Assisted conversation method, apparatus, eye-mountable device, and program product

Abstract

The application relates to the field of intelligent devices, in particular to an auxiliary conversation method and device, an eye wearable device and a program product. The method comprises the following steps: collecting voice data in a conversation scene; analyzing the voice data to obtain auxiliary information, wherein the auxiliary information comprises at least one of a knowledge label, a character label, a question and answer label and a suggestion label; and displaying the auxiliary information in a first preset display area of the eye wearable device, so that the data information displayed by the eye wearable device can be greatly reduced, and the auxiliary information obtained by analyzing the voice data can be effectively used to assist the user in conversation, and the use experience of the user in using the eye wearable device to assist the conversation can be improved.

Description

Technical Field

[0001] This application relates to the field of smart devices, and more particularly to an assistive conversation method, device, eye-wearable device, and application product. Background Technology

[0002] Eye-worn wearable devices typically refer to smart devices worn on the head in the form of glasses or similar glasses, integrating display, computing, sensing, and communication functions. The core goal of eye-worn wearable devices is to achieve immersive or enhanced human-computer interaction experiences, seamlessly integrating digital information with the physical world.

[0003] Current eye-wearable devices typically use transcription to convert speech streams into text for display during human-computer interaction. This results in a large amount of content on the screen, which can easily lead to information overload and is not conducive to improving the user experience. Summary of the Invention

[0004] In view of this, embodiments of this application provide an auxiliary conversation method, device, eye-wearable device, and program product to solve the problem that information overload is easily caused when using eye-wearable devices for human-computer interaction in the prior art, which is not conducive to improving the user experience.

[0005] A first aspect of this application provides an auxiliary session method, the method comprising: Collect voice data in conversational scenarios; The voice data is analyzed to obtain auxiliary information, which includes at least one of knowledge tags, person tags, question-and-answer tags, and suggestion tags; The auxiliary information is displayed in a first preset display area of ​​the wearable eye device.

[0006] A second aspect of this application provides an auxiliary session method, the method comprising: Collect voice data in conversational scenarios; The voice data is analyzed to obtain auxiliary information, which includes at least one of knowledge tags, person tags, question and answer tags, suggestion tags, insight tags, and goal achievement tags. The auxiliary information is displayed in a first preset display area of ​​the wearable eye device.

[0007] In a possible implementation, after displaying the auxiliary information in the first preset display area of ​​the eye-wearable device, the method further includes: triggering the auxiliary information and displaying associated information corresponding to the auxiliary information on the eye-wearable device; wherein, triggering the auxiliary information and displaying the associated information corresponding to the auxiliary information on the eye-wearable device includes at least one of the following steps: Triggering the knowledge tag displays the explanation of the term associated with the knowledge tag; When the character tag is triggered, the introductory information of the character associated with the character tag is displayed; When the question-and-answer tag is triggered, suggested answers to the questions associated with the question-and-answer tag are displayed; When the suggestion tag is triggered, the session guidance information of the session content associated with the suggestion tag is displayed.

[0008] In possible implementations, the voice data is analyzed to obtain auxiliary information, including: The auxiliary information also includes insight tags. The voice data is analyzed to determine the insight tags corresponding to the conversation content. The insight tags are used to indicate at least one of the following: the focus information of the conversation content, the situational awareness information of the conversation content, the risk assessment information of the conversation content, and the action guidance information of the conversation content.

[0009] In a possible implementation, after analyzing the voice data and determining the insight tags included in the conversation content, the method further includes: Based on the insight tags, corresponding action suggestion information is generated, which includes at least one of the following: to-do list information, preparation information, and communication plan.

[0010] In a possible implementation, after acquiring voice data from the conversational scenario, the method further includes: Monitor the conversation events included in the voice data, and generate target achievement labels corresponding to the conversation events in the first preset display area.

[0011] In possible implementations, the session events include at least one of the following: response missing event, information conflict event, critical signal event, and target deviation event; Monitor the conversation events included in the voice data, and generate target achievement labels corresponding to the conversation events in the first preset display area, including at least one of the following: When the conversation event included in the voice data is a response missing event, the question raised by the other party is obtained, and the corresponding reference answer is retrieved from the preset database. The reference answer is then displayed in the first preset display area, or the question and the reference answer are displayed. When the conversation event included in the voice data is detected to be an information conflict event, the user's current statement is compared with the reference information, preset permissions or preset capability boundaries, and a difference prompt and / or correction suggestion is displayed in the first preset display area; When the conversation event included in the voice data is detected to be a key signal event, the corresponding response strategy or advance speech is displayed in the first preset display area; When the conversation event included in the voice data is detected to be a target deviation event, it is determined whether the preset conversation target has been completed, whether the conversation is about to end, whether there are any unresolved issues in the discussed matters, or whether there are any events with higher priority than the existing prompts. Corresponding reminder information or supplementary prompts are then displayed in the first preset display area.

[0012] In a possible implementation, triggering the auxiliary information and displaying associated information corresponding to the auxiliary information on the eye-wearable device includes: Receive an activation command for auxiliary information, display associated information corresponding to the auxiliary information according to the activation command, and close the associated information after receiving a deactivation command; Alternatively, the auxiliary information can be updated based on the parsing of the voice data, automatically triggering the display of associated information corresponding to the updated auxiliary information, and automatically closing the associated information after a first predetermined duration of continuous display.

[0013] In a possible implementation, displaying the auxiliary information in the first preset display area of ​​the eye-wearable device includes: When new auxiliary information is obtained from the analysis, the new auxiliary information is displayed at the top of the list of auxiliary information in the first preset display area.

[0014] In a possible implementation, after acquiring voice data in the conversation scenario, the method further includes: The voice data is analyzed to generate topic tags, which are tags determined by the topic corresponding to the voice data; Based on the analysis, the current topic tags are updated and displayed in real time in the second preset display area.

[0015] In a possible implementation, after updating and displaying the current topic tag in real time in the second preset display area based on the analysis, the method further includes: Upon receiving the trigger instruction of the topic tag, the system jumps to a new page to display summary information generated based on the voice data, and / or displays all the topic tags generated based on the voice data.

[0016] In a possible implementation, the display page of the eye-wearable device includes a third preset display area and a fourth preset display area. The third preset display area updates and displays the summary information in real time, and the fourth preset display area updates and displays the topic tags in real time.

[0017] In possible implementations, the method further includes: At the end of the session, the original content of the voice data is stored, or at least one of the following is generated: summary data, a person database, a knowledge base, and a to-do list.

