Device wakeup method, device, electronic device and storage medium

Abstract

The present application provides a device wake-up method, apparatus, electronic device and storage medium, the method comprising: obtaining audio data, converting the audio data into text data, if it is determined that the text data contains a preset wake-up word, then determining the specificity value of the wake-up word in the text data, the specificity value is positively correlated with the intensity of the user's wake-up intention for the device, if it is determined that the specificity value belongs to a preset interval, then waking up the device. In this way, the device will only be awakened when the characteristic value of the wake-up word belongs to the preset interval. Compared with the existing wake-up as long as there is a wake-up word, it can effectively reduce the false awakening of the device, thereby improving the user experience.

Description

Technical Field

[0001] The present application relates to the field of intelligent device control, and in particular to a device wake-up method, device, electronic device and storage medium. Background Art

[0002] At present, with the development of intelligent voice technology, more and more devices can perform voice interaction. Users can wake up the device through specific words to chat or control it.

[0003] However, false wakeups may often occur in some scenarios, for example, when the device's corresponding wakeup word appears in a TV commercial, causing the device to be woken up. Another example is when a user is chatting with others and the device's corresponding wakeup word appears in the conversation, causing the device to be woken up. These situations do not belong to the scenarios where the user actually wants to wake up the device, so these wakeups are all false wakeups.

[0004] False awakening will produce a bad user experience to a certain extent, causing unnecessary trouble and trouble to the user. Therefore, how to reduce the false awakening of the device has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] In order to reduce false wake-up of a device, the present application provides a device wake-up method, apparatus, electronic device and storage medium.

[0006] In a first aspect, the present application provides a device wake-up method, comprising:

[0007] Get audio data;

[0008] Converting the audio data into text data;

[0009] If it is determined that the text data contains a preset wake-up word, determining a specificity value of the wake-up word in the text data, wherein the specificity value is positively correlated with the intensity of the user's intention to wake up the device;

[0010] If it is determined that the specificity value belongs to a preset interval, the device is woken up.

[0011] As a possible implementation manner, the method further includes:

[0012] If it is determined that the text data does not include the wake-up word, the audio data is discarded.

[0013] As a possible implementation manner, determining the specificity value of the wake-up word in the text data includes:

[0014] Calculating a first ratio of the length of the wake-up word to the length of the text data;

[0015] Determine the number of intentions in the text data, and determine the ratio of the number of intentions of the wake-up word to the number of intentions as a second ratio;

[0016] Determining a position weight of the wake-up word in the text data;

[0017] determining the number of specific words in the text data;

[0018] The sum of the first ratio, the second ratio, the position weight and the number of the specific words is determined as the specificity value of the preset wake-up word in the text data.

[0019] As a possible implementation manner, the calculating a first ratio of a length of a preset wake-up word to a length of the text data includes:

[0020] Determining the number of words in the wake-up word;

[0021] Determining the number of words in the text data;

[0022] The ratio of the number of characters in the wake-up word to the number of characters in the text data is used as the first ratio.

[0023] As a possible implementation manner, determining the number of intents in the text data includes:

[0024] Performing word segmentation processing on the text data to obtain at least one word;

[0025] For each word, determine whether there is an intent corresponding to the word in a preset mapping relationship table between words and intents;

[0026] If it is determined that there is an intention corresponding to the word, then the word is determined to be a target word;

[0027] Performing deduplication processing on target words in the text data;

[0028] Determining the number of target words in the text data after deduplication processing;

[0029] The number is regarded as the total amount of the intention of the text data.

[0030] As a possible implementation manner, determining the position weight of the wake-up word in the text data includes:

[0031] Determining a position of the wake-up word in the text data;

[0032] If it is determined that the wake-up word is located at the beginning of the sentence of the text data, determining that the position weight of the wake-up word in the text data is a preset first value;

[0033] If it is determined that the wake-up word is not located at the beginning of the sentence of the text data, the position weight of the wake-up word in the text data is determined to be a preset second value.

[0034] As a possible implementation manner, determining the number of specific words in the text data includes:

[0035] Get the preset specific words;

[0036] The text data is identified based on the specific words, and the number of the specific words contained therein is determined.

