A human-computer interaction method, device, equipment and medium

Abstract

The application discloses a human-computer interaction method and device, equipment and medium, and relates to the technical field of communication interaction. The method comprises the following steps: generating and broadcasting first device information identification signaling, so that other smart devices feed back first confirmation signaling; after receiving second device information identification signaling and the first confirmation signaling generated and broadcasted by other smart devices, analyzing the second identification signaling and updating a local interactive device list, feeding back second confirmation signaling, so that other smart devices update the local interactive device list; after receiving a target interaction instruction, performing emotion recognition and processing, generating and broadcasting first response management signaling according to the device list, and receiving second response management signaling generated and broadcasted by other smart devices; each response management signaling is used for indicating the response sequence of device interaction and human-computer interaction among a plurality of emotion accompanying smart devices; the target device response sequence is determined according to the response management signaling, and the instruction response is performed in cooperation with other smart devices.

Description

Technical Field

[0001] This invention relates to the field of communication and interaction technology, and in particular to a human-computer interaction method, apparatus, device, and medium. Background Technology

[0002] In recent years, artificial intelligence (AI) technology has rapidly penetrated various fields such as life services, healthcare, and education and training. Users' demands for AI interaction have evolved from functional responses to emotional companionship. Currently, various emotional companionship-related smart products (such as smart speakers, companion robots, smart toys, and virtual assistants) are rapidly emerging in the market. When users encounter multiple emotional companionship-related smart products in their usage scenarios, the lack of unified technical standards in the industry leads to poor compatibility between products from different manufacturers, difficulties in data interoperability, and negative impacts on user experience, thus hindering the industry's large-scale development.

[0003] In conclusion, how to achieve behavioral interaction and data interoperability among different emotional companionship smart products to improve the user experience is a problem that urgently needs to be solved. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a human-computer interaction method, device, equipment, and medium that enables behavioral interaction and data exchange between different emotional companionship smart products to improve the user experience. The specific solution is as follows: Firstly, this application provides a human-computer interaction method applied to a target emotional companionship smart device in a target scenario, wherein the target scenario includes multiple emotional companionship smart devices, and the target emotional companionship smart device is any one of the multiple emotional companionship smart devices; wherein the method includes: The first device information identification signaling of the target emotional companionship smart device is generated and broadcast based on a preset transmission frequency, so that other smart devices can send back corresponding first confirmation signaling based on the first device information identification signaling; the other smart devices are other smart devices besides the target emotional companionship smart device among the plurality of emotional companionship smart devices; Upon receiving the second device information identification signaling and the first confirmation signaling, the system parses the second device information identification signaling and updates the local first interactive device list, and sends back the corresponding second confirmation signaling so that the other smart devices can update their local second interactive device list according to the second confirmation signaling; the second device information identification signaling is a device information identification signaling generated and broadcast by the other smart devices based on a preset transmission frequency; Upon receiving a target interaction command, the system performs emotion recognition and processing on the command to generate and broadcast a first response management signaling based on the first list of interactive devices, and receives a second response management signaling. The second response management signaling is generated and broadcast by the other smart devices based on the command analysis result and the second list of interactive devices. The command analysis result is the analysis result obtained by the other smart devices through emotion recognition and processing of the target interaction command. Each response management signaling is used to indicate the response order of device interaction and human-computer interaction among the multiple emotional companionship smart devices. The response order of the target devices is determined based on the first response management signaling and the second response management signaling, and the other smart devices are coordinated to respond to the target interaction command based on the response order of the target devices.

[0005] Optionally, the step of generating and broadcasting the first device information identification signaling of the target emotional companionship smart device based on a preset transmission frequency includes: The device information of the target emotional companionship smart device is determined; the device information includes device persona information, device identifier, namespace where the device identifier is located, and a current local list of first interactive devices; the device identifier is unique within the same namespace; The device information and the current timestamp are used to generate a first device information identification signaling for the target emotional companionship smart device, and the first device information identification signaling is broadcast based on a preset transmission frequency.

[0006] Optionally, parsing the second device information identification signaling and updating the local first interactive device list includes: The second device information identification signaling is parsed to determine the corresponding target device information; the target device information includes the target namespace, the target device identifier, the target timestamp, and the target persona information; If there is no device in the local first interactive device list that matches the target namespace and the target device identifier, then add the target device information to the first interactive device list; If a device matching the target namespace and the target device identifier exists in the local first interactive device list, then the timestamp information of the corresponding device in the first interactive device list is updated using the target timestamp.

[0007] Optionally, parsing the second device information identification signaling and updating the local first interactive device list further includes: Determine the current system time, and identify devices in the first list of interactive devices whose timestamps exceed a preset time threshold from the current system time that need to be removed; Remove the device information related to the device to be removed from the first list of interactive devices.

[0008] Optionally, the step of performing emotion recognition and processing on the target interaction command includes: Identify the target intent of the target interaction command, and perform emotion recognition based on the target intent to obtain the corresponding recognition result; The target interaction command is subjected to security verification. If the security verification passes, the historical interaction memory of the target interaction command is retrieved and the current user profile is updated. Based on the user profile, the historical interaction memory, the recognition result, and the target intent, it is determined whether the current target emotional companionship smart device meets the preset response requirement conditions. If it does, a target response content is generated for the target interaction command.

[0009] Optionally, generating and broadcasting the first response management signaling based on the first list of interactive devices includes: Determine the historical dialogue and interaction data of the target emotional companionship smart device; If the target emotional companionship smart device meets the preset response requirement conditions, then a first response management signaling is generated and broadcast based on the first interactive device list, the historical dialogue interaction information, and the target response content; If the target emotional companionship smart device does not meet the preset response requirements, a first response management signaling is generated and broadcast based on the first list of interactive devices and the historical dialogue interaction information.

[0010] Optionally, determining the target device's response order based on the first response management signaling and the second response management signaling includes: If, based on the first response management signaling and the second response management signaling, it is determined that the target emotional companionship smart device and the other smart devices all meet the preset response requirement conditions, then the historical dialogue interaction situation is determined. If the historical dialogue interaction indicates that the previous round of dialogue was responded to first by the target emotional companionship smart device, then the response priority of the other smart devices is set to the highest. If the historical dialogue interaction indicates that the previous round of dialogue was responded to first by the other smart devices, then the response priority of the target emotional companionship smart device is set to the highest.

