Information interaction method, device, electronic device and storage medium

Abstract

The present application discloses an information interaction method, device, electronic device and storage medium, and relates to artificial intelligence technology fields such as speech recognition technology, computer vision technology and deep learning. The specific implementation scheme is: obtaining voice information input by the user; identifying the user's emotion category based on the voice information; responding to the input voice information, broadcasting the corresponding output voice information and displaying the preset interface expression corresponding to the emotion category. It solves the technical problem that the human-computer interaction method is mechanized and does not conform to the image of an intelligent entity. By identifying the emotion category corresponding to the voice information, the interface expression corresponding to the emotion category is displayed when the output voice information is broadcast, and different emotions correspond to different interface expressions, the natural feeling of human-to-human dialogue is reproduced, which conforms to the image of an intelligent entity and makes the dialogue experience more interesting.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence technologies such as speech recognition technology, computer vision technology, and deep learning, and in particular to information interaction methods, devices, electronic devices, and storage media. Background Art

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

[0003] With the rapid development of artificial intelligence technology, voice-based human-computer interaction devices are becoming more and more popular among users. For example, smart speakers, smart TVs, voice-activated cars, etc. have become human-computer interaction devices that users frequently use in their lives.

[0004] In the related technology, the robot's conversational interaction method lacks awareness of the user's emotional state. When the user inputs a voice command, the robot usually directly replies to the user's voice command. This method is mechanical, emotionless, and does not conform to the image of an intelligent entity. Summary of the invention

[0005] The present application provides an information interaction method, device, electronic device and storage medium for a technical problem.

[0006] According to a first aspect, there is provided an information interaction method, comprising:

[0007] Get the voice information input by the user;

[0008] Identifying the emotion category of the user according to the voice information;

[0009] In response to the input voice information, the corresponding output voice information is broadcast and a preset interface expression corresponding to the emotion category is displayed.

[0010] According to a second aspect, an information interaction device is provided, comprising:

[0011] An acquisition module is used to acquire the voice information input by the user;

[0012] A recognition module, used for recognizing the emotion category of the user according to the voice information;

[0013] The processing module is used to respond to the input voice information, broadcast the corresponding output voice information and display the preset interface expression corresponding to the emotion category.

[0014] According to a third aspect, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the information interaction method described in the above embodiment.

[0015] According to a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is proposed, wherein the computer instructions are used to enable the computer to execute the information interaction method described in the above embodiment.

[0016] According to a fifth aspect, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the information interaction method according to the first aspect.

[0017] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present application.

[0019] Figure 1 is a flowchart of an information interaction method according to an embodiment of the present application;

[0020] Figure 2 is a flowchart of an information interaction method according to an embodiment of the present application;

[0021] Figure 3 is a schematic diagram of a scenario of an information interaction method according to an embodiment of the present application;

[0022] Figure 4 is a schematic diagram of a scenario of an information interaction method according to an embodiment of the present application;

[0023] Figure 5 is a structural diagram of an information interaction device according to an embodiment of the present application;

[0024] Figure 6 is a structural diagram of an information interaction device according to an embodiment of the present application;

[0025] Figure 7 It is a block diagram of an electronic device used to implement the information interaction method of the embodiment of the present application. DETAILED DESCRIPTION

[0026] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0027] The following describes the information interaction method, device, electronic device and storage medium of the embodiments of the present application with reference to the accompanying drawings.

[0028] In order to solve the technical problem in the prior art that the human-computer interaction method is mechanized and does not conform to the image of an intelligent entity, the present application proposes to identify the emotion category corresponding to the voice information, and display the interface expression corresponding to the emotion category when broadcasting the output voice information, so as to achieve different emotions corresponding to different interface expressions, reproduce the natural feeling of human-to-human dialogue, conform to the image of an intelligent entity, and make the dialogue experience more interesting.

