Voice ticket purchasing method and device and electronic equipment

Abstract

This application provides a voice-based ticketing method, apparatus, and electronic device, relating to the field of artificial intelligence technology, and applied to the interaction module integrated into a robot system. The method includes: receiving a control management instruction issued by the robot system when it detects that a user has the intention to purchase tickets; responding to the control management instruction, collecting the user's real-time voice data; sending the real-time voice data to a remote ticketing server to receive a ticketing service processing instruction returned by the remote ticketing server after performing intent recognition based on the real-time voice data; and, according to the ticketing service processing instruction, invoking a corresponding voice control method to guide the user to complete the ticketing process. The method provided in this application decouples personalized voice-based ticketing functionality from the robot's original general functions, meeting the need for rapid deployment of personalized voice-based ticketing services on existing robot platforms in a low-cost and high-efficiency manner.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a voice ticketing method, device, and electronic device. Background Technology

[0002] In the field of robot voice interaction technology, with the development of artificial intelligence technology, more and more service scenarios are beginning to introduce robots for intelligent voice interaction, especially in places such as public transportation and shopping malls, where users can consult information or complete specific business transactions through robots.

[0003] Currently, when transportation companies or third-party service providers want to integrate specific voice-based ticketing functionality into their robots, they typically need to use the robot manufacturer's underlying SDK for native Android system-level development to control the robot's microphone, speakers, and other hardware, as well as collect and process voice data. However, this development model requires developers to possess complete underlying system development capabilities and must reimplement the entire set of interactive logic, including voice wake-up, voice recognition, and multi-turn dialogue, based on the robot manufacturer's existing SDK framework. This results in long development cycles and high costs. More importantly, third-party developers often find it difficult to reuse the mature, universal functions already implemented by robot manufacturers (such as automatic patrolling and weather information). The resulting ticketing modules often fail to reach the stability and user experience of the manufacturer's native functions, making it difficult to meet the demand for low-cost, short-cycle personalized voice-based ticketing integration. Therefore, a solution is urgently needed to address these issues. Summary of the Invention

[0004] This application provides a voice-based ticketing method, apparatus, and electronic device to address the deficiencies in the prior art.

[0005] This application provides a voice-based ticket purchasing method, applied to the interaction module integrated into a robot system, the method comprising: Receive control management instructions issued by the robot system when it detects that a user intends to purchase tickets; In response to the control delegation instruction, the user's real-time voice data is collected; The real-time voice data is sent to a remote ticketing server to receive a ticketing service processing instruction returned by the remote ticketing server after performing intent recognition based on the real-time voice data. Based on the ticket purchase service processing instruction, the corresponding voice control method is invoked to guide the user to complete the ticket purchase process.

[0006] According to an embodiment of this application, a voice-based ticketing method is provided, wherein the step of collecting the user's real-time voice data in response to the control management instruction includes: In response to the control delegation instruction, load and display the voice ticketing interface; The user's real-time voice data is collected through the voice ticketing interface.

[0007] According to an embodiment of this application, a voice-based ticket purchasing method, after invoking a corresponding voice control method based on the ticket purchasing service processing instruction to guide the user to complete the ticket purchasing process, the method further includes: Upon confirming that the user has completed the ticket purchase, a notification to reclaim control is sent to the robot system, and the robot itself and its corresponding interactive interface are closed.

[0008] According to an embodiment of this application, a voice-based ticketing method is provided, wherein collecting the user's real-time voice data through the voice-based ticketing interface includes: The voice ticketing interface is used to call the voice monitoring interface to start real-time acquisition of the user's voice input; If the user's voice input ends, the voice stop interface is invoked to terminate the current voice acquisition. The collected voice data is encapsulated into a pre-formatted voice data packet and a timestamp and session identifier are added as real-time voice data to be sent.

[0009] According to an embodiment of this application, a voice-based ticketing method, after sending the real-time voice data to a remote ticketing server and receiving a ticketing service processing instruction returned by the remote ticketing server after performing intent recognition based on the real-time voice data, the method further includes: Parse the ticket purchase service processing instruction to obtain the intent type and ticket purchase parameters contained in the ticket purchase service processing instruction; If the intent type is confirmation of ticket purchase intention, ticket purchase option information is generated based on the ticket purchase parameters; If the intent type is an information supplementation request, generate follow-up prompt information corresponding to the information supplementation request; If the intent type is "ticket purchase completion confirmation", ticket purchase result information is generated.

[0010] According to an embodiment of this application, a voice-based ticket purchasing method is provided, wherein the step of invoking a corresponding voice control method according to the ticket purchasing service processing instruction to guide the user to complete the ticket purchasing process includes: Based on the parsed intent type, a corresponding voice broadcast template is matched from a preset voice template library; Call the voice broadcast interface to convert the ticket purchase option information, the follow-up question prompt information, or the ticket purchase result information into voice signals for broadcast; After the broadcast is completed, the voice monitoring interface is called again to receive the user's next round of voice input; Repeat the above broadcasting and listening steps until the ticket purchase process is complete.

