Conversation initiating method of electronic equipment and related device

Abstract

The invention provides a dialogue initiating method of electronic equipment and a related device, and the method comprises the following steps: detecting whether dialogue data input by a user is not received in a preset time period or not under the condition that the electronic equipment is in a wake-up state and the last round of dialogue is ended; if the dialogue data input by the user is not received within the preset time period, determining whether the electronic equipment meets an active dialogue initiating condition or not; determining that the electronic equipment meets the active dialogue initiation condition, and obtaining target dialogue data to be output by the electronic equipment; and controlling the electronic equipment to output the target dialogue data. According to the invention, the flexibility and intelligence of dialogue interaction of the electronic equipment can be improved.

Description

Dialogue initiation methods and related devices for electronic devices Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method for initiating a dialogue on an electronic device and related apparatus. Background Technology

[0002] Currently, the dialogue interaction method of smart pet toys is still limited to receiving the user's dialogue data and then responding accordingly. The voice dialogue mode pursues too much certainty and consistency, resulting in monotony and a lack of dynamism and realism. Moreover, in the owner dialogue mode, it still collects voice data and passively responds based on the user's questions. The interaction process is simple and rigid, and the intelligence of smart pet toys is low. Summary of the Invention

[0003] In view of this, this application provides a method for initiating a dialogue on an electronic device. When the electronic device is in a wake-up state, if the previous dialogue has ended and no dialogue data input by the user has been received within a certain period of time, it can be determined whether the electronic device meets the conditions for initiating an active dialogue. If the electronic device meets the conditions for initiating an active dialogue, it can be controlled to actively output target dialogue data, thereby improving the flexibility and intelligence of the dialogue interaction of the electronic device.

[0004] In a first aspect, this application provides a method for initiating a dialogue using an electronic device, the method comprising the following steps:

[0005] If the electronic device is in a wake-up state and the previous round of dialogue has ended, detect whether no dialogue data input by the user has been received within a preset time period.

[0006] If no dialogue data is received from the user within the preset time period, determine whether the electronic device meets the conditions for initiating an active dialogue.

[0007] Determine that the electronic device meets the conditions for initiating an active dialogue, and obtain the target dialogue data to be output by the electronic device;

[0008] Control the electronic device to output the target data content.

[0009] Optionally, determining whether the electronic device meets the conditions for initiating an active dialogue includes:

[0010] Obtain dialogue initiation condition confirmation parameters, which include at least one of the following: dialogue category of the previous round of dialogue, user category of the previous round of dialogue, development level of the electronic device, and probability of initiating a dialogue proactively.

[0011] Based on the dialogue initiation condition confirmation parameters, it is determined whether the electronic device meets the active dialogue initiation condition.

[0012] Optionally, determining whether the electronic device meets the active dialogue initiation condition based on the dialogue initiation condition confirmation parameter includes:

[0013] The dialogue category is determined to be non-verbal attack type, the cultivation level reaches the preset minimum level corresponding to the active dialogue initiation condition, and the user category of the previous round of dialogue is real user category.

[0014] Based on the probability of initiating an active dialogue, it is determined that the electronic device meets the conditions for initiating an active dialogue.

[0015] Optionally, acquiring the target dialogue data to be output by the electronic device includes:

[0016] Detect whether the electronic device contains any content to be reminded;

[0017] If the content to be reminded does not exist, the topic of the target dialogue data is determined based on the topic reference data. The topic reference data includes at least one of the following: historical dialogue content, the user's emotion tags, social habit data, and game data.

[0018] The target dialogue data is generated based on the topic.

[0019] Optionally, determining the topic of the target dialogue data based on topic reference data includes:

[0020] The historical dialogue content is used to detect topics of interest;

[0021] If no topic of interest is detected from the historical dialogue content, the topic of the target dialogue data is determined based on the emotion tag, the social habit data, or the game data.

[0022] Optionally, the method further includes:

[0023] If the electronic device has multiple items to be reminded, determine the priority of each item to be reminded;

[0024] Based on the priority of each of the items to be reminded, the target reminder item is determined from each of the items to be reminded;

[0025] Based on the target reminder content, the target dialogue data is generated.

[0026] Optionally, after controlling the electronic device to output the target data content, the method further includes:

[0027] The current dialogue round has been detected to have ended. Based on the time period in which the current dialogue round ended, the preset time period is adjusted.