[0018] Among possible implementations, the summary data is generated, including: The information value of the voice data is evaluated to obtain voice segments whose value meets predetermined requirements; Based on the acquired speech segments, summary data is generated.

[0019] In possible implementations, the summary data includes at least one of the following: overview information, highlight information, detailed information, and action plan information, wherein the overview information is used to characterize the overall theme and key conclusions of the session, the highlight information is used to characterize conclusions or decisions with a preset level of importance in the session, the detailed information includes session content organized in chronological order, and the action plan information is used to characterize to-do items, responsible persons, and / or time limits generated in the session.

[0020] In a possible implementation, after acquiring voice data from the conversational scenario, the method further includes: Transcription data is generated based on the speech data, and the transcription data is displayed in real time in a predetermined sub-region within the first preset display area.

[0021] A third aspect of this application provides an eye-wearable device, the eye-wearable device comprising: The voice data acquisition unit is used to collect voice data in conversational scenarios. The parsing unit is used to analyze the voice data using the methods in the various implementations of the first aspect to obtain auxiliary information, wherein the auxiliary information includes at least one of knowledge tags, person tags, question-and-answer tags, and suggestion tags; A display unit is used to display the auxiliary information in a first preset display area of ​​the eye-wearable device.

[0022] A fourth aspect of this application provides a wearable eye device, comprising: The voice data acquisition unit is used to collect voice data in conversational scenarios. A transmission unit is configured to transmit the voice data and receive auxiliary information obtained by analyzing the data through the methods in the various implementations of the first aspect. The auxiliary information includes at least one of knowledge tags, person tags, question-and-answer tags, and suggestion tags, or the auxiliary information includes at least one of knowledge tags, person tags, question-and-answer tags, suggestion tags, insight tags, and goal achievement tags. A display unit is used to display the auxiliary information in a first preset display area of ​​the eye-wearable device.

[0023] A fifth aspect of this application provides an assistive conversation device, including a memory, a processor, a transmitter, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it is able to implement the methods in the various implementations of the first aspect and transmit the assistive information to the eye-wearable device.

[0024] A sixth aspect of the embodiments of this application provides a computer program product that, when run on a computer, causes the computer to execute the methods in the first aspect or its various implementations described above.

[0025] A seventh aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method as described in any of the first aspects.

[0026] An eighth aspect of this application provides a chip for implementing the methods in the various implementations of the first aspect described above. Specifically, the chip includes a processor for calling and running a computer program from a memory, causing a device equipped with the chip to perform the methods as described in the first aspect or its various implementations.

[0027] The beneficial effects of this application embodiment compared with the prior art are as follows: This application embodiment analyzes the voice data in the conversation scenario to obtain auxiliary information, and displays the auxiliary information in the form of tags in the first preset display area of ​​the eye wearable device, thereby greatly reducing the data information displayed by the eye wearable device. Furthermore, the auxiliary information obtained from the voice data analysis includes at least one of the following: displaying knowledge tags, person tags, question and answer tags, and suggestion tags, which can be effectively used to assist users in conversations and improve the user experience of using the eye wearable device for assisted conversations. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of this application, 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is a schematic diagram illustrating an implementation scenario of an auxiliary conversation method provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating the implementation flow of an auxiliary conversation method provided in an embodiment of this application; Figure 3 This is a schematic diagram of the auxiliary information display of an eye-wearable device provided in an embodiment of this application; Figure 4 This is a schematic diagram illustrating the triggering of auxiliary information provided in an embodiment of this application; Figure 5 This is a schematic diagram of a topic tag update provided in an embodiment of this application; Figure 6 This is a schematic diagram of an auxiliary conversation device provided in an embodiment of this application; Figure 7 This is a schematic diagram of an eye-wearable device provided in an embodiment of this application. Detailed Implementation

[0030] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0031] To illustrate the technical solution described in this application, specific embodiments are provided below.

[0032] Eye-wearable devices, which can take the form of glasses, are smart terminals that integrate micro-display modules, computing chips, multimodal sensors, and wireless communication modules. The design goal of eye-wearable devices is to revolutionize the traditional human-computer interaction paradigm, aiming to build an immersive or augmented reality experience. This is achieved by precisely and timely overlaying digital information onto the user's real physical field of vision, thereby realizing a seamless integration of the virtual and physical worlds.

[0033] Currently, wearable eye devices generally employ automatic speech recognition technology to achieve human-computer interaction functions such as assisted conversation. The device collects the speech stream and converts it into a text transcript in near real-time, presenting it as the main information content on the display area. This processing method easily leads to information overload, forcing users to process both auditory signals and visual text simultaneously during conversations, resulting in a significant cognitive load. This not only makes it difficult to quickly capture key content but also severely disrupts the coherence and naturalness of the conversation, ultimately posing a significant obstacle to improving the user experience.

[0034] To address the aforementioned issues, this application proposes an assisted conversation method. Some embodiments of the method are illustrated in the following implementation scenarios: an eye-wearable device, a smart ring, a server, and a smart device. Figure 1 This is a schematic diagram illustrating an implementation scenario of the method in some embodiments. The scenario includes an eye-wearable device, a smart ring, a smart device, and a server. The smart ring can establish a communication connection with the eye-wearable device and send control commands to it, including controlling the eye-wearable device to start or stop an auxiliary session and perform interactive operations during the auxiliary session. The eye-wearable device may include a voice module, a communication module, a display module, and a touch module. The voice module can be used to collect voice data in the session scenario, and in some embodiments, it can also play sound source data. The communication module can send the collected voice data to the smart device. The touch module can control the display of the eye-wearable device by recognizing touches. The display module is used to display augmented reality interactive images to the wearer of the eye-wearable device. In some embodiments, the eye-wearable device and / or the smart device can convert voice data into text data through automatic speech recognition, send the text data to the server, and request the server to return any auxiliary information that may appear in the text data, including knowledge tags, person tags, question-and-answer tags, or suggestion tags. The server uses an artificial intelligence model to perform auxiliary information analysis on the text data, and sends the analyzed auxiliary information, including various tags and related information associated with the tags, to the smart device. The smart device then sends the received auxiliary information to the eye-wearable device and displays the various tags of the auxiliary information in the first preset display area of ​​the eye-wearable device.