[0011] According to an embodiment of this application, a voice-based ticket purchasing method includes receiving a control management instruction issued by the robot system when it detects that a user has the intention to purchase tickets. Receive managed instructions transmitted by the robot system through a preset control transfer interface; Through the control transfer interface, the robot system synchronously receives initial data; wherein, the initial data includes semantic information of the user's current dialogue context and identified ticket purchase intention keywords; Based on the initial data, determine the initial display content and the first round of voice broadcast content of the voice ticketing interaction interface.

[0012] According to an embodiment of this application, a voice-based ticketing method is provided in which the interaction module, during the period of managing the interaction control, blocks the voice interaction interface of the robot system itself, ensuring that the user's voice input is processed only by the interaction module.

[0013] This application embodiment also provides a voice ticketing device, applied to the interaction module integrated into a robot system, the device comprising: The receiving unit is used to receive the control management instruction issued by the robot system when it detects that the user has the intention to purchase tickets; The acquisition unit is used to acquire the user's real-time voice data in response to the control management instruction; The sending unit is used to send the real-time voice data to the remote ticketing server, and to receive the ticketing service processing instruction returned by the remote ticketing server after performing intent recognition based on the real-time voice data. The ticket purchasing unit is used to invoke the corresponding voice control method according to the ticket purchasing service processing instruction to guide the user to complete the ticket purchasing process.

[0014] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the above-described voice ticketing methods.

[0015] This application also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the voice ticketing method as described above.

[0016] This application also provides a computer program product, including a computer program that, when executed by a processor, implements any of the above-described voice ticketing methods.

[0017] This application provides a voice-based ticketing method, apparatus, and electronic device, applied to an interaction module integrated into a robot system. The method involves receiving a control management instruction issued by the robot system when it detects a user's intention to purchase tickets; responding to the control management instruction, collecting the user's real-time voice data; sending the real-time voice data to a remote ticketing server to receive a ticketing service processing instruction returned by the remote ticketing server after performing intent recognition based on the real-time voice data; and, according to the ticketing service processing instruction, invoking a corresponding voice control method to guide the user through the ticketing process. Therefore, this application embodiment integrates an independent interaction module into the robot system. After detecting a user's intention to purchase tickets, the robot system temporarily entrusts the interaction control to this module, which independently completes the subsequent voice data collection, server interaction, and ticket purchase guidance process. This decouples the personalized voice ticket purchase function from the robot's original general functions. This allows third-party developers to avoid delving into the robot's underlying SDK for complete system development and to avoid repeatedly implementing the robot manufacturer's mature general interaction capabilities. They only need to focus on developing the interaction module for the ticket purchase business logic, thus meeting the need for rapid deployment of personalized voice ticket purchase services on existing robot platforms in a low-cost and high-efficiency manner. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application 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 some embodiments of the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating the voice ticketing method provided in the embodiments of this application.

[0020] Figure 2 This is a schematic diagram of the integrated framework of the voice ticketing method provided in the embodiments of this application.

[0021] Figure 3 This is a schematic diagram of the structure of the voice ticketing device provided in the embodiments of this application.

[0022] Figure 4 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the embodiments of this application.

[0024] The following description, in conjunction with the accompanying drawings, describes a voice-based ticketing method, apparatus, and electronic device according to embodiments of this application.

[0025] Figure 1 This is a flowchart illustrating the voice ticketing method provided in the embodiments of this application, as shown below. Figure 1 As shown, the method, applied to the interaction module integrated into a robot system, includes the following: Step 100: Receive the control management instruction issued by the robot system when it detects that the user has the intention to purchase tickets.

[0026] It should be noted that the interaction module refers to an independent software functional unit integrated into the robot system. It can be a web page rendering module based on Web technology, used to load and display a specific interactive interface when the robot system is running, and at the same time serve as a communication bridge with the underlying hardware.

[0027] Specifically, the control delegation instruction refers to the notification signal that after the robot system recognizes that the user's current conversation involves the intention to purchase tickets through its own voice interaction capabilities, it will proactively transfer the control of subsequent interactions with the user to the interaction module. This transfer allows the interaction module to exclusively call the robot's input and output resources during this period.

[0028] Step 200: In response to the control management instruction, collect the user's real-time voice data.

[0029] Specifically, real-time voice data refers to raw user voice stream data collected by the robot's microphone hardware without local processing, which is sent to the cloud or a remote ticketing server in the form of data packets.

[0030] Step 300: Send the real-time voice data to the remote ticketing server to receive the ticketing service processing instruction returned by the remote ticketing server after performing intent recognition based on the real-time voice data.

