Voice updating method and device of intelligent voice air conditioner and air conditioner

Abstract

The invention provides a voice updating method and device for an intelligent voice air conditioner and the air conditioner, and the method comprises the steps that under the condition that a voice control function of the air conditioner is started, voice data of a user is obtained; and if the control instruction corresponding to the voice data is not recognized and a control instruction input by the user in a non-voice manner is received within a preset time length, binding the voice data with the control instruction input in the non-voice manner. According to the embodiment of the invention, under the condition that the control instruction corresponding to the voice data is not recognized and the control instruction of non-voice input is received in a short time, the voice data can be set as the voice data of the control instruction, and the updating of the voice data corresponding to the control instruction is realized, so that the coverage rate and the recognition accuracy of voice control are improved, and the user experience is improved. And the user experience is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning comfort control, and in particular to a voice updating method and device for an intelligent voice air conditioner, and an air conditioner. Background Art

[0002] Currently, some air conditioners with voice control functions use an offline voice recognition method with a low voice recognition rate, while others use an online voice recognition method with a high voice recognition rate but high cost.

[0003] For example, when the user speaks in dialect, the voice recognition rate is too low, the coverage and recognition accuracy of the air conditioner's voice control are low, and the user experience is poor. Summary of the invention

[0004] To solve the above problems, an embodiment of the present invention provides a voice update method for an intelligent voice air conditioner, the method comprising: when the voice control function of the air conditioner is turned on, obtaining the user's voice data; if the control instruction corresponding to the voice data is not recognized, and a control instruction of the user's non-voice input is received within a preset time period, then binding the voice data with the control instruction of the non-voice input.

[0005] The voice update method of the intelligent voice air conditioner provided by the embodiment of the present invention can set the voice data as the voice data of the control instruction when the control instruction corresponding to the voice data is not recognized and a control instruction without voice input is received within a short period of time, thereby realizing the update of the voice data corresponding to the control instruction, thereby improving the coverage and recognition accuracy of voice control and optimizing the user experience.

[0006] Optionally, binding the voice data with the control instruction of the non-voice input includes: judging whether the voice data meets the following conditions: the volume is greater than a volume threshold, the duration is within a first duration range, and the time interval between two adjacent words is within a second duration range; if all conditions are met, directly binding the voice data with the control instruction of the non-voice input.

[0007] The above-mentioned update judgment condition is set in the embodiment of the present invention, so as to improve the efficiency of binding voice data and control instructions.

[0008] Optionally, the method further comprises: if the non-voice input control instruction has pre-stored original voice data, replacing the original voice data with the voice data.

[0009] In the binding process of the embodiment of the present invention, if the control instruction has pre-stored original voice data, the voice data is used to replace and update it, so that when the user sends the voice data again, the corresponding control instruction can be accurately recognized and executed, thereby improving the user experience.

[0010] Optionally, binding the voice data with the control instruction of the non-voice input includes: judging whether the voice data meets the following conditions: the volume is less than or equal to the volume threshold, the duration is within a first duration range, and the time interval between two adjacent words is within a second duration range; if all conditions are met, comparing the voice data with the original voice data bound to the control instruction of the non-voice input; if the error between the voice data and the original voice data is less than a first error threshold, storing the voice data as the voice data of the control instruction of the non-voice input; if the number of voice data of the control instruction of the non-voice input is greater than a threshold, determining the voice data closest to the average value as the final voice data.

[0011] In the embodiment of the present invention, through the above operation, a voice data closest to the average value can be selected from multiple voice data with little difference as the voice data of the control instruction, thereby improving the voice recognition rate.

[0012] Optionally, the method further includes: if the error between the voice data and the original voice data is greater than or equal to the first error threshold and less than or equal to a second error threshold, replacing the original voice data with the voice data.

[0013] In the embodiment of the present invention, when the voice data input by the user is the same as and different from the original voice data of the control instruction, it means that the user may have used different words to express a certain control instruction, and the above voice data can be updated to improve the voice recognition rate.

