Information interaction method and apparatus, and computer device and storage medium

Abstract

Provided in the present disclosure are an information interaction method and apparatus, and a computer device and a storage medium. The method comprises: presenting an information interaction page; in response to a first trigger operation for a target control in the information interaction page, receiving voice information, which is inputted by a user; in response to the end of the input of the voice information, presenting, on the information interaction page, an information sending result after information is sent to a target object, wherein the information sending result comprises first text information corresponding to the voice information; and presenting, on the information interaction page, a first real-time reply result, which is fed back by the target object, wherein the first real-time reply result is generated in real time by using a content generation model and on the basis of the voice information. In the present disclosure, after voice information which is inputted by a user is acquired, an information sending result which comprises corresponding text information is directly presented to the user without secondary confirmation by the user, and during the process of the user inputting the voice information, a content generation model is used to generate a real-time reply result in real time on the basis of the voice information, thereby improving the interaction efficiency.

Description

Information interaction method, device, computer equipment and storage medium

[0001] This application claims priority to Chinese patent application No. 202310988669.5 filed on August 7, 2023. The contents of the above-mentioned Chinese patent application disclosure are hereby incorporated by reference in their entirety as a part of this application. Technical Field

[0002] The present disclosure relates to an information interaction method, apparatus, computer equipment, and storage medium. Background Art

[0003] Intelligent question-answering, a key branch of artificial intelligence (AI), is widely used in various information interaction scenarios, such as information search, intelligent chat, and intelligent customer service. Artificial intelligence (AI) can automatically generate responses based on user input. Voice input, as a convenient input method, is widely adopted. However, current voice input methods for information interaction suffer from low interaction efficiency.

[0004] Summary of the Invention

[0005] The embodiments of the present disclosure at least provide an information interaction method, apparatus, computer equipment, and storage medium.

[0006] In a first aspect, an embodiment of the present disclosure provides an information interaction method, including:

[0007] Displaying an information interaction page; the information interaction page is used to interact with the target object;

[0008] In response to a first triggering operation on a target control in the information interaction page, receiving voice information input by a user;

[0009] In response to the completion of the voice message input, displaying a message sending result after sending the message to the target object on the information interaction page; the message sending result includes a first text message corresponding to the voice message;

[0010] The first real-time reply result of the target object's feedback is displayed on the information interaction page; wherein, the first real-time reply result is generated in real time based on the voice information using a content generation model.

[0011] In this way, after obtaining the voice information input by the user, there is no need for the user to confirm it again. Instead, the information sending result including the text information corresponding to the voice information is directly displayed to the user. In the process of the user inputting the voice information, the content generation model is used to generate real-time reply results based on the voice information in real time; thus, the real-time reply results can be displayed to the user without consuming much time, thereby improving the interaction efficiency.

[0012] In a possible implementation manner, the method further includes:

[0013] In response to a second triggering operation on the information sending result, displaying a modification control for the information sending result, and displaying the first text information in the modification control;

[0014] generating second text information in response to a modification operation on the first text information displayed in the modification control;

[0015] The first text information displayed on the information interaction page is replaced with the second text information.

[0016] In this way, by directly triggering the result of information sending, a modification control can be displayed, and the modification control can be used to directly modify the first text information to obtain the second text information, and then the first text information displayed on the information interaction page can be replaced with the second text information. The user does not need to withdraw the first text information sent before triggering the modification of the first text information, nor does he need to re-enter new text information. That is, the first text information that has already been sent can be modified conveniently, which is convenient for the user's operation.

[0017] In a possible implementation manner, the method further includes:

[0018] Displaying recommended modification information corresponding to the first text information; the recommended modification information includes at least one of the following: information indicating recommended vocabulary modification in the first text information, candidate vocabulary for replacing at least part of the content in the first text information, and text information obtained by content extraction from the first text information;

[0019] The modification operation includes: a third triggering operation on the recommended modification information.

[0020] In this way, by displaying the recommended modification information, it is further convenient for the user to modify the first text information, which facilitates the user's operation and improves the modification efficiency.

[0021] In a possible implementation manner, after generating the second text information, the method further includes:

[0022] A target model is trained based on the voice information and the second text information; the target model is used to convert the voice information into corresponding text information in real time.

[0023] In this way, a target model adapted to each user can be trained according to the different pronunciation conditions of each user to improve the accuracy of converting voice information into text information.

[0024] In a possible implementation, the first real-time reply result belongs to at least a portion of the first reply result corresponding to the first text message;

[0025] The method further comprises:

[0026] In response to receiving the second trigger operation on the information sending result when the first real-time reply result does not include all results of the first reply result, updating of the first real-time reply result is suspended.

[0027] In this way, when the user gives up modifying the first text content, the other contents in the first reply result can continue to be updated according to the update progress of the previous first real-time reply result. When the user confirms to modify the first text content to the second text content, the first real-time reply result will no longer be updated. Instead, the second real-time reply result based on the feedback of the target object based on the second text content will be directly displayed to the user, thereby improving the user experience during the reply result update process.

[0028] In a possible implementation manner, after replacing the first text information displayed on the information interaction page with the second text information, the method further includes:

[0029] The second real-time reply result of the target object based on the second text information feedback is displayed on the information interaction page; the second real-time reply result belongs to at least part of the second reply result corresponding to the second text information.

[0030] In this way, after the reply result is modified along with the modification of the first text message, the newly generated second real-time reply result can be displayed to the user.

[0031] In a possible implementation manner, after replacing the first text information displayed on the information interaction page with the second text information, the method further includes:

[0032] Delete the first real-time reply result displayed on the information interaction page.