[0028] Secondly, this application provides a dialogue initiation device for an electronic device, the dialogue initiation device for the electronic device comprising:

[0029] The interaction detection module is used to detect whether no user-input dialogue data has been received within a preset time period when the electronic device is in a wake-up state and the previous round of dialogue has ended.

[0030] The dialogue initiation condition determination module is used to determine whether the electronic device meets the active dialogue initiation condition if no dialogue data input by the user is received within the preset time period.

[0031] The dialogue data determination module is used to determine that the electronic device meets the conditions for initiating an active dialogue and to obtain the target dialogue data to be output by the electronic device.

[0032] An interactive execution module is used to control the electronic device to output the target data content.

[0033] Thirdly, this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in the dialogue initiation method of the electronic device provided in the embodiments of the present invention.

[0034] Fourthly, this application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in the dialogue initiation method of the electronic device provided in the embodiments of the present invention.

[0035] In this embodiment of the application, when the electronic device is in a wake-up state, if the previous round of dialogue has ended and no dialogue data input by the user has been received within a certain period of time, it can be determined whether the electronic device meets the conditions for initiating an active dialogue. If the electronic device meets the conditions for initiating an active dialogue, it can be controlled to actively output dialogue data, thereby improving the flexibility and intelligence of the electronic device's dialogue interaction. Attached Figure Description

[0036] 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 some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0037] Figure 1 is a flowchart of a dialogue initiation method for an electronic device provided in an embodiment of this application;

[0038] Figure 2 is a schematic diagram of the dialogue interaction of the electronic device provided in the embodiment of this application;

[0039] Figure 3 is a schematic diagram of the structure of a dialogue initiation device for an electronic device provided in an embodiment of this application;

[0040] Figure 4 is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0041] 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 a part of the embodiments of the present invention, and not all of them. 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.

[0042] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0043] In this document, references to "embodiment" or "implementation" mean that a particular feature, structure, or characteristic described in connection with an embodiment or implementation may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0044] Referring to Figure 1, which is a flowchart of a dialogue initiation method for an electronic device according to an embodiment of this application, the dialogue initiation method for the electronic device includes the following steps:

[0045] 101. When the electronic device is in a wake-up state and the previous round of dialogue has ended, detect whether no dialogue data input by the user has been received within a preset time period.

[0046] In this embodiment of the invention, the aforementioned electronic device is an electronic device equipped with electronic components such as a processor and capable of sensing and interactive response through data interaction. For example, the electronic device may include a smart pet toy, wherein the smart pet toy has multiple degrees of freedom, is capable of simulating the form and behavior of a real pet, and can also perform interactive operations in response to user commands such as actions, voice, and touch. The electronic device can be applied to scenarios such as learning assistance and fun interaction.

[0047] The aforementioned method for initiating dialogue on electronic devices can be applied to servers, establishing communication connections between servers and electronic devices. In another application scenario, the method for initiating dialogue on electronic devices can also be applied to electronic devices themselves.

[0048] The above-mentioned wake-up can be understood as the process by which a user activates an electronic device in a specific way, such as through voice wake-up commands, touch wake-up operations, etc.

[0049] There are several ways to determine if a previous conversation has ended, such as: 1. Detecting keywords or sentences indicating the end of the conversation in the conversation data output by the electronic device; 2. Detecting keywords or sentences indicating the end of the conversation data in the conversation data input by the user; 3. Not receiving any conversation data input by the user within a certain time period after the electronic device outputs the conversation data. For example, if the user's input conversation data contains keywords such as "goodbye" or "end chat," it is determined that the previous conversation has ended; or if the electronically output conversation data contains examples indicating the end of the conversation, such as "That's all for today's chat" or "Call me if you need anything," it is determined that the previous conversation has ended.

[0050] The preset time period can be a fixed value, or it can be dynamically determined based on the conversation in the previous round.

[0051] 102. If no dialogue data is received from the user within a preset time period, determine whether the electronic device meets the conditions for initiating an active dialogue.

[0052] Electronic devices are not always ready to initiate a conversation. For example, if an electronic device's feeding level does not meet the minimum feeding level requirement for initiating a conversation, it is not ready to initiate a conversation. Or, if the device sensed malice or an attack in the previous conversation, it indicates that it is not appropriate to interact with the user in the short term, and therefore it is not ready to initiate a conversation.

[0053] In other words, it can be determined from multiple dimensions, such as the dialogue situation in the previous round and whether the electronic device's own feeding level has reached the preset minimum level for initiating an active dialogue.

