Tour guide commentary audio and synchronous asr text delivery method based on voice intercom system

Abstract

The application discloses a guide commentary audio and synchronous ASR text transmission method based on a voice intercom system, aiming at improving the problems of low explanation efficiency, poor tourist experience, lack of perfect online payment and automatic sharing mechanism and the like in the prior art. Technical points: S100, a unique identification two-dimensional code is generated through a real-time voice intercom APP, the unique identification two-dimensional code contains guide identity information, temporary group identification information and payment information; S200, a tourist scans the unique identification two-dimensional code through a mini-program or an intercom APP, analyzes the guide identity information, the temporary group identification information and the payment information contained in the two-dimensional code, and joins a temporary group corresponding to the guide after payment according to the payment information; S300, a guide collects commentary voice information through a real-time voice intercom APP or a paired intercom device, and sends the commentary voice information to the temporary group; S400, a tourist of the temporary group receives and plays commentary voice and text information of the guide through a real-time voice intercom APP or a mini-program.

Description

Technical Field

[0001] This invention relates to the fields of tourism service technology and mobile communication technology, specifically a method for transmitting tour guide audio and synchronous ASR text based on a voice intercom system. Background Technology

[0002] With the continuous development of my country's economy and the significant improvement of people's living standards, the tourism industry has experienced tremendous growth, becoming a new growth point for the national economy. At the same time, with the development of the tourism industry, the purpose of modern tourism activities has gradually shifted from simple enjoyment to education, information acquisition, knowledge expansion, and experience enrichment. These changes have placed higher demands on tour guide services.

[0003] Tour guide services are increasingly becoming a knowledge-intensive, comprehensive service, requiring tour guides to possess extensive knowledge, standard Mandarin, and excellent communication skills. During their service, tour guides need to disseminate culture, impart knowledge, and share interesting anecdotes related to the attractions. Although the number of tour guides is constantly increasing, the quality of service remains uneven, and there is a severe shortage of tour guides with high overall qualifications, making it difficult for the tour guide workforce to adapt to the development of the modern tourism industry.

[0004] In traditional tour guide methods, tour guides often rely on loudspeakers to explain things to tourists, which presents several problems: First, it's inefficient: in noisy scenic areas, tour guides need to shout for group members to hear clearly, which is not only physically demanding but also has limited sound range, making it difficult for tourists at a distance to hear clearly. Second, it provides a poor tourist experience: traditional loudspeaker methods easily cause noise pollution, affecting the tour experience of other tourists; at the same time, tourists cannot choose to listen to or replay the explanations according to their own needs, lacking flexibility. Third, the explanations cannot be saved and reused: the tour guide's on-site explanations cannot be effectively recorded and saved, and tourists cannot review the explanations after the tour or share them with relatives and friends who were not traveling with them. Fourth, the payment and revenue sharing mechanisms are inadequate: the current tour guide service fee model is simplistic, lacking convenient online payment and automatic revenue sharing mechanisms, making it difficult for tour guides to receive reasonable compensation for their service value.

[0005] Currently, some existing technologies attempt to address the aforementioned problems. For example, patent application CN118632197A discloses a voice intercom method and system that uses QR codes for location identification. By placing a QR code on a desktop or in a designated area, users can scan the QR code to bring up an intercom interface to send voice or text messages. However, this system is mainly suitable for location identification in fixed locations and is not suitable for real-time tour guide explanations in mobile scenarios.

[0006] For example, patent application CN118379823A discloses a real-time tour guide service system based on a virtual platform. This system uses electronic guide devices with QR code labels at scenic area entrances, allowing tourists to scan the QR code and retrieve audio guides for the current attraction from a server. However, this system uses pre-recorded audio guides, which cannot provide real-time, live tour guide commentary.

[0007] Furthermore, patent application CN120186591A discloses a wireless tour guide system and method. The tour guide's device sends a pairing request via near-field communication (NFC) and establishes a pairing relationship with the tourist's device before transmitting audio signals. However, this system requires a pairing relationship to be established between the tour guide's device and the tourist's device, making it complex to operate and unsupporting simultaneous tour guide services for large groups.