[0031] Specifically, the remote ticketing server refers to a service platform deployed on the local network side of the robot, which has the ability to recognize voice intent and process ticketing business logic. After receiving voice data, it recognizes the user's ticketing intent through a pre-trained large model or natural language processing engine, and generates corresponding ticketing service processing instructions to return to the interaction module. The ticketing service processing instructions refer to structured data containing intent type (such as confirmation of ticketing intent, information supplementation request, confirmation of ticketing completion, etc.) and ticketing parameters (such as destination, time, ticket type, etc.).

[0032] Step 400: According to the ticket purchase service processing instruction, call the corresponding voice control method to guide the user to complete the ticket purchase process.

[0033] Specifically, the voice control method refers to the interface functions called by the interaction module to control the robot's voice capabilities in order to complete the ticket purchase guidance. These include methods for starting and stopping voice acquisition and methods for broadcasting prompts. Through the combined use of these methods, the interaction module can engage in multi-round voice dialogues with the user, gradually guiding the user through the entire process from confirming the intention to purchase tickets to supplementing information and finally confirming the purchase. This achieves low-cost and high-efficiency integration of personalized voice ticket purchase services without interfering with the robot's original general functions.

[0034] The above describes the steps of the voice ticketing method provided in the embodiments of this application. As can be seen from the above description, the voice ticketing method provided in the embodiments of this application is applied to the interaction module integrated into a robot system. It receives a control management instruction issued by the robot system when it detects that a user has the intention to purchase tickets; in response to the control management instruction, it collects the user's real-time voice data; it sends the real-time voice data to a remote ticketing server to receive a ticketing service processing instruction returned by the remote ticketing server after performing intent recognition based on the real-time voice data; and according to the ticketing service processing instruction, it calls the corresponding voice control method to guide the user to complete the ticketing process. Therefore, this application embodiment integrates an independent interaction module into the robot system. After detecting a user's intention to purchase tickets, the robot system temporarily entrusts the interaction control to this module, which independently completes the subsequent voice data collection, server interaction, and ticket purchase guidance process. This decouples the personalized voice ticket purchase function from the robot's original general functions. This allows third-party developers to avoid delving into the robot's underlying SDK for complete system development and to avoid repeatedly implementing the robot manufacturer's mature general interaction capabilities. They only need to focus on developing the interaction module for the ticket purchase business logic, thus meeting the need for rapid deployment of personalized voice ticket purchase services on existing robot platforms in a low-cost and high-efficiency manner.

[0035] Based on the above embodiments, in this embodiment, step 200, in response to the control management instruction, collects the user's real-time voice data, including: Step 210: In response to the control management instruction, load and display the voice ticketing interface.

[0036] Step 220: Collect the user's real-time voice data through the voice ticketing interface.

[0037] Step 220 specifically includes: Step 221: Call the voice monitoring interface through the voice ticketing interaction interface to start real-time acquisition of the user's voice input.

[0038] Step 222: When the user's voice input is detected to have ended, call the voice stop interface to terminate the current voice acquisition.

[0039] Step 223: Encapsulate the collected voice data into a preset format voice data packet, and add a timestamp and session identifier as real-time voice data to be sent.

[0040] Specifically, the interaction module responds to the control management command issued by the robot system, loads and displays the voice ticket purchase interaction interface; the voice ticket purchase interaction interface refers to a graphical user interface specifically for the ticket purchase scenario, such as a web page developed based on H5 technology, which includes ticket purchase guidance text, status prompts and background logic control scripts, used to show the user the current interaction status and trigger subsequent voice control operations.

[0041] Subsequently, in step 220, the interaction module collects real-time voice data from the user through the voice ticketing interface. The voice ticketing interface initiates real-time acquisition of user voice input by calling a voice monitoring interface. This voice monitoring interface refers to the functional interface exposed to the front-end page by the interaction module for controlling the robot's microphone hardware, such as a JavaScript interface named `startRecord`. When called, the interaction module sends a microphone occupancy request to the robot system, activating the microphone driver to begin sound pickup. Upon detecting the end of user voice input, the voice stop interface is called to terminate the acquisition. Detecting the end of user voice input can be achieved in various ways, such as recognizing a pause exceeding a preset threshold (e.g., 500 milliseconds) based on voice activity detection technology, or the user actively pressing and holding the "stop" button on the interaction interface to trigger an end signal. The voice stop interface, corresponding to the voice monitoring interface, is a functional interface used to turn off the microphone and terminate acquisition, such as the `stopRecord` interface. When called, it sends a microphone release request to the robot system, stopping sound pickup and returning hardware resources. Finally, the interaction module encapsulates the collected voice data into a pre-formatted voice data packet and adds a timestamp and session identifier as real-time voice data to be sent. The pre-formatted format can be a common audio encoding format, such as PCM, WAV, or OPUS, to ensure compatibility with the remote ticketing server. The timestamp is used to identify the time when the voice segment occurs, which facilitates the server's timing alignment of multi-turn dialogues. The session identifier is a globally unique string used to associate multiple rounds of voice interaction in the same ticketing process, enabling the server to perform continuous intent recognition based on context.

