ONU gateway interaction method and device of PON network, equipment and medium

Abstract

The invention relates to the field of gateway interaction, and discloses an ONU (Optical Network Unit) gateway interaction method, device, equipment and medium of a PON (Passive Optical Network) network, which can be applied to a Fiber To Room (FTTR), an enterprise-level Fiber To Room-Bus (FTTR-B) and a broadband fusion terminal product, and comprises the following steps: displaying interface elements in an ONU gateway management interface, the interface elements comprising information elements and interactive elements; in response to a voice reading instruction for a management interface triggered by a user, reading interface elements in the management interface according to the voice navigation tree corresponding to the management interface; receiving a voice operation instruction input by a user, extracting an operation object and an action, and matching a corresponding interactive element in the voice navigation tree based on the operation object; and executing an action corresponding to the matched interactive element, and feeding back an execution result through voice. The problems of inconvenience in user operation, high use threshold and low interaction efficiency caused by dependence on a manual operation interface and lack of voice interaction capability in the prior art are solved.

Description

Technical Field

[0001] This invention relates to the field of gateway interaction, and more particularly to an ONU gateway interaction method, apparatus, device, and medium in a PON network. Background Technology

[0002] Currently, the industry mainly relies on the traditional "visual interface manual operation" mode for the management of ONU gateways. This means that users need to log in to the ONU gateway's management interface through terminals such as computer browsers and mobile apps, and manually view gateway status, configure parameters, and troubleshoot through mouse clicks, touch screen operations, keyboard input, and other methods. In practical applications, existing ONU gateway management methods have significant technical shortcomings: Firstly, they rely entirely on manual operation interfaces and lack voice interaction capabilities—the existing management interfaces only support visual manual operation and do not provide a voice interaction channel. Users cannot obtain interface element information through voice commands, nor can they trigger management operations through voice. Secondly, this mode directly leads to three core problems: First, user operation is inconvenient—when users are busy or have poor eyesight, they cannot perform accurate manual clicks and input operations, making it difficult to complete gateway management. Second, the usage threshold is high—the existing management interfaces require users to be familiar with hierarchical menu logic and the meaning of professional parameters, and they need to manually search for target functions layer by layer. Users with weak technical foundations cannot complete management operations independently. Third, the interaction efficiency is low—when encountering gateway failures, users need to manually log in to the interface, search for the troubleshooting menu, and check parameters item by item. The manual operation steps are cumbersome, making it difficult to quickly locate and solve problems. Furthermore, manual identification of interface elements is prone to misoperation, further prolonging the interaction time.

[0003] Therefore, existing technologies rely on manual operation interfaces and lack voice interaction capabilities, resulting in inconvenience for users, high barriers to entry, and low interaction efficiency. Summary of the Invention

[0004] This invention provides an ONU gateway interaction method, device, computer equipment, and medium for PON networks, in order to solve the problems of inconvenience for users, high usage threshold, and low interaction efficiency caused by the reliance on manual operation interfaces and lack of voice interaction capabilities in the prior art.

[0005] Firstly, a method for ONU gateway interaction in a PON network is provided, including: Display the interface elements in the ONU gateway management interface, including information elements and interactive elements; In response to a user-triggered voice reading command for the management interface, the interface elements in the management interface are read aloud according to the voice navigation tree corresponding to the management interface. The voice navigation tree is constructed by recognizing the interface elements through a preset AI parsing model and combining the position hierarchy and logical relationship of the interface elements. Receive voice operation commands input by the user, extract the operation object and action, and match the corresponding interactive element in the voice navigation tree based on the operation object; Execute the action corresponding to the matched interactive element, and provide voice feedback on the execution result.

[0006] Optionally, the interface elements in the ONU gateway management interface, before including information elements and interactive elements, include: Collect the voice signal emitted by the user and preprocess the collected voice signal to filter out environmental noise; Extract speech feature vectors from the preprocessed speech signal; The similarity between the speech feature vector and the wake word features in the preset wake word feature library is calculated; If the calculated similarity exceeds a preset threshold, the wake-up is considered successful, and the interface elements in the ONU gateway management interface are displayed; otherwise, the wake-up is considered unsuccessful, and the ONU gateway is in standby mode.

[0007] Optionally, the voice navigation tree is constructed by recognizing interface elements through a preset AI parsing model and combining the positional hierarchy and logical relationships of the interface elements, including: Scan the ONU gateway management interface in real time and extract the interface elements of the management interface; The location hierarchy and logical relationship between interface elements are extracted using the preset AI parsing model to construct the navigation tree of the management interface; The navigation tree is synthesized by performing speech synthesis based on the preset AI parsing model to obtain the speech navigation tree.

[0008] Optionally, the step of reading aloud the interface elements in the management interface according to the voice navigation tree corresponding to the management interface includes: According to the voice navigation tree, the interface elements in the management interface are read aloud in hierarchical order. For information elements, descriptive voice is used to read their content, and for interactive elements, operation prompts are added while reading their names. When reading aloud the interface elements in the management interface, the system monitors the user's voice operation commands in real time, adjusts the reading path according to the voice operation commands, and automatically proceeds to the next level of reading if no voice operation command is detected.