[0029] Specifically, Figure 1 is a flow chart of an information interaction method according to an embodiment of the present application. Figure 1 As shown, the information interaction method is used in an electronic device, wherein the electronic device can be any device with computing capabilities, such as a mobile phone, a tablet computer, a personal digital assistant, a wearable device, a vehicle-mounted device, a smart speaker, a smart TV, and other hardware devices with various operating systems, touch screens, and / or display screens. The method includes:

[0030] Step 101: Acquire voice information input by a user.

[0031] Step 102: Identify the user's emotion category based on the voice information.

[0032] In an embodiment of the present application, human-computer interaction devices such as smart speakers, smart TVs, etc. have voice information input by users collected by sound collection devices such as one or more microphone arrays.

[0033] In the embodiment of the present application, after obtaining the voice information input by the user, there are many ways to identify the user's emotion category according to the voice information, which can be selected and set according to the specific application scenario. Examples are as follows:

[0034] In the first example, voice information is converted to obtain corresponding text information, the text information is segmented to generate multiple word segments, the multiple word segments are matched with preset candidate keywords, target keywords that successfully match one or more word segments are obtained, preset emotion classification information corresponding to the target keywords is queried, and the user's emotion category is identified.

[0035] In the second example, the voice information is converted to obtain the corresponding text information, the text information is processed based on a semantic understanding algorithm, the text information is simultaneously subjected to syntactic and semantic analysis, and the user's emotion category is identified using the syntactic and semantic information.

[0036] In the third example, an emotion category classification model is established in advance based on different text voice samples and neural networks (such as convolutional neural networks), classifiers, etc., and the voice information is input into the pre-established emotion category classification model to obtain the emotion category of the user corresponding to the voice information.

[0037] Step 103, in response to the input voice information, the corresponding output voice information is broadcast and the preset interface expression corresponding to the emotion category is displayed.

[0038] In an embodiment of the present application, the voice information input by the user is processed to generate output voice information and broadcast it. For example, the voice information input by the user is "How is the weather today?", and the corresponding output voice information is broadcast as "It is sunny in Beijing today, with a temperature of 16 to 20 degrees and northwest wind."

[0039] In the embodiment of the present application, there are many ways to process and generate output voice information based on the voice information input by the user, which can be selected and set according to the specific application scenario. Examples are as follows:

[0040] In the first example, a voice response model is pre-established based on a neural network (such as a convolutional neural network) and an input voice sample, and the voice information input by the user is directly processed through the pre-established voice response model to generate output voice information.

[0041] In the second example, voice information input by the user is converted into text information, the text information is matched in a preset knowledge base to obtain output text information, and the output text information is converted into output voice information.

[0042] In an embodiment of the present application, the interface expressions corresponding to the user's emotion category recognized based on voice information can be one or more. The interface expression output can be selected according to the specific scenario, or it can be selected and set based on voice duration, voice characteristics, and user preferences. Examples are as follows.

[0043] As an example of a scenario, when there is only one interface expression corresponding to an emotion category, the corresponding output voice information is broadcasted and the preset interface expression corresponding to the emotion category is displayed.

[0044] As an example of another scenario, when the emotion category includes multiple candidate interface expressions, the broadcast duration of the output voice information is obtained; based on the preset display probability corresponding to each candidate interface expression and the broadcast duration, one or more target interface expressions that need to be displayed and the display duration corresponding to each target interface expression are determined; in the process of broadcasting the corresponding output voice information, one or more target interface expressions are switched to be displayed according to the display duration corresponding to each target interface expression.

[0045] As another scenario example, when the emotion category includes multiple candidate interface expressions, the audio features of the voice information are extracted; the energy of the voice information is obtained based on the audio features; the energy of the voice information is input into a pre-trained deep learning model to obtain the occurrence probability corresponding to each candidate interface expression; and in the process of broadcasting the corresponding output voice information, the candidate interface expression with the maximum occurrence probability is displayed.