[0042] The voice ticketing method provided in this embodiment realizes the complete process from interface loading, voice acquisition to data encapsulation through the interaction module, laying the data foundation for sending the voice data to the remote server for intent recognition.

[0043] Based on the above embodiments, in this embodiment, after step 300 of sending the real-time voice data to the remote ticketing server and receiving the ticketing service processing instruction returned by the remote ticketing server after performing intent recognition based on the real-time voice data, the method further includes: Parse the ticket purchase service processing instruction to obtain the intent type and ticket purchase parameters contained in the ticket purchase service processing instruction; If the intent type is confirmation of ticket purchase intention, ticket purchase option information is generated based on the ticket purchase parameters; If the intent type is an information supplementation request, generate follow-up prompt information corresponding to the information supplementation request; If the intent type is "ticket purchase completion confirmation", ticket purchase result information is generated.

[0044] Specifically, after receiving the ticket purchase service processing instruction returned by the remote ticketing server, the interaction module first parses the instruction to obtain the intent type and ticket purchase parameters contained therein. The intent type refers to the classification of the user's current ticket purchase stage identified by the server after semantic understanding of the user's speech through a large model. For example, it can include ticket purchase intention confirmation (indicating that the user has clearly expressed the intention to buy a certain train or plane ticket), information supplementation request (indicating that the server has detected missing information in the ticket purchase process, such as the lack of destination, time, or passenger information, and needs to ask the user for follow-up), and ticket purchase completion confirmation (indicating that the user has completed the ticket selection and entered the final confirmation or payment stage). Ticket purchase parameters are structured data associated with the intent type. For example, under the intent of ticket purchase intention confirmation, it can include key information such as the destination, departure time, and ticket type mentioned by the user; under the intent of information supplementation request, it can include the identifier of the missing information type; and under the intent of ticket purchase completion confirmation, it can include a detailed summary of the selected ticket.

[0045] Subsequently, the interaction module performs corresponding information generation operations based on different intent types: When the intent type is confirmation of ticket purchase intention, the interaction module generates ticketing options for the user based on the parsed ticketing parameters (e.g., destination "City A" and time "tomorrow morning"), such as "We have found trains to City A tomorrow morning, the earliest is 8:30 AM, would you like to book?"; when the intent type is a request for supplementary information, the interaction module generates corresponding follow-up questions based on the type of missing information, such as "When do you plan to depart?" if the server detects that the departure time is missing; when the intent type is confirmation of ticket purchase completion, the interaction module generates purchase result information based on the ticketing parameters, such as "You have successfully booked the train to City A at 8:30 AM tomorrow, please check your SMS notification." Through these steps, the interaction module parses and converts the abstract instructions returned by the server into concrete interactive content that can be presented to the user, providing a structured and contextualized information foundation for guiding the user through the ticketing process via voice broadcast, achieving intelligent transformation from intent recognition results to user-understandable prompts.

[0046] Further, step 400, based on the ticket purchase service processing instruction, invokes the corresponding voice control method to guide the user through the ticket purchase process, including: Step 410: Match the corresponding voice broadcast template from the preset voice template library according to the parsed intent type.

[0047] Step 420: Call the voice broadcast interface to convert the ticket purchase option information, the follow-up question prompt information, or the ticket purchase result information into voice signals for broadcast.

[0048] Step 430: After the broadcast is completed, the voice monitoring interface is called again to receive the user's next round of voice input.

[0049] Step 440: Repeat the above broadcast and listening steps until the ticket purchase process is completed.

[0050] Specifically, the interaction module matches the corresponding voice broadcast template from the preset voice template library according to the intent type parsed in step 300. The preset voice template library refers to a set of templates that are stored locally in the interaction module or can be loaded from a remote location and contain broadcast statements for various ticket purchase scenarios. For example, for the intent to confirm the intention to purchase tickets, the template "We have found a train to [destination] at [time], would you like to book?" can be matched; for the intent to request supplementary information, the templates "What time do you plan to depart?" or "Please tell us your destination" can be matched; and for the intent to confirm the completion of ticket purchase, the template "You have successfully booked [ticket details], please check the notification" can be matched.

[0051] The matching process involves filling the placeholders in the corresponding template with the ticketing option information, follow-up prompts, or ticketing result information generated in step 300, forming a complete and natural broadcast statement. Subsequently, the interaction module calls the voice broadcast interface to convert the filled-in content into a voice signal for broadcast. The voice broadcast interface refers to the functional interface exposed by the interaction module for controlling the robot's speaker hardware, such as a JavaScript interface called `startSpeech`. When this interface is called, the interaction module sends a speaker usage request to the robot system, converts the text content into an audio stream through the speech synthesis engine, and drives the speaker to play it. During the broadcast, the interaction module can monitor the broadcast status in real time to ensure that subsequent operations are performed only after the broadcast is complete.