[0011] Secondly, this application provides a human-computer interaction device applied to a target emotional companionship smart device in a target scenario, wherein the target scenario includes multiple emotional companionship smart devices, and the target emotional companionship smart device is any one of the multiple emotional companionship smart devices; wherein the device includes: The signaling broadcast module is used to generate and broadcast the first device information identification signaling of the target emotional companionship smart device based on a preset transmission frequency, so that other smart devices can send back corresponding first confirmation signaling based on the first device information identification signaling; the other smart devices are other smart devices among the plurality of emotional companionship smart devices, excluding the target emotional companionship smart device; The list update module is used to, upon receiving the second device information identification signaling and the first confirmation signaling, parse the second device information identification signaling and update the local first interactive device list, and send back the corresponding second confirmation signaling, so that the other smart devices can update their local second interactive device list according to the second confirmation signaling; the second device information identification signaling is a device information identification signaling generated and broadcast by the other smart devices based on a preset transmission frequency; The instruction processing module is used to perform emotion recognition and processing on the target interaction instruction after receiving it, so as to generate and broadcast a first response management signaling according to the first list of interactive devices, and to receive a second response management signaling; the second response management signaling is a response management signaling generated and broadcast by the other smart devices according to the instruction analysis result and the second list of interactive devices; the instruction analysis result is the analysis result obtained by the other smart devices from performing emotion recognition and processing on the target interaction instruction; each of the response management signals is used to indicate the response order of device interaction and human-computer interaction among the multiple emotional companionship smart devices; The instruction response module is used to determine the response order of the target device based on the first response management signaling and the second response management signaling, and to coordinate with the other smart devices to respond to the target interaction instruction based on the response order of the target device.

[0012] Thirdly, this application provides an electronic device, comprising: Memory, used to store computer programs; A processor is used to execute the computer program to implement the aforementioned human-computer interaction method.

[0013] Fourthly, this application provides a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned human-computer interaction method.

[0014] In this application, a first device information identification signaling for the target emotional companionship smart device is generated and broadcast based on a preset transmission frequency, so that other smart devices can respond with a corresponding first confirmation signaling based on the first device information identification signaling; the other smart devices are smart devices other than the target emotional companionship smart device among the plurality of emotional companionship smart devices; after receiving the second device information identification signaling and the first confirmation signaling, the second device information identification signaling is parsed and the local first interactive device list is updated, and a corresponding second confirmation signaling is fed back, so that the other smart devices can update their local second interactive device list according to the second confirmation signaling; the second device information identification signaling is a device information identification signaling generated and broadcast by the other smart devices based on a preset transmission frequency; after receiving the target emotional companionship smart device, the second device information identification signaling is ... After receiving the mutual command, the target interaction command undergoes emotion recognition and processing to generate and broadcast a first response management signaling based on the first list of interactive devices, and to receive a second response management signaling. The second response management signaling is generated and broadcast by the other smart devices based on the command analysis result and the second list of interactive devices. The command analysis result is the analysis result obtained by the other smart devices through emotion recognition and processing of the target interaction command. Each response management signaling is used to indicate the response order of device interaction and human-computer interaction among the multiple emotional companionship smart devices. The target device response order is determined based on the first response management signaling and the second response management signaling, and the other smart devices respond to the target interaction command in coordination with the target device response order. As can be seen from the above, the target emotional companionship smart device of this application broadcasts its own first device information identification signaling at a preset frequency. Other devices in the cluster send back a first confirmation signaling. After receiving the second device identification signaling and the first confirmation signaling periodically broadcast by other devices, the local device parses and updates its local list of interactive devices and sends a second confirmation signaling for other devices to update their respective device lists. After receiving the target interaction command, the device performs emotion recognition processing, generates and broadcasts a first response management signaling based on the local device list, and simultaneously receives the second response management signaling generated by other devices after emotion parsing. The device response order is determined by combining the response management signaling, and multiple emotional companionship smart devices complete the interactive response in a coordinated manner according to the order.In this way, through the process described in this application, emotional companionship smart devices periodically broadcast device identification signals at a preset fixed frequency, continuously synchronizing the online status of devices within the cluster and avoiding the problem of devices being offline or new devices not being detected; upon receiving an interaction command, they complete emotion recognition processing, analyze the emotional demands contained in the command, and ensure that the response matches the user's emotional needs; based on the local list of interactive devices, they generate broadcast response management signals and simultaneously receive response management signals issued by other devices based on their own analysis results, summarizing the response weight and capability information of all devices in the cluster; by integrating all response management signals, they uniformly determine the device response order, orderly allocate the timing of each emotional companionship device's voice and interaction, avoid sound overlap and interaction chaos caused by multiple devices responding simultaneously, realize orderly collaborative emotional interaction of multiple emotional companionship devices, improve the smoothness of interaction and the continuity of emotional experience in multi-device companionship scenarios, and thus realize behavioral interaction and data interoperability between different emotional companionship smart products to improve the user experience. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0016] Figure 1 This is a flowchart of a human-computer interaction method disclosed in this application; Figure 2 This is a flowchart illustrating a human-computer interaction method disclosed in this application; Figure 3 This is a schematic diagram of a discovery device disclosed in this application; Figure 4 This is a schematic diagram of the system functions of an emotional companionship smart device disclosed in this application; Figure 5 This is a schematic diagram of the structure of a human-computer interaction device disclosed in this application; Figure 6 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Currently, various emotional companionship smart products (such as smart speakers, companion robots, smart toys, virtual assistants, etc.) are rapidly emerging in the market. When users have multiple emotional companionship smart products in their usage scenarios, the lack of unified technical standards in the industry leads to poor product compatibility and difficulty in data interoperability between different manufacturers, affecting user experience and restricting the large-scale development of the industry.

[0019] To overcome the aforementioned technical problems, this application provides a human-computer interaction method that enables behavioral interaction and data exchange between different emotional companionship smart products to improve the user experience.

[0020] See Figure 1 As shown, this embodiment of the invention discloses a human-computer interaction method applied to a target emotional companionship smart device in a target scenario. The target scenario includes multiple emotional companionship smart devices, and the target emotional companionship smart device is any one of the multiple emotional companionship smart devices. The method includes: Step S11: Generate and broadcast the first device information identification signaling of the target emotional companionship smart device based on a preset transmission frequency, so that other smart devices can feed back the corresponding first confirmation signaling based on the first device information identification signaling; the other smart devices are other smart devices besides the target emotional companionship smart device among the plurality of emotional companionship smart devices.

