Intelligent interaction method and device and computer readable storage medium

Abstract

The invention discloses an intelligent interaction method and device and a computer readable storage medium, relates to the technical field of artificial intelligence, and aims to solve the problem of how to provide emotional response content. The intelligent interaction method comprises the steps of obtaining dialogue content and first emotion data of an interaction object in a first time period; determining a first emotion type according to the first emotion data; activating a first emotion model corresponding to the first emotion type, wherein the first emotion model is used for generating first response content matched with the first emotion type according to the dialogue content; responding to the dialogue content according to the first response content. The emotion type is recognized by analyzing the emotion data of the interaction object, and then the emotion model corresponding to the emotion type is called to generate the response content adaptive to the dialogue content of the interaction object, so that the emotional response content adaptive to the emotion of the interaction object is provided, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence (AI) technology, and specifically to an intelligent interaction method, device, and computer-readable storage medium. Background Art

[0002] With the development of AI technology, interactions between users and AI are becoming increasingly frequent. Using semantic analysis, AI can analyze the user's spoken conversations, understand what the user is trying to say, and provide targeted responses. However, user conversations are often emotional, and AI-generated responses struggle to adapt to the user's mood, thus impacting the user experience. Summary of the Invention

[0003] In view of this, embodiments of the present application provide an intelligent interaction method, device, and computer-readable storage medium, aiming to solve the problem of how to provide emotional response content.

[0004] In a first aspect, an embodiment of the present application provides an intelligent interaction method, comprising: obtaining conversation content and first emotion data of an interaction partner during a first time period; determining a first emotion type based on the first emotion data; activating a first emotion model corresponding to the first emotion type, the first emotion model being used to generate first response content matching the first emotion type based on the conversation content; and responding to the conversation content based on the first response content.

[0005] In this embodiment, the emotion type is identified by analyzing the emotional data of the interacting partner. The corresponding emotion model is then invoked to generate a response tailored to the interaction partner's conversational content. This provides emotionally engaging responses tailored to the interaction partner's emotions, thereby enhancing the user experience. Furthermore, by pre-loading various emotion models, these models remain dormant when not activated, conserving system resources and power consumption. After the emotion type is identified, the corresponding emotion model is activated, eliminating the need for model loading during interaction and improving response efficiency.

[0006] In one embodiment, the method further includes: obtaining second emotion data of the interactive object during a second time period; determining a second emotion type based on the second emotion data; activating a second emotion model that matches the second emotion type based on the difference between the second emotion type and the first emotion type; using the second emotion model to generate second response content that matches the second emotion type based on the conversation content; and responding to the conversation content based on the second response content.

[0007] In this embodiment, the states of the emotion models include an active state and a dormant state. During a certain period of time, one of the multiple emotion models is in an active state, and the remaining emotion models are in a dormant state. After responding to the conversation content, the emotion data of the interactive object is collected again, and the emotion type is determined based on the new emotion data. Whether the emotion type has changed determines whether the emotion model should be adjusted. When the emotion type changes, the emotion model corresponding to the new emotion type is switched. When the emotion type does not change, the original emotion model remains unchanged. This achieves the emotion conversion of the response content, making the response content more adapted to the emotion of the interactive object, thereby improving the user experience.

[0008] In another embodiment, based on the second emotion type being different from the first emotion type, the method further includes: deactivating the first emotion model.

[0009] In this embodiment, when the second emotion type is different from the first emotion type, it indicates that the first response content is not suitable for the emotion of the interactive object, and the emotion model needs to be adaptively changed according to the emotion change of the interactive object. By deactivating the first emotion model, the state of the first emotion model is switched to the dormant state.

[0010] In another embodiment, the method further includes: based on the second emotion type being the same as the first emotion type, keeping the first emotion model activated.

[0011] In this embodiment, when the second emotion type is the same as the first emotion type, it indicates that the first response content adapts to the emotion of the interaction object, and the emotion model is not changed in the second time period.

[0012] In another embodiment, before activating the first emotion model corresponding to the first emotion type, the method further includes: adding emotional terms to the conversation content according to a first corpus corresponding to the first emotion type.

[0013] In this embodiment, the first corpus is used to store emotional terms related to the first emotion type. By adding emotional terms to the conversation content, it is helpful to increase the differences between various emotion types, thereby improving the matching degree of the emotion model.

[0014] In another embodiment, before activating the first emotion model corresponding to the first emotion type, the method further includes: training corresponding emotion models according to emotion training sets corresponding to the emotion types.

[0015] In this embodiment, various emotion models may be trained based on emotion training sets corresponding to various emotion types, and the emotion training sets may include text content corresponding to the emotion types.