[0052] After the broadcast is completed, the interaction module calls the voice monitoring interface as described above again to receive the user's next round of voice input. Calling again means restarting the microphone to enter the state of waiting for the user's response, such as calling the startRecord interface again to activate voice monitoring. This design enables the interaction module to capture the user's feedback in a timely manner after the broadcast prompt, forming a complete interactive loop of "broadcast prompt - user response".

[0053] Finally, the interaction module repeats the above broadcasting and listening steps until the ticket purchase process ends. For example, a user may need to go through multiple rounds of questions and answers to provide all the ticket purchase information. The interaction module performs template matching, voice broadcasting, and voice listening in a loop according to the intent type returned by the server in each round, gradually guiding the user to complete the entire process from intent confirmation to information supplementation and final confirmation. When the intent to confirm ticket purchase is parsed in step 300 or the user clearly expresses the intention to end, the interaction module exits the loop and enters the subsequent control recovery step.

[0054] The voice ticketing method provided in this embodiment effectively reduces the development complexity of multi-turn dialogue interaction and ensures the integrity of the ticketing process and the accuracy of guidance.

[0055] Based on the above embodiments, in this embodiment, step 100, receiving the control management instruction issued by the robot system when it detects that a user has the intention to purchase tickets, includes: Receive managed instructions transmitted by the robot system through a preset control transfer interface; Through the control transfer interface, the robot system synchronously receives initial data; wherein, the initial data includes semantic information of the user's current dialogue context and identified ticket purchase intention keywords; Based on the initial data, determine the initial display content and the first round of voice broadcast content of the voice ticketing interaction interface.

[0056] Specifically, the interaction module receives managed instructions from the robot system through a pre-defined control transfer interface. This control transfer interface is a pre-agreed communication interface between the robot system and the interaction module, such as an API function called `getUserQuestion`. When the robot system detects through its own voice interaction capabilities that the user's current dialogue involves ticket purchase intentions (e.g., the user says "I want to buy a ticket to City A"), the robot system actively calls this interface, temporarily transferring the interaction leadership to the interaction module. Simultaneously, through the same control transfer interface, the interaction module receives initial data from the robot system. This initial data refers to contextual information related to the current user's dialogue that the robot has collected and identified before transferring control. Specifically, it may include semantic information about the user's current dialogue context (e.g., the robot has recorded recent dialogue content, such as the user previously asking "What time is it?" or "How's the weather today?", which helps the ticket purchase system more accurately understand the user's intent) and identified keywords related to ticket purchase intentions (e.g., key information such as "buy tickets," "City A," and "tomorrow" initially identified by the robot from the user's current speech).

[0057] Subsequently, based on the received initial data, the interaction module determines the initial display content and the first round of voice broadcast content for the voice ticketing interface. For example, if the initial data includes the user's stated destination "City A" and time "tomorrow," the interaction module can set the initial display content of the voice ticketing interface to "Checking for trains to City A tomorrow," and generate the first round of voice broadcast content as "Do you want to buy a ticket to City A tomorrow? Please confirm," thus avoiding requiring the user to repeatedly provide information already expressed. If the initial data only contains the intention to purchase tickets but lacks specific parameters, the interaction module can set the initial display content to a ticketing guidance interface, and generate the first round of broadcast content as "Where do you want to go?" Through this mechanism, the interaction module can fully utilize the dialogue context collected by the robot system as soon as it takes over control, achieving a smooth transition and intelligent guidance in the ticketing process, avoiding users repeatedly describing their needs, and significantly improving interaction efficiency and user experience.

[0058] It should be noted that during the period when the interaction module assumes control of the interaction, it blocks the robot system's own voice interaction interface to ensure that the user's voice input is processed only by the interaction module.

[0059] Step 400: After invoking the corresponding voice control method according to the ticket purchase service processing instruction to guide the user to complete the ticket purchase process, the method further includes: Upon confirming that the user has completed the ticket purchase, a notification to reclaim control is sent to the robot system, and the robot itself and its corresponding interactive interface are closed.

[0060] Specifically, after the interaction module guides the user through the ticket purchase process according to the ticket purchase service instructions, it needs to confirm whether the user has completed the purchase. This confirmation can be achieved in several ways, such as the interaction module receiving a confirmation instruction from a remote ticketing server, the user explicitly expressing their intention to purchase (e.g., "I'll buy this one," "Confirm payment") during multiple rounds of dialogue with the interaction module, or triggering a purchase completion signal via the "Complete" button on the interactive interface. After confirming the user's purchase is complete, the interaction module sends a control relinquishment notification to the robot system. This notification, sent through a pre-defined communication interface (e.g., the onCloseHtml interface), requests the relinquishment of control. This notification can also carry purchase result information (e.g., successful purchase status, order number), allowing the robot to provide subsequent services (e.g., asking if further assistance is needed) after regaining control. Subsequently, the interaction module shuts down itself and its corresponding interaction interface; shutting down itself means that the interaction module terminates its running instance, releasing the system memory and processing resources it occupies; shutting down the corresponding interaction interface means unloading or hiding the previously loaded voice ticketing interaction interface (such as an H5 page), so that the robot's display screen returns to the state before it was hosted or the robot's default main interface.