[0046] In summary, the information interaction method of the embodiment of the present application obtains the voice information input by the user; identifies the user's emotion category based on the voice information; responds to the input voice information, broadcasts the corresponding output voice information and displays the preset interface expression corresponding to the emotion category. It solves the technical problem that the human-computer interaction method is mechanized and does not conform to the image of the intelligent body. By identifying the emotion category corresponding to the voice information, the interface expression corresponding to the emotion category is displayed when the output voice information is broadcast, and different emotions correspond to different interface expressions, the natural feeling of human-to-human dialogue is reproduced, which conforms to the image of the intelligent body and makes the dialogue experience more interesting.

[0047] Based on the description of the above embodiment, it can be understood that when the emotion category includes multiple candidate interface expressions, the displayed interface expression can be determined based on the broadcasting duration of the output voice information, the energy of the voice information, etc. Figure 2 and Figure 3 Describe in detail.

[0048] Figure 2 is a flow chart of an information interaction method according to an embodiment of the present application. Figure 2 As shown, the method includes:

[0049] Step 201, obtain voice information input by the user, convert the voice information to obtain corresponding text information, and perform word segmentation on the text information to generate multiple word segments.

[0050] In an embodiment of the present application, human-computer interaction devices such as smart speakers, smart TVs, etc. have voice information input by users collected by sound collection devices such as one or more microphone arrays.

[0051] In an embodiment of the present application, after obtaining the voice information input by the user, the voice information is converted to obtain the corresponding text information, and the text information is segmented to generate multiple word segments.

[0052] In the embodiment of the present application, there are many ways to convert the voice information to obtain the corresponding text information, which can be selected and set according to the specific application scenario. Examples are as follows:

[0053] In the first example, voice information is converted by a voice-to-text converter to obtain corresponding text information.

[0054] In a second example, the voice information may be converted by a text-to-speech (TTS) engine to obtain corresponding text information.

[0055] In the embodiment of the present application, there are many ways to perform word segmentation processing on text information to generate multiple word segments, which can be selected and set according to specific application scenarios. Examples are as follows:

[0056] In the first example, the text information is processed based on the word segmentation method of string matching, and the text information is matched with words in the machine dictionary. If a certain string is found in the machine dictionary, a word segmentation is identified, thereby generating multiple word segments.

[0057] In the second example, text information is segmented based on a word segmentation model, and the word segmentation model may adopt an existing word segmentation model.

[0058] Step 202, multiple segmented words are matched with preset candidate keywords, a target keyword successfully matched with one or more segmented words is obtained, preset emotion classification information corresponding to the target keyword is queried, and the emotion category of the user is identified.

[0059] In an embodiment of the present application, a mapping relationship between multiple keywords and emotion categories is pre-established. For example, positive emotion categories correspond to keywords A, B and C; negative emotion categories correspond to keywords D, E and F, etc. Keywords A, B, C, D, E and F can all be used as preset candidate keywords.

[0060] In the embodiment of the present application, the method of matching multiple participles with preset candidate keywords can be understood as matching multiple participles with each keyword in the preset candidate keywords respectively, which can be a word, semantic, etc. match.

[0061] In the embodiment of the present application, after obtaining the target keyword that successfully matches one or more segmented words, the preset emotion classification information corresponding to the target keyword is queried. There are many ways to identify the user's emotion category, which can be selected and set according to the application scenario. Examples are as follows:

[0062] As a possible implementation method, when the query obtains that the target keyword belongs to the preset first emotion classification information, the user is identified as being in the positive emotion category; when the query obtains that the target keyword belongs to the preset second emotion classification information, the user is identified as being in the negative emotion category; when the query obtains that the target keyword does not belong to the preset first emotion classification information and the second emotion classification information, the user is identified as being in the neutral emotion category.

[0063] Continuing with the above example, the target keyword is A. When the query finds that the target keyword A belongs to the preset positive emotion category information, the user is identified as being in the positive emotion category; the target keyword is D. When the query finds that the target keyword belongs to the preset negative emotion category information, the user is identified as being in the negative emotion category; the target keyword is H. When the query finds that the target keyword D belongs to the preset negative emotion category information, and when the query finds that the target keyword H does not belong to the preset positive emotion classification information and negative emotion classification information, the user is identified as being in the neutral emotion category.