[0035] Understandably, practical applications are not limited to... Figure 1 As shown in the application scenarios, eye-wearable devices can also communicate directly with servers, sending voice data directly to the server and receiving necessary auxiliary information directly from the server. Alternatively, eye-wearable devices can obtain text data through automatic voice recognition and send the text data to smart devices or servers. Alternatively, control commands can be triggered directly through the control buttons or touch areas of the eye-wearable device without the need for a smart ring.

[0036] Figure 2 The following is a schematic diagram illustrating the implementation flow of an auxiliary session method provided in an embodiment of this application. The method is described in detail below: In S201, voice data in the conversation scenario is collected.

[0037] The wearable eye device in this application embodiment may include smart glasses, augmented reality glasses, or mixed reality headsets. Augmented reality glasses may include a display module, which can be configured to transmit light from a light source to the human eye through any augmented reality method such as BirdBath, freeform surface, prism, off-axis total internal reflection mirror, or optical waveguide. Specifically, augmented reality glasses may also include a light source, aperture, power supply component, waveguide component, frame component, control component, and functional devices. The waveguide component is mounted on the front frame of the frame component. Specifically, the frame component may include a front frame and temples. The control component is configured to control the operation of the display and other interactive functions. The power supply component is located on the ear loops of the temples. Functional devices may include touch components, microphones, speakers, or any suitable devices.

[0038] The wearable eye device in this embodiment can collect voice data in a conversational scenario via its voice module, such as a microphone, after triggering the auxiliary conversation function. For example, when the wearable eye device establishes a communication connection with a smart ring, it can receive control commands sent by the smart ring to trigger the wearable eye device to start an auxiliary conversation. Alternatively, it can also establish a communication connection with other wearable devices, such as a smartwatch, and receive control commands sent by the smartwatch.

[0039] In one possible implementation, a wearable eye device could be used to detect conversation scenarios and automatically trigger auxiliary conversations based on pre-defined scenarios that require assistance. For example, pre-defined conversation scenarios could include meeting scenarios, or conversation scenarios involving specific domain content.

[0040] In S202, the voice data is analyzed to obtain auxiliary information, which includes at least one of knowledge tags, person tags, question-and-answer tags, and suggestion tags.

[0041] In the embodiments of this application, when analyzing voice data, it is possible to... Figure 1 In the illustrated implementation scenario, the wearable eye device sends voice data to a smart device, which then performs automatic speech recognition to obtain text data. Alternatively, the wearable eye device can first perform automatic speech recognition on the voice data to obtain text data, which is then sent to the smart device.

[0042] After acquiring text data, smart devices can analyze the text data directly, or they can send the text data to a server along with a request for analysis. The server responds to the request using an AI (Artificial Intelligence) model, returning auxiliary information obtained from the voice data analysis. In some embodiments, the voice data can also be analyzed by the processor of an eye-wearable device.

[0043] Alternatively, wearable eye devices can directly send voice data to the server, or directly send text data obtained from automatic speech recognition of the voice data. The server then uses an AI model to analyze the voice or text data to obtain auxiliary information.

[0044] The auxiliary information in the embodiments of this application may include at least one of knowledge tags, person tags, question and answer tags, and suggestion tags.

[0045] Knowledge tags include labels representing proper nouns, industry terms, uncommon characters, and rare words in the voice data. These can be names directly mentioned in the voice data or names extracted from the conversation content. For example, if the conversation includes phrases like "We can consider using zero-knowledge proof technology to ensure privacy and security during data verification," then "zero-knowledge proof" can be analyzed as a knowledge tag, and associated information can be linked to it. Specifically, this could be a semantic interpretation of the knowledge tag, such as the associated information for "zero-knowledge proof" being "a cryptographic protocol that allows one party to prove to another that a statement is true without revealing any additional information beyond the validity of the statement itself."

[0046] Person tags can be labels for individuals included in the voice data, such as names or nicknames. The associated information for these tags can be detailed descriptions of the individuals. Based on the user's familiarity with the individuals, the system can selectively filter out unfamiliar individuals from the voice data and add them to the tag list for display.

[0047] Question-and-answer tags can be summarized labels for questions initiated by the participants in a conversation within the voice data. Wearable eye devices can filter questions initiated by the user's conversation partners during the conversation; there can be one or more partners. The AI ​​model can summarize the questions based on the voice data and the question content, obtaining concise summary terms to represent the question-and-answer tags. Furthermore, based on the complete voice data analysis, suggested answers associated with these question-and-answer tags are obtained.

[0048] Suggested tags are labels generated based on voice data during the conversation, suggesting additional content. These tags can include prompts for new topics and tags used to advance the conversation. For example, prompts to advance the conversation could include tags such as "ask for details" or "summarize and advance."

[0049] In other words, knowledge tags can be associated with the explanation of terms, person tags can be associated with the introduction of people, question and answer tags can be associated with the suggested answers to questions, and suggestion tags can be associated with the conversation guidance information in the conversation content.

[0050] To differentiate between different tags, specific identifiers can be added before each tag in the auxiliary information. For example, a book icon can be added to indicate a knowledge tag, a portrait icon to indicate a person tag, a question mark to indicate a question and answer tag, and a light bulb icon to indicate a suggestion tag. Alternatively, each tag can be paired with icons such as a book, a person, a question mark, a light bulb, a computer, a brain, glasses, or eyes.

[0051] In a possible implementation, the voice data is analyzed to obtain auxiliary information, including: analyzing the voice data to determine insight tags included in the conversation content, wherein the insight tags are used to indicate at least one of the following: focus information of the conversation content, situational awareness information of the conversation content, risk assessment information of the conversation content, and action guidance information of the conversation content.

[0052] Voice data can be sent to a server, which then calls an artificial intelligence model to generate insight tags according to predetermined prompts.

[0053] The pre-defined prompts can be structured model instructions (Prompts) used to guide AI models in extracting and categorizing specific types of insightful information from speech data. These prompts may include the following elements: Role setting is used to indicate the role the model plays, focusing on extracting implicit structured information from the dialogue.

[0054] Task decomposition is used to explicitly require the model to perform four parallel analysis tasks on the input dialogue text: Focus analysis: Identify keywords, phrases, or issues that appear repeatedly, are emphasized, or are followed up on in the conversation, and summarize one to three core issues that the participants care about most, thus obtaining focus information.

[0055] Situational awareness analysis: Determine the current stage of the conversation (e.g., exploration, assessment, decision-making, closing) and assess the overall atmosphere of the conversation (positive, neutral, tense) to obtain situational awareness information.