[0021] In this embodiment, any one of the multiple emotional companionship smart devices in the target scene periodically generates and broadcasts its own first device information identification signaling according to a preset transmission frequency. Other emotional companionship smart devices, excluding the target emotional companionship smart device, send back a corresponding first confirmation signaling based on the first device information identification signaling. The device information identification signaling is used for mutual discovery between different emotional companionship smart devices within the scene and for exchanging device attribute information. Periodic transmission ensures that the status of the emotional companionship smart devices within the scene remains up-to-date (for example, some devices may have been moved and are no longer within the interaction range).

[0022] It's important to note that in the current market for emotional companionship smart products (such as smart speakers, companion robots, smart toys, and virtual assistants), users typically expect these products to possess a certain human-like personality, enabling them to interact with users. When multiple emotional companionship smart products are present in a user's scenario, interactive behaviors between these different products also need to be established. For example, in the smart toy scenario, multiple smart toys are usually present simultaneously. During the interaction with these N smart toys, the following situations may occur: the user interacts with a specific toy A (e.g., using a specific wake word, "Little A, Little A"); the user interacts with all toys in the scenario without specific targeting, for example, the user asks a question, requiring a response from a particular toy; during the smart toy's response, based on the current scenario and the personality traits of each smart toy, smart toy A can directly interact with smart toy B, for example, after A answers the user's question, it asks B if it has anything to add. In the aforementioned interactive scenarios, it is necessary to control the order in which N smart toys respond (including who responds, who doesn't respond, and who responds first). Addressing the current industry's lack of unified technical standards, which leads to poor product compatibility and data interoperability between different manufacturers, hindering the industry's large-scale development, this application proposes a human-computer interaction method for emotional companionship intelligence. By defining control signaling, data interfaces, and data processing for multi-product dialogue, it supports behavioral interaction and data interoperability between different emotional companionship intelligent products, enabling interaction between them. For example... Figure 2 The diagram shows a flowchart of a human-computer interaction method provided in this application. It is understood that in multi-device interaction scenarios, the main issues to be addressed are: determining which devices can interact in the current scenario, and managing the order of responses from multiple devices. The overall process steps include: 1. Sending device information identification signaling; 2. Receiving confirmation information and device information identification signaling from other devices; 3. Sending confirmation information and updating the list of interactive devices in the scenario based on the information in step 2; 4. When a response is required, sending a response management signaling. This allows responses to the user or other devices in the scenario; 5. If the current device needs to provide interactive feedback, then that device provides the feedback.

[0023] It should be noted that the processing flow for generating and broadcasting the first device information identification signaling of the target emotional companionship smart device based on a preset transmission frequency is as follows: The device information of the target emotional companionship smart device is determined; the device information includes device persona information, device identifier, the namespace where the device identifier resides, and the current local list of first interactive devices; the device identifier is unique within the same namespace; the first device information identification signaling of the target emotional companionship smart device is generated using the device information and the current timestamp, and broadcast based on the preset transmission frequency. That is, devices are discovered by sending device information identification signaling to indicate the device information of the emotional companionship smart product. The device information identification signaling can contain not only its own device information but also a list of interactive devices discovered within the scene, used for mutual identification between different emotional companionship smart products. Its syntax and semantics are as follows: Table 1. Syntax and Semantics of Device Information Identification Signaling

[0024] Therefore, it can be determined that the target emotional companionship smart device includes device persona information, a unique device identifier within the namespace, the namespace where the identifier resides, and the current local list of the first interactive devices. This information is then combined with the current timestamp to generate a first device information identification signaling message, which is then broadcast based on a preset transmission frequency. For example... Figure 3 The diagram shown is a flowchart illustrating a device discovery process provided in this application. Furthermore, this embodiment does not specify the specific form of the persona information, but only its interface. The persona information interface is used to provide the device's own persona information, and its code is as follows: aligned(8) class personaInterface{ unsigned int(16) persona_info_length; for(int i=0; i <persona_info_length; i++){ bit(8) persona_info_byte[i]; } } Here, persona_info_length indicates the length of the persona information in bytes. persona_info_byte[i] indicates the i-th byte of the persona information.

[0025] It should be further noted that the device information identification signaling needs to be acknowledged to ensure that the information from the current device is correctly received. This can be accomplished through a dedicated acknowledgment signaling or by extending a field within the device information identification signaling. Furthermore, when the device sends an acknowledgment message, it should include its own device information identification signaling. Each acknowledgment signaling is used to confirm the correct reception of any interactive information, such as signaling data or session data, in the interaction with the emotional companionship smart product. The syntax and semantics of the acknowledgment signaling are as follows: Table 2. Syntax and Semantics of Acknowledgment Signaling

[0026] In this way, this embodiment periodically broadcasts device identification signaling based on a preset transmission frequency, continuously publicizing the online status and basic device information of the device, allowing other devices in the cluster to perceive the device's presence in real time, solving the problem of devices not being able to be detected in a timely manner when going online or offline; the two-way signaling interaction mechanism that triggers other devices to reply with a first confirmation signaling after broadcasting the identification signaling allows the target device to obtain the response feedback from online devices in the cluster, completing the basic process of mutual discovery between devices, and providing a foundation for subsequent multi-device collaborative interaction; the device identifier is unique under the same namespace, which can isolate devices in different groups and avoid identification confusion caused by duplicate device IDs across groups; the signaling is generated by fusing device information and real-time timestamps, and new and old broadcast messages are distinguished by timestamps, preventing duplicate and expired signaling from interfering with device status determination.

[0027] Step S12: After receiving the second device information identification signaling and the first confirmation signaling, parse the second device information identification signaling and update the local first interactive device list, and send back the corresponding second confirmation signaling so that the other smart devices can update the local second interactive device list according to the second confirmation signaling; the second device information identification signaling is a device information identification signaling generated and broadcast by the other smart devices based on a preset transmission frequency.

[0028] In this embodiment, the target emotional companionship smart device receives a second device information identification signaling and a first confirmation signaling periodically broadcast by other devices. It parses the second device information identification signaling and updates its local first interactive device list. Simultaneously, it feeds back a corresponding second confirmation signaling for the second device information identification signaling, so that the other smart devices can update their local second interactive device list based on the second confirmation signaling. The generation operation of the second device information identification signaling is the same as that of the first device information identification signaling, and their signaling structure is also identical.