[0037] In a second aspect, an embodiment of the present application further provides a device for waking up a device, including:

[0038] An acquisition module, used to acquire audio data;

[0039] A conversion module, used for converting the audio data into text data;

[0040] A specificity determination module, configured to determine a specificity value of the wake-up word in the text data if it is determined that the text data contains a preset wake-up word, wherein the specificity value is positively correlated with the intensity of the user's intention to wake up the device;

[0041] The wake-up module is used to wake up the device if it is determined that the specificity value belongs to a preset interval.

[0042] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor and a memory, wherein the processor is used to execute a device wake-up program stored in the memory to implement the device wake-up method described in the first aspect.

[0043] In a fourth aspect, an embodiment of the present application further provides a storage medium, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the device wake-up method described in the first aspect.

[0044] The above technical solution provided by the embodiment of the present application has the following advantages compared with the prior art:

[0045] The embodiment of the present application provides a device wake-up method, which obtains audio data, converts the audio data into text data, and if it is determined that the text data contains a preset wake-up word, determines the specificity value of the wake-up word in the text data, and the specificity value is positively correlated with the intensity of the user's wake-up intention for the device. If it is determined that the specificity value belongs to a preset interval, the device is woken up. In this way, the device will only be woken up when the characteristic value of the wake-up word belongs to the preset interval. Compared with the existing method of waking up as long as there is a wake-up word, it can effectively reduce the false wake-up of the device, thereby improving the user experience.

[0046] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0048] Figure 1 The figure is a flow chart of a method for waking up a device according to an exemplary embodiment.

[0049] Figure 2 The figure is a flow chart of a method for waking up a device according to an exemplary embodiment.

[0050] Figure 3 The figure is a schematic diagram showing a device for waking up a device according to an exemplary embodiment.

[0051] Figure 4 The figure shows an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0052] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0053] See also Figure 1 , Figure 1 It is a flowchart of a device wake-up method provided by an embodiment of the present application.

[0054] like Figure 1 As shown, the method may include the following steps:

[0055] S11. Obtain audio data.

[0056] The device wake-up method provided in the embodiments of the present application can be applied to devices with voice interaction functions, such as smart speakers.

[0057] In actual applications, a device with a voice interaction function is usually equipped with a voice receiver for receiving externally inputted audio data. Based on this, the audio data acquired in S11 may be the audio data received by the voice receiver.

[0058] Because it is usually necessary to wake up the device when it is not in the awake state, and it is not necessary to wake up the device when it is in the awake state. Therefore, as an embodiment, before executing S11, it is also possible to first determine whether the current device is in the awake state. If it is determined that the device is not in the awake state, execute S11. If it is determined that the device is in the awake state, it means that there is no need to execute the device wake-up operation at this time, so S11 is not executed, and the device wake-up process ends.

[0059] S12. Convert the audio data into text data.

[0060] In an embodiment of the present application, after the audio data is acquired, speech recognition technology can be used to convert the audio data into text data.

[0061] As an embodiment, existing speech recognition software may be used to convert audio data into text data.

[0062] S13. If it is determined that the text data contains a preset wake-up word, determine the specificity value of the wake-up word in the text data.

[0063] The wake-up word is a word that is pre-set according to needs and is used to wake up the device. The wake-up words of different devices may be different. Generally, the wake-up word of a device is pre-stored in the device and can be directly obtained when used.

[0064] In an embodiment of the present application, after the audio data is converted into text data, a stored preset wake-up word can be obtained, and the text data can be identified based on the wake-up word to determine whether the text data contains the wake-up word. If it is determined that the wake-up word is contained, the specificity value of the wake-up word in the text data is calculated. If the text data does not contain the wake-up word, it is determined that there is no need to wake up the device, and the audio data is directly discarded and filtered out, and the wake-up process ends.

[0065] In the embodiment of the present application, the specificity value refers to the proportion of the wake-up word in the entire text data and the score after semantic understanding. The specificity value of the wake-up word in the text data is positively correlated with the strength of the user's intention to wake up the device, that is, the larger the specificity value of the wake-up word in the text data, the stronger the user's intention to wake up the device, and the smaller the specificity value of the wake-up word in the text data, the weaker the user's intention to wake up the device. Therefore, the strength of the user's intention to wake up the device can be determined based on the characteristic value of the wake-up word in the text data, so as to determine whether to wake up the device.