[0014] Optionally, the method further includes: if the error between the voice data and the original voice data is greater than the second error threshold, storing the voice data as voice data of other language types of the non-voice input control instruction.

[0015] In the embodiment of the present invention, the above-mentioned voice data can be stored as another type of voice data, and the existing original voice data can be retained, thereby improving the voice recognition rate.

[0016] Optionally, the method further includes: if it is recognized that the control instruction corresponding to the voice data is a broadcast instruction, broadcasting the operating status of the air conditioner according to the broadcast instruction.

[0017] In the embodiment of the present invention, the user can control the air conditioner to broadcast the operating status through voice control, thereby further controlling the air conditioner based on the operating status.

[0018] An embodiment of the present invention provides a voice updating device for an intelligent voice air conditioner, the device comprising: a voice acquisition module, used to obtain the user's voice data when the voice control function of the air conditioner is turned on; a voice update module, used to bind the voice data with the non-voice input control instruction if the control instruction corresponding to the voice data is not recognized and a control instruction of the user's non-voice input is received within a preset time period.

[0019] An embodiment of the present invention provides an air conditioner, comprising a computer-readable storage medium storing a computer program and a processor, wherein the computer program implements the above method when read and executed by the processor.

[0020] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is read and executed by a processor, the above method is implemented.

[0021] The voice updating device of the intelligent voice air conditioner and the air conditioner of the present invention can achieve the same technical effect as the voice updating method of the intelligent voice air conditioner mentioned above. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic flow chart of a voice updating method for an intelligent voice air conditioner in an embodiment of the present invention is shown;

[0023] Figure 2 A structural schematic diagram of a voice updating device for an intelligent voice air conditioner in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0024] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0025] In the embodiment of the present invention, the air conditioner may have hardware devices such as a smart terminal with an air conditioner APP installed, a remote controller, and a display panel. The air conditioner has a voice control function, and voice collection can be turned on or off.

[0026] The above-mentioned intelligent terminal, remote controller and display panel may be provided with a voice module, which mainly includes: a microphone (for collecting audio data) and a speaker, and can execute functional instructions.

[0027] A variety of voice recognition modules can be loaded into the air conditioner chip, which can be installed by default before leaving the factory or collected and installed by the user.

[0028] Figure 1 A schematic flow chart of a voice updating method for an intelligent voice air conditioner in an embodiment of the present invention is shown, and the method comprises the following steps:

[0029] S102, when the voice control function of the air conditioner is turned on, obtaining the user's voice data.

[0030] The air conditioner has a voice control function, and the user can control the function to turn on. After the voice control function is turned on, the display panel of the air conditioner, the remote control or the microphone of a mobile terminal such as a mobile phone can collect surrounding voice signals. The user can input voice data through the above hardware devices.

[0031] S104: If the control instruction corresponding to the voice data is not recognized, and a control instruction of the user's non-voice input is received within a preset time period, the voice data is bound to the control instruction of the non-voice input.

[0032] After the air conditioner obtains the voice data, it recognizes it. If the corresponding control command is not recognized, the air conditioner will not work. The user is likely to turn to directly input control commands using the above hardware devices in a short period of time, such as directly controlling the air conditioner through a mobile phone APP, a remote control, etc., that is, the voice data and the control command obtained subsequently have a certain consistency.

[0033] Considering the consistency between the above voice data and the control instruction of the user's non-voice input, the voice data can be bound to the control instruction. Specifically, if the control instruction does not store voice data, the above unrecognized voice data can be stored as the voice data of the control instruction; if the control instruction already stores voice data, the above unrecognized voice data can be used to replace the stored voice data, thereby updating the voice data. After the two are bound, when the air conditioner obtains the voice data, it can execute the above control instruction accordingly, thereby improving the voice coverage and recognition accuracy.