[0064] Step 203, in response to the input voice information, when the emotion category includes multiple candidate interface expressions, the broadcasting duration of the output voice information is obtained.

[0065] Step 204, based on the preset display probability and broadcast duration corresponding to each candidate interface expression, determine one or more target interface expressions to be displayed, and the display duration corresponding to each target interface expression.

[0066] Step 205, in the process of broadcasting the corresponding output voice information, one or more target interface expressions are switched to be displayed according to the display duration corresponding to each target interface expression.

[0067] In an embodiment of the present application, an emotion category includes multiple candidate interface expressions. When the emotion category includes multiple candidate interface expressions, the broadcast duration of the output voice information is obtained, such as 10 seconds, 20 seconds, etc.

[0068] In an embodiment of the present application, the display probability and broadcast time corresponding to each candidate interface expression can be pre-set, for example, candidate interface expression 1 corresponds to a display probability x1 and a broadcast time y1; candidate interface expression 2 corresponds to a display probability x2 and a broadcast time y2, and so on; candidate interface expression 3 corresponds to a display probability x3 and a broadcast time y3.

[0069] Therefore, when determining that the broadcast duration of the output voice information is 10 seconds, for example, a target interface expression 1 is matched, corresponding to a display probability x1 of 90% and a broadcast duration of 10 seconds; when determining that the broadcast duration of the output voice information is 20 seconds, a target interface expression 1 and 2 are matched, and the target interface expression 1 corresponds to a display probability x1 of 90% and a broadcast duration of 10 seconds; the target interface expression 2 corresponds to a display probability x1 of 85% and a broadcast duration of 10 seconds.

[0070] In an embodiment of the present application, the broadcast duration of the output voice information can be matched with the preset display probability and broadcast duration corresponding to each candidate interface expression. After matching one or more interface expressions of the broadcast duration, a target interface expression or a combination of multiple target interface expressions is selected for display according to the display probability, as well as the display duration corresponding to each target interface expression. Finally, in the process of broadcasting the corresponding output voice information, one or more target interface expressions are switched for display according to the display duration corresponding to each target interface expression.

[0071] In the embodiments of the present application, it can be understood that according to the display time corresponding to each target interface expression, one or more target interface expressions are switched in sequence or randomly switched to display one or more target interface expressions, so as to further improve the flexibility and fun of the displayed interface expressions.

[0072] It should be noted that in order to further meet user needs, users can select interface expressions according to actual application scenarios, and set the display probability and broadcast duration corresponding to the interface expressions for pre-storage, and associate each interface expression with the corresponding emotion category, such as using their favorite animal expressions as interface expressions corresponding to positive emotion categories, etc., to meet user personalized needs while satisfying the fun of interaction.

[0073] In summary, the information interaction method of the embodiment of the present application obtains the voice information input by the user, converts the voice information to obtain the corresponding text information, performs word segmentation processing on the text information to generate multiple word segments, matches the multiple word segments with the preset candidate keywords, obtains the target keyword that successfully matches one or more word segments, queries the preset emotion classification information corresponding to the target keyword, identifies the user's emotion category, responds to the input voice information, and when the emotion category includes multiple candidate interface expressions, obtains the broadcast duration of the output voice information, and determines one or more target interface expressions to be displayed according to the preset display probability and broadcast duration corresponding to each candidate interface expression, and the display duration corresponding to each target interface expression. In the process of broadcasting the corresponding output voice information, according to the display duration corresponding to each target interface expression, switch to display one or more target interface expressions. Therefore, by identifying the emotion category corresponding to the voice information, the interface expression corresponding to the emotion category is displayed when the output voice information is broadcast, so that different emotions correspond to different interface expressions. Further, the same emotion can also realize the display of different interface expressions, and the human-computer dialogue experience is more vivid and interesting.

[0074] Figure 3 is a flow chart of an information interaction method according to an embodiment of the present application. Figure 2 As shown, the method includes:

[0075] Step 301: Acquire voice information input by a user.