[0033] In this way, after the first text message is modified, the first real-time reply result corresponding to the first text message can be deleted from the information interaction page, and only information useful to the user is retained in the information interaction page, avoiding interference of unnecessary information on the user.

[0034] In a possible implementation, displaying the second real-time reply result of the target object based on the second text information feedback on the information interaction page includes:

[0035] In response to the second real-time reply result being the same as the first real-time reply result, the first real-time reply result displayed on the information interaction page is continued, and other reply results in the second reply result except the first real-time reply result continue to be displayed.

[0036] In this way, the continuity of response result updates is ensured, improving user experience.

[0037] In a possible implementation manner, the method further includes:

[0038] In response to a voice playback control displayed on the information interaction page being in an engaged state, playing the first real-time reply result based on a timbre corresponding to the target object;

[0039] In response to the second triggering operation on the information sending result, the playing of the first real-time reply result is paused.

[0040] In this way, it is possible to use the voice playback control to play the first real-time reply result based on the silver color corresponding to the target object, providing users with more interactive methods.

[0041] In a second aspect, an embodiment of the present disclosure further provides an information interaction device, including:

[0042] A display module is used to display an information interaction page; the information interaction page is used to interact with the target object;

[0043] an acquisition module, configured to receive voice information input by a user in response to a first triggering operation on a target control in the information interaction page;

[0044] The display module is also used to display the information sending result after sending information to the target object on the information interaction page in response to the completion of the voice information input; the information sending result includes the first text information; and display the first real-time reply result fed back by the target object on the information interaction page; wherein, the first real-time reply result is generated in real time based on the voice information using a content generation model.

[0045] In a possible implementation, the apparatus further includes a modification module; the modification module is configured to:

[0046] In response to a second triggering operation on the information sending result, displaying a modification control for the information sending result, and displaying the first text information in the modification control;

[0047] generating second text information in response to a modification operation on the first text information displayed in the modification control;

[0048] The display module is further configured to replace the first text information displayed on the information interaction page with the second text information.

[0049] In a possible implementation manner, the display module is further configured to:

[0050] Displaying recommended modification information corresponding to the first text information; the recommended modification information includes at least one of the following: information indicating recommended vocabulary modification in the first text information, candidate vocabulary for replacing at least part of the content in the first text information, and text information obtained by content extraction from the first text information;

[0051] The modification operation includes: a third triggering operation on the recommendation modification information.

[0052] In a possible implementation, the method further includes: a training module for training a target model based on the voice information and the second text information after generating the second text information; the target model is used to convert the voice information into corresponding text information in real time.

[0053] In a possible implementation, the first real-time reply result belongs to at least a portion of the first reply result corresponding to the first text message;

[0054] The display module is further used for:

[0055] In response to receiving the second trigger operation on the information sending result when the first real-time reply result does not include all results of the first reply result, updating of the first real-time reply result is suspended.

[0056] In a possible implementation, after replacing the first text information displayed on the information interaction page with the second text information, the display module is further configured to:

[0057] The second real-time reply result of the target object based on the second text information feedback is displayed on the information interaction page; the second real-time reply result belongs to at least part of the second reply result corresponding to the second text information.

[0058] In a possible implementation, after replacing the first text information displayed on the information interaction page with the second text information, the display module is further configured to:

[0059] Delete the first real-time reply result displayed on the information interaction page.

[0060] In a possible implementation, when displaying the second real-time reply result fed back by the target object based on the second text information on the information interaction page, the display module is configured to:

[0061] In response to the second real-time reply result being the same as the first real-time reply result, the first real-time reply result displayed on the information interaction page is continued, and other reply results in the second reply result except the first real-time reply result continue to be displayed.

[0062] In a possible implementation, the device further includes a voice playback module configured to:

[0063] In response to a voice playback control displayed on the information interaction page being in an engaged state, playing the first real-time reply result based on a timbre corresponding to the target object;

[0064] In response to the second triggering operation on the information sending result, the playing of the first real-time reply result is paused.

[0065] In a third aspect, an optional implementation of the present disclosure further provides a computer device, a processor, and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the processor is used to execute the machine-readable instructions stored in the memory. When the machine-readable instructions are executed by the processor, the machine-readable instructions perform the steps of the above-mentioned first aspect, or any possible implementation of the first aspect.

[0066] In a fourth aspect, an optional implementation of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, it executes the steps of the above-mentioned first aspect or any possible implementation of the first aspect.

[0067] For a description of the effects of the above-mentioned information interaction device, computer equipment, and computer-readable storage medium, please refer to the description of the above-mentioned information interaction method, which will not be repeated here.

[0068] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present disclosure.

[0069] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments. The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without inventive effort.

[0071] FIG1 shows a flow chart of an information interaction method provided by some embodiments of the present disclosure;

[0072] FIG2 shows one example of an information interaction page provided by some embodiments of the present disclosure;

[0073] FIG3 shows a second example of an information interaction page provided by some embodiments of the present disclosure;

[0074] FIG4 shows a schematic diagram of an information interaction device provided in some embodiments of the present disclosure;

[0075] FIG5 shows a schematic diagram of a computer device provided by some embodiments of the present disclosure. DETAILED DESCRIPTION

[0076] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure is not intended to limit the scope of the present disclosure for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present disclosure.