[0056] Risk assessment analysis: Identify potential risks exposed in the dialogue, including but not limited to contradictory information, exceeding commitment limits, missing key information, unresolved objections, etc., and obtain risk assessment information.

[0057] Action guidance analysis: Based on the three analyses mentioned above, clear and actionable suggestions for the user's next steps are generated, resulting in action guidance information.

[0058] Among these, focus information is used to indicate the content that participants repeatedly focus on, ask follow-up questions about, or emphasize during the conversation. It can reflect the issues that participants truly care about and their priorities. For example, in a sales conversation, if a customer has already accepted the product features but repeatedly asks about downtime, phased migration, and rollback methods, then the focus information can be identified as implementation continuity. This suggests that the focus of the next communication may not be to continue introducing the features, but rather to clarify the downtime window and migration conditions that the customer can accept.

[0059] Situational awareness information is used to indicate the current state or stage of a conversation, such as whether the conversation is in the initial interest stage, the conditional assessment stage, or the stage where a clear commitment has been formed, and where the conversation has progressed.

[0060] Risk assessment information is used to indicate potential risks or opportunities in a conversation, such as risks that may arise from the combination of multiple facts, disagreements or trade-offs that have not yet been directly stated, or missing information that may hinder the next step.

[0061] Action guidance information is used to indicate the direction of action to be taken in response to the current conversation situation, such as what should be confirmed first in the next communication, what materials need to be prepared, who needs to be involved, and which issue should be resolved first.

[0062] It's important to note that knowledge tags, person tags, Q&A tags, and suggestion tags typically correspond directly to specific content within a conversation, representing content that has already appeared in the session. Insight tags, on the other hand, are generated based on the analysis of relationships between multiple conversation segments. Insight tags do not need to have a direct, word-for-word correspondence with any single segment in the target conversation; they emphasize logical relevance. When determining insight tags, at least one of the following can be considered: conversation context information, participant roles, conversation topic, conversation progress, user response status, preset conversation goals, and external reference information. Each insight tag can be associated with its corresponding basis, i.e., the conversation content that triggered that insight tag, allowing users to trace its origins. For content that cannot yet be confirmed, it can be marked as pending confirmation to avoid writing a possibility as a definitive conclusion.

[0063] In a possible implementation, after analyzing the voice data and determining the insight tags included in the conversation content, the method further includes: generating corresponding action suggestion information based on the insight tags. The action suggestion information includes at least one of to-do list information, preparation information, and a communication plan. Specifically, the to-do list information indicates specific tasks to be completed after the conversation ends, and may include items to be confirmed, tasks to be completed, contacts to be contacted, and subsequent deadlines. The preparation information indicates materials or information to be prepared before the next communication, and may include materials to be prepared and topics for the next conversation. The communication plan indicates arrangements for subsequent communication, and may include subsequent communication questions, topics for the next conversation, contacts to be contacted, and subsequent deadlines. The action suggestion information can be matched with the user's current role. For example, in a sales scenario, based on the information already confirmed in the current conversation, potential risks, and key deficiencies, action suggestions consistent with the sales role are provided; in a financing communication scenario, action suggestions consistent with the founder role are provided. The action suggestion information may include specific, actionable content.

[0064] In a sales scenario, the customer (the other party in the conversation) has already approved the product features, but during the meeting, they ask three follow-up questions about downtime, phased migration, and rollback methods. A standard summary would simply record these questions.

[0065] The insight tags in this application embodiment will generate the following information: Implementation continuity may have a greater impact on the customer's current choices than feature richness. The focus of the next communication should not be to continue introducing features, but to clarify the downtime window and migration conditions that the customer can accept.

[0066] Based on the identified insight tags, action recommendations can be provided as follows: Based on the information already confirmed, potential risks, and key gaps, offer action suggestions that align with the user's current role. Specifically, this could include: What should be confirmed first next time? What materials should be prepared? Who needs to participate? Which issue should be addressed first? How can vague discussions be advanced into verifiable next steps? For example, a client wants to launch in September, but the budget, final approver, and acceptable downtime window are not yet confirmed. Insight tags might suggest actions such as: the next technical communication should address two things simultaneously: first, confirm the client's acceptable downtime, rollback conditions, and verification criteria; second, confirm who will approve the budget and how to proceed with procurement once the technology is approved. Otherwise, even if the technical solution is approved, the business opportunity may still be stalled before commercial approval. Users don't need to listen to the entire meeting again to quickly determine the next steps.

[0067] In potential implementation scenarios, when the user does indeed assume a role such as sales, fundraising, interviewing, hosting, or public speaking, and there is sufficient evidence in the conversation, insight tags can provide coaching for the performance in that session, focusing on the key moments that actually occurred: what signals appeared at that time; how the user responded; what observable impact this response had; how to handle it next time; or, it can also provide a directly usable alternative expression.

[0068] For example, when a sales coach says, "The stores cannot be closed," the salesperson immediately starts introducing the backup function without asking how many stores will be affected or how long the downtime is acceptable. The customer then returns to the issues of downtime and rollback.

[0069] The sales coach who uses insightful tags will point out: quantify the impact first, then explain the solution.

[0070] It can generate prompts such as: "If the switch is scheduled outside of business hours, what is the maximum read-only duration that can be accepted at one time? How many stores will be affected? Under what circumstances must an immediate rollback be implemented?"

[0071] By first clarifying the customer's selection criteria, subsequent solutions can truly address the customer's concerns. This can be practiced directly in the next sales communication.

[0072] In this application embodiment, when an effective practice is discovered, insight tags can turn accidental actions into reusable methods.

[0073] For example, in fundraising discussions, founders first provide the metrics, then proactively explain the statistical scope and data boundaries, successfully avoiding repeated questioning from investors. Insight tags can remind you to continue using the "number—time range—data boundaries" answer sequence.

[0074] In different contexts, insight tags can provide different content information.

[0075] For example, in sales communication, insight tags can analyze a customer's real business problems and selection criteria, determine whether a business opportunity is in the initial interest, conditional evaluation, or clear-cut stage, identify breakpoints in budget, decision-makers, procurement processes, and technical verification, distinguish between general concerns, real objections, and closing conditions, prepare for the next round of exploration, product demonstration, quotation, or negotiation, and review the methods of demand exploration, objection handling, solution presentation, and implementation.

[0076] In this application embodiment, when a customer makes a technical requirement, the insight tag can be used to distinguish different capability statuses, including: capabilities that have been confirmed to be supported; capabilities that require further verification; capabilities that are partially met but have limitations; and conditions that still need to be completed before starting a proof of concept.