[0009] Optionally, the ONU gateway interaction method of the PON network further includes: The system monitors the operating status parameters of the ONU gateway in real time. When the operating status parameters exceed a preset threshold, the system determines that the status is abnormal, automatically synthesizes the abnormal information, and converts it into voice for broadcast.

[0010] Optionally, the step of matching the corresponding interactive element in the voice navigation tree based on the operation object includes: If no interactive element is found, the user will be prompted to re-enter the voice operation command via voice prompt.

[0011] Optionally, the ONU gateway interaction method of the PON network further includes: Record user interaction data, which includes at least one of the following: voice command expression format, operation frequency, hierarchical jump preference, and average interaction duration; The interactive data is statistically analyzed, and the reading strategy of the interface elements is adjusted based on the analysis results.

[0012] Secondly, an ONU gateway interaction device for a PON network is provided, comprising: The display module is used to display the interface elements in the ONU gateway management interface, including information elements and interactive elements. The reading module is used to respond to the user's voice reading command for the management interface, and read the interface elements in the management interface according to the voice navigation tree corresponding to the management interface. The voice navigation tree is constructed by recognizing the interface elements through a preset AI parsing model and combining the position hierarchy and logical relationship of the interface elements. The receiving module is used to receive voice operation commands input by the user, extract the operation object and action, and match the corresponding interactive element in the voice navigation tree based on the operation object; The execution module is used to execute the actions corresponding to the matched interactive elements and provide feedback on the execution results via voice.

[0013] Thirdly, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the ONU gateway interaction method of the PON network described above.

[0014] Fourthly, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the ONU gateway interaction method of the PON network described above.

[0015] The aforementioned solution implemented by the ONU gateway interaction method, device, computer equipment, and medium in the PON network replaces manual interface viewing by responding to voice reading commands and broadcasting interface elements based on a voice navigation tree; it receives voice operation commands and extracts the operation object and action, matching interactive elements to replace manual clicking and input; after executing the action, voice feedback provides the result, eliminating the need to manually refresh the interface for confirmation and completely eliminating the dependence on visual manual operation; element information and management functions can be obtained through voice, adapting to scenarios such as busy hands and poor eyesight, eliminating operational scenario limitations; the voice navigation tree reads elements hierarchically, clearly distinguishing between information elements, interactive elements, and operation prompts, so users do not need to memorize menu paths or understand professional parameters, but can complete the operation by following voice guidance, lowering the technical threshold; voice commands can directly match target interactive elements, saving the tedious steps of manually searching layer by layer; the navigation tree constructed by the AI ​​parsing model ensures the accuracy of element matching, reduces misoperation, and combined with real-time voice feedback, significantly shortens the interaction time. This solves the problems of existing technologies that rely on manual operation interfaces and lack voice interaction capabilities, resulting in inconvenience for users, high usage thresholds, and low interaction efficiency. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating an ONU gateway interaction method in a PON network according to an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of an ONU gateway interaction device in a PON network according to an embodiment of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0019] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0020] It should also be understood that the term “and / or” as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0021] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," or "in response to determination." Similarly, the phrase "if determined" or "if matched to [described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once matched to [described condition or event]," or "in response to matched to [described condition or event]."

[0022] Furthermore, in the description of this invention and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0023] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of the invention include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0024] It should be understood that the sequence number of each step in the following embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0025] To illustrate the technical solution of the present invention, specific embodiments are described below.

[0026] Please see Figure 1 As shown, Figure 1 A flowchart illustrating the ONU gateway interaction method in a PON network provided in this embodiment of the invention includes the following steps: S11: Displays the interface elements in the ONU gateway management interface, including information elements and interactive elements.

[0027] The demonstration visualizes the interface elements in the ONU gateway management interface.

[0028] Information elements refer to interface content used only to display "non-operable" information from the ONU gateway. Their core function is to convey static / dynamic information required for gateway management to the user, without triggering any actions. Examples include basic device information, network operating status, parameter configuration results, and fault prompts for the ONU gateway.

[0029] Interactive elements refer to "operable" interface components used to trigger ONU gateway management actions (such as parameter modification, function start / stop). Their core function is to carry out the gateway's management functions. Examples include ONU gateway function operation buttons, parameter configuration input components, status switching controls, and menu navigation components.

[0030] S12: In response to a user-triggered voice command for the management interface, read aloud the interface elements in the management interface according to the voice navigation tree corresponding to the management interface.

[0031] This step transforms the visual elements of the management interface into voice information, completely eliminating the limitation of "having to manually view the interface to obtain information".

[0032] The voice navigation tree is constructed by recognizing interface elements through a preset AI parsing model and combining the positional hierarchy and logical relationships of the interface elements.