[0054] 103. Determine if the electronic device meets the conditions for initiating an active dialogue, and obtain the target dialogue data to be output by the electronic device.

[0055] The target dialogue data can be obtained by first determining the topic of the target data, and then generating target dialogue data based on that topic. The target dialogue data can be questions, such as open-ended guiding questions, which can promote multi-turn interactions.

[0056] 104. Control the electronic device to output target dialogue data.

[0057] Specifically, the speaker of the control electronic device outputs the corresponding target dialogue data. As shown in Figure 2, the target dialogue data output by the control electronic device 10 is "Little master, do you want to sing with me?"

[0058] Specifically, the system can output target dialogue data with a specific tone, or overlay corresponding sound effects during the output of the target dialogue data. For example, the tone can be lively, gentle, or languid. Furthermore, the electronic device can select a corresponding timbre when outputting the target dialogue data to match the device's role and positioning.

[0059] In this embodiment of the invention, when the electronic device is in a wake-up state, if the previous round of dialogue has ended and no dialogue data input by the user has been received within a certain period of time, it can be determined whether the electronic device meets the conditions for initiating an active dialogue. If the electronic device meets the conditions for initiating an active dialogue, it can be controlled to actively output dialogue data, thereby improving the flexibility and intelligence of the electronic device's dialogue interaction.

[0060] It is understood that in the specific implementation of this application, any data related to personal information, such as historical dialogue content, emotion tags, social habit data, and game data, is involved. When the embodiments in this application are applied to specific products or technologies, user permission or consent is required. Furthermore, the collection, use, and processing of related data, as well as the training, deployment, and invocation of algorithm models, must comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0061] Optionally, the above method for determining whether an electronic device meets the conditions for initiating an active dialogue may be: obtaining dialogue initiation condition confirmation parameters, which include at least one of the following: the dialogue category of the previous round of dialogue, the user category of the previous round of dialogue, the development level of the electronic device, and the probability of initiating an active dialogue; and determining whether the electronic device meets the conditions for initiating an active dialogue based on the dialogue initiation condition confirmation parameters.

[0062] The previous round of dialogue can be categorized as either verbal or non-verbal. Specifically, if the previous round of dialogue data contains insulting, malicious, or offensive language, the previous round of dialogue is classified as verbal attack; conversely, if the previous round of dialogue data does not contain insulting, malicious, or offensive language, the previous round of dialogue is classified as non-verbal attack.

[0063] For example, during each round of dialogue, after receiving the dialogue data input by the user, natural language processing technology can be used to identify whether the dialogue data contains insulting, malicious, or offensive language. If so, the dialogue type of this round is marked as language attack, so that the electronic device can subsequently determine the dialogue type of the previous round by querying the mark. Alternatively, after determining that the previous round of dialogue has ended, natural language processing technology can be used again to identify whether the dialogue data input by the user in the previous round contained insulting, malicious, or offensive language.

[0064] The aforementioned natural language processing technologies aim to enable machines to understand, interpret, and generate human language, achieving effective communication between humans and machines, and enabling computers to perform tasks such as language translation, sentiment analysis, and text summarization.

[0065] The user category in the previous round of dialogue can include real user categories and non-real user categories. A real user category indicates that the voice was spoken by the user and the electronic device in the same context and in real time, while a non-real user category indicates that the voice was not spoken in real time. Examples of non-real user categories include recorded playback categories and speech synthesis categories. If the user category is non-real user category, it means that the electronic device did not need to initiate the dialogue. The user category can be determined by extracting dynamic voiceprint features from the user's input voice data during the previous round of dialogue. Dynamic voiceprint features can include, but are not limited to, tone fluctuations and speech rate changes.

[0066] Furthermore, in addition to the actual user categories, the user category can be further differentiated based on whether the user in the previous round of dialogue was the owner of the electronic device. For example, the voiceprint features extracted from the user's input data in the previous round of dialogue are matched with voiceprint features in the owner's voiceprint database. If a matching voiceprint feature exists, the user category in the previous round of dialogue is determined to be the owner. Once the electronic device detects dialogue data input by the owner, it can switch to owner mode. In owner mode, interaction can be based on the owner's historical interaction data (such as interaction records and preferences), while in non-owner mode, the user's identity is not distinguished, providing standardized basic functions and possessing universal applicability.

[0067] The development level of electronic devices is related to their feeding. The more diverse the types of food provided and the more frequently they are fed, the higher the development level of the electronic device.