[0077] Research has found that when interacting with an agent, users can currently input voice messages through the voice input control set up on the information interaction page. After the voice input is completed, the input voice message is converted into text and displayed to the user, allowing the user to confirm whether to send it to the agent based on the displayed text message. After the user confirms that the displayed text message will be sent to the agent, the message sending operation is executed. After receiving the message sent by the user, the agent generates a reply based on the message and displays the reply to the user. This process involves multiple steps, including voice input, converting the voice message into text and displaying it to the user, user confirmation, sending, and the agent generating a reply based on the text. The operation is cumbersome and time-consuming, and the process of the agent generating the reply based on the text also takes a certain amount of time, resulting in low interaction efficiency.

[0078] Based on the above research, the present disclosure provides an information interaction method. After obtaining the voice information input by the user, the user does not need to confirm it again. Instead, the information sending result including the text information corresponding to the voice information is directly displayed to the user. In the process of the user inputting the voice information, the content generation model is used to generate real-time reply results based on the voice information in real time; thus, the real-time reply results can be displayed to the user without consuming much time, thereby improving the interaction efficiency.

[0079] The defects in the above solutions are the results obtained by the inventors after practice and careful research. Therefore, the process of discovering the above problems and the solutions proposed by this disclosure for the above problems below should be the contributions made by the inventors to this disclosure during the disclosure process.

[0080] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0081] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0082] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0083] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0084] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0085] To facilitate understanding of this embodiment, an information interaction method disclosed in an embodiment of the present disclosure is first introduced in detail. The execution subject of the information interaction method provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities. The computer device includes, for example, a terminal device or a server or other processing device. The terminal device can be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the information interaction method can be implemented by a processor calling computer-readable instructions stored in a memory.

[0086] The information interaction method provided by the embodiment of the present disclosure is described below by taking the execution subject as a terminal device as an example.

[0087] 1 is a flowchart of an information interaction method according to an embodiment of the present disclosure. The method includes steps S101 to S104, wherein:

[0088] S101: Displaying an information interaction page; the information interaction page is used to perform information interaction with a target object.

[0089] In specific implementations, the target object may include, for example, an agent; an agent is a computing entity based on artificial intelligence technology. The agent may host an artificial intelligence model and utilize the model to generate a corresponding response based on received text or voice information. The agent may have different identities in different application scenarios. For example, in a customer service scenario, the agent may be an intelligent customer service representative; in a chat scenario, the agent may be an intelligent chatbot.

[0090] Furthermore, in chat scenarios, the agent's identity can be set by the user. For example, if a user wants to practice a certain language, they can set the agent's identity to a virtual "person" familiar with that language. Based on the user's set identity, the agent can generate corresponding responses based on the user's text or voice messages. These responses can include answers to questions, information aggregation, and replies to chat content, and are set according to actual application needs.

[0091] The information interaction page may also be different in different application scenarios; illustratively, in a chat scenario, the information interaction interface may include a chat interface; in an information query scenario, the chat interface may include an information query interface.

[0092] S102: In response to a first triggering operation on a target control in the information interaction page, receiving voice information input by a user.

[0093] In a specific implementation, the target control is, for example, a control set on an information interaction page for user voice input control. The first trigger operation on the target control includes, for example, long press, click, slide, double-click, and the like. After the user performs the first trigger operation on the target control, the target control enters a voice input enabled state, at which point the terminal device can capture external sounds and obtain the user's input voice information.

[0094] The example shown in Figure 2a shows a specific example of an information interaction page; in this information interaction page, an information display area s1 is included for displaying information interaction content to the user; in this information display area s1, text information converted from the user's voice input can be displayed; and text content sent by the target object can also be displayed. The text content sent by the target object can, for example, include text content obtained by the target object in reply based on the user's text information or voice information. In this example, the user has previously entered another text content, and at this time, the reply result corresponding to the other text content is displayed in the information display area s1. In addition, the information interaction page can also include a target control s2; at the location of the target control s2, an instruction message of "press and hold to speak" is also displayed to prompt the user that they can trigger the input of voice information by long pressing the target control s2.

[0095] The example shown in Figure 2b shows the state of the target control s2 after the user performs the first trigger operation on the target control by long pressing the target control s2. In this state, the terminal device can receive the voice information input by the user.

[0096] The above embodiment merely shows a specific example of a first trigger operation. The embodiment of the present disclosure may also set other first trigger operations according to actual application requirements, which is not limited here.

[0097] S103: In response to the completion of the voice information input, displaying the information sending result after sending the information to the target object on the information interaction page; the information sending result includes the first text information.

[0098] In a specific implementation, for different first triggering operations, the triggering operation for the end of voice information input may also be different. After receiving the triggering operation for the end of voice information input, the receiving of external voice is stopped.

[0099] For example, in the case where the first trigger operation includes a long press operation on the target button, when the user releases the pressed target button, it is considered that the voice information input is completed.

[0100] The first trigger operation includes a click operation or a double-click operation on the target button. When the user clicks or double-clicks the target button, the terminal device enters the voice acquisition state, captures external sounds, and receives the voice information input by the user. In this case, the user can trigger the end of voice input by clicking or double-clicking the target button again; or directly trigger the end of voice input through a set voice instruction. Exemplary, the voice instruction includes, for example, "end input" with specific semantics, or a specific short sentence set. For example, if the target object is called someone, the phrase can be set to: "OK someone", "What do you think of someone", etc., which is not limited in the embodiment of the present disclosure.

[0101] The first trigger operation includes a sliding operation on the target button. For example, the target button can be slid to a preset area of ​​the information interaction page by sliding. At this time, the terminal device enters the voice acquisition state, captures external sounds, and receives the voice information input by the user. In this case, the user can trigger the end of the voice input by dragging the target button out of the preset area by sliding. In addition, the sliding operation can also be a sliding operation in a first direction. When the user performs the sliding operation in the first direction, the terminal device enters the voice acquisition state, captures external sounds, and receives the voice information input by the user. In this case, the user can end the voice input by sliding again in the second direction.