[0008] Therefore, there is an urgent need in this field for a method of delivering tour guide audio narration that can efficiently convey real-time tour guide explanations, support large groups listening simultaneously, have convenient group entry methods and payment sharing mechanisms, and provide multiple listening methods and auxiliary functions. Summary of the Invention

[0009] The purpose of this invention is to provide a method for transmitting tour guide audio and synchronous ASR text based on a voice intercom system. This method aims to improve the problems of low efficiency, poor tourist experience, inability to retain and reuse content, difficulty in adapting to large-scale group services, and lack of a sound online payment and automatic revenue sharing mechanism in existing tour guide audio transmission methods.

[0010] This invention provides a method for transmitting tour guide audio and synchronized ASR text based on a voice intercom system, wherein the voice intercom system includes: A real-time voice intercom APP or intercom device with real-time voice intercom function installed on the tour guide's mobile terminal, wherein the real-time voice intercom APP or intercom device is used to collect and send the tour guide's narration voice information. A real-time voice intercom APP installed on the tourist's mobile terminal, the real-time voice intercom APP being used to receive voice information from the tour guide's real-time voice intercom APP or intercom device; The method for transmitting audio guide narration includes the following steps: S100. Generate a unique identification QR code through a real-time voice intercom APP or intercom device. The unique identification QR code contains the tour guide's identity information, temporary group identification information, and payment information. S200: Tourists scan the unique QR code through the mini-program or walkie-talkie APP, and then analyze the tour guide's identity information, temporary group identification information, and payment information contained in the QR code. After completing the payment according to the payment information, they join the temporary group corresponding to that tour guide. S300: The tour guide collects narration audio information through a real-time voice intercom APP or paired intercom device and sends it to a temporary group. Tourists in S400 and temporary groups can receive and play the tour guide's audio and text information through a real-time voice intercom app or mini-program.

[0011] Furthermore, both the real-time voice intercom app and the intercom device are equipped with a PTT function key. When the tour guide is giving a commentary, the PTT function key is triggered to start the collection and transmission of voice information, and the collection and transmission of voice information is stopped when the PTT function key is released or triggered again.

[0012] Furthermore, the collection and transmission of tour guide narration audio includes the following modes: Mode 1: The tour guide triggers the continuous automatic voice acquisition mode, and the real-time voice intercom APP or intercom device begins to acquire the tour guide's narration voice; the real-time voice intercom APP or intercom device has a built-in VAD module to detect silent periods in the tour guide's voice in real time; when a valid voice from the tour guide is detected, it begins to be sent; when the detected silence duration exceeds a preset threshold, the current voice segment is automatically terminated and then sent to a temporary group; it continues to automatically start again based on VAD detection, and repeats continuously.

[0013] Furthermore, the collection and transmission of tour guide narration audio also includes the following modes: Mode 2: The tour guide continuously presses and holds the PTT function button. The real-time voice intercom app or device continuously captures the tour guide's narration while the button is held and sends it to the temporary group in real time. When the tour guide releases the PTT function button, the capture and sending stop. Similar to the basic intercom mode, this allows tour guides to independently control the content of their narration, improving the relevance of their presentations.

[0014] Furthermore, the real-time voice intercom app or intercom device has an ASR module, which is used to convert the tour guide's narration into text; the converted text is sent to tourists through at least one of the following methods: Method 1: Send to the temporary group, and tourists can read it through the real-time voice intercom app; Method 2: Send to tourists via WeChat mini-program.

[0015] Furthermore, the payment amount corresponding to the payment information of the unique identification QR code is set by the tour guide through a real-time voice intercom APP or intercom device. When the payment amount is greater than 0, tourists can join the temporary group only after completing the payment; when the payment amount is 0, tourists can join the temporary group directly for free.

[0016] Furthermore, the payment information also includes a paid usage period, which is the effective listening time and listening area range preset by the tour guide through a real-time voice intercom APP or intercom device; after the tourist completes the payment, he / she enjoys temporary group voice listening privileges within the paid usage period, and the listening privileges automatically expire after the paid usage period expires.

[0017] Furthermore, the real-time voice intercom app on the tour guide's end and the real-time voice intercom app on the tourist's end are different functional modes of the same app.

[0018] In a preferred embodiment, the present invention further includes a dedicated earphone authorized listening mode: The dedicated earphone is an earphone with a unique identifier, which is stored inside the earphone and can be read through a wired audio interface or Bluetooth channel; After a tourist connects the dedicated headset to a mobile terminal for the first time, the real-time voice intercom APP reads the headset's identification and sends it to the server. The server then associates the identification with the tour guide's current temporary group and brings the headset under the tour guide's management authority. When the headset is reconnected, the real-time voice intercom app reads the headset's identity identifier and sends it to the server for permission verification. After the server verifies that the headset has been registered under the tour guide's management authority, it grants the tourist access to the current temporary group's audio listening privileges.

