Voice data processing method and system, electronic equipment and storage medium

Abstract

The invention provides a voice data processing method and system, electronic equipment and a storage medium. The method comprises the following steps: sending voice data to be processed to a server through a screened data transmission path; and if the to-be-processed voice data is not successfully sent to the server, determining a voice escape result of the to-be-processed voice data by using a first voice model deployed in the terminal equipment. And querying a function matched with the voice escape result of the to-be-processed voice data from a local cache of the terminal equipment. When the voice data is processed, the degree of dependence on the network is reduced, and the availability of the intelligent voice model is improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and specifically to a method, system, electronic device, and storage medium for processing voice data. Background Technology

[0002] With the development of internet technology, intelligent voice AI has been widely applied in various industries. The intelligent agent of intelligent voice AI is usually stored on servers. Intelligent voice AI relies on the network when performing speech recognition and speech transcribing. When there is network latency or jitter, intelligent voice AI may fail to output content or output incorrect content, making its availability unstable. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method, system, electronic device, and storage medium for processing voice data to improve the usability of intelligent voice AI.

[0004] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0005] The first aspect of this invention discloses a method for processing voice data, the method comprising:

[0006] Acquire the voice data to be processed;

[0007] The voice data to be processed is sent to the server through the selected data transmission path;

[0008] If the voice data to be processed cannot be successfully sent to the server, the voice escaping result of the voice data to be processed is determined using the first voice model deployed on the terminal device;

[0009] The function of querying the local cache of the terminal device to match the voice escape result of the voice data to be processed. The local cache of the terminal device stores at least: multiple voice escape results, the ID of the voice escape result, and the function of matching the voice escape result.

[0010] Preferably, the voice data to be processed is sent to the server through the selected data transmission path, including:

[0011] Optimize data transmission paths;

[0012] Select the data transmission path with the best network quality from the optimized data transmission paths;

[0013] The voice data to be processed is sent to the server via a data transmission path with optimal network quality.

[0014] Preferably, after sending the voice data to be processed to the server through the selected data transmission path, the method further includes:

[0015] If the voice data to be processed is successfully sent to the server, the processing result fed back by the server is received. The processing result includes the voice escaping result and its ID of the voice data to be processed, or the processing result includes the ID of the voice escaping result of the voice data to be processed. The voice escaping result and its ID of the voice data to be processed are obtained by processing the voice data to be processed by a second voice model deployed on the server. The second voice model is larger in scale than the first voice model.

[0016] When the processing result includes the speech escaping result and its ID of the speech data to be processed, the function of querying the speech escaping result that matches the speech data to be processed is executed.

[0017] When the processing result includes the ID of the voice escaping result of the voice data to be processed, the step of searching for the voice escaping result of the voice data to be processed in the local cache of the terminal device according to the ID of the voice escaping result of the voice data to be processed, and performing the function of querying the voice escaping result that matches the voice data to be processed.

[0018] Preferred options also include:

[0019] When the processing result includes the speech escape result and its ID of the speech data to be processed, the processing result is stored in the local cache of the terminal device.

[0020] Preferably, after the function of querying the speech escape results that match the speech data to be processed, the function further includes:

[0021] When a function matching the speech escaping result of the speech data to be processed is found, the function matching the speech escaping result of the speech data to be processed is executed in response to the speech data to be processed.

[0022] If no matching voice escaping result is found for the voice data to be processed, the function will not respond to the voice data to be processed.

[0023] A second aspect of this invention discloses a voice data processing system, the system comprising:

[0024] The acquisition unit is used to acquire the voice data to be processed.

[0025] The sending unit is used to send the voice data to be processed to the server through the selected data transmission path;

[0026] The determining unit is used to determine the speech escaping result of the speech data to be processed using a first speech model deployed on the terminal device if the speech data to be processed cannot be successfully sent to the server.

[0027] The query unit is used to query the local cache of the terminal device to find the voice escaping result that matches the voice data to be processed. The local cache of the terminal device stores at least: multiple voice escaping results, the ID of the voice escaping result, and the voice escaping result matching function.

[0028] Preferably, the transmitting unit includes:

[0029] The optimization module is used to optimize data transmission paths.

[0030] The selection module is used to select the data transmission path with the best network quality from the optimized data transmission paths;

[0031] The sending module is used to send the voice data to be processed to the server through the data transmission path with the best network quality.