[0061] It should be noted that during the entire period when the interaction module holds the control of the interaction, it sends an interface disable command to the robot system or uses a control transfer protocol to make the robot system suspend its own voice interaction interface, ensuring that the user's voice input is processed only by the interaction module. This exclusive control mechanism avoids the conflict and chaos caused by the robot system and the interaction module competing for microphone resources or responding to the user's voice at the same time, thus ensuring the continuity and stability of the ticket purchase interaction process.

[0062] The voice ticketing method provided in this embodiment achieves smooth switching and seamless connection between the interactive module and the robot system through the above-mentioned control recovery mechanism and exclusive control during the hosting period: when the ticketing task begins, the robot system smoothly transfers control to the interactive module; when the ticketing task is completed, control is promptly and completely returned to the robot system, and the robot can immediately restore its original general functions, providing users with a continuous and consistent overall service experience.

[0063] Figure 2 This is a schematic diagram of the integrated framework of the voice ticketing method provided in the embodiments of this application. The following is in conjunction with... Figure 2 The following is a detailed description of the voice ticketing method provided in the embodiments of this application.

[0064] like Figure 2As shown, the robot system integrates an interaction module (in this embodiment, a webpage rendering module based on WebPages technology) and several general-purpose functional modules such as voice, camera, and navigation. The WebPages module exposes a series of interface methods for interactive control and underlying hardware capability calls with the robot system: the getUserQuestion interface serves as a control transfer interface, receiving the managed instructions and initial dialogue context transmitted by the robot system after detecting a user's ticket purchase intention; the startRecord and stopRecord interfaces control the robot's microphone to start and stop, enabling real-time acquisition of user voice data; the startSpeech and stopSpeech interfaces control the robot's speaker to broadcast prompts and terminate broadcasts; and the onCloseHtml interface closes the interface, sending a control revocation notification and closing the interactive interface after ticket purchase. The robot system's integrated large-scale voice model can be used for remote voice intent recognition (or in conjunction with a remote ticketing server). The camera auto-navigation and navigation modules serve as general robot functions, operating normally when not managed, ensuring the robot's original service capabilities remain unaffected.

[0065] In a specific ticket-buying scenario, a user approaches the robot and says, "I want to buy a high-speed rail ticket to City A tomorrow." The robot, using its speech recognition capabilities, detects the user's intention to purchase a ticket and then sends a control delegation instruction to the WebPages module via the getUserQuestion interface, simultaneously transmitting the identified purchase intent keywords "tomorrow," "City A," and the current dialogue context. Upon receiving the instruction, the WebPages module loads the H5 ticket-buying interface and, based on the initial data, generates the first round of announcements as "Do you want to buy a high-speed rail ticket to City A tomorrow?" It then calls the startSpeech interface to broadcast this prompt through the robot's speaker. After the announcement, the WebPages module calls the startRecord interface to start microphone listening and capture the user's confirmation voice. The user responds "Yes," and the voice data, after being collected and encapsulated, is sent to a remote ticket-buying server. The server, using a large-scale model, recognizes the user's intention to confirm the purchase and returns an instruction containing confirmation of purchase intent, destination, and time parameters. After parsing the instructions, the WebPages module generates ticketing options: "We've found two trains tomorrow morning at 8:30 AM and 9:30 AM. Which one would you like to choose?". It then calls `startSpeech` again to announce the selection and `startRecord` to listen for the user's choice. This process repeats multiple times until the user confirms their ticket purchase. Finally, the WebPages module calls the `onCloseHtml` interface to send a control relinquishment notification to the robot system. The robot regains control of its own voice interface, the WebPages module closes the H5 interface and releases resources, ending the ticketing process. The robot can then continue to provide other consulting services to the user.

[0066] The voice ticketing device provided in the embodiments of this application is described below. The voice ticketing device described below can be referred to in correspondence with the voice ticketing method described above.

[0067] Figure 3 This is a schematic diagram of the structure of the voice ticketing device provided in the embodiments of this application, as shown below. Figure 3 As shown in the embodiment of this application, the voice ticketing device includes: The receiving unit 301 is used to receive the control management instruction issued by the robot system when it detects that the user has the intention to purchase tickets; The acquisition unit 302 is used to acquire the user's real-time voice data in response to the control management instruction; The sending unit 303 is used to send the real-time voice data to the remote ticketing server, so as to receive the ticketing service processing instruction returned by the remote ticketing server after performing intent recognition based on the real-time voice data; The ticket purchasing unit 304 is used to call the corresponding voice control method according to the ticket purchasing service processing instruction to guide the user to complete the ticket purchasing process.