[0068] The probability of initiating a conversation can characterize the likelihood that an electronic device will initiate a conversation. It can be a fixed value or dynamically adjusted based on the conversation's context. For example, the initial probability of initiating a conversation can be n%, which can be iteratively adjusted based on the historical interaction frequency with the user. For instance, if the frequency of initiating conversations by the electronic device in the past m days is less than x times / day, the probability of initiating a conversation can be increased. Conversely, if the frequency is greater than or equal to a times / day in the past m days, the probability of initiating a conversation can be decreased, where a is greater than x. This balances the interactivity of the electronic device with its potential to disturb the user.

[0069] The above method of determining whether an electronic device meets the conditions for initiating an active dialogue based on the dialogue initiation condition confirmation parameters can be: judging whether at least some or all of the dialogue initiation condition confirmation parameters meet their respective conditions; if so, then the electronic device is determined to meet the conditions for initiating an active dialogue.

[0070] In the above solution, by determining whether the electronic device meets the conditions for initiating an active dialogue from multiple dimensions, it is possible to reduce potential disturbances to users while improving the interactive flexibility of the electronic device, thereby achieving a balance between the interactive flexibility of the electronic device and the disturbance to users.

[0071] Optionally, the above method for determining whether an electronic device meets the conditions for initiating an active dialogue based on the dialogue initiation condition confirmation parameters can be as follows: determining that the dialogue category is non-verbal attack type, the cultivation level reaches the preset minimum level corresponding to the active dialogue initiation condition, and the user category in the previous round of dialogue is a real user category; and determining that the electronic device meets the conditions for initiating an active dialogue based on the active dialogue initiation probability.

[0072] The dialogue category being non-verbal attack type indicates that the user is currently suitable for interaction; the cultivation level reaching the preset minimum level corresponding to the conditions for initiating an active dialogue indicates that the electronic device has the authority to initiate a dialogue; and the user category of the previous round of dialogue being a real user category indicates that the person interacting with the electronic device is the actual user and not a recording or other non-real user. If all three conditions are met, it indicates that the electronic device can initiate an active dialogue.

[0073] Considering that electronic devices may disturb users if they initiate conversations too frequently, in order to ensure a balance between the interactivity of electronic devices and the disturbance to users, if an electronic device is determined to initiate a conversation based on the probability of initiating a conversation, then the electronic device is determined to meet the conditions for initiating a conversation. If it is determined not to initiate a conversation based on the probability of initiating a conversation, then the electronic device is determined not to meet the conditions for initiating a conversation.

[0074] In one possible embodiment, an interaction score between the user and the electronic device can also be obtained, and it can be determined whether the user in the previous round of dialogue is the owner of the electronic device. Furthermore, if the dialogue category is determined to be non-verbal attack type, the user level reaches the preset minimum level corresponding to the active dialogue initiation condition, the interaction score is greater than or equal to a preset interaction score, and the user category in the previous round of dialogue is a real user category and the owner of the electronic device; based on the active dialogue initiation probability, it can be determined that the electronic device meets the active dialogue initiation condition.

[0075] Interaction scores can be related to the frequency of conversations between users and electronic devices, as well as the duration or depth of each conversation.

[0076] In the above solution, by determining whether the timing of the electronic device initiating a dialogue is appropriate from multiple dimensions, it is possible to reduce disturbance to the user while improving the flexibility of electronic device interaction.

[0077] Optionally, the above method for obtaining the target dialogue data to be output by the electronic device may be: detecting whether the electronic device has content to be reminded; if there is no content to be reminded, determining the topic of the target dialogue data based on topic reference data, wherein the topic reference data includes at least one of the following: historical dialogue content, user's emotion tags, social habit data, and game data; and generating target dialogue data based on the topic.

[0078] The reminders can include, but are not limited to, schedule reminders, health reminders, interactive reminders, and feeding reminders. Schedule reminders include reminders for walking, health reminders include reminders for cleaning toys, and reminders for user eye health. Interactive reminders include wake-up prompts for long-term inactivity, and feeding reminders include reminders for feeding or hydrating electronic devices.

[0079] Among them, it can retrieve the cached and / or cloud-synchronized list of reminders to determine whether there are any reminders on the electronic device within a certain time period (e.g., half an hour) from the current time.