[0033] The voice navigation tree is structured according to the hierarchical location of interface elements (e.g., "top-level management interface - sub-functional modules - specific elements"). When reading aloud, it generally needs to follow a "from whole to part" order to avoid confusing element presentation. For example, first read "WiFi configuration module," then read "WiFi name, number of connected devices, and edit button" under that module in sequence, allowing users to clearly understand the relationships between the elements.

[0034] The voice navigation tree has pre-defined logical relationships between interface elements (such as associating "network bandwidth information" with the "adjust bandwidth button" and "device connection status" with the "disconnect button"). When reading aloud, it will link the related elements together, rather than broadcasting them in isolation. For example, after reading "current downlink bandwidth 300Mbps", it will immediately read "interactive elements for adjusting bandwidth limit", helping users establish a cognitive association between "information and operation".

[0035] When reading aloud, it is also necessary to differentiate the content being broadcast to ensure accurate information delivery. For information elements, the broadcast should fully explain the element's attributes and specific information so that users are clear about the current status. For example, "Information element: The current WiFi name is ONU_5G_88AB, and 8 devices are connected; the gateway's current uplink bandwidth is 50Mbps, and the downlink bandwidth is 300Mbps." For interactive elements, the broadcast should clearly state the element name and corresponding operation attributes to prepare users for possible subsequent operations. For example, "Interactive element: The element that restarts the gateway can restart the device after being triggered; the element that changes the WiFi password can adjust the password after being triggered."

[0036] Voice reading commands are initiated by the user and delivered in natural language. They generally need to explicitly point to the "management interface" and the "reading action" to ensure that the gateway can accurately recognize the user's needs. Common voice reading commands can include global reading, such as "read all elements of the current management interface" or "read the content on the current interface" (which covers all currently displayed interface elements by default); and targeted reading, such as "read only the operable elements in the management interface" or "read the interface elements related to network configuration" (users can filter the reading scope according to their needs to improve the accuracy of information retrieval).

[0037] In one example, taking "users need to understand the elements of the 'Device Management Module' in the current ONU gateway management interface" as an example, the specific steps include: The first step is for the user to directly issue a voice command: "Read the elements of the device management module in the management interface"; The second step is for the ONU gateway to call the voice navigation tree corresponding to the "Device Management Module". This voice navigation tree has been organized into elements according to the hierarchy and logical association of "Device Management Module - Basic Device Information - Device Operation Functions". The third step involves reading aloud the voice navigation tree, first broadcasting the information elements under the module: "Information element: The current gateway device model is HG8546M, the device SN code is 694523100015, and the firmware version is V3.2.1; the connected devices include 2 mobile phones, 1 computer, and 1 smart TV." Then, it broadcasts the interactive elements under the module: "Interactive elements: elements to view device details, which, when triggered, show the connection duration and IP address of a single device; elements to disconnect a device, which, when triggered, can take a specified device offline; elements to refresh the device list, which, when triggered, can update the information of the currently connected devices."

[0038] S13: Receive voice operation commands input by the user, extract the operation object and action, and match the corresponding interactive element in the voice navigation tree based on the operation object.

[0039] The core function of this step is to convert the user's "natural language commands" into "locatable and executable gateway interface element operation signals", replacing the operation of "manually searching and clicking interactive elements" in the existing technology. It is the core execution step to achieve "manual operation-free" voice interaction.

[0040] Receiving voice operation commands input by users refers to the ONU gateway interaction system receiving voice commands issued by users in real time for the purpose of "operating gateway functions". The voice operation commands must include a clear target and action.

[0041] Extracting the operation object and action means that the system performs semantic parsing on the received voice operation commands to separate the operation object and action, thus avoiding misoperation caused by ambiguous commands.

[0042] The system matches the corresponding interactive element in the voice navigation tree based on the operation object. It uses "extracted operation object" as the search keyword to locate the "interactive element" that perfectly matches the operation object in the "voice navigation tree".

[0043] In one example, the user has already heard the system announce through "voice reading command": "Current interactive elements in the management interface: WiFi name modification, WiFi password modification, gateway restart, port control." After clarifying the operable functions, and based on their own needs (changing the original WiFi name "ONU_default5G" to "ONU_Bedroom5G"), the user issues a specific voice operation command: "Change the WiFi name of the ONU gateway to 'ONU_Bedroom5G'." Through voice semantic recognition, the above voice operation command is broken down into elements, extracting the operation object as "WiFi name," corresponding to the specific "interactive element," namely the dedicated component in the management interface used to modify the WiFi name; the action is "change to 'ONU_Bedroom5G'." Using the operation object "WiFi name" as the search keyword, a hierarchical traversal and semantic matching are performed in the voice navigation tree, and the final matching result is the interactive element "WiFi name modification input box."

[0044] S14: Execute the action corresponding to the matched interactive element and provide voice feedback on the execution result.