[0019] Furthermore, the dedicated earphone is a wired earphone or a Bluetooth earphone; the Bluetooth earphone has a built-in unique identification chip, which transmits the identification through the Bluetooth channel.

[0020] Compared with the prior art, the beneficial effects of the present invention are: 1. This invention collects tour guides' narration voice through a real-time voice intercom APP and transmits it to tourists' terminals in real time via the Internet, overcoming the problems of limited sound propagation range and noise pollution of traditional loudspeaker methods.

[0021] 2. This invention provides tour guides with flexible voice acquisition methods through two modes: VAD automatic sentence segmentation and button control, adapting to different explanation scenarios; through ASR technology, the speech is converted into text and pushed to the APP or WeChat mini program, which not only realizes the retention and reuse of the explanation content, but also provides tourists with two options: audio listening and text reading.

[0022] 3. This invention uses an online payment and automatic revenue sharing mechanism, allowing tourists to complete payments within the app and tour guides to receive corresponding service compensation, eliminating the need for manual reconciliation and transfers.

[0023] 4. After purchasing the dedicated earphones, tourists can listen directly by plugging them in without scanning a code or paying. This is especially suitable for tourists with poor signal in scenic areas or those who are not familiar with mobile phone operation, and it can also increase the income of tour guides. Attached Figure Description

[0024] Figure 1 This is a flowchart of a method for transmitting audio guide commentary and synchronous ASR text based on a voice intercom system, as provided in Embodiment 1 of the present invention. Detailed Implementation

[0025] The following description, in conjunction with the accompanying drawings and specific embodiments, provides further details: Example 1

[0026] This embodiment provides a tour guide audio transmission system based on a voice intercom system, including a tour guide terminal, a tourist terminal, and a server.

[0027] The tour guide terminal is a mobile device carried by tour guides, and it includes two implementation methods: one is a general mobile terminal such as a smartphone with a real-time voice intercom app installed; the other is an intercom device with real-time voice intercom functionality. This intercom device is a smart intercom terminal with a display screen and network communication capabilities (such as 4G / 5G / Wi-Fi), and it has a real-time voice intercom app installed or has built-in equivalent software modules, capable of displaying QR codes, communicating online, and running VAD and ASR modules. The two methods are completely equivalent in core functions such as QR code generation, voice capture, group management, and revenue sharing.

[0028] The tour guide terminal has the following functional modules: a QR code generation module for automatically generating a unique identification QR code; a voice acquisition module for acquiring the tour guide's narration; a PTT control module for responding to the tour guide's PTT function key triggering operations; a VAD module for real-time detection of voice activity in the voice signal, identifying silent and voice periods; an ASR module for converting the tour guide's narration into text; a communication module for establishing a communication connection with the server; a group management module for creating and managing temporary groups; and a payment setting module for setting the payment amount and paid usage duration.

[0029] The tourist terminal is a mobile device carried by the tourist, such as a smartphone, with a real-time voice intercom app installed. The tourist terminal or tourist mode of the real-time voice intercom app has a scanning module (for scanning a unique identification QR code), a voice playback module (for playing the tour guide's narration), a text display module (for displaying text information converted from the tour guide's voice), a payment module (for completing Alipay or WeChat payments), a communication module (for establishing a communication connection with the server), and an earphone recognition module (for identifying and reading the identification of the dedicated earphone).

[0030] The tour guide terminal, tourist terminal and server establish a communication connection through the Internet, such as 4G / 5G mobile communication network or Wi-Fi network, to realize the real-time transmission of voice data and text data.

[0031] Example 2

[0032] This embodiment provides a method for transmitting tour guide audio narration based on the voice intercom system provided in Embodiment 1, such as... Figure 1 As shown, the specific steps include: S100 generates a unique identification QR code through a real-time voice intercom app. The unique identification QR code contains the tour guide's identity information, temporary group identification information, and payment information.