[0102] In addition, other triggering operations for ending voice input may also be set, which are not limited in the embodiments of the present disclosure.

[0103] After the voice information input is completed, the information sending result after sending the information to the target object is displayed on the information interaction page. The information sending result, for example, includes: a first text message obtained by converting the voice information input by the user.

[0104] Specifically, while receiving a user's voice message, the terminal device can convert the received voice message into a text message in real time. Shortly after the voice message input is completed, a first text message corresponding to the user's voice message is obtained. The first text message is then sent to the target recipient, and the message sending result is displayed on the message interaction page.

[0105] In addition, the information sending result may include, in addition to the first text information, an indication mark indicating that the sending is successful or failed.

[0106] As shown in Figure 2c, after the voice message input is completed, a specific example of displaying the message sending result after the message is sent to the target object on the information interaction page is shown. In this example, the first voice message in the message sending result includes: "What is quantum?", and the first text is displayed in the information display area s1.

[0107] Following S103 above, the information interaction method provided by the embodiment of the present disclosure further includes:

[0108] S104: Displaying a first real-time reply result of the target object's feedback on the information interaction page; wherein, the first real-time reply result is generated in real time based on the voice information using a content generation model.

[0109] In a specific implementation, the first text message corresponds to the first reply result. In one possible implementation, the process of the content generation model generating the first reply result lasts for a certain period of time. Therefore, the process of the target object providing feedback on the reply result can also last for a certain period of time; the content that has been provided is referred to as the first real-time reply content. This first real-time reply result is at least a portion of the first reply result corresponding to the first text message.

[0110] Exemplarily, assuming that the first reply result corresponding to the first text message includes three parts of content, a1, a2, and a3, the first real-time reply result may be, for example, at least part of the content of a1, a2, and a3.

[0111] The target object is the intelligent entity that carries the content generation model; the target object can be deployed on a device other than the terminal device, or on the terminal device.

[0112] When the target object is deployed on a terminal device:

[0113] The first text information corresponding to the voice information is obtained by converting the real-time voice input by the user during the process of the user inputting the voice information. Therefore, in the case where the content generation model is deployed on the terminal device, the terminal device can input the real-time generated text into the content generation model, and use the content generation model to generate the first real-time reply content before the user's voice input is completed. In this process, as the first text information is continuously generated, the content generation model can be used to continuously generate new first real-time reply results using the continuously input text information, or to update the already generated first real-time reply results, so that the first real-time reply results can be quickly obtained after the user finishes the voice input, and the first real-time reply results can be displayed on the information interaction page.

[0114] In the case where the target object is deployed on a device other than the terminal device, the device may include, for example, a server or a cloud device.

[0115] The first text information corresponding to the voice information is obtained by converting the real-time voice input by the user during the process of the user inputting the voice information. As the vocabulary in the first text information is continuously generated, search keywords can be extracted based on the generated vocabulary. If the search keywords are extracted, the extracted search keywords are sent to the other device in real time. The target object deployed in the other device inputs the search keywords into the content generation model, and simultaneously with the user inputting the voice information, a first real-time response result corresponding to the voice information is generated.

[0116] When the user finishes voice input, since part of the first real-time reply result has been generated during the voice input process, the generated first real-time reply result can be displayed in the information interaction interface; at the same time, if the first real-time reply result belongs to a part of the first reply result corresponding to the first text message, the generated first real-time reply result can be displayed while the remaining reply results are generated.

[0117] Taking the above example, assuming that the first reply result corresponding to the first text message includes three parts, k1, k2, and k3. Assuming that after the voice input is completed, k1 and k2 have been generated based on the voice information; k1 and k2 can be continuously displayed on the information interaction page while k3 is generated; and after k3 is generated, k1 and k2 are displayed on the information interaction page.

[0118] As shown in d in Figure 2, a specific example of displaying the first real-time reply result in the information interaction page is provided; in this example, the first text information includes "What is a quantum"; the first reply content corresponding to the first text information includes "If a physical quantity has a smallest unit and cannot be continuously divided, it is said that the physical quantity is quantized, and the smallest unit is called a quantum. The basic concept is that all tangible properties may be "quantized". "Quantization" means that the numerical value of its physical quantity will be some specific numerical value, not an arbitrary value. For example, in an atom (at rest), the energy of an electron is quantized, which can determine the stability and general problems of the atom.", and the first real-time result displayed in the information display area s1 is part of the above-mentioned first reply result, including: "If a physical quantity has a minimum".

[0119] The information interaction method provided by the embodiment of the present disclosure can receive the voice information input by the user in response to the first trigger operation of the target control in the information interaction page; in response to the end of the voice information input, the information sending result after the information is sent to the target object is displayed on the information interaction page; the information sending result includes the first text information corresponding to the voice information; and then the first real-time reply result fed back by the target object is displayed on the information interaction page; wherein, the first real-time reply result is generated in real time based on the voice information using a content generation model. In this way, after obtaining the voice information input by the user, there is no need for the user to confirm it twice, but the information sending result including the text information corresponding to the voice information is directly displayed to the user, and in the process of the user inputting the voice information, the content generation model is used to generate a real-time reply result based on the voice information in real time; thus, the real-time reply result can be displayed to the user without consuming much time, thereby improving the interaction efficiency.