[0016] A second aspect of an embodiment of the present application provides an intelligent interactive device, comprising a memory, a processor, a sensor, a microphone, and a speaker. The microphone is configured to record the conversation content of an interactive subject. The sensor is configured to collect the emotional data of the interactive subject. The speaker is configured to play the response content. The memory is configured to store a plurality of emotion models. The processor is configured to: obtain the conversation content and first emotion data of the interactive subject during a first time period; determine a first emotion type based on the first emotion data; activate a first emotion model corresponding to the first emotion type, the first emotion model being configured to generate a first response content matching the first emotion type based on the conversation content; and respond to the conversation content based on the first response content.

[0017] In one embodiment, the processor is also used to: obtain second emotion data of the interactive object in a second time period; determine a second emotion type based on the second emotion data; activate a second emotion model that matches the second emotion type based on the fact that the second emotion type is different from the first emotion type, and the second emotion model is used to generate second response content that matches the second emotion type based on the conversation content; and respond to the conversation content based on the second response content.

[0018] In another embodiment, the intelligent interactive device further includes a display, and the display is configured to display the first response content.

[0019] A third aspect of an embodiment of the present application provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a computer, the computer executes the intelligent interaction method of the embodiment of the present application.

[0020] It can be understood that the specific implementation methods and beneficial effects of the intelligent interactive device provided in the second aspect and the computer-readable storage medium provided in the third aspect of the embodiment of this application are the same as the specific implementation methods and beneficial effects of the intelligent interactive method provided in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a schematic diagram of the structure of an intelligent interactive device provided by an embodiment of the present application.

[0022] Figure 2 This is a flowchart of an intelligent interaction method provided by an embodiment of the present application. DETAILED DESCRIPTION

[0023] It should be noted that in the embodiments of the present application, "at least one" and "several" refer to one or more, and "multiple" refers to two or more. "And / or" describes the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The terms "first", "second", etc. in the specification, claims, and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0024] It should also be noted that the method disclosed in the embodiments of the present application or the method shown in the flowchart includes one or more steps for implementing the method. Without departing from the scope of the claims, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.

[0025] Figure 1 This is a schematic diagram of the structure of an intelligent interactive device provided by an embodiment of the present application.

[0026] like Figure 1 As shown, the intelligent interactive device 100 includes a sensor 110, a microphone 120, a speaker 130, a display 140, a memory 150, and a processor 160. The processor 160 is electrically connected to the sensor 110, the microphone 120, the speaker 130, the display 140, and the memory 150.

[0027] Sensor 110 is used to collect emotional data of the interacting object. Emotional data may include physiological data and behavioral data. Physiological data may include heart rate, skin conductivity, respiratory rate, and facial images, while behavioral data may include body movement images. Exemplarily, sensor 110 may include multiple types of biosensors for collecting physiological data of the interacting object. For example, sensor 110 may include a biosensor for collecting heart rate, a biosensor for collecting skin conductivity, a biosensor for collecting respiratory rate, etc. Sensor 110 may also include a camera for collecting facial images and body movement images of the interacting object.

[0028] The microphone 120 is used to record the conversation content of the interactive object. The user can speak through the microphone 120, input the voice signal into the microphone 120, and the microphone 120 converts the voice signal into an electrical signal, thereby collecting the voice signal and realizing the recording function.

[0029] The speaker 130 is used to play the answer content. The speaker 130 can convert the electrical signal into a voice signal, thereby realizing the voice playing function.

[0030] The display 140 is used to display the response content. In some embodiments, the display 140 can display the conversation content recorded by the microphone 120. In other embodiments, the display 140 can display the conversation content in text form input by the interactive object.

[0031] The display 140 includes a display panel, which can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active matrix organic light-emitting diode or an active matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a Miniled, a MicroLed, a Micro-oLed, a quantum dot light-emitting diode (QLED), etc.

[0032] Memory 150 is used to store a plurality of emotion models. The emotion models are used to generate responses that match the emotion type based on the conversation content. For example, the emotion models may include an excitement model, a calm model, a depression model, and a tension model. Each emotion model can be trained using emotion training sets corresponding to various emotion types. The emotion training sets may include text content corresponding to the emotion type.

[0033] In some embodiments, memory 150 may also store corpora corresponding to various emotion types, each corpus storing emotional terms related to that emotion type. Emotional terms may include particles, adjectives, and other expressions used to express the emotion type. Including emotional terms in conversations can help increase the differences between various emotion types, thereby improving the matching accuracy of the emotion model.

