In a possible implementation, the dialogue data to be processed is data input based on an input method.

[0152] Fig.14 is a schematic diagram of the structure of another communication device provided by an embodiment of the present disclosure, and the communication device can execute the conversation processing method provided by the above method embodiment. Fig.14 As shown, the communication device includes: a display unit 1401 and a sending unit 1402.

[0153] The display unit 1401 is used to display the dialogue data to be processed in the dialogue input box in the dialogue interface in response to the dialogue input instruction in the dialogue interface.

[0154] The display unit 1401 is also used to respond to the scene adaptation adjustment instruction in the dialogue interface and display the target recommended dialogue data in the dialogue input box of the dialogue interface; wherein the target recommended dialogue data is obtained after the dialogue object corresponding to the dialogue data to be processed is subjected to the scene adaptation adjustment; the scene adaptation adjustment includes at least one of the following: semantic adjustment and tone adjustment.

[0155] The sending unit 1402 is used to send the target recommendation dialogue data in the dialogue input box in response to a dialogue sending instruction in the dialogue interface.

[0156] In one possible implementation, the display unit 1401 is specifically used to: display a recommended dialogue interface in response to a scene adaptation adjustment instruction in the dialogue interface, the recommended dialogue interface including at least one recommended dialogue data, the recommended dialogue data being obtained after scene adaptation adjustment of the dialogue data to be processed based on the dialogue object corresponding to the dialogue data to be processed; and display the selected target recommended dialogue data in the dialogue input box of the dialogue interface in response to a selection instruction in the recommended dialogue interface.

[0157] In a possible implementation, the recommendation dialogue interface also includes at least one personalized recommendation dialogue data, wherein the personalized recommendation dialogue data is obtained by fusing the recommendation dialogue data and the personalized dialogue data, and the personalized dialogue data is obtained by personalizing the dialogue data to be processed through a personalized dialogue model.

[0158] In a possible implementation, the device further includes an adjustment unit 1403. The adjustment unit 1403 is configured to adjust the scene adjustment configuration of the dialogue object in the dialogue interface to the scene adjustment configuration indicated by the configuration instruction in response to the configuration instruction in the dialogue interface, wherein the scene adjustment configuration includes an adjustment level.

[0159] In the case of implementing the functions of the above-mentioned integrated modules in the form of hardware, the embodiments of the present disclosure provide another possible structure of the communication device involved in the above-mentioned embodiments. Fig.15 As shown, the communication device 150 includes: a processor 1502 and a bus 1504. Optionally, the communication device may further include a memory 1501; optionally, the communication device may further include a communication interface 1503.

[0160] The processor 1502 may be a processor that implements or executes various exemplary logic blocks, modules, and circuits described in conjunction with the embodiments of the present disclosure. The processor 1502 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the embodiments of the present disclosure. The processor 1502 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0161] The communication interface 1503 is used to connect with other devices via a communication network, such as Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0162] The memory 1501 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0163] As a possible implementation, the memory 1501 may exist independently of the processor 1502, and the memory 1501 may be connected to the processor 1502 via a bus 1504 to store instructions or program codes. When the processor 1502 calls and executes the instructions or program codes stored in the memory 1501, the dialog processing method provided in the embodiment of the present disclosure can be implemented.

[0164] In another possible implementation, the memory 1501 may also be integrated with the processor 1502 .

[0165] The bus 1504 may be an extended industry standard architecture (EISA) bus, etc. The bus 1504 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.15 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0166] Some embodiments of the present disclosure provide a computer-readable storage medium (e.g., a non-transitory computer-readable storage medium), in which computer program instructions are stored. When the computer program instructions are executed on a computer, the computer executes the dialog processing method described in any of the above embodiments.

[0167] Exemplarily, the above-mentioned computer-readable storage media may include, but are not limited to: magnetic storage devices (e.g., hard disks, floppy disks or magnetic tapes, etc.), optical disks (e.g., compact disks (CD), digital versatile disks (DVD), etc.), smart cards and flash memory devices (e.g., erasable programmable read-only memory (EPROM), cards, sticks or key drives, etc.). The various computer-readable storage media described in the present disclosure may represent one or more devices and / or other machine-readable storage media for storing information. The term "machine-readable storage medium" may include, but is not limited to, wireless channels and various other media capable of storing, containing and / or carrying instructions and / or data.