[0032] Preferred options also include:

[0033] A receiving unit is configured to receive a processing result from the server if the voice data to be processed is successfully sent to the server. The processing result includes the voice escaping result and its ID of the voice data to be processed, or the processing result includes the ID of the voice escaping result of the voice data to be processed. The voice escaping result and its ID of the voice data to be processed are obtained by processing the voice data to be processed by a second voice model deployed on the server. The second voice model is larger in magnitude than the first voice model.

[0034] The processing unit is configured to execute the query unit when the processing result includes the voice escaping result and its ID of the voice data to be processed; and when the processing result includes the ID of the voice escaping result of the voice data to be processed, to search for the voice escaping result of the voice data to be processed from the local cache of the terminal device according to the ID of the voice escaping result of the voice data to be processed, and to execute the query unit.

[0035] A third aspect of the present invention discloses a computer device, comprising: a processor and a memory, the processor and the memory being connected via a bus; wherein the processor is used to call and execute a program stored in the memory; the memory is used to store the program, the program being used to implement the voice data processing method disclosed in the first aspect of the present invention.

[0036] A fourth aspect of the present invention discloses a storage medium storing computer-executable instructions for executing the voice data processing method disclosed in the first aspect of the present invention.

[0037] Based on the above embodiments of the present invention, a method, system, electronic device, and storage medium for processing voice data are provided. The method includes: acquiring voice data to be processed; sending the voice data to be processed to a server through a selected data transmission path; if the voice data to be processed cannot be successfully sent to the server, determining the voice escaping result of the voice data to be processed using a first voice model deployed on a terminal device; and querying the local cache of the terminal device for functions matching the voice escaping result of the voice data to be processed. In this solution, the voice data to be processed is sent to the server through a selected data transmission path. If the voice data to be processed cannot be successfully sent to the server, the voice escaping result of the voice data to be processed is determined using a first voice model deployed on the terminal device. Then, the local cache of the terminal device is queried for functions matching the voice escaping result of the voice data to be processed. This reduces the dependence on the network when processing voice data and improves the availability of the intelligent voice model. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0039] Figure 1 A flowchart illustrating a method for processing voice data provided in an embodiment of the present invention;

[0040] Figure 2 This is a flowchart of sending voice data to be processed to a server, provided in an embodiment of the present invention.

[0041] Figure 3 A structural block diagram of a voice data processing system provided in an embodiment of the present invention;

[0042] Figure 4 Another structural block diagram of a voice data processing system provided in an embodiment of the present invention;

[0043] Figure 5 Another structural block diagram of a voice data processing system provided in an embodiment of the present invention;

[0044] Figure 6 This is another structural block diagram of a voice data processing system provided in an embodiment of the present invention. Detailed Implementation

[0045] 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 embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] In this application, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0047] With the development of internet technology, intelligent voice AI has been widely applied across various industries. The intelligent agents of intelligent voice AI are typically stored on servers, and they rely on the network for speech recognition and transcription. In complex environments, if network latency or jitter occurs, the intelligent voice AI may fail to output content or output incorrect content, resulting in unstable availability.

[0048] To address this, this invention proposes a method, system, electronic device, and storage medium for processing voice data. The method involves sending the voice data to be processed to a server via a selected data transmission path. If the transmission fails, a first voice model deployed on the terminal device determines the voice escaping result of the voice data. Then, a function matching the voice escaping result of the voice data is retrieved from the terminal device's local cache. This reduces reliance on the network during voice data processing and improves the usability of the intelligent voice model.

[0049] See Figure 1 The diagram illustrates a flowchart of a voice data processing method provided by an embodiment of the present invention. This processing method is applicable to terminal devices and includes:

[0050] Step S101: Obtain the voice data to be processed.

[0051] In the specific implementation step S101, the terminal device acquires voice data to be processed during use. The terminal device can be a diagnostic device (such as a tablet computer) used in automobile repair.

[0052] Step S102: Send the voice data to be processed to the server through the selected data transmission path.

[0053] In the specific implementation step S102, the data transmission link with the best network quality is selected, and the voice data to be processed is sent to the server through the selected data transmission path.

[0054] In some specific embodiments, the local cache of the terminal device stores at least: multiple voice escaping results, the ID of the voice escaping result, and the function of matching voice escaping results.

[0055] During the process of sending the voice data to be processed to the server, network fluctuations may cause the voice data to be sent to the server successfully or unsuccessfully.