[0120] The information interaction method provided in another embodiment of the present disclosure also includes: in response to a second trigger operation on the information sending result, displaying a modification control for the information sending result, and displaying the first text information in the modification control; in response to a modification operation on the first text information displayed in the modification control, generating a second text information; replacing the first text information displayed on the information interaction page with the second text information.

[0121] In a specific implementation, after the information sending result after sending information to the target object is displayed on the information interaction page, the second trigger operation on the information sending result can be, for example, a click operation, a double-click operation, a sliding operation, etc. on the information sending result.

[0122] Exemplary:

[0123] a1: When the second trigger operation includes a click operation or a double-click operation on the information sending result, the user can trigger the modification of the first text information by clicking or double-clicking the first text information displayed on the information interaction page.

[0124] At this time, a corresponding modification control may be displayed in a preset area of ​​the information interaction page, and the first text information may be displayed in the modification control.

[0125] a2: For the case where the second trigger operation includes a sliding operation on the information sending result, for example, a specific trigger area can be set in the information interaction page; the first text message can be dragged into the trigger area by using the sliding operation.

[0126] After the first text information is dragged to the trigger area, a corresponding modification control is triggered to be displayed in the interactive control page, and the first text information is displayed in the modification control.

[0127] Here, the modification control can be a separately set modification control specifically used to modify the first text information. In another possible implementation, the target control s1 can, for example, switch states, that is, the target control s1 can be switched between a voice input state and a text input state; when the target control is in the voice input state, the user can trigger the input of a voice message through a first trigger operation on the target control; when the target control is in the text input state, a virtual keyboard can be displayed to the user; the user can directly input text through the virtual keyboard in the target control. In this case, the target control in the text input state can be used as a modification control.

[0128] As shown in Figure 3a, a specific example is shown in which, after a second trigger operation, a modification control is displayed on an information interaction page, and a first text message is displayed in the modification control. In this example, the target control can be, for example, a modification control specifically used to modify the first text message. The modification control can, for example, be displayed in a floating manner on the information interaction page.

[0129] The modification control includes, for example, an information input box s3 for displaying a first text message, wherein the information input box displays the first text message "What is quantum?", and a virtual keyboard s4 for editing the first text message displayed in the information input box s3. Using the virtual keyboard s4, the first text message displayed in the information input box s3 can be modified, such as deleting at least some words, adding words, adjusting the format, and the like.

[0130] In addition, the modification control may further include a first button s5 for triggering the abandonment of modification of the first text information, and a second button s6 for confirming the result of modification of the first text information.

[0131] Among them, when the user triggers the first button s5, that is, the user gives up modifying the first text information, at this time, the modification control is hidden, the information interaction page switches to the state shown in Figure 2d, and continues to update the subsequent part of the first reply content. When the user modifies the first text information in the information input box s3 and triggers the second button s6, the content in the information input box s3 is used as the second text content, and the first text information displayed on the information interaction page is replaced by the second text information.

[0132] In another possible implementation, when the target control in the text input state is used as a modification control, its style may be, for example, as shown in the example a of FIG3 . For example, if the target control in the text input state is called up by the second trigger operation, the target control may display, for example, a first button s5 and a second button s6 for abandoning or accepting the modification of the first text information.

[0133] In order to distinguish it from the normal input text content of the target control, when the target control is awakened by switching the target control state (that is, switching the target control from the voice input state to the text input state), the state of the first button s5 and the second button s6 can be set to an invalid state. In this invalid state, the first button s5 and the second button s6 will not respond to any user operation, that is, it will not affect the normal information input function of the target control in the text input state.

[0134] Alternatively, an association relationship may be established between the first text content of the text input box in the target control and the first text content displayed in the information display area s1, and the first text content displayed in the information display area s1 may be specially marked. When the first text content in the text input box is modified, if the user further triggers confirmation of the modification, then based on the association relationship between the first text content of the text input box in the target control and the first text content displayed in the information display area s1, the second text information obtained after the modification and displayed in the text input box may be used to replace the first text content displayed in the information display area s1, so as to realize the modification of the first text information using the target control without adding another modification control.

[0135] In this way, using the above method, the user does not need to withdraw the first text message sent before triggering the modification of the first text message, nor does he need to re-enter new text information, which means that the modification of the first text message that has been sent can be easily implemented, which is convenient for the user's operation.

[0136] In another embodiment of the present disclosure, in response to a second trigger operation on the information sending result, recommended modification information corresponding to the first text message may also be displayed.

[0137] The recommended modification information includes, for example, at least one of the following: indication information of suggested modified words in the first text information, candidate words for replacing at least part of the content in the first text information, and text information obtained after content extraction from the first text information.

[0138] b1: For the case where the recommended modification information includes indication information of the suggested modified words in the first text information:

[0139] For example, the first text message may contain short sentences or words that are incompatible with the content expressed in the first text message as a whole or that are not logically coherent; in this case, for example, instruction information can be used to mark the problematic words or short sentences to remind the user of the possible inaccurate expression problems in the first text message, thereby reminding the user to modify the words or short sentences in the corresponding position.

[0140] Here, the indication information may include, for example, at least one of the following: giving a special color mark to the word or phrase to be indicated, underlining, indicating arrows, etc. near the word or phrase to be indicated. Specifically, it can be determined according to actual needs.

[0141] In this case, the user can directly trigger the modification of the word or phrase indicated by the indication information through a third trigger operation on the indication information, such as clicking, double-clicking, long pressing, etc.

[0142] b2: For the case where the recommended modification information includes candidate words for replacing at least part of the content in the first text information:

[0143] After determining the words that may have problems in the first text information, candidate words that replace the words with problems may be predicted based on, for example, the content expressed in the entire first text information or based on language logic.