[0034] The voice update method of the intelligent voice air conditioner provided by the embodiment of the present invention can set the voice data as the voice data of the control instruction when the control instruction corresponding to the voice data is not recognized and a control instruction without voice input is received within a short period of time, thereby realizing the update of the voice data corresponding to the control instruction, thereby improving the coverage and recognition accuracy of voice control and optimizing the user experience.

[0035] In order to avoid interference from non-command voices during the voice update process, the present embodiment further provides a step of determining whether the voice meets a preset condition. Optionally, the above binding step includes:

[0036] Determine whether the voice data meets the following conditions: the volume is greater than the volume threshold, the duration is within a first duration range, and the time interval between two adjacent words is within a second duration range; if all of the above conditions are met, the voice data is directly bound to the non-voice input control instruction.

[0037] By judging the volume, duration and interval between two adjacent words of the collected voice data, it is possible to judge whether the voice data is a control voice. For the user, in order to facilitate the air conditioner to accept voice control, the control voice it emits is usually louder, lasts for a certain period of time, and has a certain interval between words (for clear pronunciation). Therefore, this embodiment sets the above update judgment conditions to improve the efficiency of binding voice data with control instructions.

[0038] Furthermore, if the control instruction that is not voice input has the original voice data pre-stored, the voice data will replace the original voice data. During the binding process, if the control instruction has the original voice data pre-stored, the above voice data will be used to replace and update it, so that when the user sends the voice data again, the corresponding control instruction can be accurately recognized and executed, improving the user experience.

[0039] Optionally, the above binding step may further include:

[0040] Determine whether the voice data meets the following conditions: the volume is less than or equal to the volume threshold, the recording duration is within the first duration range, and the time interval between two adjacent words is within the second duration range;

[0041] If all conditions are met, the voice data is compared with the original voice data bound to the non-voice input control instruction;

[0042] If the error between the voice data and the original voice data is less than a first error threshold, storing the voice data as voice data of the control instruction of the non-voice input;

[0043] If the number of voice data of the control instruction not input by voice is greater than a threshold, the voice data closest to the average value is determined as the final voice data.

[0044] In the case where the voice data input by the user is not much different from the original voice data of the control instruction, it can be stored first. When the number of voice data stored in the control instruction exceeds a certain value, the voice data closest to the average value is used as the voice data of the control instruction. Through the above operation, the voice data closest to the average value can be selected from multiple voice data with little difference as the voice data of the control instruction, thereby improving the voice recognition rate.

[0045] Optionally, the above binding step may further include:

[0046] If the error between the speech data and the original speech data is greater than or equal to the first error threshold and less than or equal to the second error threshold, the speech data replaces the original speech data.

[0047] When the voice data input by the user is the same as or different from the original voice data of the control instruction, it means that the user may have used different words to express a certain control instruction, and the above voice data can be updated to improve the voice recognition rate.

[0048] Optionally, the above binding step may further include:

[0049] If the error between the voice data and the original voice data is greater than a second error threshold, the voice data is stored as voice data of other language types of the control instruction of the non-voice input.

[0050] In the case where the voice data input by the user is significantly different from the original voice data of the control instruction, it means that the user may have used a different language (such as a dialect, a foreign language, etc.) to express a certain control instruction. The above voice data can be stored as another type of voice data, and the existing original voice data can be retained, thereby improving the voice recognition rate. The above another type of voice data and the existing original voice data can both trigger the air conditioner to execute the above control instruction.

[0051] Furthermore, the method further includes: if the control instruction corresponding to the voice data is identified as a broadcast instruction, broadcasting the operating status of the air conditioner according to the broadcast instruction. The user can control the air conditioner to broadcast the operating status through voice, thereby further controlling the air conditioner based on the operating status.