[0076] Step 302: Identify the user's emotion category based on the voice information.

[0077] In an embodiment of the present application, human-computer interaction devices such as smart speakers, smart TVs, etc. have voice information input by users collected by sound collection devices such as one or more microphone arrays.

[0078] In the embodiment of the present application, after obtaining the voice information input by the user, there are many ways to identify the user's emotion category according to the voice information, which can be selected and set according to the specific application scenario. Examples are as follows:

[0079] In the first example, voice information is converted to obtain corresponding text information, the text information is segmented to generate multiple word segments, the multiple word segments are matched with preset candidate keywords, target keywords that successfully match one or more word segments are obtained, preset emotion classification information corresponding to the target keywords is queried, and the user's emotion category is identified.

[0080] In the second example, the voice information is converted to obtain the corresponding text information, the text information is processed based on a semantic understanding algorithm, the text information is simultaneously subjected to syntactic and semantic analysis, and the user's emotion category is identified using the syntactic and semantic information.

[0081] In the third example, an emotion category classification model is established in advance based on different text voice samples and neural networks (such as convolutional neural networks), classifiers, etc., and the voice information is input into the pre-established emotion category classification model to obtain the emotion category of the user corresponding to the voice information.

[0082] Step 303: When the emotion category includes multiple candidate interface expressions, extract the audio features of the voice information, and obtain the energy of the voice information according to the audio features.

[0083] Step 304: Input the energy of the voice information into a pre-trained deep learning model to obtain the occurrence probability corresponding to each candidate interface expression.

[0084] Step 305 , during the process of broadcasting the corresponding output voice information, the candidate interface expressions with the maximum probability of appearing are displayed.

[0085] In an embodiment of the present application, when the emotion category includes multiple candidate interface expressions, audio features of the speech information, such as duration-related features, fundamental frequency-related features, and energy-related features, are extracted through a sound extraction model or a sound extraction algorithm, and the energy of the speech information, i.e., positive energy, neutral energy, and negative energy, is further obtained based on the audio features. The energy of the speech information is input into a pre-trained deep learning model to obtain the occurrence probability corresponding to each candidate interface expression.

[0086] In the embodiments of the present application, it can be understood that the energy samples of the voice information and the occurrence probability samples corresponding to each candidate interface expression are trained in advance based on a neural network to generate a deep learning model. Therefore, the energy of the voice information is input into the pre-trained deep learning model to obtain the occurrence probability corresponding to each candidate interface expression.

[0087] Finally, in the process of broadcasting the corresponding output voice information, the candidate interface expression with the maximum probability of appearing is displayed.

[0088] In summary, the information interaction method of the embodiment of the present application obtains voice information input by the user; identifies the user's emotion category based on the voice information, and when the emotion category includes multiple candidate interface expressions, extracts the audio features of the voice information, obtains the energy of the voice information based on the audio features, inputs the energy of the voice information into a pre-trained deep learning model, obtains the probability of occurrence corresponding to each candidate interface expression, and displays the candidate interface expression with the maximum probability of occurrence during the process of broadcasting the corresponding output voice information. Thus, by identifying the emotion category corresponding to the voice information, the interface expression corresponding to the emotion category is displayed when the output voice information is broadcast, and different emotions correspond to different interface expressions. Furthermore, the same emotion can also display different interface expressions, making the human-computer dialogue experience more vivid and interesting.

[0089] Based on the above description, this application mainly converts the user's voice information into text information, and then performs emotion recognition of the text information, identifies the user's emotions behind the text information, and different emotions correspond to different interface expressions, and broadcasts the corresponding output voice information. This interactive way of dialogue restores the natural feeling of talking to people, is more in line with the image of an intelligent body, and the dialogue experience is more interesting, stimulating the user's desire to explore.