[0080] Historical dialogue content can include dialogue data from previous rounds or more. For example, the historical dialogue content can be used to detect topics of interest, and the topic of the target dialogue data can be determined based on the detected topics of interest. For instance, the extracted topics of user interest can be used as the topic of the target dialogue data. For example, if the topics of interest are "yesterday's park" or "the new toy," then the target dialogue data generated based on these topics could be an open-ended guiding question, such as "Do you remember that special flower in the park yesterday?" Open-ended guiding questions can promote the continuation of multi-round interactions.

[0081] User emotion tags can be used to characterize a user's emotions in the previous round of conversation. For example, a user's emotion can be determined by the tone of voice and emotional keywords in the user's input data from the previous round of conversation. For instance, if a user is determined to be in a low mood (such as "unhappy" or "sad"), the topic can be identified as a comforting topic, and the target dialogue data generated based on this topic could be "Want to hear me sing a song?" or "Want to play hide-and-seek with me?" If the user is in a high mood, the topic can be identified as a sharing topic, and the target dialogue data generated based on this topic could be "What was your happiest moment today?".

[0082] Social habit data can be used to characterize users' interaction habits. For example, a user often asks about science popularization around 7 pm, but today, after the conversation ended at 6 pm, the user did not ask about science popularization as usual. Therefore, the topic determined based on this social habit data can be a question topic targeting this social habit. The target dialogue data generated based on this topic could be, "Little master, why didn't you continue to ask me about science popularization about xxx today?"

[0083] Game data can include, but is not limited to, game types and / or game progress associated with electronic devices. For example, electronic devices can access a dynamically updated, lightweight game library containing games like riddles, idiom games, and guessing animals / song titles. Topics can be intelligently recommended based on user tags (such as age, gender, and interests) (e.g., recommending "guess animals" for children and "guess song titles" or "guess movies" for adults). The generated target dialogue could be something like, "Little master, shall we play the animal guessing game together?". If a user hasn't finished a game (e.g., one riddle question remaining), they can be given priority to continue playing that game, with the generated target dialogue being, "There's one riddle left from the last game, want to try again?".

[0084] The method for determining the topic of the target dialogue data based on the topic reference data mentioned above can be: selecting one topic reference data from multiple topic reference data, and determining the topic of the target dialogue data based on the selected topic reference data.

[0085] The above solution provides a variety of topic reference data, making the topics available to electronic devices more diverse and further improving the flexibility of electronic device interaction.

[0086] Optionally, the above method of determining the topic of the target dialogue data based on topic reference data can be: detecting topics of interest in historical dialogue content; if no topics of interest are detected in historical dialogue content, determining the topic of the target dialogue data based on emotion tags, social habit data, or game data.

[0087] The process involves segmenting historical dialogue content into words, then clustering each word to obtain multiple candidate topics of interest corresponding to each cluster. If no cluster has a popularity greater than or equal to a preset popularity, it is determined that no topic of interest was detected from the historical dialogue content. If a cluster has a popularity greater than or equal to a preset popularity, the candidate topic of interest corresponding to the cluster with the highest popularity can be used as the topic of interest detected from the historical dialogue content, or the candidate topics of interest corresponding to several clusters with relatively high popularity can be used as the topic of interest detected from the historical dialogue content.

[0088] Alternatively, the historical dialogue content can be directly input into a pre-trained topic extraction model. The topic extraction model performs contextual semantic analysis on the historical dialogue content to obtain several candidate topics of interest and their confidence levels. If there are no candidate topics of interest with a confidence level greater than or equal to the preset confidence level, it is determined that no topic of interest has been detected from the historical dialogue content. If there are candidate topics of interest with a confidence level greater than or equal to the preset confidence level, the candidate topic of interest with the highest confidence level or several candidate topics of interest with relatively high confidence levels can be taken as the topic of interest.

[0089] The above-mentioned method of determining the topic of target dialogue data based on emotion tags, social habit data, or game data can be to select the topic reference data corresponding to the highest priority of emotion tags, social habit data, or game data to determine the topic of target dialogue data.

[0090] In the above scheme, in order to ensure the continuity of topics between multiple rounds of dialogue, it is advisable to prioritize finding topics from historical dialogues. If the historical dialogues were initiated randomly by the user, the topic of the target dialogue data can be determined based on other topic reference data.

[0091] Optionally, the method further includes: if there are multiple items to be reminded on the electronic device, determining the priority of each item to be reminded; determining the target reminder item from the items to be reminded based on the priority of each item to be reminded; and generating target dialogue data based on the target reminder item.