[0029] It should be noted that the processing flow for parsing the second device information identification signaling and updating the local first interactive device list is as follows: The second device information identification signaling is parsed to determine the corresponding target device information; the target device information includes a target namespace, a target device identifier, a target timestamp, and target persona information; if no device matching the target namespace and the target device identifier exists in the local first interactive device list, the target device information is added to the first interactive device list; if a device matching the target namespace and the target device identifier exists in the local first interactive device list, the timestamp information of the corresponding device in the first interactive device list is updated using the target timestamp. That is, the syntax and semantics of the interactive device list are as follows: Table 3. Syntax and semantics of the list of interactive devices

[0030] The second device information identification signaling is parsed to extract target device information containing the target namespace, target device identifier, target timestamp, and target persona information. If the local first interactive device list does not have a device entry matching the target namespace and target device identifier, the target device information is added. If a match exists, the timestamp of the corresponding device in the list is updated using the latest target timestamp carried in the signaling. In addition, after receiving persona information from a third-party device, the persona information of the third-party device can be processed, and a new user profile can be created to maintain the third-party persona. It is understandable that ACK signaling may not be sent during device discovery. For example, when device A receives device information identification signaling from device B, it can add device B to the interactive device list. Simultaneously, the ACK mechanism can also reuse existing confirmation mechanisms, such as using the TCP ACK mechanism after establishing a TCP (Transmission Control Protocol) connection.

[0031] It should be further noted that updating the list of interactive devices also includes removing device information that is no longer within the interactive range. The process is as follows: determine the current system time, and identify devices in the first list of interactive devices whose timestamps differ from the current system time by a preset time threshold; delete the device information related to the devices to be removed from the first list of interactive devices. That is, obtain the current system time, traverse the local first list of interactive devices, filter out devices whose timestamps differ from the current system time by a preset time threshold, and remove all information about such devices from the list. In this way, other smart devices in this embodiment broadcast second device information identification signaling at a fixed frequency to ensure periodic synchronization of cluster device status, and new and offline devices can be quickly identified; the received second device information identification signaling is parsed and the local device list is updated, and information such as external device personas, unique identifiers, and online status is synchronized in real time to maintain interactive devices; relying on the target timestamps embedded in the signaling to update local records, and relying on periodic broadcasting to refresh the online timeliness of devices, the offline status of devices that have not broadcast messages for a long time can be quantitatively determined by the timestamp difference, and lost devices can be identified without additional heartbeat messages, ensuring that the local interactive device list only retains stable online devices, improving the communication efficiency and collaborative accuracy of multi-emotional companionship device networking interaction.

[0032] Step S13: After receiving the target interaction instruction, perform emotion recognition and processing on the target interaction instruction to generate and broadcast a first response management signaling according to the first list of interactive devices, and receive a second response management signaling; the second response management signaling is a response management signaling generated and broadcast by the other smart devices according to the instruction analysis result and the second list of interactive devices; the instruction analysis result is the analysis result obtained by the other smart devices through emotion recognition and processing of the target interaction instruction; each of the response management signaling is used to indicate the response order of device interaction and human-computer interaction among the multiple emotional companionship smart devices.

[0033] In this embodiment, upon receiving a target interaction command, a response requirement is determined. The target emotional companionship smart device performs emotion recognition and processing on the command, generates and broadcasts a first response management signaling based on the local first interactive device list, and simultaneously receives a second response management signaling from other smart devices after undergoing the same processing operation. The target interaction command can be issued by the user or by other smart devices. Each response management signaling is used to indicate the response order of device interactions and human-computer interactions among the multiple emotional companionship smart devices, mainly including the device's interaction intent, including whether the device should respond, whether it recommends other devices to respond, and whether it specifies other devices to respond.

[0034] It should be noted that the processing flow for emotion recognition and processing of the target interaction command is as follows: The target intent of the target interaction command is identified, and emotion recognition is performed based on the target intent to obtain the corresponding recognition result; a security check is performed on the target interaction command. If the security check passes, the historical interaction memory of the target interaction command is retrieved, and the current user profile is updated; based on the user profile, the historical interaction memory, the recognition result, and the target intent, it is determined whether the current target emotional companionship smart device meets the preset response requirement conditions. If it does, target response content for the target interaction command is generated. That is, the target intent of the target interaction command is identified, emotion recognition is performed to obtain the recognition result, a security check is performed on the target interaction command, and high-risk content such as violence, discrimination, and self-harm induction is intercepted and filtered. After the security check passes, the historical interaction memory corresponding to the command is retrieved and the user profile is updated. The user profile, the historical interaction memory, the recognition result, and the target intent are combined to determine whether the device meets the preset response requirement conditions, that is, whether there is a need to respond to the user. If so, target response content corresponding to the target interaction command is generated. Figure 4 The diagram shown illustrates the system functions of an emotional companionship smart device provided in this application. It includes voice recognition and processing, emotion recognition and processing, anthropomorphic feedback, and basic functions such as large-scale modeling, storage, security, and communication.