[0033] Tour guides create temporary groups via a real-time voice intercom app, and the server automatically assigns a unique temporary group identifier. The app then automatically generates a unique QR code. This QR code contains the following information: the tour guide's identity information, the temporary group identifier, and payment information. The tour guide's identity information uniquely identifies them and can be a tour guide ID, tour guide certificate number, or a unique user code assigned by the server. The temporary group identifier is the group ID automatically generated and assigned by the server when the tour guide creates the group. Payment information includes the payment amount and usage duration preset by the tour guide in the group settings interface. The payment amount can be any value; setting it to 0 indicates free use, and setting it to a value greater than 0 indicates paid use. The usage duration determines the valid listening period for tourists, such as 2 hours, 4 hours, etc. Listening privileges automatically expire after this duration. The QR code also includes a timestamp to record the generation time, allowing the server to verify if the QR code is still valid, and an encrypted verification code to prevent forgery or tampering. The server uses this verification code to verify the authenticity and integrity of the QR code.

[0034] After the tour guide completes the above settings, the real-time voice intercom app generates a unique identification QR code based on all the information provided. Once generated, the tour guide can display the QR code to tourists through various means, such as displaying it directly on their mobile device screen, printing it as a paper QR code for tourists to scan, or sharing the QR code image via social media.

[0035] S200: Tourists scan the unique QR code, parse the guide's identity information, temporary group identification information, and payment information contained in the QR code, and join the temporary group corresponding to that guide after completing the payment based on the payment information.

[0036] After installing and registering a real-time voice intercom app on their mobile devices, such as smartphones, tourists can use the app's QR code scanning function to scan the unique identification QR code displayed by the tour guide. The app then parses the QR code, extracting the tour guide's identification information, temporary group identification information, and payment information. The parsing results, along with the tourist's identification information, are packaged into a group joining request and sent to the server.

[0037] After receiving the group joining request, the server first verifies the validity of the QR code, including whether the timestamp is within the validity period and whether the encrypted verification code is correct. If the verification fails, the server returns an invalid QR code message to the tourist's terminal, and the process terminates. If the verification passes, the server further reads the payment mode configuration for the temporary group, which is pre-set and stored on the server by the tour guide before S100 via a real-time voice intercom app.

[0038] If it's a free trial (i.e., the paid amount is 0), the server directly adds the visitor's identification information to the temporary group's member list and returns a successful entry message to the visitor's terminal, granting them listening access. If it's a paid trial (i.e., the paid amount is greater than 0), the server returns a payment request to the visitor's terminal, including the paid amount, the paid usage duration, and payment methods such as Alipay and WeChat. The visitor selects a payment method and completes the payment on the real-time voice chat app. After successful payment, the payment platform returns a payment success certificate to the server. The server verifies the certificate, adds the visitor's identification information to the temporary group's member list, records the entry time, and sets the expiration time (the entry time plus the paid usage duration). Finally, a successful entry message is returned to the visitor's terminal. If the visitor fails to complete payment or the payment fails, the server will refuse to add the visitor to the temporary group.

[0039] After confirming receipt of payment, the server automatically calculates the tour guide's share based on a preset revenue-sharing ratio and credits it to the tour guide's account balance on the server. For example, the company receives 70% and the tour guide receives 30%. The tour guide can view the balance on the real-time voice chat app and apply for withdrawal to their personal bank account, Alipay, or WeChat account. If the paid usage time is zero or not set, it is considered unlimited and the privilege will not expire automatically.

[0040] S300: The tour guide collects the narration audio information through a real-time voice intercom APP and sends it to a temporary group.

[0041] The tour guide collects and sends audio narration information to a temporary group via a real-time voice intercom app. Both the app and the intercom device have PTT (Personal Toll-Free) function keys, available in both physical and virtual touchscreen formats. The tour guide selects one of the following two modes for audio collection and transmission based on the specific narration scenario.

[0042] Mode 1 is a continuous automatic voice acquisition mode. The real-time voice intercom app activates the voice acquisition module and begins acquiring the tour guide's narration via the built-in or external microphone. During acquisition, the built-in VAD module continuously analyzes the audio stream frame by frame, extracting the energy and spectral characteristics of each frame to determine whether the current frame is a speech frame or a non-speech frame, i.e., silence or ambient noise. The VAD module also maintains a silence timer. When the duration of continuously detected non-speech frames reaches a preset threshold, the current narration statement is considered to have ended. This silence duration threshold is set to 1 second by default. Tour guides can adjust this threshold in the real-time voice intercom app's settings interface according to their speaking speed and pausing habits; the adjustment range is typically 0.5 to 2 seconds. After the statement ends, the real-time voice intercom app automatically extracts the speech segment since the last pause from the audio cache, encodes and packages it, generates an independent message, and sends it to the server via the internet. Upon receiving the voice message, the server immediately distributes it to the terminals of all online tourists in the temporary group. During a single explanation, the tour guide can continuously trigger the PTT function key, and the VAD module will automatically complete the sentence segmentation and transmission between sentences without the tour guide needing to intervene manually.