[0092] The method for determining the priority of each reminder can be as follows: First, sort the reminders according to the time interval between the reminder and the current time to determine the reminders that belong to the first priority. For example, urgent matters that are ≤5 minutes away from the current time belong to the first priority. If there are multiple reminders that belong to the first priority, and at least some of them belong to different categories, then sort the reminders that belong to the first priority according to the preset weight of "feeding > schedule > health > interaction". Add the reminder with the highest weight in the first priority to the second priority queue. If there are multiple reminders in the second priority queue, one of them can be randomly selected as the target reminder.

[0093] The method for generating target dialogue data based on the target reminder content described above can be as follows: combining the target reminder content with the corresponding reminder template to obtain the target dialogue data. For example, the generated target dialogue data could be "It's time to feed me."

[0094] This system can not only control the output of target dialogue data by electronic devices, but also push visual reminder cards to terminal devices associated with the electronic devices, including task details and interactive buttons (such as "Completed" and "Postponed Reminder"), thus achieving a closed-loop information flow across multiple terminals. Terminal devices associated with electronic devices refer to devices containing applications logged into by the user accounts linked to the electronic devices.

[0095] In the above solution, by determining the target dialogue data by referring to the priority of each reminder, it is possible to ensure that more urgent or important matters are promptly communicated to the user, making it easier for the user to handle them.

[0096] Optionally, after controlling the electronic device to output the target dialogue data, the method further includes: detecting that the current dialogue has ended, and adjusting the preset time period according to the time period in which the end time of the current dialogue is located.

[0097] If the current dialogue ends during nighttime, the preset time period will be adjusted to the preset time period corresponding to nighttime. If the current dialogue ends during daytime active hours, the preset time period will be adjusted to the preset time period corresponding to daytime active hours.

[0098] The preset time period for daytime active periods is longer than that for nighttime active periods. This reduces the probability of users being woken up by initiating conversations from electronic devices after ending a conversation at night, while the longer time allowed during daytime active periods provides a window for users to respond, reducing the likelihood of electronic devices initiating conversations that could lead to topic changes or disrupt users' thinking.

[0099] In the above scheme, setting corresponding preset time periods for different time periods can balance the interactive flexibility of electronic devices with the disturbance to users.

[0100] Optionally, if it is detected that the user has not interacted with the electronic device for an extended period of time, the electronic device can be controlled to enter a dormant state. Before entering the dormant state, resource reclamation operations can be performed, such as disabling unnecessary voice recognition modules to reduce the computing power consumption of the electronic device. In addition, user feedback data (such as whether a response was triggered, response duration, user preferences for topic types, etc.) can be recorded before entering the dormant state for subsequent iteration of proactive interaction strategies (such as adjusting topic weights, the range of probabilities for initiating proactive dialogues, etc.).

[0101] Please refer to Figure 3, which is a schematic diagram of the structure of a dialogue initiation device for an electronic device according to an embodiment of this application. The dialogue initiation device for the electronic device includes:

[0102] The interaction detection module 201 is used to detect whether no dialogue data input by the user has been received within a preset time period when the electronic device is in a wake-up state and the previous round of dialogue has ended.

[0103] The dialogue initiation condition determination module 202 is used to determine whether the electronic device meets the active dialogue initiation condition if no dialogue data input by the user is received within the preset time period.

[0104] The dialogue data determination module 203 is used to determine that the electronic device meets the conditions for initiating an active dialogue and to obtain the target dialogue data to be output by the electronic device.

[0105] The interactive execution module 204 is used to control the electronic device to output the target data content.

[0106] Optionally, in determining whether the electronic device meets the conditions for initiating an active dialogue, the dialogue initiation condition determination module 202 is specifically used for:

[0107] Obtain dialogue initiation condition confirmation parameters, which include at least one of the following: dialogue category of the previous round of dialogue, user category of the previous round of dialogue, development level of the electronic device, and probability of initiating a dialogue proactively.

[0108] Based on the dialogue initiation condition confirmation parameters, it is determined whether the electronic device meets the active dialogue initiation condition.

[0109] Optionally, in the operation of determining whether the electronic device meets the active dialogue initiation condition based on the dialogue initiation condition confirmation parameter, the dialogue initiation condition determination module 202 is specifically used for:

[0110] The dialogue category is determined to be non-verbal attack type, the cultivation level reaches the preset minimum level corresponding to the active dialogue initiation condition, and the user category of the previous round of dialogue is real user category.

[0111] Based on the probability of initiating an active dialogue, it is determined that the electronic device meets the conditions for initiating an active dialogue.