[0035] It should be noted that technical specifications for speech recognition and processing functions can be defined, including the technical specifications for the speech perception module and the command perception module. The technical specifications for the speech perception module are mainly standardized from the following three dimensions: Speech recognition accuracy (WER (Word Error Rate) / CER (Character Error Rate)): the word / character error rate in different scenarios such as quiet, noisy, and emotionally charged environments; far-field recognition robustness: the success rate of voice wake-up and the accuracy of recognition at specified distances and angles; speech recognition response latency: the time interval between the user stopping speaking and the system completing speech recognition and outputting the final text result. The technical specifications for the command perception module are mainly standardized from the following dimensions: Command understanding accuracy: the accuracy of classifying the intent of explicit operation commands (such as playing music or telling a story). Technical specifications for emotion recognition and processing functions should also be defined, including the specific technical requirements for the intent classification module, emotion computing module, security filtering module, memory retrieval module, and user profiling module. The technical metrics for the intent classification module are primarily standardized across two dimensions: Intent classification accuracy: the percentage of accurate classification of potential intents (e.g., seeking comfort, playing music) in a single user expression; Contextual intent recognition accuracy: the percentage of accurate understanding of the true intent of the current utterance in multiple consecutive rounds of dialogue, considering the preceding context. The technical metrics for the sentiment computing module are primarily standardized across two dimensions: Sentiment fusion recognition accuracy: the accuracy of determining the user's overall emotional state (e.g., mild anxiety, happiness) after fusing voice, text, and other information; Sentiment intensity assessment error: the average absolute error between the assessed value of sentiment intensity (e.g., from 1 to 10) and the labeled value of the test subject. The technical metrics for the security filtering module are primarily standardized across two dimensions: Harmful / inappropriate content blocking rate: the percentage of successful identification and blocking of high-risk content such as violence, discrimination, and self-harm inducement; False blocking rate: the percentage of normal emotional expressions misjudged as harmful content. The technical indicators for the memory retrieval module are primarily standardized from the following two dimensions: Long-term memory association accuracy: the percentage of long-term memory information that can be accurately associated with the user's historical preferences, key experiences, etc., during dialogue; Contextual memory retention rounds: the average number of rounds in which the system can effectively retain and reference the contextual information of the current topic in multiple rounds of dialogue. The technical indicators for the user profiling module are primarily standardized from the following dimensions: Personalized preference prediction consistency: the degree of consistency between responses, content, or activities recommended based on the user profile and the user's actual satisfaction. Specific technical requirements for the anthropomorphic feedback function are specified, including the specific technical requirements for the voice and expression module, the personalized persona module, and the dialogue interaction module.The technical indicators for the timbre and expression module are mainly standardized from the following three dimensions: Naturalness of Emotional Speech Synthesis (MOS: Mean Opinion Score, subjective average score): This uses the average opinion score, subjectively evaluated by users to assess the naturalness and fluency of the synthesized speech under specific emotions; Timbre Cloning Similarity: When authorized to clone a specific human voice, the acoustic feature similarity between the synthesized speech and the target timbre; Emotional Expression Matching Degree: The degree to which the emotion (e.g., gentle, cheerful) of the system's feedback speech matches the current dialogue context and the user's emotion, evaluated by the test subjects. The technical indicators for the personalized persona module are mainly standardized from the following two dimensions: Persona Consistency: An evaluation score assessing whether the system's character portrayal remains consistent over long-term interaction; Feedback Personalization Index: The degree to which the system differentiates and personalizes its responses to different users in terms of content and tone. The technical metrics for the dialogue interaction module are mainly standardized from the following three dimensions: Dialogue content satisfaction: users' subjective satisfaction rating of a single or overall dialogue response; Empathic response appropriateness rate: the ratio of the system generating inclusive and empathetic rather than didactic or perfunctory responses when users express negative emotions, evaluated by test subjects; Proactive care initiation appropriateness rate: the assessment of the timing and content appropriateness of the system initiating proactive care dialogues when users are detected to be silent for a long time or in low spirits.

[0036] Furthermore, the evaluation metrics for the speech perception module of the speech recognition and processing function include speech recognition accuracy (objective metric): Word Error Rate (CER) = (Number of inserted words + Number of deleted words + Number of replaced words) / Total number of reference words 100% Word Error Rate (WER) = (Number of inserted words + Number of deleted words + Number of replaced words / Total number of reference words) 100%; Far-field recognition robustness (objective indicator): Voice wake-up success rate = Number of successful wake-ups / Total number of wake-up tests 100% Far-field recognition accuracy = Number of correct far-field speech recognitions / Total number of far-field test entries 100%; Speech recognition response latency (objective indicator): Speech recognition response latency = ∑ (time from completion of acquisition of a single speech to output of recognition result) / total number of test commands. Evaluation indicators for the instruction perception module include instruction understanding accuracy (objective indicator): number of instructions correctly classified by intent / total number of test instructions. 100%. The evaluation metrics for the intent classification module of the emotion recognition and processing function include intent classification accuracy (objective metric): number of correctly classified intents per test / total number of tests. 100%; Context-related intent recognition accuracy (subjective metric): Number of dialogue turns in which the true intent was correctly identified / Total number of context-related test turns. 100%. The evaluation metrics for the emotion computing module include emotion fusion recognition accuracy (objective metric): the number of samples correctly judged in terms of emotion after fusing various information types / the total number of test samples. 100%; Emotional intensity assessment error (objective indicator): ∑(System evaluation value - Test object labeled value) / Total number of test samples. Evaluation indicators for the security filtering module include harmful / inappropriate content blocking rate (objective indicator): Number of successfully identified and blocked high-risk content items / Total number of high-risk content items tested. 100%; False Blocking Rate (Objective Indicator): Number of legitimate emotional expressions that were mistakenly identified as harmful content and blocked / Total number of legitimate emotional expressions tested. 100%. The evaluation metrics for the memory retrieval module include long-term memory association accuracy (objective indicator): the number of times the test subject accurately associated long-term memories in relevant contexts / the total number of long-term memory tests. 100%; Contextual memory retention rounds (objective metric): ∑ number of rounds of effective contextual memory retention under a single topic / total number of test topics. Evaluation metrics for the user profile module include personalized preference prediction accuracy (objective + subjective metrics): (number of preference recommendation matches) 0.6) + (average satisfaction score of test subjects / 5) 100 0.4). Wherein, the number of preference recommendation matches = the number of times the profile-based recommendation matches the test subject's actual preferences / the total number of recommendations. 100% of test subjects gave a satisfaction rating of 1-5 points, which is the average score. The evaluation metrics for the timbre and expression module in the anthropomorphic feedback function include the MOS score for naturalness of emotional speech synthesis (a subjective indicator): ∑(ratings from all evaluators) / (number of evaluators). (Number of test samples), average score on a 5-point scale; timbre cloning similarity (objective indicator): acoustic feature matching degree between synthesized speech and target timbre. 100% accuracy was achieved by extracting features such as pitch, timbre, speech rate, formants, and fundamental frequency using algorithms like MFCC (Mel-Frequency Cepstral Coefficients), and calculating using cosine similarity. Emotional expression matching (subjective indicator): ∑(all evaluators' scores / (number of evaluators)) The number of test samples is used, and a 10-point scoring system is employed. The evaluation indicators for the personalized persona module include persona consistency (subjective indicator): ∑ total scores of all test subjects / number of test subjects, scored on a 10-point scale; and feedback personalization index (objective + subjective indicator): (differentiated feedback rate). 0.5) + (Personalized perception average score / 5) 100 0.5), where the differential response rate = number of differential responses for different test subjects / total number of responses. 100% personalized perception rating is the average of test subject ratings from 1 to 5. The evaluation metrics for the dialogue content module include dialogue content satisfaction (subjective indicator): (∑ total test subject ratings / total number of ratings) / 5 100%, using a 5-point scale for participant satisfaction rating; Empathic response appropriateness rate (subjective indicator): number of empathic responses marked as "appropriate" by the participant / total number of system responses under negative emotions. 100%; Proactive Care Initiation Appropriateness Rate (Subjective Indicator): Number of proactive care actions marked as "appropriate" by the test subjects / Total number of proactive care actions initiated by the system. 100%.