[0043] Mode 2 is a button-controlled mode. The tour guide continuously presses and holds the PTT (Push-to-Talk) button, and the real-time voice intercom app continuously captures the tour guide's audio narration throughout the entire press-and-hold period. The captured audio data is encoded in real-time as an audio stream and continuously sent to the server. Upon receiving the audio stream, the server pushes it to all tourist terminals in the temporary group. When the tour guide releases the PTT button, the real-time voice intercom app detects the button release signal, immediately stops audio capture, and terminates the audio stream upload. This mode is similar to the basic intercom mode, allowing tour guides to independently control the content of their audio messages and improve the relevance of their presentations. Mode 2 does not perform VAD (Voice-Only Message) detection or automatic sentence segmentation; the start and end of the audio are entirely controlled by the tour guide's pressing and releasing of the PTT button.

[0044] The two modes can be switched at any time in the settings interface of the real-time voice intercom app, allowing tour guides to choose the appropriate mode based on the current narration scenario. For example, when providing a mobile tour of a scenic area, mode one can be selected to free up the hands, while mode two can be selected for precise control of the start and end of the voice when providing a detailed explanation at a fixed point.

[0045] Tourists in S400 and temporary groups can receive and play the tour guide's audio and text information through a real-time voice intercom app or mini-program.

[0046] Visitors in the temporary group receive and automatically play narration messages pushed by the server through a real-time voice intercom app. The app maintains a real-time message receiving channel in the background; when the server pushes a new voice message or audio stream, the app immediately plays it through the mobile device's speaker or connected wired or wireless headphones. Visitors can use the app's playback control interface to play and pause the current audio, adjust the volume, and drag the progress bar to replay previous audio clips. Voice messages are arranged in the app's message list in chronological order of reception, and visitors can replay any message at any time.

[0047] Furthermore, in a preferred embodiment, after receiving the tour guide's narration voice data, the server not only pushes it to the tourist's terminal in real time but also sends the voice data to the ASR module for speech recognition processing. The ASR module decodes the voice data into an audio stream, performs front-end processing such as noise reduction and echo cancellation, and then sends it to the speech recognition engine for feature extraction and pattern matching, converting it into corresponding text content. The ASR module supports the recognition of multiple languages ​​and dialects, including Mandarin, Cantonese, Sichuanese, and Wu dialect.

[0048] After conversion, the server sends the text content to the visitor using at least one of the following methods: Method 1: The server sends the text content as a message to a temporary group. This text message is displayed as supplementary content associated with the corresponding voice message. The visitor can see both the voice message and the text content simultaneously in the message list of the real-time voice intercom app, and can read the text separately. Method 2: The server pushes the text content to a WeChat mini-program associated with the real-time voice intercom app. The visitor can view the text version of the explanation in the WeChat mini-program, regardless of whether the real-time voice intercom app is running in the background. Visitors can choose to listen to the voice or read the text according to their needs. For example, they can choose to read the text in a noisy environment and listen to the voice in a quiet environment, or they can do both simultaneously to deepen their understanding.

[0049] Example 3

[0050] This embodiment provides an authorized listening method based on dedicated earphones, which are earphones with unique identifiers. For wired earphones, the unique identifier is stored inside the earphone and can be read through the audio interface; for Bluetooth earphones, a built-in unique identifier chip can be read through the Bluetooth channel.

[0051] When a tourist first connects the dedicated headset to their mobile device, the real-time voice intercom app automatically detects the headset connection. For wired headsets, the app reads the headset's identifier through the audio interface; for Bluetooth headsets, it reads the identifier through the Bluetooth channel. The app then sends the headset's identifier to the server, which associates it with the tour guide's current temporary group, thus adding the headset to the tour guide's management permissions.