[0045] Once an interactive element is matched in the voice navigation tree, the corresponding action is automatically triggered. This action is strongly bound to the function of the interactive element (e.g., "input box" corresponds to the "parameter write / update" action, and "button" corresponds to the "function start / stop / trigger" action). The action is executed directly through the system backend by calling the management interface of the ONU gateway without the user having to click or confirm.

[0046] In the example above, after the interactive element "WiFi name modification input box" is matched, the corresponding action "change to 'ONU_Bedroom5G'" is automatically triggered, and "ONU_Bedroom5G" is automatically entered into the "WiFi name modification input box" and saved.

[0047] The aforementioned ONU gateway interaction method in the PON network responds to voice commands and broadcasts interface elements based on a voice navigation tree, replacing manual interface viewing. It receives voice operation commands, extracts the operation object and action, and matches interactive elements to replace manual clicking and input. After executing the action, voice feedback provides the result, eliminating the need for manual interface refresh confirmation and completely freeing users from reliance on visual manual operation. Element information and management functions can be obtained and triggered via voice, adapting to scenarios with busy hands or poor eyesight, eliminating operational limitations. The voice navigation tree reads elements hierarchically, clearly distinguishing between information elements, interactive elements, and operation prompts. Users do not need to memorize menu paths or understand technical parameters; they can complete operations simply by following voice guidance, lowering the technical threshold. Voice commands can directly match target interactive elements, saving the tedious steps of manual layer-by-layer searching. The navigation tree constructed by the AI ​​parsing model ensures accurate element matching, reducing misoperations. Combined with real-time voice feedback, it significantly shortens interaction time. This solves the problems of existing technologies that rely on manual interface operation and lack voice interaction capabilities, leading to inconvenience for users, high usage thresholds, and low interaction efficiency.

[0048] Optionally, the interface elements in the ONU gateway management interface are displayed. Before the information elements and interactive elements, the interface elements include: collecting the voice signal emitted by the user; preprocessing the collected voice signal to filter out environmental noise; extracting the voice feature vector from the preprocessed voice signal; calculating the similarity between the voice feature vector and the wake word features in the preset wake word feature library; if the calculated similarity exceeds a preset threshold, the wake-up is determined to be successful and the interface elements in the ONU gateway management interface are displayed; otherwise, the wake-up is determined to be unsuccessful and the ONU gateway is in standby mode.

[0049] This step is a pre-trigger step for displaying ONU gateway management interface elements. Its core function is to replace the existing startup method of "manually opening the management APP / browser and entering the account password" with "voice wake-up". This solves the problem of "high startup threshold and cumbersome operation" in gateway management. Users only need to issue specific voice commands to activate the gateway interaction system, laying the foundation for subsequent interface element display and voice interaction. At the same time, noise filtering and feature comparison ensure the accuracy of wake-up and avoid false triggering or wake-up failure.

[0050] The voice signals emitted by users are typically captured in real time through the microphone built into the ONU gateway (or the microphone of a connected smart terminal, such as a mobile phone or speaker) to activate the gateway.

[0051] Preprocessing the acquired speech signal to filter out environmental noise involves technically processing the raw speech signal to remove irrelevant noise interference from the environment and retain the pure "wake-up word speech signal." This avoids noise causing deviations in subsequent feature extraction and wake-up judgment errors. Common speech signal preprocessing algorithms (such as spectral subtraction and wavelet transform) can be used to specifically filter out common noise types, such as television sounds, air conditioner sounds, and family conversations in a home setting, and keyboard typing and colleague conversations in an office setting, ensuring that the preprocessed signal meets the extraction requirements.

[0052] Extracting speech feature vectors from preprocessed speech signals involves converting the "denoised wake word speech" into computer-recognizable "digital features" (i.e., speech feature vectors). These vectors uniquely characterize the acoustic properties of the wake word (such as pitch, frequency, and speech rate) and serve as the "core basis" for subsequent comparison with preset features. Generally, mature feature extraction methods in the field of speech signal processing (such as MFCC Mel-frequency cepstral coefficients) can be used to decompose the continuous speech signal into multiple frames, calculate the frequency, energy, and other parameters of each frame, and finally integrate them into a fixed-dimensional feature vector (such as a 39-dimensional MFCC vector) to ensure that the features accurately reflect the uniqueness of the wake word.

[0053] Similarity calculation and wake-up result determination involve comparing the extracted speech feature vector with the standard features in the "preset wake-up word feature library" to determine whether to activate the gateway. The preset wake-up word feature library stores the standard wake-up word features set at the time of gateway departure (such as the standard MFCC vector of the default wake-up word "wake up the ONU gateway"). Algorithms such as cosine similarity and Euclidean distance are used to calculate the similarity between the extracted speech feature vector and the standard wake-up word features. If the calculation result is greater than a threshold, the wake-up is successful; otherwise, it fails.