[0056] If the voice data to be processed is not successfully sent to the server, proceed to step S103; if the voice data to be processed is successfully sent to the server, proceed to step S104.

[0057] Step S103: If the voice data to be processed cannot be successfully sent to the server, the voice escaping result of the voice data to be processed is determined using the first voice model deployed on the terminal device, and step S107 is executed.

[0058] It should be noted that the terminal device has a first voice model deployed locally, which is a lightweight intelligent voice AI.

[0059] In the specific implementation step S103, if the voice data to be processed cannot be successfully sent to the server, the first voice model deployed locally on the terminal device is called to perform voice recognition and voice escaping on the voice data to be processed, thereby obtaining the voice escaping result of the voice data to be processed.

[0060] After obtaining the speech escaping result of the speech data to be processed, step S107 is executed.

[0061] For example, suppose a terminal device obtains the user's voice input "rapid diagnosis" as the voice data to be processed. When sending the voice data to the server, the network is unstable, which prevents the voice data from being successfully sent to the server. At this time, the terminal device calls the first speech model deployed locally to perform speech recognition and speech escaping on the voice data to be processed, thereby obtaining the speech escaping result of the voice data to be processed.

[0062] Step S104: If the voice data to be processed is successfully sent to the server, receive the processing result from the server.

[0063] In the specific implementation of step S104, if the voice data to be processed is successfully sent to the server, the terminal device receives the processing result fed back by the server. The processing result includes the voice escaping result of the voice data to be processed and its ID, or the processing result includes the ID of the voice escaping result of the voice data to be processed.

[0064] The speech escaping result and its ID of the speech data to be processed are obtained by the second speech model deployed on the server. The second speech model is larger in scale than the first speech model. That is, the second speech model deployed on the server is a smart speech AI with a larger scale and better performance than the first speech model.

[0065] Understandably, the server also has a corresponding cache space, which synchronously stores the "voice escaping result and the ID of the voice escaping result in the terminal device's local cache". After receiving the voice data to be processed from the terminal device, the server calls the second voice model deployed on the server to perform speech recognition and semantic conversion on the voice data to be processed, obtain the voice escaping result of the voice data to be processed, and set a corresponding ID for the voice escaping result of the voice data to be processed. The server stores the "voice escaping result of the voice data to be processed" and the "ID of the voice escaping result of the voice data to be processed" in the server's cache space.

[0066] When the network quality is good, the server will send the "voice escaping result of the voice data to be processed" and the "ID of the voice escaping result of the voice data to be processed" back to the terminal device. That is, when the network quality is good, the processing result sent back by the server includes the voice escaping result of the voice data to be processed and its ID.

[0067] When network jitter occurs, the server only sends the "ID of the voice escaping result of the voice data to be processed" back to the terminal device. That is, when network jitter occurs, the processing result sent back by the server only includes the ID of the voice escaping result of the voice data to be processed. This reduces the amount of data transmitted over the network and ensures that the processing result can be sent back to the terminal device.

[0068] For example, when a server receives a voice message "rapid diagnosis" from a terminal device, it uses a second speech model deployed on the server to perform speech recognition and speech escaping on the voice data, obtaining the escaping result and assigning a corresponding ID to it. If network jitter occurs when the server sends the processing result back to the terminal device, the server will only send the "ID of the escaping result of the voice data" in the processing result; it will not return any other content besides this ID.

[0069] Step S105: When the processing result includes the speech escaping result and its ID of the speech data to be processed, proceed to step S107.

[0070] In the specific implementation of step S105, when the processing result returned by the server includes the voice escaping result and its ID of the voice data to be processed, the terminal device can directly obtain the voice escaping result of the voice data to be processed and execute step S107.

[0071] In some specific embodiments, when the processing result returned by the server includes the voice escaping result and its ID of the voice data to be processed, the processing result is stored in the local cache of the terminal device.

[0072] In other words, if the server returns the "voice escaping result of the voice data to be processed" and the "ID of the voice escaping result of the voice data to be processed", the terminal device will store the "voice escaping result of the voice data to be processed" and the "ID of the voice escaping result of the voice data to be processed" returned by the server in the local cache of the terminal device.

[0073] By continuously accumulating and updating the local cache of terminal devices and the cache space of servers through the above methods, the response speed of intelligent voice AI can be improved.