[0034] The memory 150 may include an external memory interface and an internal memory. The external memory interface may be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the intelligent interactive device 100. The external memory card communicates with the processor 160 via the external memory interface to implement a data storage function. The internal memory may be used to store computer executable program code, and the executable program code includes instructions. The internal memory may include a program storage area and a data storage area. The program storage area may store an operating system, an application required for at least one function (such as a sound playback function), etc. The data storage area may store data (such as audio data) created during the use of the intelligent interactive device 100, etc. In addition, the internal memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or a universal flash memory (UFS). The processor 160 executes various functional applications and data processing of the intelligent interactive device 100 by running instructions stored in the internal memory and / or instructions stored in a memory provided in the processor 160.

[0035] The processor 160 is used to obtain the conversation content and emotion data of the interaction object, determine the emotion type according to the emotion data, activate the emotion model corresponding to the emotion type, and respond to the conversation content according to the response content.

[0036] In some embodiments, processor 160 may further collect emotional data of the interacting party after responding to the conversation content, determine the emotion type based on the new emotional data, and determine whether to adjust the emotion model based on whether the emotion type has changed. If the emotion type changes, the emotion model corresponding to the new emotion type is switched. If the emotion type does not change, the original emotion model remains unchanged. This achieves emotional conversion of the response content, making the response content more adapted to the emotion of the interacting party, thereby improving the user experience.

[0037] The processor 160 may include one or more processing units. For example, the processor 160 may include, but is not limited to, an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, a neural network processing unit (NPU), etc. The different processing units may be independent devices or integrated into one or more processors.

[0038] Processor 160 may also include a memory for storing instructions and data. In some embodiments, the memory in processor 160 is a cache memory. The memory can store instructions or data that have just been used or are being recycled by processor 160. If processor 160 needs to use an instruction or data again, it can directly call it from the memory.

[0039] It is understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the intelligent interactive device 100. In other embodiments, the intelligent interactive device 100 may include more or fewer components than shown, or combine or separate certain components, or arrange the components differently.

[0040] The intelligent interactive device provided in the embodiments of this application can be applied in various scenarios. For example, the intelligent interactive device can be applied in an intelligent customer service system, for example, by integrating the intelligent interactive device into a customer service robot, enabling the customer service robot to acquire and analyze emotional data provided by customers via text or voice, identify the emotion type, and then invoke the emotion model corresponding to the emotion type to generate a response content that is appropriate to the customer's conversation content. This provides emotional responses that are appropriate to the customer's emotions, thereby improving the user experience.

[0041] For another example, intelligent interactive devices can be applied in social media sentiment analysis tools, such as integrating intelligent interactive devices into computers, so that the computers can obtain and analyze emotional data from text content of social media (or other data sources), identify the emotion type, and then call the emotion model corresponding to the emotion type to generate response content that is suitable for the text content of social media. This helps administrators grasp the public's emotional trends in social media, and guide the public's emotional trends by actively adjusting the emotion model, so as to intervene in the negative emotional trends of social media in a timely manner and maintain the public opinion atmosphere of social media.

[0042] Figure 2 This is a flowchart of an intelligent interaction method provided by an embodiment of the present application.

[0043] Intelligent interaction methods are applied to intelligent interactive devices, e.g. Figure 1 The intelligent interactive device 100 shown in FIG. Figure 2 As shown, the intelligent interaction method includes the following steps:

[0044] S101, obtaining conversation content and first emotion data of an interaction object in a first time period.

[0045] In this embodiment, the intelligent interactive device can use a microphone to record the conversation content of the interactive object in the first time period, and then use a semantic recognition algorithm to identify the intention of the conversation content, so as to accurately know the content of the conversation, and use sensors to collect the first emotional data of the interactive object in the first time period, such as collecting the heart rate, skin conductivity, breathing rate, facial image or body movement image of the interactive object in the first time period.

[0046] The first time period can be set as needed, for example, the first time period can be 3 minutes or 5 minutes.

[0047] In some embodiments, the intelligent interactive device may be provided with an input module, which may receive the text-based dialogue content input by the interactive object during the first time period. The input module may include a touch screen.

[0048] S102: Determine a first emotion type according to the first emotion data.

[0049] In this embodiment, the intelligent interactive device can extract characteristic parameters from the emotional data using methods such as time-domain / frequency-domain analysis and nonlinear fitting, and then classify the data based on the characteristic parameters to determine the emotion type corresponding to the emotional data. The emotion type can be set as needed. For example, the emotion type can include excitement, calmness, depression, and tension.