[0054] In one example, a user has an ONU gateway in their home, with the default wake-up phrase being "Wake up the ONU gateway," and a preset similarity threshold of 0.82. The user is in the living room (3 meters from the gateway), and a TV is playing a program (ambient noise: 60 decibels TV sound). The user wants to manage the gateway's WiFi via voice, and must first complete the wake-up process. The wake-up process specifically includes: The first step is for the user to clearly say "Wake up the ONU gateway" towards the gateway. The gateway's built-in microphone will pick up the voice signal of "user's voice + TV noise" (the original signal contains TV sound interference). The second step is to process the speech signal using spectral subtraction: identify and remove the high-frequency noise components of the TV sound (the TV sound frequency is mostly between 1000-3000Hz, which overlaps with the 300-3400Hz part of human speech; the algorithm distinguishes noise from speech by energy difference), and finally obtain a speech signal containing only the pure speech "wake up the ONU gateway". The third step is to segment the clean speech signal into 20ms / frames, calculate the MFCC features of each frame (39 dimensions in total), and generate the "wake word feature vector A" that represents the user's pronunciation. The fourth step is to retrieve the standard feature vector B of "wake up the ONU gateway" from the preset wake-up word feature library, and use the cosine similarity algorithm to calculate the similarity between A and B. The result is 0.86 (> the preset threshold of 0.82). The system determines that the wake-up is successful and immediately displays the ONU gateway management interface elements on the display terminal associated with the gateway.

[0055] Optionally, the voice navigation tree is constructed by recognizing interface elements through a preset AI parsing model and combining the position hierarchy and logical relationship of interface elements. This includes: real-time scanning of the ONU gateway management interface and extracting interface elements from the management interface; extracting the position hierarchy and logical relationship between interface elements through a preset AI parsing model and constructing a navigation tree for the management interface; and synthesizing speech from the navigation tree based on the preset AI parsing model to obtain the voice navigation tree.

[0056] This step describes the core construction logic of the voice navigation tree. Through three steps, namely "real-time scanning and element extraction → AI analysis of hierarchy and association → voice synthesis", the "visual elements" of the ONU gateway management interface are transformed into a "voice-callable tree navigation structure". This solves the problems in the existing technology that the interface navigation relies on manual preset, cannot dynamically adapt to different gateway interfaces, and has no structured support for voice interaction.

[0057] The real-time scanning refers to actively collecting visual and structural data of the ONU gateway management interface at a preset cycle (e.g., 5 seconds / time) or when the interface is updated (e.g., when the user switches the management menu), and then extracting the interface elements in the management interface.

[0058] The preset AI parsing model is specifically adapted for the ONU gateway management interface. Its core function is to extract the positional hierarchy and logical relationships between interface elements. "Positional hierarchy" solves the problem of "how elements are ordered in the navigation tree," while "logical relationships" solve the problem of "how elements interact." Ultimately, a navigation tree is constructed. Specifically, the AI ​​parsing model can determine the positional hierarchy by comparing the "screen coordinates" of interface elements. If the coordinate range of element A completely contains element B (e.g., the "WiFi Settings" menu box contains the "Change WiFi Name" input box), then A is the "parent node" and B is the "child node." If the coordinates of element B and element C are not related, but they are under the same parent node and arranged horizontally (e.g., the "Change WiFi Name" input box and the "Save" button), then B and C are "sibling nodes," ordered from left to right. AI analysis models can determine the logical relationships between interface elements through "functional semantic matching". If the triggering function of element X (such as "save WiFi name") depends on the input content of element Y (such as the text in the "modify WiFi name" input box), then X and Y are determined to have a "functional dependency relationship". If the names of element M and element N are highly related (such as "WiFi switch" and "current WiFi status"), then the two are determined to have an "information linkage relationship".

[0059] Speech synthesis refers to the AI ​​parsing model converting the "text attributes" of each node (element / parent node) in the navigation tree into "standardized speech segments" and adding speech identifiers to the "hierarchical relationship" and "logical association" between nodes.

[0060] Optionally, based on the voice navigation tree corresponding to the management interface, the interface elements in the management interface are read aloud, including: reading the interface elements in the management interface in hierarchical order according to the voice navigation tree, wherein descriptive voice is used to broadcast the content of information elements, and operation prompts are added while broadcasting the name of interactive elements; while reading the interface elements in the management interface, the voice operation commands input by the user are monitored in real time, and the reading path is adjusted according to the voice operation commands. If no voice operation commands are detected, the reading will automatically proceed to the next level.

[0061] The voice navigation tree hierarchy corresponds to the functional categories of the ONU gateway management interface (e.g., "Root node: ONU gateway management → First-level child node: Network configuration / System management / Port management → Second-level child node: Specific functional elements under each category"). The "hierarchical order" refers to broadcasting from the root node down layer by layer to ensure that users can clearly perceive the hierarchical relationship between interface elements.

[0062] For informational elements, "descriptive voice broadcast content" is used, allowing users to know the gateway status / parameters and other information without looking at the interface; for interactive elements, "add operation prompts" are added when broadcasting the name, clearly informing users of the actions that can be performed by the element, reducing the operational threshold of "not knowing what can be done".