[0037] It should be further noted that the processing flow for generating and broadcasting the first response management signaling based on the first list of interactive devices is as follows: Determine the historical dialogue interaction status of the target emotional companionship smart device; if the target emotional companionship smart device currently meets the preset response requirement conditions, then generate and broadcast the first response management signaling based on the first list of interactive devices, the historical dialogue interaction status, and the target response content; if the target emotional companionship smart device currently does not meet the preset response requirement conditions, then generate and broadcast the first response management signaling based on the first list of interactive devices and the historical dialogue interaction status. That is, the process of establishing a session between different devices can reuse the existing communication session establishment process, such as TCP or Bluetooth. The response order defined in this embodiment is extended based on this. This embodiment does not specify the specific form of dialogue data, only the dialogue data interface. The dialogue data interface is used to provide dialogue data information of the device during user interaction, and its code is as follows: aligned(8) class dialogueInterface { unsigned int(16) dialogue_info_length; for(int i=0; i< dialogue_info_length; i++){ bit(8) dialogue_info_byte[i]; } } Where `dialogue_info_length` indicates the length of the dialogue information in bytes. `dialogue_info_byte[i]` indicates the i-th byte of the dialogue information. Response management signaling is used to indicate the response order of interactions between different devices and users, as well as interactions between different devices, in multi-device scenarios. Its syntax and semantics are as follows: Table 4. Syntax and Semantics of Responding to Management Signaling

[0038] Therefore, the historical dialogue interaction of the target emotional companionship smart device is determined, i.e., whether it responded to the user in the previous round of dialogue. When the target emotional companionship smart device meets the preset response requirement conditions, it generates and broadcasts the first response management signaling using the local first interactive device list, the historical dialogue interaction situation, and the target response content; when the preset response requirement conditions are not met, the signaling is generated and broadcast only based on the interactive device list and the historical dialogue interaction situation. In this way, this embodiment generates local response management signaling based on the locally maintained interactive device list in real time, and the signaling content is consistent with the perceived online device cluster; the response management signaling uniformly carries the global response order rules, standardizes the device collaborative interaction and human-machine response timing, and multiple devices execute responses according to the unified timing rules, effectively avoiding the sound overlap and chaotic interaction problems caused by multiple companionship devices speaking simultaneously. Relying on distributed emotion analysis combined with the timing signaling broadcasting mechanism, it realizes orderly and emotion-matched collaborative companionship interaction of multiple emotional companionship devices; it first extracts the target intent of the instruction and then matches it with emotion recognition, and simultaneously grasps the user's behavioral demands and emotions. The system is designed to align responses with genuine emotional needs for companionship. An interactive command security checkpoint is added to block illegal and risky content, ensuring safe and compliant human-computer interaction. Upon successful check, the system synchronizes historical interaction memories with updated user profiles, continuously accumulating personalized data such as user preferences and emotional habits for iterative optimization of interaction effects. By integrating multi-dimensional information to jointly determine device response needs, the system can differentiate whether to participate in responses based on device persona, capabilities, and user suitability, preventing devices from outputting replies inconsistent with their intended purpose. Ultimately, personalized responses matching the user's personality, current emotions, and genuine needs are generated, enhancing the relevance and user experience of emotional companionship interactions.

[0039] Step S14: Determine the target device response order based on the first response management signaling and the second response management signaling, and coordinate with the other smart devices to respond to the target interaction command based on the target device response order.

[0040] In this embodiment, the first response management signaling and the second response management signaling are summarized to determine the response order of the target device, and then the other smart devices are coordinated to respond to the target interaction command in accordance with the order.

[0041] It should be noted that the processing flow for determining the response order of the target device based on the first response management signaling and the second response management signaling is as follows: If, based on the first response management signaling and the second response management signaling, it is determined that both the target emotional companionship smart device and the other smart devices meet the preset response requirement conditions, then the historical dialogue interaction situation is determined; if the historical dialogue interaction situation indicates that the target emotional companionship smart device responded first in the previous round of dialogue, then the response priority of the other smart devices is set to the highest; if the historical dialogue interaction situation indicates that the other smart devices responded first in the previous round of dialogue, then the response priority of the target emotional companionship smart device is set to the highest. That is, when both the local device and other devices meet the preset response requirement conditions, that is, when they all want to respond to the user, the historical dialogue interaction situation is retrieved; if the local device was the first responding device in the previous round, then the response priority of the other devices is increased; if the other devices responded first in the previous round, then the local device's priority is set to the highest. In this way, this embodiment integrates all response management signaling to uniformly determine the response order, and integrates the situation of each device, avoiding response conflicts caused by local scheduling of a single device. It drives multi-device collaborative response based on the response order of the target device, avoiding sound overlap and chaotic interaction caused by multiple devices outputting voice at the same time, making the multi-device emotional companionship dialogue clear and smooth, and improving the overall comfort and emotional continuity of human-computer interaction. Based on the response subject of the previous round, the highest priority of the current round is adjusted for rotation scheduling, so that multiple emotional companionship devices take turns to dominate the response, balancing the voice opportunities of each device, making the multi-device companionship dialogue alternate naturally, and preventing a single device from continuously dominating while other devices remain silent for a long time during long-term interaction, thus optimizing the balanced interactive experience of multi-machine collaborative companionship.