[0050] Among them, emotional data corresponds to emotional types. Taking heart rate as an example, changes in heart rate frequency bands are related to sympathetic nerve activity. The ratio of low frequency (LF) to high frequency (HF) can measure the strength of sympathetic nerve activity, and the HF frequency can measure the strength of parasympathetic nerve activity. An increase in the ratio of LF frequency to HF frequency indicates increased sympathetic nerve activity, and an increase in HF frequency indicates increased parasympathetic nerve activity. For example, the LF frequency range can be 0.04-0.15Hz, and the HF frequency range can be 0.15-0.4Hz. When the LF frequency increases and the HF frequency decreases, the ratio of LF frequency to HF frequency increases, indicating increased sympathetic nerve activity and decreased parasympathetic nerve activity, and the corresponding emotional type is excitement. When the LF frequency decreases and the HF frequency increases, the ratio of LF frequency to HF frequency decreases, indicating decreased sympathetic nerve activity and increased parasympathetic nerve activity, and the corresponding emotional type is stable. When both the LF and HF frequencies decrease, the ratio of the LF to HF frequencies may change, indicating changes in sympathetic nerve activity and weakened parasympathetic nerve activity, corresponding to depression. When the LF frequency decreases and the HF frequency increases, the ratio of the LF to HF frequencies decreases, indicating weakened sympathetic nerve activity and enhanced parasympathetic nerve activity, corresponding to tension.

[0051] It can be understood that, similar to heart rate, a correspondence between emotion data and emotion types can also be established based on other physiological data and behavioral data.

[0052] S103: Add emotional terms to the conversation content according to the first corpus corresponding to the first emotion type.

[0053] In this embodiment, the intelligent interactive device can access corpora corresponding to various emotion types, each of which is used to store emotional terms related to the emotion type. Emotional terms can include particles, adjectives, etc. used to express the emotion type. For example, the corpus corresponding to excitement stores emotional terms related to excitement, the corpus corresponding to calmness stores emotional terms related to calmness, the corpus corresponding to depression stores emotional terms related to depression, and the corpus corresponding to tension stores emotional terms related to tension.

[0054] By adding emotional terms to the conversation content, intelligent interactive devices can increase the differences between various emotion types, thereby improving the matching degree of the emotion model.

[0055] It is understandable that the corpus corresponding to various emotion types can be stored locally or in the cloud.

[0056] S104: Activate a first emotion model corresponding to the first emotion type.

[0057] The first emotion model is used to generate first response content that matches the first emotion type based on the conversation content.

[0058] In this embodiment, the intelligent interactive device stores several emotion models. These emotion models are used to generate responses that match the emotion type based on the conversation content. For example, the emotion models may include an excitement model, a stability model, a depression model, and a tension model. The excitement model is used to generate responses that match excitement based on the conversation content; the stability model is used to generate responses that match stability based on the conversation content; the depression model is used to generate responses that match depression based on the conversation content; and the tension model is used to generate responses that match tension based on the conversation content.

[0059] It is understood that various emotion models can be designed as needed, and the emotion model can be a random forest model, a neural network model, or a deep learning model, etc. Various emotion models can be trained based on emotion training sets corresponding to various emotion types, and the emotion training sets can include text content corresponding to the emotion types.

[0060] Smart interactive devices can automatically load various emotion models upon power-up. These models remain dormant when inactive, saving system resources and power consumption. After identifying an emotion, the device triggers an activation command, which activates the corresponding emotion model. This eliminates the need for model loading during interaction, improving response efficiency.

[0061] S105: Respond to the conversation content according to the first response content.

[0062] In this embodiment, after the emotion model is activated, a response content matching the emotion type can be generated according to the conversation content. The intelligent interactive device can play the response content using a speaker and display the response content on a display.

[0063] S106: Acquire second emotion data of the interaction object in a second time period.

[0064] The second time period is after the first time period, and the second time period can be set as needed, for example, the second time period is 1 minute or 2 minutes.

[0065] In this embodiment, after responding to the conversation content, the intelligent interactive device can collect the emotional data of the interactive object again to confirm whether the response content is suitable for the emotion of the interactive object.

[0066] S107: Determine a second emotion type according to the second emotion data.

[0067] It can be understood that the specific implementation of step S107 is the same as that of step S102 and will not be repeated here.

[0068] S108: Determine whether the second emotion type is the same as the first emotion type.

[0069] If yes, execute step S109; if no, execute steps S110 to S112.

[0070] In this embodiment, if the second emotion type is the same as the first emotion type, then the first response content is adapted to the emotion of the interacting party. If the second emotion type is different from the first emotion type, then the first response content is not adapted to the emotion of the interacting party, and the emotion model needs to be adaptively changed according to the change in the emotion of the interacting party.