[0144] After the corresponding candidate words are predicted, the candidate words are displayed to the user; the user can modify the problematic words or phrases through a third trigger operation on the candidate words, such as a selection operation (such as clicking on the candidate word) or a sliding operation (such as using a sliding operation to drag the candidate word to the position of the problematic word in the first text information).

[0145] b3: For the case where the recommended modification information includes text information obtained by content extraction of the first text information:

[0146] For example, when a user inputs voice information, in order to clearly express the meaning he wants to express, he may use more cumbersome language to describe a problem, resulting in the first text information being not refined enough; or the problem that the user himself wants to express is not particularly clear. At this time, the first text information can be further refined, and the refined text information can be more refined and can more accurately express the meaning the user wants to express, and the refined text information can be displayed to the user. At this time, the user can modify the first text information through a third trigger operation on the refined text information (such as a click operation, a double-click operation, etc. on the refined text information).

[0147] As shown in Figure 3b, a specific example of displaying recommended modification information corresponding to a first text message is shown. In this example, the first text message includes "What is quantum?" Meanwhile, the word pronounced "liangzi" may also contain other words, such as "liangzi" and "handsome boy." Furthermore, there are other words related to "quantum," such as "quantum entanglement." In this case, the word "quantum" is marked out by bolding and underlining the word as indicator information. At the same time, three other candidate words, "liangzi," "handsome boy," and "quantum entanglement," are also displayed on the information interaction page.

[0148] As shown in c in FIG3 , after the user selects the candidate word “quantum entanglement” through the third trigger operation, the first text content “What is quantum” displayed in the information display area s1 is modified to “What is quantum entanglement”.

[0149] As shown in Figure 3(d), following Figure 3(c), if the user triggers the modification confirmation, the text "What is quantum?" displayed in information display area s1 is also replaced with "What is quantum entanglement?" The modification control is hidden, and the second response result determined for the second text content includes: "Quantum entanglement, or quantum entanglement, is a quantum mechanical phenomenon that describes a special type of quantum state in a composite system (with two or more component systems) that cannot be decomposed into the tensor product of the individual quantum states of the component systems. Quantum entanglement technology is a secure encryption technology for transmitting information and has nothing to do with superluminal information transmission. Although we know that these particles "communicate" at high speeds, we cannot use this connection to control and transmit information at such high speeds. Therefore, Einstein's rule that no information can be transmitted faster than the speed of light still holds true. In reality, entanglement does not affect very far, and if one of the particles is interfered with, the entangled state is automatically eliminated."

[0150] The second real-time reply result belongs to the part of the second reply result, which includes: "Quantum entanglement, or quantum entanglement, is a quantum mechanical phenomenon, which is defined as complex." Therefore, the second real-time reply result is displayed under the second text information.

[0151] In another embodiment of the present disclosure, the conversion of semantic information into text information is achieved by using a target model; in order to make the target model more accurate, the target model can be retrained using voice information and second text information obtained by modifying the first text information, so that the target model can be continuously converted more accurately according to the pronunciation characteristics of a specific user.

[0152] In another embodiment of the present disclosure, the first real-time reply result belongs to at least part of the first reply result corresponding to the first text message. The information interaction method provided by the embodiment of the present disclosure also includes:

[0153] In response to receiving the second trigger operation on the information sending result when the first real-time reply result does not include all results of the first reply result, updating of the first real-time reply result is suspended.

[0154] In a specific implementation, the process of the target object feeding back the reply result is, for example, a process that lasts for a certain period of time; and the content that has been fed back is called the first real-time reply content. The first real-time reply content belongs to at least part of the first reply result corresponding to the first text message. For the convenience of user reading, the first real-time reply content fed back by the target object can be received while the received first real-time reply content is displayed to the user. In addition, if the target object feeds back a complete first reply result at one time, the first reply content can also be displayed to the user at a certain update rate (in this case, the real-time updated content is the first implementation reply result). In this way, the display of the first reply content is a continuous process, rather than a one-time full display, which facilitates user reading.

[0155] As shown in the example d in FIG2 , after the first text message is sent to the target object, a specific example of the first real-time reply result is displayed to the user. In this example, the first real-time reply result only includes a partial reply result in the first reply result.

[0156] Furthermore, in the case where the first real-time reply result is only a part of the first reply result, if a second trigger operation on the information sending result is received at this time, the update of the first real-time reply result will be suspended, that is, the display of the part of the first reply result that is not displayed to the user will be suspended. In this way, it can be ensured that after the user abandons the modification of the first text content, he can continue to update the other content in the first reply result according to the previous update progress of the first real-time reply result. In addition, after the user confirms that the first text content is modified to the second text content, the second real-time reply result based on the feedback of the second text content of the target object can be directly displayed to the user, thereby improving the user experience during the reply result update process.

[0157] In another embodiment of the present disclosure, after replacing the first text information displayed on the information interaction page with the second text information, the method further includes:

[0158] The second real-time reply result of the target object based on the second text information feedback is displayed on the information interaction page; the second real-time reply result belongs to at least part of the second reply result corresponding to the second text information.

[0159] Here, the generation method and display method of the second real-time reply result are similar to the generation method and display method of the first real-time reply result mentioned above, and will not be repeated here.

[0160] In addition, in another embodiment, after replacing the first text information displayed on the information interaction page with the second text information, the method further includes:

[0161] Delete the first real-time reply result displayed on the information interaction page.

[0162] In the example shown in Figure 3d, after replacing "What is quantum" displayed in the information display area s1 with "What is quantum entanglement", the first real-time response result "If a physical quantity has a minimum" previously displayed is deleted from the information display area s1, and the second real-time response result feedback from the target object is displayed.