[0052] In this embodiment, there are two ways to bind commands: ① active binding, ② passive binding (binding is enabled through voice recognition results). Voice data sources include: network, manufacturer offline voice, and user input. Intelligent voice control mainly adds the following two usage methods:

[0053] 1. Active voice binding

[0054] Voice binding command (APP / remote control / display panel) → click the function to be bound (APP / remote control / display panel) → enter the user voice command → click the function to be bound to confirm (APP / remote control / display panel).

[0055] It should be noted that after the air conditioner command is successfully bound, the air conditioner will run the binding function by default. Whether voice recording is turned on or recording is successful can be confirmed by a special display or buzzer sounding.

[0056] 2. Passive Voice Binding

[0057] The user issues a voice command to the air conditioner. When the air conditioner determines that it cannot recognize the command, if the user clicks the function button through the APP / remote control / display panel to turn on the function within a certain period of time, the unrecognized command will be bound to the function and the original voice data of the function will be replaced.

[0058] Among them, there are three conditions for the voice determined to be the command that needs to update the voice: ① volume, ② recording duration, and ③ interval between each word.

[0059] (1) Fast update method (immediate update):

[0060] Volume > Z dB, T 1 <Voice recording duration < T 2 , interval time between each word T 3

[0061] Exemplarily, Z = 60, T 1 = 1 s, T 2 = 60 s, T 3 = 2 s.

[0062] (2) Slow update:

[0063] Condition 1: When the volume < Z dB, T 1 <Voice recording duration < T 2 , interval time between each word T 3 .

[0064] Exemplarily, Z = 60, T 1 = 1 s, T 2 = 60 s, T 3 = 2 s.

[0065] Condition 2: When entering passive voice binding, the voice data of the previous function binding needs to be compared each time.

[0066] If 50% > error > 40%, then replace and delete the previous voice data;

[0067] If the error is not greater than 40%, then keep the previous data and save the current voice data. If the same function voice data is saved 5 times, then extract the voice data closest to the average value from the 5 times as the voice command for this function.

[0068] If the error > 50%, then it is considered that the voice command of another language is entered and saved in the database of another language value.

[0069] The embodiment of the present invention proposes a method for intelligent voice user update and air conditioner operation state broadcast, which improves the voice coverage rate and recognition rate.

[0070] Figure 2 The structural schematic diagram of a voice update device of an intelligent voice air conditioner in the embodiment of the present invention is shown, and the device includes:

[0071] A voice acquisition module 201, configured to acquire the voice data of the user when the voice control function of the air conditioner is turned on;

[0072] The voice updating module 202 is used to bind the voice data with the control instruction of the non-voice input if the control instruction corresponding to the voice data is not recognized and a control instruction of the non-voice input of the user is received within a preset time period.

[0073] The voice updating device for the intelligent voice air conditioner provided in the embodiment of the present invention can set the voice data as the voice data of the control instruction when the control instruction corresponding to the voice data is not recognized and a control instruction of non-voice input is received within a short period of time, thereby updating the voice data corresponding to the control instruction, thereby improving the coverage and recognition accuracy of voice control and optimizing the user experience.

[0074] As a feasible method, the above-mentioned voice update module is specifically used to: determine whether the voice data meets the following conditions: the volume is greater than the volume threshold, the duration is within a first duration range, and the time interval between two adjacent words is within a second duration range; if all are met, the voice data is directly bound to the control instruction of the non-voice input.

[0075] As a feasible manner, the voice updating module is specifically used for: if the non-voice input control instruction has pre-stored original voice data, then replacing the original voice data with the voice data.

[0076] As a feasible method, the above-mentioned voice update module is specifically used to: determine whether the voice data meets the following conditions: the volume is less than or equal to the volume threshold, the duration is within a first duration range, and the time interval between two adjacent words is within a second duration range; if all are met, the voice data is compared with the original voice data bound to the non-voice input control instruction; if the error between the voice data and the original voice data is less than a first error threshold, the voice data is stored as the voice data of the non-voice input control instruction; if the number of voice data of the non-voice input control instruction is greater than a threshold, the voice data closest to the average value is determined as the final voice data.