[0063] Real-time monitoring refers to continuously listening for user voice commands (such as "skip this" or "read system management") during the playback of elements at any level, rather than waiting for the entire level to finish playing before monitoring, ensuring timely response. If a new voice command is detected, the playback of the current level is immediately terminated, and the system jumps to the level / element specified by the command (e.g., if the user says "read port management directly," the system switches from the "network configuration" level to the "port management" level). If no new voice command is detected, the system automatically moves to the next level after playing all elements at the current level, ensuring a smooth workflow.

[0064] In one example, taking the "ONU gateway voice navigation tree (root node: ONU gateway management → first-level child node: network configuration / system management → second-level child node: network configuration including "WiFi information (information element)", "WiFi name modification box (interactive element)", and "WiFi switch (interactive element)") as an example, the execution process of this step is fully presented: The first step is the initial hierarchical announcement. After the system starts reading aloud, it first announces the affiliation of the first-level child nodes corresponding to the root node: "The current ONU gateway management interface contains two main functional categories: Network Configuration and System Management. Now we will read aloud the elements under the 'Network Configuration' category: Information elements: The current WiFi name is ONU_5G_88AB, 8 devices are connected, and the current downlink bandwidth is 300Mbps; Interactive element 1: WiFi name modification box, which allows you to perform the 'Enter New WiFi Name' operation; Interactive element 2: WiFi switch, which allows you to perform the 'Turn WiFi On / Off' operation." The second step is to monitor commands and path adjustments in real time. When the user interrupts during the broadcast of "Interactive Element 1" by saying, "I don't need to read the network configuration anymore, I'll just read the system management," the broadcast of the "Network Configuration" level is immediately terminated upon detecting this voice command, and the system is switched to the "System Management" level. The broadcast continues according to the rules: "You have been switched to the 'System Management' category. Elements under this category include: Information element: Current firmware version V3.2.1, last reboot time 2025-10-30 08:00; Interactive element: Reboot gateway button, which can perform the 'Trigger Gateway Reboot' operation."

[0065] Optionally, the ONU gateway interaction method in the PON network also includes: real-time monitoring of the ONU gateway's operating status parameters; when the operating status parameters exceed a preset threshold, determining an abnormal status; automatically synthesizing abnormal information and converting it into voice for broadcast.

[0066] Operational status parameters are key indicators that directly affect network functionality, not irrelevant data. They mainly include three categories: Network connection parameters: Uplink / downlink bandwidth rate (whether it is lower than the package's agreed value), WiFi signal strength (whether it is lower than the normal coverage threshold), network connection stability (whether there are frequent disconnections), number of connected devices (whether it exceeds the gateway's maximum capacity); Hardware status parameters: Gateway CPU utilization (whether it is consistently too high, causing lag), memory usage, port connection status (e.g., whether port 1 suddenly disconnects), gateway temperature (whether it exceeds the safe operating range); Functional configuration parameters: DHCP server operation status (whether it is abnormally shut down), firewall status (whether it has unexpectedly failed), firmware operation status (whether there are program errors).

[0067] Anomaly information should generally include three core elements: "anomaly type + specific parameters + scope of impact" to avoid vague descriptions (such as simply saying "the gateway has a problem" which cannot guide users to troubleshoot). The combination rule can be: [anomaly type] + [specific details of the anomaly parameters] + [functions that may be affected], ensuring that users can understand "what problem has occurred and what usage is affected" at a glance.

[0068] The timing of voice broadcasts is not limited by whether the user is currently interacting with the voice. Regardless of whether the user is currently operating the gateway (such as changing the WiFi name with voice or not triggering any commands), once an anomaly is detected, the system will immediately broadcast in a clear and non-harsh voice, and the broadcast content will be repeated 1-2 times (to avoid the user not hearing clearly). At the same time, other voice interactions that are currently in progress can be paused (such as reading interface elements aloud, which will be interrupted first and the anomaly will be broadcast, and then the user will be asked whether to continue the original operation).

[0069] In one example, network bandwidth abnormally decreased. The downlink bandwidth rate in the operating status parameters was monitored and remained at 8Mbps for 5 minutes (the user's plan is 300Mbps), which is lower than the "normal threshold (≥200Mbps)". The abnormal information was synthesized as "An abnormal downlink bandwidth was detected in the ONU gateway. The current rate is 8Mbps, which is lower than the 300Mbps agreed in the plan. This may cause video stuttering and slow downloads". The current interface element reading was interrupted (if the user did not operate, it was directly broadcast), and the above abnormal information was clearly broadcast twice. Then, a follow-up question could be asked: "Do you need voice guidance to help you troubleshoot the bandwidth problem?"

[0070] Optionally, based on the object of operation, the corresponding interactive element in the voice navigation tree can be matched, including: if no interactive element is matched, prompting the user to re-enter the voice operation command via voice.