[0163] In addition, when the information interaction page displays the second real-time reply result of the target object based on the second text information feedback, for example, the following manner may be adopted:

[0164] In response to the second real-time reply result being the same as the first real-time reply result, the first real-time reply result displayed on the information interaction page is continued, and other reply results in the second reply result except the first real-time reply result continue to be displayed.

[0165] For example, assume that the first reply result includes: a1, a2, and a3; the second reply result includes: a1, a2, a4, and a5; wherein the first real-time reply result displayed to the user includes: a1; since the first and second reply results are the same reply results, when the second reply result is displayed, the already displayed a1 can be continued to display a2, a4, and a5 without deleting the originally displayed a1.

[0166] In this way, the continuity of reply result updates is guaranteed.

[0167] In addition, in order to allow users to perceive that the determined reply result is also updated after the first text information is updated to the second text information, a special mark can be made on the second reply result to prompt the user that the determined reply result has also been adjusted to a certain extent.

[0168] In another embodiment of the present disclosure, a voice playback control is further displayed on the information interaction page. In response to the voice playback control displayed on the information interaction page being in use, the first real-time reply result is played based on the timbre corresponding to the target object;

[0169] In response to the second triggering operation on the information sending result, the playing of the first real-time reply result is paused.

[0170] Here, the timbre corresponding to the target object can be any of a variety of selectable timbre options, including, for example, adult male voice, adult female voice, sweet female voice, urban female voice, attractive male voice, child female voice, child male voice, etc. The target object's selectable timbre options can be set based on actual needs. Users can trigger the timbre change control on the information interaction page to change the timbre corresponding to the target object.

[0171] The voice playback control is in use. For example, the following situations may occur:

[0172] d1: The voice playback control is in the default open state; in this state, as long as the real-time response result is displayed, the displayed real-time response result will be played.

[0173] d2: The voice playback control is in the default closed state; after receiving the real-time reply result, in response to the triggering operation of the voice playback control in the default closed state, the voice playback control is switched from the closed state to the open state, and at this time, the real-time reply result is played and displayed.

[0174] After playing the implementation response result, you can switch the voice playback control from the open state to the default closed state again.

[0175] In the example shown in FIG3 , a voice playing control s7 is displayed. When the voice playing control s7 is in use, the second real-time reply result is played using the timbre corresponding to the target object.

[0176] Those skilled in the art will understand that in the above-mentioned method of the specific implementation method, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0177] Based on the same inventive concept, an information interaction device corresponding to the information interaction method is also provided in the embodiment of the present disclosure. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the above-mentioned information interaction method in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0178] 4 is a schematic diagram of an information interaction device provided in an embodiment of the present disclosure, the device comprising:

[0179] Display module 41, used to display the information interaction page; the information interaction page is used to interact with the target object;

[0180] an acquisition module 42 for receiving voice information input by a user in response to a first triggering operation on a target control in the information interaction page;

[0181] The display module 41 is also used to display the information sending result after sending the information to the target object on the information interaction page in response to the completion of the voice information input; the information sending result includes the first text information; and display the first real-time reply result fed back by the target object on the information interaction page; wherein, the first real-time reply result is generated in real time based on the voice information using a content generation model.

[0182] In a possible implementation manner, the apparatus further includes a modification module 43; the modification module 43 is configured to:

[0183] In response to a second triggering operation on the information sending result, displaying a modification control for the information sending result, and displaying the first text information in the modification control;

[0184] generating second text information in response to a modification operation on the first text information displayed in the modification control;

[0185] The display module 41 is further configured to replace the first text information displayed on the information interaction page with the second text information.

[0186] In a possible implementation, the display module 41 is further configured to:

[0187] Displaying recommended modification information corresponding to the first text information; the recommended modification information includes at least one of the following: information indicating recommended vocabulary modification in the first text information, candidate vocabulary for replacing at least part of the content in the first text information, and text information obtained by content extraction from the first text information;

[0188] The modification operation includes: a third triggering operation on the recommended modification information.

[0189] In a possible implementation, the present invention further includes: a training module 44 for training a target model based on the voice information and the second text information after generating the second text information; the target model is used to convert the voice information into corresponding text information in real time.

[0190] In a possible implementation, the first real-time reply result belongs to at least a portion of the first reply result corresponding to the first text message;

[0191] The display module 41 is further used for:

[0192] In response to receiving the second trigger operation on the information sending result when the first real-time reply result does not include all results of the first reply result, updating of the first real-time reply result is suspended.

[0193] In a possible implementation, after replacing the first text information displayed on the information interaction page with the second text information, the display module 41 is further configured to:

[0194] The second real-time reply result of the target object based on the second text information feedback is displayed on the information interaction page; the second real-time reply result belongs to at least part of the second reply result corresponding to the second text information.

[0195] In a possible implementation, after replacing the first text information displayed on the information interaction page with the second text information, the display module 41 is further configured to:

[0196] Delete the first real-time reply result displayed on the information interaction page.

[0197] In a possible implementation, when the information interaction page displays the second real-time reply result fed back by the target object based on the second text information, the display module 41 is configured to:

[0198] In response to the second real-time reply result being the same as the first real-time reply result, the first real-time reply result displayed on the information interaction page is continued, and other reply results in the second reply result except the first real-time reply result continue to be displayed.

[0199] In a possible implementation, the device further includes a voice playback module 45 configured to:

[0200] In response to a voice playback control displayed on the information interaction page being in an engaged state, playing the first real-time reply result based on a timbre corresponding to the target object;

[0201] In response to the second triggering operation on the information sending result, the playing of the first real-time reply result is paused.