[0077] If a salesperson gives a positive answer before their capabilities are confirmed, the insight label will also point out the risks and provide a more accurate way of expressing them.

[0078] In a pricing scenario, when a customer says "the competitor's product is 15% cheaper," the real difference may not just be the price, but also include the contract term, payment method, scope of implementation, service content, and approval conditions.

[0079] By leveraging tags, we can generate alerts such as: what the customer is comparing; verbal information from negotiations included in the conversation; conditions the customer has accepted and those still pending approval; approval thresholds that the next version of the solution should address; and whether commitments were made prematurely without approval authority.

[0080] In renewal and upsizing scenarios, during the same meeting, a customer may propose both reducing their account size and expressing potential upsizing interest. Insight tags can generate prompts: what specific risks are currently facing renewal; what conditions need to be met to maintain the original size; whether the upsizing interest is conditional or a committed commitment; and which issues should be prioritized and not overshadowed by "potential expansion."

[0081] In founder fundraising and strategic communication scenarios, insight tags can be used to: understand the common judgment logic behind investors' continuous questioning; determine whether the project has moved to the next stage or is still waiting for supplementary materials; identify explanation gaps between numerical data, customer concentration, retention, or delivery progress; prepare materials and Q&A for the next round; and review the order of answers, evidence presentation, and boundary clarification during the roadshow.

[0082] In recruitment and interview scenarios, insight tags can be used to: differentiate between abilities that have been proven and those that are not yet verified; identify whether a candidate's answers are only conceptual and lack real-world examples; prepare the most worthwhile follow-up questions for the next round; and review whether the candidate moved on to the next question too early and missed the opportunity for key follow-up questions.

[0083] In expert consultations and critical decision-making scenarios, when different viewpoints are intertwined, insight tags can be used to: identify the premises and reasoning behind expert opinions; determine the real disagreements between the parties; identify undefined judgment criteria; and transform insights into questions that can be verified in the next step.

[0084] In S203, the auxiliary information is displayed in the first preset display area of ​​the eye wearable device.

[0085] By analyzing voice data and displaying auxiliary information that assists in conversation in a tagged manner, the amount of screen content displayed can be effectively reduced, thus preventing information overload and improving the user experience.

[0086] The first preset display area can be the main content display area of ​​the eye-wearable device, and the second preset display area can be the theme area. The first and second preset display areas can be displayed on the same page. For example... Figure 3 As shown, the display area of ​​the eye-wearable device includes a topic area and a main content display area. The auxiliary information displayed in the main content display area includes only tags, such as knowledge tags, person tags, question-and-answer tags, and suggestion tags, or one or more of these. The topic area can display the topic tags for the current conversation. These topic tags can be dynamically updated as the voice data content is updated.

[0087] When displaying auxiliary information labels in the first preset display area, a threshold for the number of label rows that can be directly displayed can be set. If the number of labels in the current list is less than the threshold, all labels in the current list can be displayed. If the number of labels in the list is greater than the threshold, a scroll bar can be generated, which can receive scrolling commands to scroll and display the labels in the list.

[0088] Since the eye-wearable device in this embodiment only displays the label of the auxiliary information of the current session when assisting the conversation, it can greatly reduce the amount of data information displayed by the eye-wearable device. Moreover, the auxiliary information is obtained by analyzing the voice data of the conversation, which can effectively assist the user in the conversation and improve the user's conversation experience when using the eye-wearable device.

[0089] To enable timely viewing of the associated information corresponding to tags in auxiliary information, the system can receive user trigger commands to display the associated information. For example, the associated information of a tag can be displayed in at least one of the following ways: triggering a knowledge tag displays the explanation of the terminology associated with the knowledge tag; triggering a person tag displays the introduction information of the person associated with the person tag; triggering a question-and-answer tag displays suggested answers to the questions associated with the question-and-answer tag; triggering a suggestion tag displays conversation guidance information for the conversation content associated with the suggestion tag.

[0090] The triggering method for tags can include two modes: automatic triggering and manual triggering.

[0091] When the tag association information is set to be automatically triggered, new auxiliary information can be analyzed from the voice data, and the association information corresponding to the tag of the auxiliary information can be automatically displayed. The information will be displayed for a first predetermined duration based on the complexity of the association information, such as 2-4 seconds, and then automatically turned off.

[0092] like Figure 4 As shown, in some embodiments, a maximum of four tags can be displayed simultaneously in the first preset display area of ​​the eye-wearable device. Currently, three tags already exist: a person tag (3), a question-and-answer tag (1), and a suggestion tag (2). When new auxiliary information is generated through analysis, the tag for this auxiliary information is "knowledge tag N." The newly generated tag, "knowledge tag N," can be added to the auxiliary information list, i.e., the tag list used for displaying tags, and highlighted at the top of the list (in bold in the figure; in some embodiments, it can also be highlighted or displayed in a different color). The new tag is automatically added to the top of the tag list, allowing the tag list to be arranged sequentially for easy tag retrieval based on time.

[0093] After the new auxiliary information tag is displayed at the top, after a second predetermined time, such as 1-2 seconds (e.g., 2 seconds as shown in the image), the associated information of the knowledge tag N will be automatically displayed on a new page, allowing users to quickly understand the specific content of the tag. Additionally, to prevent the associated information from being displayed for too long and affecting the normal display of other tags, after a first predetermined time, such as 3 seconds, the associated information display page can be automatically closed, returning to the tag display page showing the tag list, and the highlighted knowledge tag N will be changed to a normal display state, such as changing from bold to non-bold.

[0094] When manually displaying associated information, users can select the tag containing the auxiliary information to be displayed using a swipe command. Once the tag for which associated information is desired is selected, an activation command for the auxiliary information is received. This could be a touch command from the eye-wearing device itself, or a click command from another wearable device connected to the eye-wearing device, such as a smart ring. Upon receiving the activation command, the associated information corresponding to the tag is displayed on a new page on the eye-wearing device. Upon receiving a deactivation command, the display page for that associated information is closed, and the user returns to the tag list display page.

[0095] In one possible implementation, when a user displays the labels of auxiliary information via a swipe command, the currently displayed label may not be the top label in the label list. When analyzing and generating new labels for auxiliary information, a prompt message indicating the generation of new labels can be displayed. The user can then swipe to display the newly generated labels within the first preset display area.