[0042] As can be seen from the above, in this embodiment of the application, the target emotional companionship smart device broadcasts its own first device information identification signaling at a preset frequency, and the other devices in the cluster send back a first confirmation signaling. After receiving the second device identification signaling and the first confirmation signaling periodically broadcast by other devices, the local device parses and updates its local list of interactive devices and sends a second confirmation signaling for the other devices to update their respective device lists. After receiving the target interaction command, the device performs emotion recognition processing, generates and broadcasts a first response management signaling based on the local device list, and simultaneously receives the second response management signaling generated by other devices after emotion parsing. The device response order is determined by combining the response management signaling, and multiple emotional companionship smart devices work together to complete the interactive response in order. In this way, through the above process of the embodiments of this application, the emotional companionship smart device periodically broadcasts device identification signaling at a preset fixed frequency, which can continuously synchronize the online status of devices in the cluster, avoiding the problem of devices being offline or new devices not being detected; after receiving an interaction command, it completes emotion recognition processing, analyzes the emotional appeal contained in the command, and ensures that the response matches the user's emotional needs; it generates broadcast response management signaling based on the local list of interactive devices, and synchronously receives response management signaling issued by other devices based on their own analysis results, and summarizes the response weight and capability information of all devices in the cluster; it integrates all response management signaling to uniformly determine the device response order, and orderly allocates the speaking and interaction timing of each emotional companionship device, avoiding sound overlap and interaction chaos caused by multiple devices responding at the same time, realizing orderly collaborative emotional interaction of multiple emotional companionship devices, improving the smoothness of interaction and the continuity of emotional experience in multi-device companionship scenarios, and thus realizing behavioral interaction and data interoperability between different emotional companionship smart products to improve the user experience.

[0043] Accordingly, see Figure 5 As shown, this application embodiment also provides a human-computer interaction device, applied to a target emotional companionship smart device in a target scenario, wherein the target scenario includes multiple emotional companionship smart devices, and the target emotional companionship smart device is any one of the multiple emotional companionship smart devices; wherein, the device includes: The signaling broadcast module 11 is used to generate and broadcast the first device information identification signaling of the target emotional companionship smart device based on a preset transmission frequency, so that other smart devices can feed back the corresponding first confirmation signaling based on the first device information identification signaling; the other smart devices are other smart devices among the plurality of emotional companionship smart devices besides the target emotional companionship smart device; The list update module 12 is used to parse the second device information identification signaling and update the local first interactive device list after receiving the second device information identification signaling and the first confirmation signaling, and to send back the corresponding second confirmation signaling so that the other smart devices can update the local second interactive device list according to the second confirmation signaling; the second device information identification signaling is a device information identification signaling generated and broadcast by the other smart devices based on a preset transmission frequency; The instruction processing module 13 is used to perform emotion recognition and processing on the target interaction instruction after receiving it, so as to generate and broadcast a first response management signaling according to the first list of interactive devices, and to receive a second response management signaling; the second response management signaling is a response management signaling generated and broadcast by the other smart devices according to the instruction analysis result and the second list of interactive devices; the instruction analysis result is the analysis result obtained by the other smart devices from performing emotion recognition and processing on the target interaction instruction; each of the response management signals is used to indicate the response order of device interaction and human-computer interaction among the multiple emotional companionship smart devices; The instruction response module 14 is used to determine the response order of the target device according to the first response management signaling and the second response management signaling, and to coordinate with the other smart devices to respond to the target interaction instruction according to the response order of the target device.

[0044] In some specific embodiments, the signaling broadcast module 11 may specifically include: An information determination unit is used to determine the device information of the target emotional companionship smart device; the device information includes device persona information, device identifier, namespace where the device identifier is located, and a current local list of first interactive devices; the device identifier is unique within the same namespace; The signaling generation unit is used to generate a first device information identification signaling for the target emotional companionship smart device using the device information and the current timestamp, and to broadcast the first device information identification signaling based on a preset transmission frequency.

[0045] In some specific embodiments, the list update module 12 may specifically include: The signaling parsing unit is used to parse the second device information identification signaling to determine the corresponding target device information; the target device information includes the target namespace, the target device identifier, the target timestamp, and the target person information; The information addition unit is used to add the target device information to the first interactive device list if there is no device in the local first interactive device list that matches the target namespace and the target device identifier; The information update unit is used to update the timestamp information of the corresponding device in the first interactive device list using the target timestamp if there is a device in the local first interactive device list that matches the target namespace and the target device identifier.

[0046] In some specific embodiments, the list update module 12 may further include: The device determination unit is used to determine the current system time and identify devices to be removed from the first list of interactive devices whose timestamps exceed a preset time threshold from the current system time. The information deletion unit is used to delete the device information related to the device to be removed from the first list of interactive devices.

[0047] In some specific embodiments, the instruction processing module 13 may specifically include: An emotion recognition unit is used to identify the target intent of the target interaction command, and to perform emotion recognition based on the target intent to obtain the corresponding recognition result; The profile update unit is used to perform security verification on the target interaction command. If the security verification is passed, the historical interaction memory of the target interaction command is retrieved and the current user profile is updated. The content generation unit is used to determine whether the current target emotional companionship smart device meets the preset response requirement conditions based on the user profile, the historical interaction memory, the recognition result and the target intent. If it does, the unit generates target response content for the target interaction command.

[0048] In some specific embodiments, the instruction processing module 13 may specifically include: The first situation determination unit is used to determine the historical dialogue and interaction information of the target emotional companionship smart device; The first signaling broadcasting unit is used to generate and broadcast a first response management signaling based on the first list of interactive devices, the historical dialogue interaction, and the target reply content if the target emotional companionship smart device meets the preset response requirement conditions. The second signaling broadcasting unit is used to generate and broadcast a first response management signaling based on the first list of interactive devices and the historical dialogue interaction if the target emotional companionship smart device does not meet the preset response requirement conditions.

[0049] In some specific embodiments, the instruction response module 14 may specifically include: The second situation determination unit is used to determine the historical dialogue interaction situation if, based on the first response management signaling and the second response management signaling, it is determined that both the target emotional companionship smart device and the other smart devices meet the preset response requirement conditions. The first priority setting unit is used to set the response priority of the other smart devices to the highest if the historical dialogue interaction situation indicates that the previous round of dialogue was responded to first by the target emotional companionship smart device. The second priority setting unit is used to set the response priority of the target emotional companionship smart device to the highest if the historical dialogue interaction situation indicates that the previous round of dialogue was responded to first by the other smart devices.

[0050] Furthermore, embodiments of this application also disclose an electronic device, Figure 6 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the human-computer interaction method disclosed in any of the foregoing embodiments. Furthermore, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0051] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0052] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon can include operating system 221, computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0053] The operating system 221 is used to manage and control the various hardware devices on the electronic device 20 and the computer program 222, which may be Windows Server, Netware, Unix, Linux, etc. In addition to including computer programs capable of performing the human-computer interaction methods executed by the electronic device 20 as disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs capable of performing other specific tasks.