[0074] Step S106: When the processing result includes the ID of the voice escaping result of the voice data to be processed, search for the voice escaping result of the voice data to be processed in the local cache of the terminal device according to the ID of the voice escaping result of the voice data to be processed, and execute step S107.

[0075] In the specific implementation of step S106, when the processing result returned by the server only includes the ID of the voice escaping result of the voice data to be processed, the terminal device matches the "ID of the voice escaping result of the voice data to be processed" returned by the server in the local cache of the terminal device, finds the voice escaping result corresponding to the "ID of the voice escaping result of the voice data to be processed" returned by the server, and thus obtains the voice escaping result of the voice data to be processed, and executes step S107.

[0076] Step S107: Query the local cache of the terminal device for a function that matches the speech escaping result of the speech data to be processed.

[0077] It should be noted that the local cache of the terminal device stores at least: multiple voice escaping results, the ID of the voice escaping result, and the function of matching voice escaping results.

[0078] In the specific implementation step S107, after obtaining the voice escaping result of the voice data to be processed, a function is used to query the local cache of the terminal device to match the "voice escaping result of the voice data to be processed".

[0079] Understandably, terminal devices can be configured to handle only functions related to a specific aspect.

[0080] In some specific embodiments, when a function matching the speech escaping result of the speech data to be processed is found, the function matching the speech escaping result of the speech data to be processed is executed in response to the speech data to be processed.

[0081] If no matching voice escaping result is found for the voice data to be processed, the function will not respond to the voice data to be processed.

[0082] For example: Suppose the terminal device only processes functions related to vehicle diagnostics; if the voice translation result of the voice data to be processed is "rapid diagnosis", then the rapid diagnosis function is executed; if the voice translation result of the voice data to be processed is "today's weather", then the terminal device does not respond to the voice data to be processed.

[0083] In this embodiment of the invention, the voice data to be processed is sent to the server through a selected data transmission path. If the voice data to be processed fails to be sent to the server, the voice escaping result of the voice data to be processed is determined using a first voice model deployed on the terminal device. Then, a function matching the voice escaping result of the voice data to be processed is queried from the local cache of the terminal device. This reduces the dependence on the network when processing voice data and improves the availability of the intelligent voice model.

[0084] Regarding the above embodiments of the present invention Figure 1 Step S102, which involves "sending the voice data to be processed to the server through the selected data transmission path," can be found in [reference needed]. Figure 2 This illustrates a flowchart of sending voice data to be processed to a server according to an embodiment of the present invention. Figure 2 Includes the following steps:

[0085] Step S201: Optimize the data transmission path.

[0086] In the specific implementation step S201, the data transmission path is optimized using a protocol optimized for low latency.

[0087] Among them, protocols for low latency can be QUIC, WebRTC, etc.

[0088] It should be noted that QUIC (Quick UDP Internet Connections) is a next-generation Internet transport protocol based on the User Datagram Protocol (UDP), while WebRTC is a technology that supports real-time audio and video communication in browsers.

[0089] In practical applications, when data fluctuations and network instability occur (such as packet loss rate exceeding 5% and latency exceeding 500ms), protocols such as QUIC and WebRTC are used to optimize the data transmission path.

[0090] Step S202: Select the data transmission path with the best network quality from the optimized data transmission paths.

[0091] Step S203: Send the voice data to be processed to the server through the data transmission path with the best network quality.

[0092] The above embodiments of the present invention Figure 2 This is an explanation of how to select data transmission paths.

[0093] To better understand this solution, the following example illustrates the interaction between the terminal device and the server:

[0094] The terminal device acquires the voice data to be processed and sends it to the server through the selected data transmission path with the best network quality.

[0095] If the voice data to be processed cannot be successfully sent to the server, the terminal device uses the first voice model deployed on the terminal device to determine the voice escaping result of the voice data to be processed, and then queries the local cache of the terminal device for a function that matches the voice escaping result.

[0096] If the voice data to be processed is successfully sent to the server, the server calls the second voice model deployed on the server to perform speech recognition and semantic conversion on the voice data to be processed, and obtains the speech translation result of the voice data to be processed.

[0097] When the network quality is good, the server will send the voice escaping result and its ID of the voice data to be processed back to the terminal device. The terminal device will then query the local cache for functions that match the voice escaping result.

[0098] When the network quality is unstable, the server only sends the ID of the voice escaping result of the voice data to be processed back to the terminal device. The terminal device then uses this ID to query the voice escaping result of the voice data to be processed from the local cache, and then queries the local cache for the function that matches the voice escaping result.