[0096] When displaying the tag list, the system can automatically update to show the latest tags at the current time. For example, if the tag list is arranged chronologically, and the latest tag is at the top, a predetermined number of tags at the top can be automatically displayed. To easily distinguish newly generated tags, they can be highlighted, such as by bolding, or using a different color. Furthermore, to easily distinguish the generation time of the most recent tags, the highlighting can be automatically canceled after a third predetermined time interval, and the tag can be displayed in normal mode, such as a grayscale display.

[0097] In this embodiment, to facilitate users' timely understanding of the main information of the current conversation, topic tags can be updated and displayed in real time in the topic area of ​​the display area. Topic tags are generated by analyzing the voice data, obtaining tags determined by the topic corresponding to the voice data. In a conversation scenario, the topic may be updated as the conversation progresses. When a difference is detected between the current topic and a previous topic, the current topic tag can be updated and displayed in the topic area.

[0098] for example Figure 5The diagram illustrating topic tag updates shows that at time t, the displayed topic tag is topic tag 1. At time t+1, based on voice data analysis, the current topic tag has changed, and the updated topic tag is topic tag 2. Therefore, the current topic tag can be updated and displayed in the topic area, i.e., updated to topic tag 2. Topic tag 1 can be displayed after selecting topic tag 2 in the second preset area. In other words, the eye-wearable device receives the topic tag trigger command, jumps to a new page displaying summary information generated based on voice data, and displays all topic tags generated based on voice data. At this time, the main content display area can correspondingly update the tags in the generated auxiliary information.

[0099] To further enrich the diversity of display content of the wearable eye device in this application embodiment, after updating and displaying the current topic tag in real time, this application embodiment can also receive a trigger command for the topic tag, and display a new display page based on the trigger command. The new display page displays summary information generated based on voice data, or may also include topic tags generated based on voice data. The summary information can be displayed in a third preset display area in the new display page. The summary information is a summary of the entire conversation content generated based on voice data. This summary information can be updated in real time according to the voice data. The same display page also includes a fourth preset display area, which can be used to display topic tags. This topic tag can be all topic tags generated in the current conversation, including topic tags generated in historical moments. Updating historically displayed topic tags through the fourth preset display area facilitates users' quick review of historical topics.

[0100] The third and fourth preset display areas are located on the same display page. The third and fourth preset display areas can display a predetermined number of rows of data. The latest data, including the latest topic tags and the latest summary information, can be updated in real time by scrolling.

[0101] In this embodiment, to enhance the convenience of conversation use, when the eye-wearable device is connected to a smart device, voice data can be recorded in real time, and the original content of the transcribed conversation can be stored in the smart device. This allows users to review or analyze the conversation based on the original content using their smart terminal. Alternatively, a conversation summary can be generated based on all topic tags of the conversation content, providing summary data that summarizes the main content of the conversation according to the topic tags. Furthermore, a person database can be generated based on person tags, and to-do items can be generated based on the voice data, categorized according to different types of to-do items. In some embodiments, the topic summary corresponding to each topic tag can also be stored and displayed in the smart device for easy review of conversation information by the user.

[0102] In possible implementations, obtaining summary data includes: evaluating the information value of the voice data using an artificial intelligence model, obtaining voice segments whose value meets predetermined requirements, and generating summary data based on the obtained voice segments.

[0103] The pre-defined requirement can be a voice segment with a value higher than a pre-defined value threshold, or a voice segment with a pre-defined duration or number of sentences obtained from high to low based on value ranking.

[0104] When assessing the information value of voice data, contextual information such as the conversation background and purpose can be considered to more accurately determine the value of the information mentioned in the conversation. Low-value, obsolete, redundant, or meaningless information can be filtered out, while high-value information can be retained for better extraction and summarization without losing key points. Information value assessment avoids including non-factual content such as guesses, inferences, and suggestions generated by artificial intelligence models in the summary, reducing the illusion of quality. It also ensures that the summary information conforms more to the syntax of formal documents, minimizing obvious traces of AI generation.

[0105] Specifically, the summary data can be structured summary information, including at least one of the following: overview information, highlight information, detailed information, and action plan information. The overview information represents the overall theme and key conclusions of the session, allowing users to grasp the overall picture and understand the main topics and key outcomes of the session within seconds. The highlight information represents conclusions or decisions with a predetermined level of importance in the session, allowing users to understand the most valuable conclusions within tens of seconds. The detailed information includes session content organized chronologically, allowing users to review the discussion process in detail without losing information. In possible implementations, the detailed information may include timestamps, allowing users to click on the timestamps to jump to the corresponding speech-to-text location to trace the original text and review the reasoning process. The action plan information represents to-do items, responsible persons, and / or deadlines generated during the session, allowing users to quickly understand what unresolved matters are and what actions should be taken next.

[0106] In one possible implementation, the page used to display auxiliary information labels can also generate transcribed data from the speech data. This transcribed data can be displayed in a predetermined sub-region within a first preset display area, such as a sub-region that displays two lines. This can better help users understand the current conversation content, and even in cases where they might mishear or miss something, they can still reproduce the conversation content through text, improving the convenience of using the conversation.

[0107] In possible implementations, the overview, highlight, or detail information in the summary data of this application embodiment can be sorted by time or alphabetically. Different information can correspond to timestamps, and the correspondence between each sentence in the conversation content and its timestamp can be pre-recorded. Based on the correspondence between information in the summary data and its timestamp, combined with the correspondence between conversations and timestamps, users can trigger any information in the summary data on a computer or mobile device to jump to the conversation statement associated with the timestamp of that information, facilitating users' tracing of the original content.

[0108] In a possible implementation, after collecting voice data in a conversational scenario, the method further includes: monitoring conversational events included in the voice data, and generating a target achievement label corresponding to the conversational event in the first preset display area. The conversational event includes at least one of a response missing event, an information conflict event, a key signal event, and a target deviation event. The target achievement label is used to characterize the degree of achievement of a preset conversational goal or the progress status of the conversation. For example, when a response missing event is detected, the target achievement label is displayed as a "pending response" status and a corresponding identifier.

[0109] When monitoring session events, the current session state can be analyzed based on real-time voice data of the target session, contextual information associated with the target session, and / or preset session goals. When it is determined that the prompt triggering conditions are met, prompt information is generated and output to assist the user in performing current or subsequent session operations. The current session state can be determined by at least one of the following: the current session segment, one or more previous session segments, participant roles, session topic, session progress, user response status, preset session goals, and external reference information.