[0054] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned human-computer interaction method. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0055] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0056] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0057] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0058] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0059] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A human-computer interaction method, characterized in that, A target emotional companionship smart device is applied to a target scenario, wherein the target scenario includes multiple emotional companionship smart devices, and the target emotional companionship smart device is any one of the multiple emotional companionship smart devices; wherein, the method includes: The first device information identification signaling of the target emotional companionship smart device is generated and broadcast based on a preset transmission frequency, so that other smart devices can send back corresponding first confirmation signaling based on the first device information identification signaling; the other smart devices are other smart devices besides the target emotional companionship smart device among the plurality of emotional companionship smart devices; Upon receiving the second device information identification signaling and the first confirmation signaling, the system parses the second device information identification signaling and updates the local first interactive device list, and sends back the corresponding second confirmation signaling so that the other smart devices can update their local second interactive device list according to the second confirmation signaling; the second device information identification signaling is a device information identification signaling generated and broadcast by the other smart devices based on a preset transmission frequency; Upon receiving a target interaction command, the system performs emotion recognition and processing on the command to generate and broadcast a first response management signaling based on the first list of interactive devices, and receives a second response management signaling. The second response management signaling is generated and broadcast by the other smart devices based on the command analysis result and the second list of interactive devices. The command analysis result is the analysis result obtained by the other smart devices through emotion recognition and processing of the target interaction command. Each response management signaling is used to indicate the response order of device interaction and human-computer interaction among the multiple emotional companionship smart devices. The response order of the target devices is determined based on the first response management signaling and the second response management signaling, and the other smart devices are coordinated to respond to the target interaction command based on the response order of the target devices.

2. The human-computer interaction method according to claim 1, characterized in that, The first device information identification signaling of the target emotional companionship smart device, generated and broadcast based on a preset transmission frequency, includes: The device information of the target emotional companionship smart device is determined; the device information includes device persona information, device identifier, namespace where the device identifier is located, and a current local list of first interactive devices; the device identifier is unique within the same namespace; The device information and the current timestamp are used to generate a first device information identification signaling for the target emotional companionship smart device, and the first device information identification signaling is broadcast based on a preset transmission frequency.

3. The human-computer interaction method according to claim 1, characterized in that, The step of parsing the second device information identification signaling and updating the local list of first interactive devices includes: The second device information identification signaling is parsed to determine the corresponding target device information; the target device information includes the target namespace, the target device identifier, the target timestamp, and the target persona information; If there is no device in the local first interactive device list that matches the target namespace and the target device identifier, then add the target device information to the first interactive device list; If a device matching the target namespace and the target device identifier exists in the local first interactive device list, then the timestamp information of the corresponding device in the first interactive device list is updated using the target timestamp.

4. The human-computer interaction method according to claim 1, characterized in that, The step of parsing the second device information identification signaling and updating the local first interactive device list further includes: Determine the current system time, and identify devices in the first list of interactive devices whose timestamps exceed a preset time threshold from the current system time that need to be removed; Remove the device information related to the device to be removed from the first list of interactive devices.

5. The human-computer interaction method according to any one of claims 1 to 4, characterized in that, The emotion recognition and processing of the target interaction command includes: Identify the target intent of the target interaction command, and perform emotion recognition based on the target intent to obtain the corresponding recognition result; The target interaction command is subjected to security verification. If the security verification passes, the historical interaction memory of the target interaction command is retrieved and the current user profile is updated. Based on the user profile, the historical interaction memory, the recognition result, and the target intent, it is determined whether the current target emotional companionship smart device meets the preset response requirement conditions. If it does, a target response content is generated for the target interaction command.

6. The human-computer interaction method according to claim 5, characterized in that, The step of generating and broadcasting the first response management signaling based on the first list of interactive devices includes: Determine the historical dialogue and interaction data of the target emotional companionship smart device; If the target emotional companionship smart device meets the preset response requirement conditions, then a first response management signaling is generated and broadcast based on the first interactive device list, the historical dialogue interaction information, and the target response content; If the target emotional companionship smart device does not meet the preset response requirements, a first response management signaling is generated and broadcast based on the first list of interactive devices and the historical dialogue interaction information.

7. The human-computer interaction method according to claim 6, characterized in that, Determining the target device's response order based on the first response management signaling and the second response management signaling includes: If, based on the first response management signaling and the second response management signaling, it is determined that the target emotional companionship smart device and the other smart devices all meet the preset response requirement conditions, then the historical dialogue interaction situation is determined. If the historical dialogue interaction indicates that the previous round of dialogue was responded to first by the target emotional companionship smart device, then the response priority of the other smart devices is set to the highest. If the historical dialogue interaction indicates that the previous round of dialogue was responded to first by the other smart devices, then the response priority of the target emotional companionship smart device is set to the highest.

8. A human-computer interaction device, characterized in that, A target emotional companionship smart device applied in a target scenario, wherein the target scenario includes multiple emotional companionship smart devices, and the target emotional companionship smart device is any one of the multiple emotional companionship smart devices; wherein the device includes: The signaling broadcast module is used to generate and broadcast the first device information identification signaling of the target emotional companionship smart device based on a preset transmission frequency, so that other smart devices can send back corresponding first confirmation signaling based on the first device information identification signaling; the other smart devices are other smart devices among the plurality of emotional companionship smart devices, excluding the target emotional companionship smart device; The list update module is used to, upon receiving the second device information identification signaling and the first confirmation signaling, parse the second device information identification signaling and update the local first interactive device list, and send back the corresponding second confirmation signaling, so that the other smart devices can update their local second interactive device list according to the second confirmation signaling; the second device information identification signaling is a device information identification signaling generated and broadcast by the other smart devices based on a preset transmission frequency; The instruction processing module is used to perform emotion recognition and processing on the target interaction instruction after receiving it, so as to generate and broadcast a first response management signaling according to the first list of interactive devices, and to receive a second response management signaling; the second response management signaling is a response management signaling generated and broadcast by the other smart devices according to the instruction analysis result and the second list of interactive devices; the instruction analysis result is the analysis result obtained by the other smart devices from performing emotion recognition and processing on the target interaction instruction; each of the response management signals is used to indicate the response order of device interaction and human-computer interaction among the multiple emotional companionship smart devices; The instruction response module is used to determine the response order of the target device based on the first response management signaling and the second response management signaling, and to coordinate with the other smart devices to respond to the target interaction instruction based on the response order of the target device.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the human-computer interaction method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store computer programs; wherein, when the computer programs are executed by a processor, they implement the human-computer interaction method as described in any one of claims 1 to 7.

Images