[0112] Optionally, in the operation of acquiring the target dialogue data to be output by the electronic device, the dialogue data determination module 203 is specifically used for:

[0113] Detect whether the electronic device contains any content to be reminded;

[0114] If the content to be reminded does not exist, the topic of the target dialogue data is determined based on the topic reference data. The topic reference data includes at least one of the following: historical dialogue content, the user's emotion tags, social habit data, and game data.

[0115] The target dialogue data is generated based on the topic.

[0116] Optionally, in the operation of determining the topic of the target dialogue data based on topic reference data, the dialogue data determination module 203 is specifically used for:

[0117] The historical dialogue content is used to detect topics of interest;

[0118] If no topic of interest is detected from the historical dialogue content, the topic of the target dialogue data is determined based on the emotion tag, the social habit data, or the game data.

[0119] Optionally, the dialogue data determination module 203 is further configured to:

[0120] If the electronic device has multiple items to be reminded, determine the priority of each item to be reminded;

[0121] Based on the priority of each of the items to be reminded, the target reminder item is determined from each of the items to be reminded;

[0122] Based on the target reminder content, the target dialogue data is generated.

[0123] Optionally, after controlling the electronic device to output the target data content, the interaction detection module 201 is further configured to:

[0124] The current dialogue round has been detected to have ended. Based on the time period in which the current dialogue round ended, the preset time period is adjusted.

[0125] Please refer to Figure 4, which is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. This application also provides an electronic device, including: a memory 302, a processor 301, and a computer program stored in the memory 302 and executable on the processor 301. When the processor 301 executes the computer program, it implements the steps in the dialogue initiation method of the electronic device provided in this embodiment of the application.

[0126] When processor 301 runs the computer program for the dialog initiation method of an electronic device stored in memory 302, it specifically performs the following steps:

[0127] If the electronic device is in a wake-up state and the previous round of dialogue has ended, detect whether no dialogue data input by the user has been received within a preset time period.

[0128] If no dialogue data is received from the user within the preset time period, determine whether the electronic device meets the conditions for initiating an active dialogue.

[0129] Determine that the electronic device meets the conditions for initiating an active dialogue, and obtain the target dialogue data to be output by the electronic device;

[0130] Control the electronic device to output the target data content.

[0131] Optionally, the process of determining whether the electronic device meets the conditions for initiating an active dialogue, executed by the processor 301, includes:

[0132] Obtain dialogue initiation condition confirmation parameters, which include at least one of the following: dialogue category of the previous round of dialogue, user category of the previous round of dialogue, development level of the electronic device, and probability of initiating a dialogue proactively.

[0133] Based on the dialogue initiation condition confirmation parameters, it is determined whether the electronic device meets the active dialogue initiation condition.

[0134] Optionally, the process executed by processor 301 to determine whether the electronic device meets the active dialogue initiation condition based on the dialogue initiation condition confirmation parameters includes:

[0135] The dialogue category is determined to be non-verbal attack type, the cultivation level reaches the preset minimum level corresponding to the active dialogue initiation condition, and the user category of the previous round of dialogue is real user category.

[0136] Based on the probability of initiating an active dialogue, it is determined that the electronic device meets the conditions for initiating an active dialogue.

[0137] Optionally, the step of acquiring the target dialogue data to be output by the electronic device, performed by the processor 301, includes:

[0138] Detect whether the electronic device contains any content to be reminded;

[0139] If the content to be reminded does not exist, the topic of the target dialogue data is determined based on the topic reference data. The topic reference data includes at least one of the following: historical dialogue content, the user's emotion tags, social habit data, and game data.

[0140] The target dialogue data is generated based on the topic.

[0141] Optionally, the processor 301 executes the topic-based reference data to determine the topic of the target dialogue data, including:

[0142] The historical dialogue content is used to detect topics of interest;

[0143] If no topic of interest is detected from the historical dialogue content, the topic of the target dialogue data is determined based on the emotion tag, the social habit data, or the game data.

[0144] Optionally, the method executed by processor 301 further includes:

[0145] If the electronic device has multiple items to be reminded, determine the priority of each item to be reminded;

[0146] Based on the priority of each of the items to be reminded, the target reminder item is determined from each of the items to be reminded;

[0147] Based on the target reminder content, the target dialogue data is generated.

[0148] Optionally, after controlling the electronic device to output the target data content, the method executed by the processor 301 further includes:

[0149] The current dialogue round has been detected to have ended. Based on the time period in which the current dialogue round ended, the preset time period is adjusted.