[0110] The prompt triggering conditions can be based on real-time voice data and judgment logic of preset rules or models, including triggering conditions for missing response events (the natural language processing model detects that the other party's speech contains a clear question, and within the next predetermined time (e.g., 5-10 seconds), the user's speech does not contain a direct or indirect answer to the question), triggering conditions for information conflict events (detecting that the user's statement is substantially contradictory to the factual information in the database), triggering conditions for key signal events (identifying that the speech belongs to a preset key signal category, and the confidence level of the signal exceeds a preset threshold (e.g., 85%)), and triggering conditions for target deviation events (finding that a preset target item is not covered or there are unclosed items), etc.

[0111] Specifically, when the monitored conversation events in the voice data are response missing events, i.e., when a question is raised by the other party but the user has not yet made a valid response, the question raised by the other party can be obtained, and the corresponding reference answer can be retrieved from a preset database. The reference answer can then be displayed in the first preset display area, or the question and the reference answer can be displayed together. The preset database may include, for example, product manuals, quotations, technical documents, meeting notes, and customer background information.

[0112] For example, if a customer asks, "How many concurrent requests can your single cluster support?" and the user can't recall a specific number at the moment, the system can retrieve the accurate figure of "5000 QPS (Queries Per Second) per cluster" from the preset database and display it in the first preset display area. The system can also use the retrieved information to provide answers such as "If the other party has a larger scale, we can continue to understand the peak traffic and then discuss a multi-cluster solution," to help the user naturally continue the conversation.

[0113] When the conversation event included in the voice data is detected to be an information conflict event, that is, when the user's current statement is inconsistent with the reference information, or when the user's current statement exceeds the preset permissions or preset capability boundaries, the user's current statement can be compared with the reference information, preset permissions or preset capability boundaries, and a difference prompt and / or correction suggestion can be displayed in the first preset display area.

[0114] For example, if product documentation specifies a standard delivery time of 4 weeks, but a user tells a customer that "delivery will be available in two weeks after ordering," a discrepancy warning can be displayed: "You just said 2 weeks, but the quotation says 4 weeks," along with a correction suggestion: "It is recommended to provide the accurate delivery date now to avoid future delivery disputes." Another example is if technical documentation states "supports private cloud, but does not currently support private deployment in customer data centers." When a customer asks, "Can the entire system be deployed in our own data center?" and the user is about to answer "It should be possible," a warning can be displayed: "Currently, we support private cloud, but do not currently support private deployment in customer data centers. We should first understand whether the customer truly needs data isolation or compliance requirements before discussing feasible solutions." This avoids both easily rejecting customers and promising capabilities that cannot be delivered in order to push through a transaction.

[0115] When the conversation event included in the voice data is detected as a key signal event, that is, when the target object's purchase, objection, withdrawal or promotion signal is detected, the corresponding response strategy or promotion speech can be displayed in the first preset display area.

[0116] For example, if a customer repeatedly inquires about implementation steps, contract timelines, and invoicing methods, it indicates they are already considering "how to implement the product after purchase." However, if the conversation remains focused on feature introductions, a follow-up message could be displayed: "If the scope of implementation is confirmed, can we start scheduling a pilot program?" This helps translate the customer's interest into further action. Another example: if a customer initially says "the price is a bit high," and the user responds with product features and long-term value, but a few minutes later the customer says again, "but this year's budget is definitely not approved," it indicates a recurring objection, and the previous response may not have truly addressed the concerns. A response strategy could be displayed, determining whether the issue to address this time is value, budget, or payment terms. For instance, a follow-up message could be displayed: "Is it that the total budget hasn't been approved, or is the current payment schedule unacceptable?"

[0117] When the conversation event included in the voice data is detected to be a target deviation event, it can be determined whether the preset conversation target has been completed, whether the conversation is about to end, whether there are any unresolved issues in the discussed matters, or whether there are any events with higher priority than the existing prompts, and the corresponding reminder information or supplementary prompts can be displayed in the first preset display area.

[0118] For example, if a user states at the beginning of the conversation that they want to confirm the budget, launch date, and final decision-maker, and the first two items have been discussed but the final decision-maker is still unconfirmed near the end of the conversation, a reminder message could be displayed: "Who made the final decision hasn't been confirmed yet," along with a supplementary prompt: "You could add a sentence before ending: If the solution passes the technical evaluation, will you be the one to confirm it, or will it require approval from other responsible persons?" Another example is if a client says, "The solution is good, I'll discuss it with my supervisor," and the user simply replies, "Okay, no problem," a reminder message could be displayed: "Discussed, but no follow-up arrangements," along with a supplementary prompt: "Could you first confirm whether your supervisor is most concerned about the budget, risks, or implementation timeline, and then schedule a specific feedback time: I'll complete the necessary materials, and we can review the progress again next Wednesday, okay?" This way, even if a deal isn't closed this time, a clear entry point is left for future communication.

[0119] When generating goal achievement labels for session events, if multiple prompts simultaneously meet the triggering conditions, only the most important one at the current moment can be displayed; if the user has already handled the corresponding event, no repeated reminders will be given; if there is insufficient reliable information, no prompt message will be generated. This avoids prompt messages interfering with the user and ensures that prompt messages appear only when truly needed.

[0120] The auxiliary conversation method in this application embodiment can also be used for real-time translation processing. When the two parties in a conversation communicate in different languages, the speech data of the other party can be translated into text information in the user's language in real time, facilitating instant cross-language communication.

[0121] In possible implementations, to enhance the intelligence of the auxiliary session, embodiments of this application may also receive prompts input by the user, or background information of the current session or other meeting background information before conducting the auxiliary session, so as to improve the accuracy of the auxiliary content.

[0122] During assisted conversations, pre-set notes can be retrieved to facilitate smoother and more efficient communication. These notes can be pre-set by the user or automatically generated by the model for the current conversation.

[0123] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0124] Figure 6 This is a schematic diagram of an eye-wearable device provided in an embodiment of this application. The device includes: The voice data acquisition unit 601 is used to acquire voice data in a conversational scenario; The parsing unit 602 is used to analyze the voice data obtained by the method of this application to obtain auxiliary information, wherein the auxiliary information includes at least one of knowledge tags, person tags, question and answer tags and suggestion tags; Display unit 603 is used to display the auxiliary information in a first preset display area of ​​the eye wearable device.

[0125] Figure 6 The auxiliary conversation device shown is, with Figure 2 The corresponding auxiliary session method is shown.