[0099] As can be seen from the above embodiments, this solution reduces the dependence of intelligent voice AI on the network from two aspects: network optimization and local caching, thereby optimizing intelligent voice AI.

[0100] Corresponding to the voice data processing method provided in the above embodiments of the present invention, see also... Figure 3 The present invention also provides a structural block diagram of a voice data processing system, which is applicable to terminal devices and includes: an acquisition unit 301, a sending unit 302, a determination unit 303, and a query unit 304.

[0101] Acquisition unit 301 is used to acquire the voice data to be processed.

[0102] The sending unit 302 is used to send the voice data to be processed to the server through the selected data transmission path.

[0103] The determining unit 303 is used to determine the speech escaping result of the speech data to be processed using the first speech model deployed on the terminal device if the speech data to be processed cannot be successfully sent to the server.

[0104] The query unit 304 is used to query the local cache of the terminal device to find the voice escaping result that matches the voice data to be processed. The local cache of the terminal device stores at least: multiple voice escaping results, the ID of the voice escaping result, and the voice escaping result matching function.

[0105] In this embodiment of the invention, the voice data to be processed is sent to the server through a selected data transmission path. If the voice data to be processed fails to be sent to the server, the voice escaping result of the voice data to be processed is determined using a first voice model deployed on the terminal device. Then, a function matching the voice escaping result of the voice data to be processed is queried from the local cache of the terminal device. This reduces the dependence on the network when processing voice data and improves the availability of the intelligent voice model.

[0106] Preferred, combined Figure 3 See Figure 4 The diagram shows another structural block diagram of a voice data processing system provided by an embodiment of the present invention. The sending unit 302 includes an optimization module 3021, a selection module 3022 and a sending module 3023.

[0107] Optimization module 3021 is used to optimize the data transmission path.

[0108] Selection module 3022 is used to select the data transmission path with the best network quality from the optimized data transmission paths.

[0109] The sending module 3023 is used to send the voice data to be processed to the server through the data transmission path with the best network quality.

[0110] Preferred, combined Figure 3 See Figure 5 This diagram illustrates another structural block diagram of a voice data processing system provided in an embodiment of the present invention. The processing system further includes:

[0111] The receiving unit 305 is configured to receive the processing result fed back by the server if the voice data to be processed is successfully sent to the server. The processing result includes the voice escaping result and its ID of the voice data to be processed, or the processing result includes the ID of the voice escaping result of the voice data to be processed. The voice escaping result and its ID of the voice data to be processed are obtained by processing the voice data to be processed by a second voice model deployed on the server. The second voice model is larger in magnitude than the first voice model.

[0112] The processing unit 306 is configured to execute the query unit 304 when the processing result includes the voice escaping result and its ID of the voice data to be processed; and when the processing result includes the ID of the voice escaping result of the voice data to be processed, to search for the voice escaping result of the voice data to be processed in the local cache of the terminal device according to the ID of the voice escaping result of the voice data to be processed, and to execute the query unit 304.

[0113] Preferably, the processing unit 306 is further configured to: when the processing result includes the speech escaping result and its ID of the speech data to be processed, store the processing result in the local cache of the terminal device.

[0114] Preferred, combined Figure 3 See Figure 6 This diagram illustrates another structural block diagram of a voice data processing system provided in an embodiment of the present invention. The processing system further includes:

[0115] The execution unit 307 is configured to execute the function that matches the speech escaping result of the speech data to be processed when a function matching the speech escaping result of the speech data to be processed is found, in order to respond to the speech data to be processed; and not to respond to the speech data to be processed when no function matching the speech escaping result of the speech data to be processed is found.

[0116] Preferably, the present invention also provides a computer device, including: a processor and a memory, the processor and the memory being connected via a bus; wherein, the processor is used to call and execute a program stored in the memory; the memory is used to store the program, the program being used to implement the voice data processing method provided in the above method embodiments.

[0117] Preferably, the present invention also provides a storage medium storing computer-executable instructions for executing the voice data processing method provided in the above method embodiments.

[0118] In summary, this invention provides a method, system, electronic device, and storage medium for processing voice data. The voice data to be processed is sent to a server via a selected data transmission path. If the voice data cannot be successfully sent to the server, a first voice model deployed on the terminal device is used to determine the voice escaping result of the voice data. Then, a function matching the voice escaping result of the voice data is retrieved from the local cache of the terminal device. This reduces the dependence on the network when processing voice data and improves the availability of the intelligent voice model.