[0090] Combination Figure 4 To give an example, obtaining user input voice information and performing emotion recognition on the voice information, it can be understood that in order to further meet user needs, a robot interface expression system can be drawn based on human emotions, such as 32 types of dynamic interface expressions, and based on actual dialogue situations, interface expressions that can express "positive and neutral emotions" can be extracted from the expression system, which can be 9 types of positive interface expressions; and the probability of the appearance of the 9 types of interface expressions can be determined based on the degree of positivity of the emotions.

[0091] Specifically, the user inputs voice information, and the robot recognizes the voice information as text information in real time and automatically detects the emotional characteristics contained in the conversation text, such as Figure 4 In the process of identifying the user's emotions as positive and neutral, the robot interface displays positive interface expressions; continuously identifying positive and neutral emotions, the interface expressions can be switched and displayed according to a certain probability of occurrence; identifying negative emotions, the interface can display neutral emotion interface expressions. The interface displays different interface expressions, combined with the corresponding voice information feedback, and the human-computer dialogue experience is more vivid and interesting.

[0092] In order to implement the above embodiments, the present application also proposes an information interaction device. Figure 5 is a schematic diagram of the structure of an information interaction device according to an embodiment of the present application. Figure 5 As shown, the information interaction device includes: an acquisition module 510, an identification module 520 and a processing module 530.

[0093] The acquisition module 510 is used to acquire the voice information input by the user.

[0094] The recognition module 520 is used to recognize the emotion category of the user according to the voice information.

[0095] The processing module 530 is used to respond to the input voice information, broadcast the corresponding output voice information and display the preset interface expression corresponding to the emotion category.

[0096] It should be noted that the above explanation of the information interaction method is also applicable to the information interaction device of the embodiment of the present invention, and its implementation principle is similar, which will not be repeated here.

[0097] In summary, the information interaction device of the embodiment of the present application obtains the voice information input by the user; identifies the user's emotion category according to the voice information; responds to the input voice information, broadcasts the corresponding output voice information and displays the preset interface expression corresponding to the emotion category. The technical problem that the human-computer interaction mode is mechanized and does not conform to the image of the intelligent body is solved. By identifying the emotion category corresponding to the voice information, the interface expression corresponding to the emotion category is displayed when the output voice information is broadcast, and different emotions correspond to different interface expressions, the natural feeling of human-to-human dialogue is reproduced, which conforms to the image of the intelligent body and makes the dialogue experience more interesting.

[0098] In one embodiment of the present application, Figure 6 As shown, in Figure 5 On the basis shown, the recognition module 520 includes: an acquisition unit 521, a word segmentation unit 522, a matching unit 523 and a query unit 524.

[0099] The acquisition unit 521 is used to convert the voice information to obtain the corresponding text information.

[0100] The word segmentation unit 522 is used to perform word segmentation processing on the text information to generate multiple word segments.

[0101] The matching unit 523 is used to match the multiple segmented words with preset candidate keywords to obtain target keywords that successfully match one or more segmented words.

[0102] The query unit 524 is used to query preset emotion classification information corresponding to the target keyword and identify the emotion category of the user.

[0103] In one embodiment of the present application, the query unit 524 is specifically used to: identify the user as being in a positive emotion category when the query indicates that the target keyword belongs to the preset first emotion classification information; identify the user as being in a negative emotion category when the query indicates that the target keyword belongs to the preset second emotion classification information; and identify the user as being in a neutral emotion category when the query indicates that the target keyword does not belong to the preset first emotion classification information and the second emotion classification information.

[0104] In one embodiment of the present application, when the emotion category includes multiple candidate interface expressions, the processing module 530 is specifically used to: obtain the broadcast duration of the output voice information; determine one or more target interface expressions that need to be displayed, and the display duration corresponding to each target interface expression based on the preset display probability corresponding to each candidate interface expression and the broadcast duration; in the process of broadcasting the corresponding output voice information, switch to display one or more target interface expressions according to the display duration corresponding to each target interface expression.