[0077] As a feasible manner, the above-mentioned voice updating module is specifically used to: if the error between the voice data and the original voice data is greater than or equal to the first error threshold and less than or equal to the second error threshold, then replace the original voice data with the voice data.

[0078] As a feasible manner, the voice updating module is specifically used for: if the error between the voice data and the original voice data is greater than the second error threshold, storing the voice data as voice data of other language types of the non-voice input control instruction.

[0079] As a feasible manner, the above-mentioned device also includes a broadcast module, which is used to: if the control instruction corresponding to the voice data is identified as a broadcast instruction, then broadcast the operating status of the air conditioner according to the broadcast instruction.

[0080] An embodiment of the present invention provides an air conditioner, comprising a computer-readable storage medium storing a computer program and a processor, wherein the computer program implements the above method when read and executed by the processor.

[0081] The embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is read and executed by a processor, the method provided in the above embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0082] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the control device through a computer, and the program can be stored in a computer-readable storage medium. When the program is executed, it may include the processes of the above-mentioned method embodiments, wherein the storage medium may be a memory, a disk, an optical disk, etc.

[0083] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the scope defined by the claims.

[0084] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0085] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the voice update device and air conditioner of the intelligent voice air conditioner disclosed in the embodiment, since it corresponds to the voice update method of the intelligent voice air conditioner disclosed in the above embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0086] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the scope defined by the claims.

Claims

1. A voice updating method for an intelligent voice air conditioner, characterized in that: The method comprises: When the voice control function of the air conditioner is turned on, obtaining the user's voice data; If the control instruction corresponding to the voice data is not recognized, and a control instruction of the user's non-voice input is received within a preset time period, the voice data is bound to the control instruction of the non-voice input.

2. The method according to claim 1, characterized in that The step of binding the voice data to the control instruction of the non-voice input includes: Determine whether the voice data meets the following conditions: the volume is greater than a volume threshold, the duration is within a first duration range, and the time interval between two adjacent words is within a second duration range; If all conditions are met, the voice data is directly bound to the control instruction of the non-voice input.

3. The method according to claim 2, characterized in that The method further comprises: If the non-voice input control instruction has pre-stored original voice data, the original voice data is replaced by the voice data.

4. The method according to claim 1, characterized in that The step of binding the voice data to the control instruction of the non-voice input includes: Determine whether the voice data meets the following conditions: the volume is less than or equal to the volume threshold, the duration is within a first duration range, and the time interval between two adjacent words is within a second duration range; If all conditions are met, the voice data is compared with the original voice data bound to the non-voice input control instruction; If the error between the voice data and the original voice data is less than a first error threshold, storing the voice data as voice data of the control instruction of the non-voice input; If the number of voice data of the control instruction inputted without voice is greater than a threshold, the voice data closest to the average value is determined as the final voice data.

5. The method according to claim 4, characterized in that The method further comprises: If the error between the voice data and the original voice data is greater than or equal to the first error threshold and less than or equal to the second error threshold, the original voice data is replaced by the voice data.

6. The method according to claim 4, characterized in that The method further comprises: If the error between the voice data and the original voice data is greater than the second error threshold, the voice data is stored as voice data of other language types of the non-voice input control instruction.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: If the control instruction corresponding to the voice data is identified as a broadcast instruction, the operating status of the air conditioner is broadcast according to the broadcast instruction.

8. A voice updating device for an intelligent voice air conditioner, characterized in that: The device comprises: A voice acquisition module, used to acquire the user's voice data when the air conditioner voice control function is turned on; The voice updating module is used to bind the voice data with the control instruction of the non-voice input if the control instruction corresponding to the voice data is not recognized and the control instruction of the non-voice input of the user is received within a preset time period.

9. An air conditioner, characterized in that: The invention comprises a computer-readable storage medium storing a computer program and a processor, wherein when the computer program is read and executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is read and executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images