[0068] The voice ticketing device provided in this application embodiment is applied to the interaction module integrated into a robot system. It receives a control delegation instruction issued by the robot system when it detects a user's intention to purchase tickets; in response to the control delegation instruction, it collects the user's real-time voice data; it sends the real-time voice data to a remote ticketing server to receive a ticketing service processing instruction returned by the remote ticketing server after intention recognition based on the real-time voice data; and according to the ticketing service processing instruction, it calls the corresponding voice control method to guide the user to complete the ticketing process. Therefore, this application embodiment integrates an independent interaction module into the robot system, and after detecting a user's intention to purchase tickets, the robot system temporarily delegates the interaction control to this module, which independently completes the subsequent voice data collection, server interaction, and ticketing guidance process. This decouples the personalized voice ticketing function from the robot's original general functions. This allows third-party developers to focus solely on the development of the interaction module for the ticketing business logic without needing to delve into the robot's underlying SDK for complete system development or repeatedly implement the robot manufacturer's mature general interaction capabilities. They can meet the need for rapid deployment of personalized voice ticketing services on existing robot platforms in a low-cost and high-efficiency manner.

[0069] Based on the above embodiments, in this embodiment, the acquisition unit 302 is specifically used for: In response to the control delegation instruction, load and display the voice ticketing interface; The user's real-time voice data is collected through the voice ticketing interface.

[0070] Based on the above embodiments, in this embodiment, the device further includes a cleaning unit, specifically used for: After the user is guided through the ticket purchase process by invoking the corresponding voice control method according to the ticket purchase service processing instruction, the process is completed. Upon confirming that the user has completed the ticket purchase, a notification to reclaim control is sent to the robot system, and the robot itself and its corresponding interactive interface are closed.

[0071] Based on the above embodiments, in this embodiment, the acquisition unit 302 is further used for: The voice ticketing interface is used to call the voice monitoring interface to start real-time acquisition of the user's voice input; If the user's voice input ends, the voice stop interface is invoked to terminate the current voice acquisition. The collected voice data is encapsulated into a pre-formatted voice data packet and a timestamp and session identifier are added as real-time voice data to be sent.

[0072] Based on the above embodiments, in this embodiment, the device further includes a parsing unit, specifically used for: After sending the real-time voice data to the remote ticketing server and receiving the ticketing service processing instruction returned by the remote ticketing server after performing intent recognition based on the real-time voice data, Parse the ticket purchase service processing instruction to obtain the intent type and ticket purchase parameters contained in the ticket purchase service processing instruction; If the intent type is confirmation of ticket purchase intention, ticket purchase option information is generated based on the ticket purchase parameters; If the intent type is an information supplementation request, generate follow-up prompt information corresponding to the information supplementation request; If the intent type is "ticket purchase completion confirmation", ticket purchase result information is generated.

[0073] Based on the above embodiments, in this embodiment, the ticket purchasing unit 304 is specifically used for: Based on the parsed intent type, a corresponding voice broadcast template is matched from a preset voice template library; Call the voice broadcast interface to convert the ticket purchase option information, the follow-up question prompt information, or the ticket purchase result information into voice signals for broadcast; After the broadcast is completed, the voice monitoring interface is called again to receive the user's next round of voice input; Repeat the above broadcasting and listening steps until the ticket purchase process is complete.

[0074] Based on the above embodiments, in this embodiment, the receiving unit 301 is specifically used for: Receive managed instructions transmitted by the robot system through a preset control transfer interface; Through the control transfer interface, the robot system synchronously receives initial data; wherein, the initial data includes semantic information of the user's current dialogue context and identified ticket purchase intention keywords; Based on the initial data, determine the initial display content and the first round of voice broadcast content of the voice ticketing interaction interface.

[0075] Based on the above embodiments, in this embodiment, the interaction module shields the robot system's own voice interaction interface during the period of managing the interaction control, ensuring that the user's voice input is processed only by the interaction module.

[0076] Figure 4An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown, the electronic device can be a robot or other electronic device. This electronic device may include: a processor 410, a communications interface 420, a memory 430, and a communication bus 450. The processor 410, communications interface 420, and memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions from the memory 430 to execute a voice ticketing method, applied to the interactive module integrated into the robot system. The method includes: Receive control management instructions issued by the robot system when it detects that a user intends to purchase tickets; In response to the control delegation instruction, the user's real-time voice data is collected; The real-time voice data is sent to a remote ticketing server to receive a ticketing service processing instruction returned by the remote ticketing server after performing intent recognition based on the real-time voice data. Based on the ticket purchase service processing instruction, the corresponding voice control method is invoked to guide the user to complete the ticket purchase process.

[0077] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application embodiment, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in at least one embodiment of this application embodiment. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0078] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the voice ticketing method provided by the above methods, and apply it to the interaction module integrated in a robot system. The method includes: Receive control management instructions issued by the robot system when it detects that a user intends to purchase tickets; In response to the control delegation instruction, the user's real-time voice data is collected; The real-time voice data is sent to a remote ticketing server to receive a ticketing service processing instruction returned by the remote ticketing server after performing intent recognition based on the real-time voice data. Based on the ticket purchase service processing instruction, the corresponding voice control method is invoked to guide the user to complete the ticket purchase process.