[0126] This application also provides a wearable eye device, including: The voice data acquisition unit is used to collect voice data in conversational scenarios. The transmission unit is used to transmit voice data and receive auxiliary information obtained by the method of this application, the auxiliary information including at least one of knowledge tags, person tags, question and answer tags and suggestion tags; A display unit is used to display the auxiliary information in a first preset display area of ​​the eye-wearable device.

[0127] This application also provides an assistive conversation device, including a memory, a processor, a transmitter, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it can implement the method of this application and transmit the assistive information to an eye-wearable device.

[0128] Figure 7This is a schematic diagram of a wearable eye device provided in an embodiment of this application. Figure 7 As shown, the wearable eye device 7 of this embodiment includes: a processor 70, a memory 71, and a computer program 72 stored in the memory 71 and executable on the processor 70, such as an auxiliary conversation program. When the processor 70 executes the computer program 72, it implements the steps in the various auxiliary conversation method embodiments described above. Alternatively, when the processor 70 executes the computer program 72, it implements the functions of each module / unit in the various device embodiments described above.

[0129] For example, the computer program 72 may be divided into one or more modules / units, which are stored in the memory 71 and executed by the processor 70 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 72 in the eye wearable device 7.

[0130] The wearable eye device may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art will understand that... Figure 7 This is merely an example of an eye-wearable device 7 and does not constitute a limitation on the eye-wearable device 7. It may include more or fewer components than shown, or combine certain components, or different components. For example, the eye-wearable device may also include input / output devices, network access devices, buses, etc.

[0131] The processor 70 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0132] The memory 71 can be an internal storage unit of the eye-wearable device 7, such as a hard drive or memory. The memory 71 can also be an external storage device of the eye-wearable device 7, such as a plug-in hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the eye-wearable device 7. Furthermore, the memory 71 can include both internal and external storage units of the eye-wearable device 7. The memory 71 is used to store the computer program and other programs and data required by the eye-wearable device. The memory 71 can also be used to temporarily store data that has been output or will be output.

[0133] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0134] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0135] Those skilled in the art will 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, or a combination of computer software and electronic hardware. 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.

[0136] In the embodiments provided in this application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0137] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0138] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0139] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by hardware related to computer program instructions. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0140] In addition, this application also provides a computer program product that, when run on a computer, causes the computer to execute the methods in the above-described implementations.

[0141] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. An auxiliary conversation method, characterized in that, The method includes: Collect voice data in conversational scenarios; The voice data is analyzed to obtain auxiliary information, which includes at least one of knowledge tags, person tags, question-and-answer tags, and suggestion tags; The auxiliary information is displayed in the first preset display area of ​​the eye-wearable device.

2. The method according to claim 1, characterized in that, After displaying the auxiliary information in the first preset display area of ​​the eye-wearable device, the method further includes: triggering the auxiliary information and displaying associated information corresponding to the auxiliary information on the eye-wearable device; wherein, triggering the auxiliary information and displaying the associated information corresponding to the auxiliary information on the eye-wearable device includes at least one of the following steps: Triggering the knowledge tag displays the explanation of the term associated with the knowledge tag; When the character tag is triggered, the introductory information of the character associated with the character tag is displayed; When the question-and-answer tag is triggered, suggested answers to the questions associated with the question-and-answer tag are displayed; When the suggestion tag is triggered, the session guidance information of the session content associated with the suggestion tag is displayed.

3. The method according to claim 2, characterized in that, The triggering of the assistance information and the display of associated information corresponding to the assistance information on the wearable eye device includes: Receive the activation command of the auxiliary information, display the associated information corresponding to the auxiliary information according to the activation command, and close the associated information after receiving the deactivation command; Alternatively, the auxiliary information can be updated based on the parsing of the voice data, automatically triggering the display of associated information corresponding to the updated auxiliary information, and automatically closing the associated information after a first predetermined duration of continuous display.

4. The method according to claim 1, characterized in that, Displaying the auxiliary information in the first preset display area of ​​the wearable eye device includes: When new auxiliary information is obtained from the analysis, the new auxiliary information is displayed at the top of the list of auxiliary information in the first preset display area.

5. The method according to claim 1, characterized in that, After collecting voice data in the conversation scenario, the method further includes: The voice data is analyzed to generate topic tags, which are tags determined by the topic corresponding to the voice data; Based on the analysis, the current topic tags are updated and displayed in real time in the second preset display area.

6. The method according to claim 5, characterized in that, After updating and displaying the current topic tag in real time in the second preset display area based on the analysis, the method further includes: Upon receiving the trigger instruction of the topic tag, the system jumps to a new page to display summary information generated based on the voice data, and / or displays all the topic tags generated based on the voice data.

7. The method according to claim 6, characterized in that, The display page of the eye-wearable device includes a third preset display area and a fourth preset display area. The third preset display area updates and displays the summary information in real time, and the fourth preset display area updates and displays the topic tags in real time.

8. The method according to claim 7, characterized in that, The method further includes: At the end of the session, the original content of the voice data is stored, or at least one of the following is generated: summary data, a person database, a knowledge base, and a to-do list.

9. The method according to claim 1, characterized in that, After collecting voice data from the conversation, the method further includes: Transcription data is generated based on the speech data, and the transcription data is displayed in real time in a predetermined sub-region within the first preset display area.

10. A wearable eye device, characterized in that, The wearable eye device includes: The voice data acquisition unit is used to collect voice data in conversational scenarios. The parsing unit is configured to analyze the voice data using the method described in any one of claims 1-9 to obtain auxiliary information, wherein the auxiliary information includes at least one of knowledge tags, person tags, question-and-answer tags, and suggestion tags; A display unit is used to display the auxiliary information in a first preset display area of ​​the eye-wearable device.

11. A wearable eye device, characterized in that, include: The voice data acquisition unit is used to collect voice data in conversational scenarios. A transmission unit is configured to transmit the voice data and receive auxiliary information obtained by the method according to any one of claims 1-9, wherein the auxiliary information includes at least one of knowledge tags, person tags, question-and-answer tags, and suggestion tags; A display unit is used to display the auxiliary information in a first preset display area of ​​the eye-wearable device.

12. An auxiliary conversation device, comprising a memory, a processor, a transmitter, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it can implement the method as described in any one of claims 1-9 and transmit the auxiliary information to the eye wearable device.

13. A computer program product comprising computer program instructions, characterized in that, When the computer program instructions are executed, the method as described in any one of claims 1-9 is performed.

Images