[0202] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference can be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0203] The present disclosure also provides a computer device, as shown in FIG5 , which is a schematic diagram of the structure of the computer device provided by the present disclosure, including:

[0204] A processor 51 and a memory 52; the memory 52 stores machine-readable instructions executable by the processor 51, and the processor 51 is configured to execute the machine-readable instructions stored in the memory 52. ​​When the machine-readable instructions are executed by the processor 51, the processor 51 performs the following steps:

[0205] Displaying an information interaction page; the information interaction page is used to interact with the target object;

[0206] In response to a first triggering operation on a target control in the information interaction page, receiving voice information input by a user;

[0207] In response to the completion of the voice message input, displaying a message sending result after sending the message to the target object on the information interaction page; the message sending result includes a first text message corresponding to the voice message;

[0208] The first real-time response result of the target object's feedback is displayed on the information interaction page; wherein the first real-time response result is generated in real time based on the voice information using a content generation model. The above-mentioned memory 52 includes internal memory 521 and external memory 522; the internal memory 521 here is also called internal memory, which is used to temporarily store calculation data in the processor 51 and data exchanged with external memory 522 such as a hard disk. The processor 51 exchanges data with the external memory 522 through the internal memory 521.

[0209] The specific execution process of the above instructions can refer to the steps of the information interaction method described in the embodiment of the present disclosure, and will not be repeated here.

[0210] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computer program executes the steps of the information interaction method described in the above method embodiment. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0211] The embodiments of the present disclosure also provide a computer program product, which carries program code. The instructions included in the program code can be used to execute the steps of the information interaction method described in the above method embodiment. For details, please refer to the above method embodiment and will not be repeated here.

[0212] The computer program product may be implemented in hardware, software, or a combination thereof. In one embodiment, the computer program product is implemented as a computer storage medium. In another embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0213] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems and devices described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0214] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0215] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0216] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0217] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The scope of protection of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed in the present disclosure, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure shall be subject to the scope of protection of the claims.

Claims

1. An information interaction method, comprising: Displaying an information interaction page; the information interaction page is used to interact with the target object; In response to a first trigger operation on a target control in the information interaction page, receiving voice information input by a user; In response to the voice information input being completed, displaying the information sending result after sending the information to the target object on the information interaction page; The information sending result includes the first text information corresponding to the voice information; The first real-time reply result of the target object's feedback is displayed on the information interaction page; wherein the first real-time reply result is generated in real time based on the voice information using a content generation model.

2. The method according to claim 1, further comprising: In response to a second trigger operation on the information sending result, displaying a modification control for the information sending result, and displaying the first text information in the modification control; In response to a modification operation on the first text information displayed in the modification control, generating second text information; The first text information displayed on the information interaction page is replaced with the second text information.

3. The method according to claim 2, further comprising: Displaying recommended modification information corresponding to the first text information; The recommended modification information includes at least one of the following: indication information of a word suggested to be modified in the first text information, candidate words for replacing at least part of the content in the first text information, and text information obtained by content extraction of the first text information; The modification operation includes: a third trigger operation on the recommended modification information.

4. The method according to claim 2 or 3, wherein: After the second text information is generated, the method further includes: Based on the voice information and the second text information, a target model is trained; the target model is used to convert the voice information into corresponding text information in real time.

5. The method according to any one of claims 3 to 4, wherein: The first real-time reply result belongs to at least a part of the first reply result corresponding to the first text information; The method further comprises: In response to receiving the second trigger operation on the information sending result when the first real-time reply result does not include all results of the first reply result, updating of the first real-time reply result is suspended.

6. The method according to claim 5, wherein: After the first text information displayed on the information interaction page is replaced with the second text information, the method further includes: The second real-time reply result of the target object based on the second text information feedback is displayed on the information interaction page; the second real-time reply result belongs to at least part of the second reply result corresponding to the second text information.

7. The method according to claim 5, wherein: After the first text information displayed on the information interaction page is replaced with the second text information, the method further includes: Delete the first real-time reply result displayed on the information interaction page.

8. The method according to claim 6, wherein: The displaying, on the information interaction page, a second real-time reply result fed back by the target object based on the second text information includes: In response to the second real-time reply result being the same as the first real-time reply result, the first real-time reply result displayed on the information interaction page is continued, and other reply results in the second reply result except the first real-time reply result continue to be displayed.

9. The method according to any one of claims 5 to 8, further comprising: In response to the voice playback control displayed on the information interaction page being in use, playing the first real-time reply result based on the timbre corresponding to the target object; In response to the second trigger operation on the information sending result, the playing of the first real-time reply result is paused.

10. An information interaction device, comprising: A display module is configured to display an information interaction page; the information interaction page is used to interact with the target object; An acquisition module, configured to receive voice information input by a user in response to a first trigger operation on a target control in the information interaction page; The display module is further configured to display, in response to the end of the voice information input, a message sending result after sending the message to the target object on the information interaction page; the message sending result includes the first text message; and display the target object's feedback on the information interaction page. A first real-time reply result; wherein, the first real-time reply result is generated in real time based on the voice information using a content generation model.

11. A computer device comprising: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, the processor is configured to execute the machine-readable instructions stored in the memory, and when the machine-readable instructions are executed by the processor, the processor performs the steps of the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, wherein: The computer-readable storage medium stores a computer program, and when the computer program is executed by a computer device, the computer device executes the steps of the method according to any one of claims 1 to 9.

Images