[0071] S109: Based on the fact that the second emotion type is the same as the first emotion type, the first emotion model remains activated.

[0072] In this embodiment, the state of the emotion model may include an active state or a dormant state. During a certain time period, one of the multiple emotion models is in an active state, while the remaining emotion models are in a dormant state. If the second emotion type is the same as the first emotion type, the emotion model is not changed during the second time period.

[0073] S110 , deactivating the first emotion model based on the second emotion type being different from the first emotion type.

[0074] In this embodiment, when the second emotion type is different from the first emotion type, a deactivation instruction is triggered, and the deactivation instruction is used to deactivate the emotion model corresponding to the emotion type, so that the state of the emotion model is switched to the dormant state.

[0075] S111: Activate a second emotion model that matches the second emotion type.

[0076] The second emotion model is used to generate second response content that matches the second emotion type based on the conversation content.

[0077] It can be understood that the specific implementation of step S111 is the same as that of step S104 and will not be repeated here.

[0078] S112, responding to the conversation content according to the second response content.

[0079] In this embodiment, after the new emotion model is activated, response content that matches the new emotion type can be generated based on the conversation content, thereby achieving emotional conversion of the response content, making the response content more adapted to the emotions of the interactive object, and thus improving the user experience.

[0080] An embodiment of the present application provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a computer, the computer executes the intelligent interaction method of the embodiment of the present application.

[0081] Computer-readable storage media include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media include, but are not limited to, random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer.

[0082] The embodiments of the present application are described in detail above in conjunction with the accompanying drawings, but the present application is not limited to the above embodiments. Various changes can be made within the scope of knowledge possessed by ordinary technicians in the relevant technical field without departing from the purpose of the present application.

Claims

1. An intelligent interaction method, characterized in that: The method comprises: Obtaining conversation content and first emotion data of an interaction object in a first time period; determining a first emotion type according to the first emotion data; activating a first emotion model corresponding to the first emotion type, the first emotion model being used to generate a first response content matching the first emotion type according to the conversation content; Respond to the conversation content according to the first response content.

2. The intelligent interaction method according to claim 1, wherein: The method further comprises: Acquire second emotion data of the interactive object in a second time period; determining a second emotion type according to the second emotion data; Based on the difference between the second emotion type and the first emotion type, activating a second emotion model that matches the second emotion type, wherein the second emotion model is used to generate second response content that matches the second emotion type based on the conversation content; Respond to the conversation content according to the second response content.

3. The intelligent interaction method according to claim 2, wherein: Based on the second emotion type being different from the first emotion type, the method further includes: The first emotion model is deactivated.

4. The intelligent interaction method according to claim 2, wherein: The method further comprises: Based on the fact that the second emotion type is the same as the first emotion type, the first emotion model is kept activated.

5. The intelligent interaction method according to any one of claims 1 to 4, characterized in that: Before activating the first emotion model corresponding to the first emotion type, the method further includes: Emotional terms are added to the conversation content according to a first corpus corresponding to the first emotion type.

6. The intelligent interaction method according to any one of claims 1 to 4, characterized in that: Before activating the first emotion model corresponding to the first emotion type, the method further includes: Several corresponding emotion models are trained according to several emotion training sets corresponding to several emotion types.

7. An intelligent interactive device, characterized in that: The intelligent interactive device includes a memory, a processor, a sensor, a microphone and a speaker; The microphone is used to record the conversation content of the interactive object; The sensor is used to collect emotional data of the interactive object; The speaker is used to play the response content; The memory is used to store a plurality of emotion models; The processor is configured to: Acquire the conversation content and first emotion data of the interactive object in a first time period; determining a first emotion type according to the first emotion data; activating a first emotion model corresponding to the first emotion type, the first emotion model being used to generate a first response content matching the first emotion type according to the conversation content; Respond to the conversation content according to the first response content.

8. The intelligent interactive device according to claim 7, wherein: The processor is further configured to: Acquire second emotion data of the interactive object in a second time period; determining a second emotion type according to the second emotion data; Based on the difference between the second emotion type and the first emotion type, activating a second emotion model that matches the second emotion type, wherein the second emotion model is used to generate second response content that matches the second emotion type based on the conversation content; Respond to the conversation content according to the second response content.

9. The intelligent interactive device according to claim 7 or 8, wherein: The intelligent interactive device further includes a display, and the display is configured to display the first response content.

10. A computer-readable storage medium for storing computer instructions, characterized in that: When the computer instructions are executed by a computer, the computer is enabled to execute the intelligent interaction method according to any one of claims 1 to 6.

Images