[0052] When the headset reconnects, the real-time voice intercom app reads the headset's identifier and sends it to the server for permission verification. Once the server verifies that the headset is registered under the tour guide's management permissions, it grants the tourist access to the real-time voice communication for the current temporary group. The tourist can then listen to the tour guide's live commentary directly through the dedicated headset without needing to scan a code or pay. If verification fails—for example, if the headset is not registered, the registration has expired, or it has already been registered by another group—the server returns a verification failure message to the real-time voice intercom app, and the tourist cannot listen.

[0053] A tour guide can manage multiple dedicated headsets to meet the needs of multiple tourists in the group; a dedicated headset can only be registered under the management authority of one tour guide at a time.

[0054] In one implementation, tour guides can generate revenue by selling dedicated earpieces to tourists. Upon purchasing the earpiece, tourists gain access to its unique identifier and can directly listen to the tour guide's commentary without needing to scan QR codes or make payments through WeChat mini-programs or real-time voice communication apps. This method is particularly suitable for scenarios with poor signal in scenic areas, elderly tourists unfamiliar with mobile payment methods, and large groups seeking to simplify the group entry process.

[0055] The listening permissions granted to tourists through dedicated headsets can be set to have an expiration period. For example, tour guides can set the headset authorization to be valid only for the current temporary group, and the authorization will automatically expire after the group is disbanded; alternatively, the authorization can be set to be valid only for the current day, and must be re-authorized after expiration. When the dedicated headset is disconnected from the mobile terminal, the real-time voice intercom app on the tourist's end automatically pauses voice playback; when the headset is reconnected, if the authorization is still valid, the real-time voice intercom app on the tourist's end automatically resumes voice playback.

[0056] The working principle of this invention is as follows: Tour guides generate a unique QR code using a real-time voice intercom app or intercom device on their end. Tourists scan this QR code using their own real-time voice intercom app to join a temporary group. Tour guides preset a payment amount (which can be zero) and a usage duration on the server side. After scanning the code, tourists complete the payment according to the amount, and the server automatically allocates a portion of the fee to the tour guide, maintaining the tourist's listening access for the duration of the paid usage. Tour guides initiate voice capture by triggering the PTT function key, using either VAD automatic sentence segmentation or button control mode, pushing the voice to the tourist's terminal in real time via the server. Simultaneously, the server converts the voice into text using an ASR module and sends it to the tourist via the group or WeChat mini-program. Furthermore, tour guides can bind the identity of a dedicated headset to the temporary group by scanning a QR code. After a tourist inserts the headset, the system automatically completes authentication and permission granting, enabling plug-and-play functionality. Tour guides can generate additional revenue by selling dedicated headsets.

[0057] In summary, this invention overcomes the limitations of traditional speaker-based methods by capturing tour guides' narration via a real-time voice intercom app and transmitting it to tourists' terminals in real time via the internet. It simplifies the tour entry process by allowing quick group entry via QR code scanning. The invention provides tour guides with flexible voice capture methods through both VAD automatic sentence segmentation and button control, adapting to different narration scenarios. ASR technology converts speech into text and pushes it to the app or WeChat mini-program, enabling the retention and reuse of narration content and providing tourists with both audio listening and text reading options. Through online payment and automatic revenue sharing, tourists can complete payment within the app, and tour guides receive corresponding service compensation without manual reconciliation or transfers. Furthermore, after tourists purchase dedicated earphones, tour guides can bind them by scanning a code, and tourists can listen directly by plugging in the earphones without further scanning or payment. This is especially suitable for tourists with poor signal in scenic areas or those unfamiliar with mobile phone operation, and it can also generate additional income for tour guides.

[0058] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for transmitting tour guide audio and synchronized ASR text based on a voice intercom system, characterized in that, The voice intercom system includes: A real-time voice intercom APP or intercom device with real-time voice intercom function installed on the tour guide's mobile terminal, wherein the real-time voice intercom APP or intercom device is used to collect and send the tour guide's narration voice information. A real-time voice intercom app installed on tourists' mobile terminals is used to receive voice information from tour guides' real-time voice intercom apps or intercom devices. The method for transmitting audio guide narration includes the following steps: S100. Generate a unique identification QR code through a real-time voice intercom APP or intercom device. The unique identification QR code contains the tour guide's identity information, temporary group identification information, and payment information. S200: Tourists scan the unique QR code through the mini-program or walkie-talkie APP, and then analyze the tour guide's identity information, temporary group identification information, and payment information contained in the QR code. After completing the payment according to the payment information, they join the temporary group corresponding to that tour guide. S300: The tour guide collects narration audio information through a real-time voice intercom APP or paired intercom device and sends it to a temporary group. Tourists in S400 and temporary groups can receive and play the tour guide's audio and text information through a real-time voice intercom app or mini-program.