[0105] In one embodiment of the present application, when the emotion category includes multiple candidate interface expressions, the processing module 530 is specifically used to: extract the audio features of the voice information; obtain the energy of the voice information based on the audio features; input the energy of the voice information into a pre-trained deep learning model to obtain the occurrence probability corresponding to each candidate interface expression; and display the candidate interface expression with the maximum occurrence probability during the process of broadcasting the corresponding output voice information.

[0106] It should be noted that the above explanation of the information interaction method is also applicable to the information interaction device of the embodiment of the present invention, and its implementation principle is similar, which will not be repeated here.

[0107] In summary, the information interaction device of the embodiment of the present application obtains the voice information input by the user; identifies the user's emotion category based on the voice information; responds to the input voice information, broadcasts the corresponding output voice information and displays the preset interface expression corresponding to the emotion category. It solves the technical problem that the human-computer interaction method is mechanized and does not conform to the image of an intelligent entity. By identifying the emotion category corresponding to the voice information, the interface expression corresponding to the emotion category is displayed when the output voice information is broadcast, and different emotions correspond to different interface expressions, the natural feeling of human-to-human dialogue is reproduced, which conforms to the image of an intelligent entity and makes the dialogue experience more interesting. Furthermore, the same emotion can also be used to display different interface expressions, making the human-computer dialogue experience more vivid and interesting.

[0108] According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.

[0109] like Figure 7, is a block diagram of an electronic device according to a method for information interaction of an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0110] like Figure 7 As shown, the electronic device includes: one or more processors 701, a memory 702, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 701 is taken as an example.

[0111] The memory 702 is a non-transient computer-readable storage medium provided in the present application. The memory stores instructions executable by at least one processor to enable the at least one processor to perform the information interaction method provided in the present application. The non-transient computer-readable storage medium of the present application stores computer instructions, which are used to enable a computer to perform the information interaction method provided in the present application.

[0112] The memory 702 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules corresponding to the information interaction method in the embodiment of the present application (for example, the attached Figure 5 The processor 701 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 702, that is, the information interaction method in the above method embodiment is realized.

[0113] The memory 702 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device for information interaction, etc. In addition, the memory 702 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 702 may optionally include a memory remotely arranged relative to the processor 701, and these remote memories may be connected to the electronic device for information interaction via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0114] The electronic device of the information interaction method may further include: an input device 703 and an output device 704. The processor 701, the memory 702, the input device 703 and the output device 704 may be connected via a bus or other means. Figure 7 The example of connecting through bus is taken in the following.

[0115] The input device 703 can receive input digital or character information, and generate key signal input related to user settings and function control of the electronic device that interacts with the information, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick and other input devices. The output device 704 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device may be a touch screen.

[0116] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, dedicated ASICs (application-specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs, that is, the present application also proposes a computer program, which, when executed by a processor, implements the information interaction method described in the above embodiment, and the one or more computer programs can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general programmable processor, which can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device. These computing programs (also referred to as programs, software, software applications, or codes) include machine instructions for programmable processors, and these computing programs can be implemented using high-level procedures and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0117] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0118] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0119] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. Among them, the server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS (Virtual Private Server) services.

[0120] According to the technical solution of the embodiment of the present application, by obtaining the voice information input by the user; identifying the user's emotion category according to the voice information; responding to the input voice information, broadcasting the corresponding output voice information and displaying the preset interface expression corresponding to the emotion category. The technical problem that the human-computer interaction mode is mechanized and does not conform to the image of the intelligent body is solved. By identifying the emotion category corresponding to the voice information, the interface expression corresponding to the emotion category is displayed when the output voice information is broadcast, and different emotions correspond to different interface expressions, the natural feeling of human-to-human dialogue is reproduced, which conforms to the image of the intelligent body and makes the dialogue experience more interesting.