[0119] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the descriptions in the method embodiments. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0120] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0121] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for processing voice data, characterized in that, The method includes: Acquire the voice data to be processed; The voice data to be processed is sent to the server through the selected data transmission path; If the voice data to be processed cannot be successfully sent to the server, the voice escaping result of the voice data to be processed is determined using the first voice model deployed on the terminal device; The function of querying the local cache of the terminal device to match the voice escape result of the voice data to be processed. The local cache of the terminal device stores at least: multiple voice escape results, the ID of the voice escape result, and the function of matching the voice escape result.

2. The method according to claim 1, characterized in that, The voice data to be processed is sent to the server through the selected data transmission path, including: Optimize data transmission paths; Select the data transmission path with the best network quality from the optimized data transmission paths; The voice data to be processed is sent to the server via a data transmission path with optimal network quality.

3. The method according to claim 1, characterized in that, After sending the voice data to be processed to the server through the selected data transmission path, the process further includes: If the voice data to be processed is successfully sent to the server, the processing result fed back by the server is received. The processing result includes the voice escaping result and its ID of the voice data to be processed, or the processing result includes the ID of the voice escaping result of the voice data to be processed. The voice escaping result and its ID of the voice data to be processed are obtained by processing the voice data to be processed by a second voice model deployed on the server. The second voice model is larger in scale than the first voice model. When the processing result includes the speech escaping result and its ID of the speech data to be processed, the function of querying the speech escaping result that matches the speech data to be processed is executed. When the processing result includes the ID of the voice escaping result of the voice data to be processed, the step of searching for the voice escaping result of the voice data to be processed in the local cache of the terminal device according to the ID of the voice escaping result of the voice data to be processed, and performing the function of querying the voice escaping result that matches the voice data to be processed.

4. The method according to claim 3, characterized in that, Also includes: When the processing result includes the speech escape result and its ID of the speech data to be processed, the processing result is stored in the local cache of the terminal device.

5. The method according to any one of claims 1-4, characterized in that, After the function of querying the speech escape results that match the speech data to be processed, it also includes: When a function matching the speech escaping result of the speech data to be processed is found, the function matching the speech escaping result of the speech data to be processed is executed in response to the speech data to be processed. If no matching voice escaping result is found for the voice data to be processed, the function will not respond to the voice data to be processed.

6. A voice data processing system, characterized in that, The system includes: The acquisition unit is used to acquire the voice data to be processed. The sending unit is used to send the voice data to be processed to the server through the selected data transmission path; The determining unit is used to determine the speech escaping result of the speech data to be processed using a first speech model deployed on the terminal device if the speech data to be processed cannot be successfully sent to the server. The query unit is used to query the local cache of the terminal device to find the voice escaping result that matches the voice data to be processed. The local cache of the terminal device stores at least: multiple voice escaping results, the ID of the voice escaping result, and the voice escaping result matching function.

7. The system according to claim 6, characterized in that, The transmitting unit includes: The optimization module is used to optimize data transmission paths. The selection module is used to select the data transmission path with the best network quality from the optimized data transmission paths; The sending module is used to send the voice data to be processed to the server through the data transmission path with the best network quality.

8. The system according to claim 6, characterized in that, Also includes: A receiving unit is configured to receive a processing result from the server if the voice data to be processed is successfully sent to the server. The processing result includes the voice escaping result and its ID of the voice data to be processed, or the processing result includes the ID of the voice escaping result of the voice data to be processed. The voice escaping result and its ID of the voice data to be processed are obtained by processing the voice data to be processed by a second voice model deployed on the server. The second voice model is larger in magnitude than the first voice model. The processing unit is configured to execute the query unit when the processing result includes the voice escaping result and its ID of the voice data to be processed; and when the processing result includes the ID of the voice escaping result of the voice data to be processed, to search for the voice escaping result of the voice data to be processed from the local cache of the terminal device according to the ID of the voice escaping result of the voice data to be processed, and to execute the query unit.

9. A computer device, characterized in that, include: A processor and a memory are connected via a bus; wherein the processor is used to call and execute a program stored in the memory; The memory is used to store a program for implementing the voice data processing method as described in any one of claims 1-5.

10. A storage medium, characterized in that, The storage medium stores computer-executable instructions for performing the voice data processing method as described in any one of claims 1-5.

Images