[0168] The embodiment of the present disclosure provides a computer program product including instructions. When the computer program product is run on a computer, the computer executes the dialog processing method described in any of the above embodiments. The above description is only a specific implementation method of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present disclosure should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for processing a conversation, characterized in that: The method comprises: Get the conversation data to be processed; Based on the dialogue object corresponding to the dialogue data to be processed, the dialogue data to be processed is subjected to scene adaptation adjustment to obtain recommended dialogue data; the scene adaptation adjustment includes at least one of the following: semantic adjustment and tone adjustment.

2. The method according to claim 1, characterized in that The step of performing scene adaptation adjustment on the dialogue data to be processed based on the dialogue object corresponding to the dialogue data to be processed includes: Obtaining the adjustment level of the dialogue object; The scene adaptation adjustment is performed on the to-be-processed dialogue data based on the adjustment level of the dialogue object.

3. The method according to claim 1, characterized in that The scene adaptation adjustment of the to-be-processed dialogue data includes: Based on natural language processing (NLP) technology, scene adaptation and adjustment are performed on the dialogue data to be processed.

4. The method according to claim 1, characterized in that The method further comprises: Performing personalized adjustment on the to-be-processed conversation data through a personalized conversation model to obtain personalized conversation data, wherein the personalized conversation model is a model obtained based on the user's historical conversation data; The recommendation dialogue data and the personalized dialogue data are fused to generate personalized recommendation dialogue data.

5. The method according to claim 4, characterized in that The recommendation dialogue data or the personalized recommendation dialogue is multiple, and the method further includes: In response to a selection operation triggered by a user, target recommended conversation data is determined from multiple recommended conversation data or multiple personalized recommended conversation data; the target recommended conversation data is used to determine conversation data to be transmitted, and the conversation data to be transmitted is the target recommended conversation data or data obtained after adjusting the target recommended conversation data.

6. The method according to claim 5, characterized in that The method further comprises: Acquire the conversation data to be transmitted; A personalized dialogue model is trained based on the dialogue data to be transmitted, where the personalized dialogue model is a model obtained based on the user's historical dialogue data.

7. The method according to claim 1, characterized in that The dialogue data to be processed is data input based on an input method.

8. A method for processing a conversation, characterized in that: The method comprises: In response to a dialogue input instruction in the dialogue interface, displaying the dialogue data to be processed in a dialogue input box in the dialogue interface; In response to a scene adaptation adjustment instruction in a dialogue interface, target recommended dialogue data is displayed in a dialogue input box of the dialogue interface; wherein the target recommended dialogue data is obtained by performing scene adaptation adjustment on the dialogue data to be processed based on the dialogue object corresponding to the dialogue data to be processed; the scene adaptation adjustment includes at least one of the following: semantic adjustment, tone adjustment; In response to a dialogue sending instruction in the dialogue interface, the target recommendation dialogue data in the dialogue input box is sent.

9. The method according to claim 8, characterized in that The step of displaying target recommendation dialogue data in a dialogue input box of the dialogue interface in response to a scene adaptation adjustment instruction in the dialogue interface includes: In response to the scene adaptation adjustment instruction in the dialogue interface, a recommended dialogue interface is displayed, wherein the recommended dialogue interface includes at least one recommended dialogue data, wherein the recommended dialogue data is obtained by performing scene adaptation adjustment on the dialogue data to be processed based on the dialogue object corresponding to the dialogue data to be processed; In response to a selection instruction in the recommendation dialogue interface, the selected target recommendation dialogue data is displayed in a dialogue input box of the dialogue interface.

10. The method according to claim 9, characterized in that The recommendation dialogue interface also includes at least one personalized recommendation dialogue data, wherein the personalized recommendation dialogue data is obtained by fusing the recommendation dialogue data and the personalized dialogue data, and the personalized dialogue data is obtained by personalizing the dialogue data to be processed through a personalized dialogue model.

11. The method according to claim 8, characterized in that The method further comprises: In response to a configuration instruction in a dialogue interface, a scene adjustment configuration of a dialogue object in the dialogue interface is adjusted to the scene adjustment configuration indicated by the configuration instruction, wherein the scene adjustment configuration includes an adjustment level.

12. A communication device, characterized in that: include: Memory and processor; Memory and processor coupling; The memory is used to store instructions executable by the processor; When the processor executes the instructions, the method according to any one of claims 1 to 11 is performed.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer is enabled to execute the method according to any one of claims 1 to 11.

14. A computer program product, characterized in that The computer program product comprises computer program instructions, and when the computer program instructions are executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images