[0121] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0122] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. An information interaction method, characterized in that: include: Get the voice information input by the user; Identifying the emotion category of the user according to the voice information; In response to the input voice information, the corresponding output voice information is broadcasted and a preset interface expression corresponding to the emotion category is displayed; When the emotion category includes multiple candidate interface expressions, The broadcasting of the corresponding output voice information and displaying of the preset interface expression corresponding to the emotion category includes: Extracting audio features of the voice information; Acquire the energy of the voice information according to the audio feature; Inputting the energy of the voice information into a pre-trained deep learning model to obtain the occurrence probability corresponding to each of the candidate interface expressions; Obtaining the broadcasting duration of the output voice information; Determine a plurality of target interface expressions to be displayed and a display duration corresponding to each of the target interface expressions according to the preset occurrence probability corresponding to each of the candidate interface expressions and the broadcast duration; During the process of broadcasting the corresponding output voice information, multiple target interface expressions are switched for display according to the display duration corresponding to each target interface expression.

2. The method according to claim 1, characterized in that The identifying the emotion category of the user according to the voice information comprises: Convert the voice information to obtain corresponding text information; Performing word segmentation processing on the text information to generate multiple word segments; Matching the multiple segmented words with preset candidate keywords to obtain target keywords that successfully match one or more segmented words; The preset emotion classification information corresponding to the target keyword is queried to identify the emotion category of the user.

3. The method according to claim 2, characterized in that The querying preset emotion classification information corresponding to the target keyword to identify the emotion category of the user includes: In the case where it is learned through query that the target keyword belongs to the preset first emotion classification information, identifying the user as belonging to the positive emotion category; In the case where it is learned through query that the target keyword belongs to the preset second emotion classification information, identifying the user as belonging to the negative emotion category; When it is learned through query that the target keyword does not belong to the preset first emotion classification information and second emotion classification information, the user is identified as being in the neutral emotion category.

4. The method according to claim 1, characterized in that The broadcasting of the corresponding output voice information and displaying of the preset interface expression corresponding to the emotion category includes: During the broadcast of the corresponding output voice information, the candidate interface expressions with the highest probability of appearing are displayed.

5. An information interaction device, characterized in that: include: An acquisition module is used to acquire the voice information input by the user; A recognition module, used for recognizing the emotion category of the user according to the voice information; A processing module, used to respond to the input voice information, broadcast the corresponding output voice information and display a preset interface expression corresponding to the emotion category; When the emotion category includes multiple candidate interface expressions, The processing module is specifically used for: Extracting audio features of the voice information; Acquire the energy of the voice information according to the audio feature; Inputting the energy of the voice information into a pre-trained deep learning model to obtain the occurrence probability corresponding to each of the candidate interface expressions; Obtaining the broadcasting duration of the output voice information; Determine a plurality of target interface expressions to be displayed and a display duration corresponding to each of the target interface expressions according to the preset occurrence probability corresponding to each of the candidate interface expressions and the broadcast duration; During the process of broadcasting the corresponding output voice information, multiple target interface expressions are switched for display according to the display duration corresponding to each target interface expression.

6. The device according to claim 5, characterized in that The identification module comprises: An acquisition unit, configured to convert the voice information to obtain corresponding text information; A word segmentation unit, used for performing word segmentation processing on the text information to generate a plurality of word segments; A matching unit, used to match the multiple segmented words with preset candidate keywords, and obtain a target keyword that successfully matches one or more segmented words; The query unit is used to query preset emotion classification information corresponding to the target keyword to identify the emotion category of the user.

7. The device according to claim 6, characterized in that The query unit is specifically used for: In the case where it is learned through query that the target keyword belongs to the preset first emotion classification information, identifying the user as belonging to the positive emotion category; In the case where it is learned through query that the target keyword belongs to the preset second emotion classification information, identifying the user as belonging to the negative emotion category; When it is learned through query that the target keyword does not belong to the preset first emotion classification information and second emotion classification information, the user is identified as being in the neutral emotion category.

8. The device according to claim 5, characterized in that The processing module is specifically used for: During the broadcast of the corresponding output voice information, the candidate interface expressions with the highest probability of appearing are displayed.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the information interaction method according to any one of claims 1 to 4.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable the computer to execute the information interaction method according to any one of claims 1 to 4.

11. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the information interaction method according to any one of claims 1 to 4.

Images