[0079] In another aspect, embodiments of this application also provide a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the voice ticketing method provided by the above methods, and is applied to the interaction module integrated into a robot system. The method includes: Receive control management instructions issued by the robot system when it detects that a user intends to purchase tickets; In response to the control delegation instruction, the user's real-time voice data is collected; The real-time voice data is sent to a remote ticketing server to receive a ticketing service processing instruction returned by the remote ticketing server after performing intent recognition based on the real-time voice data. Based on the ticket purchase service processing instruction, the corresponding voice control method is invoked to guide the user to complete the ticket purchase process.

[0080] The device embodiments described above are merely illustrative. 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0081] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0082] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of this application, and are not intended to limit them; although the embodiments of this application have been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features; and these 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.

Claims

1. A voice ticketing method, characterized by, The method, applied to an interaction module integrated into a robot system, includes: Receive control management instructions issued by the robot system when it detects that a user intends to purchase tickets; In response to the control delegation instruction, the user's real-time voice data is collected; The real-time voice data is sent to a remote ticketing server to receive a ticketing service processing instruction returned by the remote ticketing server after performing intent recognition based on the real-time voice data. Based on the ticket purchase service processing instruction, the corresponding voice control method is invoked to guide the user to complete the ticket purchase process.

2. The voice ticketing method of claim 1, wherein, The step of collecting the user's real-time voice data in response to the control delegation instruction includes: In response to the control delegation instruction, load and display the voice ticketing interface; The user's real-time voice data is collected through the voice ticketing interface.

3. The voice ticketing method of claim 2, wherein, After invoking the corresponding voice control method according to the ticket purchase service processing instruction to guide the user to complete the ticket purchase process, the method further includes: Upon confirming that the user has completed the ticket purchase, a notification to reclaim control is sent to the robot system, and the robot itself and its corresponding interactive interface are closed.

4. The voice ticketing method of claim 2, wherein, The process of collecting the user's real-time voice data through the voice ticketing interface includes: The voice ticketing interface is used to call the voice monitoring interface to start real-time acquisition of the user's voice input; If the user's voice input ends, the voice stop interface is invoked to terminate the current voice acquisition. The collected voice data is encapsulated into a pre-formatted voice data packet and a timestamp and session identifier are added as real-time voice data to be sent.

5. The voice ticketing method of claim 4, wherein, After sending the real-time voice data to a remote ticketing server and receiving a ticketing service processing instruction returned by the remote ticketing server after performing intent recognition based on the real-time voice data, the method further includes: Parse the ticket purchase service processing instruction to obtain the intent type and ticket purchase parameters contained in the ticket purchase service processing instruction; If the intent type is confirmation of ticket purchase intention, ticket purchase option information is generated based on the ticket purchase parameters; If the intent type is an information supplementation request, generate follow-up prompt information corresponding to the information supplementation request; If the intent type is "ticket purchase completion confirmation", ticket purchase result information is generated.

6. The voice ticketing method of claim 5, wherein, The step of invoking the corresponding voice control method according to the ticket purchase service processing instruction to guide the user to complete the ticket purchase process includes: Based on the parsed intent type, a corresponding voice broadcast template is matched from a preset voice template library; Call the voice broadcast interface to convert the ticket purchase option information, the follow-up question prompt information, or the ticket purchase result information into voice signals for broadcast; After the broadcast is completed, the voice monitoring interface is called again to receive the user's next round of voice input; Repeat the above broadcasting and listening steps until the ticket purchase process is complete.

7. The voice ticketing method of claim 2, wherein, The receiving of the control management instruction issued by the robot system when it detects that a user intends to purchase tickets includes: Receive managed instructions transmitted by the robot system through a preset control transfer interface; Through the control transfer interface, the robot system synchronously receives initial data; wherein, the initial data includes semantic information of the user's current dialogue context and identified ticket purchase intention keywords; Based on the initial data, determine the initial display content and the first round of voice broadcast content of the voice ticketing interaction interface.

8. The voice ticketing method according to any one of claims 1 to 7, characterized by, During the period when the interaction module assumes control of the interaction, it blocks the robot system's own voice interaction interface to ensure that the user's voice input is processed only by the interaction module.

9. A voice ticketing apparatus, characterized by comprising: The device is used in an interaction module integrated into a robot system, and includes: The receiving unit is used to receive the control management instruction issued by the robot system when it detects that the user has the intention to purchase tickets; The acquisition unit is used to acquire the user's real-time voice data in response to the control management instruction; The sending unit is used to send the real-time voice data to the remote ticketing server, and to receive the ticketing service processing instruction returned by the remote ticketing server after performing intent recognition based on the real-time voice data. The ticket purchasing unit is used to invoke the corresponding voice control method according to the ticket purchasing service processing instruction to guide the user to complete the ticket purchasing process.

10. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the voice ticketing method as described in any one of claims 1 to 8.

Images