[0150] In addition, this embodiment of the invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by the processor 301, it implements the various processes of the dialogue initiation method of the electronic device provided in this embodiment of the invention and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0151] Those skilled in the art will understand that implementing all or part of the processes in the above embodiments can be accomplished by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0152] In this application, the terms "embodiment" and "implementation" mean that a specific feature, structure, or characteristic described in connection with an embodiment can be included in at least one embodiment of this application. The appearance of these phrases in various locations throughout the specification does not necessarily refer to the same embodiment, nor are they independent or alternative embodiments mutually exclusive with other embodiments. Those skilled in the art will understand, explicitly and implicitly, that the embodiments described in this application can be combined with other embodiments. Furthermore, it should be understood that the features, structures, or characteristics described in the various embodiments of this application can be arbitrarily combined to form another embodiment that does not depart from the spirit and scope of the technical solution of this application, provided there is no contradiction between them.

[0153] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to the above preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions to the technical solutions of this application should not depart from the spirit and scope of the technical solutions of this application.

Claims

1. A method for initiating a dialogue on an electronic device, characterized in that, The method includes the following steps: when the electronic device is in a wake-up state and the previous round of dialogue has ended, detect whether no dialogue data input by the user has been received within a preset time period; if no dialogue data input by the user has been received within the preset time period, determine whether the electronic device meets the conditions for initiating an active dialogue; if the electronic device meets the conditions for initiating an active dialogue, obtain the target dialogue data to be output by the electronic device; control the electronic device to output the target data content.

2. The method as described in claim 1, characterized in that, Determining whether the electronic device meets the conditions for initiating an active dialogue includes: obtaining dialogue initiation condition confirmation parameters, wherein the dialogue initiation condition confirmation parameters include at least one of the following: the dialogue category of the previous round of dialogue, the user category of the previous round of dialogue, the development level of the electronic device, and the probability of initiating an active dialogue; and determining whether the electronic device meets the conditions for initiating an active dialogue based on the dialogue initiation condition confirmation parameters.

3. The method as described in claim 2, characterized in that, The step of determining whether the electronic device meets the active dialogue initiation conditions based on the dialogue initiation condition confirmation parameters includes: determining that the dialogue category is non-verbal attack type, the cultivation level reaches the preset minimum level corresponding to the active dialogue initiation conditions, and the user category of the previous round of dialogue is a real user category; and determining that the electronic device meets the active dialogue initiation conditions based on the active dialogue initiation probability.

4. The method according to any one of claims 1 to 3, characterized in that, The step of obtaining the target dialogue data to be output by the electronic device includes: detecting whether the electronic device has content to be reminded; if there is no content to be reminded, determining the topic of the target dialogue data based on topic reference data, wherein the topic reference data includes at least one of the following: historical dialogue content, the user's emotion tags, social habit data, and game data; and generating the target dialogue data according to the topic.

5. The method as described in claim 4, characterized in that, The step of determining the topic of the target dialogue data based on topic reference data includes: detecting topics of interest in the historical dialogue content; if no topics of interest are detected in the historical dialogue content, determining the topic of the target dialogue data based on the emotion tag, the social habit data, or the game data.

6. The method as described in claim 4, characterized in that, The method further includes: if the electronic device has multiple items to be reminded, determining the priority of each item to be reminded; determining a target reminder item from the items to be reminded according to the priority of each item to be reminded; and generating the target dialogue data according to the target reminder item.

7. The method according to any one of claims 1 to 3, characterized in that, After controlling the electronic device to output the target data content, the method further includes: detecting that the current round of dialogue has ended, and adjusting the preset time period according to the time period in which the end time of the current round of dialogue is located.

8. A dialogue initiation device for an electronic device, characterized in that, The dialogue initiation device of the electronic device includes: an interaction detection module, used to detect whether no dialogue data input by the user has been received within a preset time period when the electronic device is in a wake-up state and the previous round of dialogue has ended; a dialogue initiation condition determination module, used to determine whether the electronic device meets the active dialogue initiation condition if no dialogue data input by the user has been received within the preset time period; a dialogue data determination module, used to determine that the electronic device meets the active dialogue initiation condition and obtain the target dialogue data to be output by the electronic device; and an interaction execution module, used to control the electronic device to output the target data content.

9. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the dialogue initiation method of the electronic device as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the dialogue initiation method of an electronic device as described in any one of claims 1 to 7.

Images