2. The method for transmitting tour guide audio and synchronized ASR text based on a voice intercom system according to claim 1, characterized in that, Both the real-time voice intercom app and the intercom device are equipped with a PTT function key. When the tour guide is giving a commentary, the PTT function key is triggered to start the collection and transmission of voice information, and the collection and transmission of voice information is stopped when the PTT function key is released or triggered again.

3. The method for transmitting tour guide audio and synchronized ASR text based on a voice intercom system according to claim 2, characterized in that, The collection and transmission of tour guide audio includes the following modes: Mode 1: The tour guide triggers the continuous automatic voice acquisition mode, and the real-time voice intercom APP or intercom device begins to acquire the tour guide's narration voice; the real-time voice intercom APP or intercom device has a built-in VAD module to detect silent periods in the tour guide's voice in real time; when a valid voice from the tour guide is detected, it begins to be sent; when the detected silence duration exceeds a preset threshold, the current voice segment is automatically terminated and then sent to a temporary group; it continues to automatically start again based on VAD detection, and repeats continuously.

4. The method for transmitting tour guide audio and synchronized ASR text based on a voice intercom system according to claim 2, characterized in that, The collection and transmission of tour guide audio also includes the following modes: Mode 2: The tour guide holds down the PTT function button, and the real-time voice intercom app or intercom device continuously collects the tour guide's narration voice while it is held down and sends it to the temporary group in real time; when the tour guide releases the PTT function button, the collection and sending stop.

5. The method for transmitting tour guide audio and synchronized ASR text based on a voice intercom system according to claim 1, characterized in that, The real-time voice intercom app or intercom device has an ASR module, which is used to convert the tour guide's narration into text; the converted text is sent to tourists through at least one of the following methods: Method 1: Send to the temporary group, and tourists can read it through the real-time voice intercom app; Method 2: Send to tourists via WeChat mini-program.

6. The method for transmitting tour guide audio and synchronized ASR text based on a voice intercom system according to claim 1, characterized in that, The payment amount corresponding to the payment information of the unique identification QR code is set by the tour guide through a real-time voice intercom APP or intercom device. When the payment amount is greater than 0, tourists can join the temporary group only after completing the payment; when the payment amount is 0, tourists can join the temporary group directly for free.

7. The method for transmitting tour guide audio and synchronized ASR text based on a voice intercom system according to claim 1, characterized in that, The payment information also includes the paid usage time, which is the effective listening time and listening area range preset by the tour guide through the real-time voice intercom APP or intercom device; after the tourist completes the payment, he / she has temporary group voice listening privileges within the paid usage time, and the listening privileges will automatically expire after the paid usage time is exceeded.

8. The method for transmitting tour guide audio and synchronized ASR text based on a voice intercom system according to claim 1, characterized in that, The real-time voice intercom app on the tour guide's end and the real-time voice intercom app on the tourist's end are different functional modes of the same app.

9. The method for transmitting tour guide audio and synchronized ASR text based on a voice intercom system according to claim 1, characterized in that, It also includes a dedicated headphone-licensed listening mode: The dedicated earphone is an earphone with a unique identifier, which is stored inside the earphone and can be read through a wired audio interface or Bluetooth channel; After a tourist connects the dedicated headset to a mobile terminal for the first time, the real-time voice intercom APP reads the headset's identification and sends it to the server. The server then associates the identification with the tour guide's current temporary group and brings the headset under the tour guide's management authority. When the headset is reconnected, the real-time voice intercom app reads the headset's identity identifier and sends it to the server for permission verification. After the server verifies that the headset has been registered under the tour guide's management authority, it grants the tourist access to the current temporary group's audio listening privileges.

10. The method for transmitting tour guide audio and synchronized ASR text based on a voice intercom system according to claim 9, characterized in that, The dedicated earphone can be a wired earphone or a Bluetooth earphone; the Bluetooth earphone has a built-in unique identification chip, which transmits the identification through the Bluetooth channel.

Images