[0071] This step is the core fault-tolerance mechanism in the voice interaction process of the PON network ONU gateway to ensure the validity of commands and avoid interaction lag. Its core value lies in solving the matching failure problem caused by "vague expression of user voice commands and unclear operation objects". By "active voice prompts", it replaces the deadlock of "no feedback and user not knowing how to operate" in the existing technology, and ensures the continuity of the voice interaction process.

[0072] In one example, the user inputs the voice command "Help me turn on the Bluetooth function of the ONU gateway and connect my headphones"; the operation object "gateway Bluetooth function" is extracted from the command; all interactive elements are searched in the voice navigation tree, but no element related to "gateway Bluetooth function" is found (most ONU gateways do not have a Bluetooth module), so it is determined that there is no match; the voice prompts "No operation option corresponding to 'gateway Bluetooth function' was found. The ONU gateway does not currently support Bluetooth control function. Please re-enter other voice operation commands."

[0073] Optionally, the ONU gateway interaction method in the PON network also includes: recording user interaction data, which includes at least one of the following: voice command expression format, operation frequency, hierarchical jump preference, and average interaction duration; performing statistical analysis on the interaction data, and adjusting the reading strategy of interface elements based on the analysis results.

[0074] The core value of this step lies in solving the problem of "single reading strategies and inability to adapt to different user habits" in existing technologies. By recording and analyzing user interaction data to capture personalized user needs, the reading of interface elements can be transformed from a "uniform mode" to a "customized mode that fits user habits", continuously improving the convenience and efficiency of voice interaction.

[0075] Recording user interaction data generally needs to meet the following requirements: 1. Only record user interaction behavior data, without associating it with personal privacy information (such as name, mobile phone number), to ensure data security; 2. Every time a user completes an interaction (such as inputting a command, triggering reading aloud, or jumping to a different level), the data should be recorded immediately to avoid omissions; 3. Cover the complete interaction cycle from "user triggering voice command" to "operation completed" to ensure that the data can reflect complete usage habits.

[0076] Statistical analysis of interactive data involves extracting patterns from the data that can guide adjustments to reading strategies. The analysis can generally include: Preference expression clustering: Classify different expressions of the same function by users (e.g., "restart gateway" and "gateway restart" are classified into the "restart function expression cluster"), and count the usage percentage of each expression (e.g., "restart gateway" accounts for 70%). High-frequency function sorting: Sort all function elements by operation frequency (e.g., "View bandwidth" > "Change WiFi name" > "Restart gateway") to identify the core functions needed by users; Path efficiency analysis: Calculate the time taken for commonly used hierarchical jump paths (e.g., direct jump to "Network Configuration → Bandwidth Monitoring" takes 8 seconds, while hierarchical broadcast takes 15 seconds) and determine the optimal navigation path; Identify time-consuming processes: Analyze operations with long average interaction times to pinpoint time-consuming bottlenecks (such as long waiting times for "System Management" level announcements, as this level is not frequently used by users).

[0077] Adjusting the reading strategy involves different adjustments based on different analysis results to avoid blind modifications without a basis. Specific adjustment directions can include the following: 1. Based on "voice command expression form": optimize semantic recognition and prioritize responding to user-preferred expressions; 2. Based on "operation frequency": increase the reading priority and level of detail for high-frequency functional elements; 3. Based on "hierarchical jump preference": simplify the playback of infrequently used hierarchical levels and prioritize the playback of familiar paths; 4. Based on "average interaction time": shorten the reading time of time-consuming steps to improve overall efficiency.

[0078] In one example, the process of adjusting the reading strategy based on "voice command expression form + operation frequency" includes the following steps: The first step is to record user interaction data. Users access "Check bandwidth" 5 times per week (high frequency), and each time they say "Check my home bandwidth" (preferred expression), rarely using "Check upload / download bandwidth"; The second step was statistical analysis. The analysis concluded that "users frequently perform the action 'check bandwidth,' prefer to describe it as 'check my home bandwidth,' and are not sensitive to technical jargon." The third step is strategy adjustment. When a user triggers the reading of interface elements, prioritize reading elements related to "bandwidth monitoring" (e.g., instead of reading "System Management" first, read "Network Configuration → Bandwidth Monitoring" first). When reading the "bandwidth monitoring" element, use user-preferred expressions to guide subsequent operations, such as "You can view the bandwidth information now. If you need to know the bandwidth status, you can directly say 'Check your home bandwidth'". Simplify the reading of technical terms, changing "Current upload bandwidth 50Mbps, download bandwidth 300Mbps" to "Current home upload speed 50Mbps, download speed 300Mbps" to better suit user expression habits.

[0079] In one embodiment, an ONU gateway interaction device for a PON network is provided. For example... Figure 2 As shown, it includes a display module 21, a reading module 22, a receiving module 23, and an execution module 24. Detailed descriptions of each functional module are as follows: Display module 21 is used to display the interface elements in the ONU gateway management interface, including information elements and interactive elements; The reading module 22 is used to respond to the user's voice reading command for the management interface. Based on the voice navigation tree corresponding to the management interface, it reads the interface elements in the management interface. The voice navigation tree is constructed by recognizing the interface elements through a preset AI parsing model and combining the position hierarchy and logical relationship of the interface elements. The receiving module 23 is used to receive voice operation commands input by the user, extract the operation object and action, and match the corresponding interactive element in the voice navigation tree based on the operation object; The execution module 24 is used to execute the actions corresponding to the matched interactive elements and provide voice feedback on the execution results.

[0080] This invention also provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the aforementioned ONU gateway interaction method for a PON network; to avoid repetition, this will not be described further. Alternatively, the electronic device can implement the functions of each module in this embodiment of the ONU gateway interaction device for a PON network; this will not be described further.

[0081] This invention also provides a readable storage medium storing a program. When the program is executed by a processor, it implements the ONU gateway interaction method of the PON network described above. To avoid repetition, this will not be described again here. Alternatively, when the program is executed by a processor, it implements the functions of each module in this embodiment of the ONU gateway interaction device for the PON network, which will not be described again here.

[0082] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

[0083] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0084] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

Claims

1. A method for ONU gateway interaction in a PON network, characterized in that, include: Display the interface elements in the ONU gateway management interface, including information elements and interactive elements; In response to a user-triggered voice reading command for the management interface, the interface elements in the management interface are read aloud according to the voice navigation tree corresponding to the management interface. The voice navigation tree is constructed by recognizing the interface elements through a preset AI parsing model and combining the position hierarchy and logical relationship of the interface elements. Receive voice operation commands input by the user, extract the operation object and action, and match the corresponding interactive element in the voice navigation tree based on the operation object; Execute the action corresponding to the matched interactive element, and provide voice feedback on the execution result.

2. The method according to claim 1, characterized in that, The interface elements in the ONU gateway management interface, before including information elements and interactive elements, include: Collect the voice signal emitted by the user and preprocess the collected voice signal to filter out environmental noise; Extract speech feature vectors from the preprocessed speech signal; The similarity between the speech feature vector and the wake word features in the preset wake word feature library is calculated; If the calculated similarity exceeds a preset threshold, the wake-up is considered successful, and the interface elements in the ONU gateway management interface are displayed; otherwise, the wake-up is considered unsuccessful, and the ONU gateway is in standby mode.

3. The method according to claim 1, characterized in that, The voice navigation tree is constructed by recognizing interface elements through a preset AI parsing model and combining the positional hierarchy and logical relationships of the interface elements, including: Scan the ONU gateway management interface in real time and extract the interface elements of the management interface; The location hierarchy and logical relationship between interface elements are extracted using the preset AI parsing model to construct the navigation tree of the management interface; The navigation tree is synthesized by performing speech synthesis based on the preset AI parsing model to obtain the speech navigation tree.

4. The method according to claim 1, characterized in that, The step of reading aloud interface elements in the management interface according to the voice navigation tree corresponding to the management interface includes: According to the voice navigation tree, the interface elements in the management interface are read aloud in hierarchical order. For information elements, descriptive voice is used to read their content, and for interactive elements, operation prompts are added while reading their names. When reading aloud the interface elements in the management interface, the system monitors the user's voice operation commands in real time, adjusts the reading path according to the voice operation commands, and automatically proceeds to the next level of reading if no voice operation command is detected.

5. The method according to claim 1, characterized in that, Also includes: The system monitors the operating status parameters of the ONU gateway in real time. When the operating status parameters exceed a preset threshold, the system determines that the status is abnormal, automatically synthesizes the abnormal information, and converts it into voice for broadcast.

6. The method according to claim 1, characterized in that, The process of matching the corresponding interactive element in the voice navigation tree based on the operation object includes: If no interactive element is found, the user will be prompted to re-enter the voice operation command via voice prompt.

7. The method according to claim 1, characterized in that, Also includes: Record user interaction data, which includes at least one of the following: voice command expression format, operation frequency, hierarchical jump preference, and average interaction duration; The interactive data is statistically analyzed, and the reading strategy of the interface elements is adjusted based on the analysis results.

8. An ONU gateway interaction device for a PON network, characterized in that, include: The display module is used to display the interface elements in the ONU gateway management interface, including information elements and interactive elements. The reading module is used to respond to the user's voice reading command for the management interface, and read the interface elements in the management interface according to the voice navigation tree corresponding to the management interface. The voice navigation tree is constructed by recognizing the interface elements through a preset AI parsing model and combining the position hierarchy and logical relationship of the interface elements. The receiving module is used to receive voice operation commands input by the user, extract the operation object and action, and match the corresponding interactive element in the voice navigation tree based on the operation object; The execution module is used to execute the actions corresponding to the matched interactive elements and provide feedback on the execution results via voice.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the ONU gateway interaction method of the PON network as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the ONU gateway interaction method of the PON network as described in any one of claims 1 to 7.

Images