[0066] As for how to calculate the specificity value of the wake-up word in the text data, it will be explained below and will not be described in detail here.

[0067] As an implementation, when recognizing text data based on a wake-up word, the wake-up word can be compared with the text data. If the text data is compared and contains a word that is consistent with the wake-up word, it is determined that the text data contains the wake-up word. If the text data is compared and does not contain a word that is consistent with the wake-up word, it is determined that the text data does not contain the wake-up word.

[0068] S14. If it is determined that the specific degree value belongs to the preset range, the device is woken up.

[0069] After determining the specificity value of the wake-up word in the text data, the specificity value is compared with the preset interval to determine whether the specificity value belongs to the preset interval. If it is determined that the specificity value belongs to the preset interval, it is determined that the user's intention to wake up the device is obvious, and the device is thus woken up. If it is determined that the specificity value does not belong to the preset interval, it is determined that the user's intention to wake up the device is not obvious. In order to prevent false wake-ups, the device is not woken up at this time. Among them, the preset interval is an interval set according to actual needs or experience. For example, the preset interval is [n, +∞), and the value of n can be set according to actual needs or experience. When it is determined that the specificity value is less than n, the corresponding voice data is filtered out, the device is not woken up, and the wake-up process is explained; when it is determined that the specificity value is greater than or equal to n, the device is woken up.

[0070] The embodiment of the present application provides a device wake-up method, which obtains audio data, converts the audio data into text data, determines the specificity value of the preset wake-up word in the text data, and the specificity value is positively correlated with the strength of the user's wake-up intention for the device. If it is determined that the specificity value belongs to the preset interval, the device is woken up. In this way, the device will only be woken up when the characteristic value of the wake-up word belongs to the preset interval. Compared with the existing method of waking up as long as there is a wake-up word, it can effectively reduce the false wake-up of the device, thereby improving the user experience.

[0071] See also Figure 2 , is a device wake-up method provided by another embodiment of the present application, such as Figure 2 As shown, in Figure 1 Based on the device wake-up method shown, determining the specificity value of the wake-up word in the text data may include the following steps:

[0072] S21. Calculate a first ratio of the length of the wake-up word to the length of the text data.

[0073] In an embodiment of the present application, the wake-up word contained in the text data is first determined, and then the length of the wake-up word contained in the text and the length of the text data are respectively determined.

[0074] As an embodiment, the first ratio may be calculated using the following formula:

[0075] P 1 =M 1 / M 2

[0076] Among them, P 1 Represents the first ratio, M 1 Indicates the length of the wake-up word contained in the text data, M 2 Indicates the length of the text data.

[0077] As an embodiment, the length of a word can be the number of characters in the word, and the length of text data can be the number of characters in the text data. Therefore, the number of characters in the wake-up word and the number of characters in the text data can be determined separately, and the ratio of the number of characters in the wake-up word to the number of characters in the text data can be used as the first ratio.

[0078] As another embodiment, the wake-up word and text data may sometimes contain English characters, numbers, etc., so the number of characters in the word can be used as the length of the word, the number of characters in the text data can be used as the length of the text data, and then the ratio of the number of characters in the wake-up word to the number of characters in the text data can be used as the first ratio.

[0079] S22. Determine the total amount of intentions of the text data, and determine the ratio of the number of intentions of the wake-up words to the total amount of intentions as the second ratio.

[0080] As an embodiment, a mapping relationship table between words and intents can be pre-constructed and stored in a device, wherein the mapping relationship table can be determined based on the user's historical behavior data, wherein the behavior data can include voice data input by the user and the corresponding control results. Based on this, when determining the number of intents in the text data, the text data can be segmented to obtain at least one word, and then the mapping relationship table can be searched for each word to determine whether there is an intent corresponding to the word in the mapping relationship table (that is, an intent with a mapping relationship with the word). If it is determined that there is an intent corresponding to the word, the word is determined to be a target word. After determining whether all the words obtained by the segmentation are target words, the target words are deduplicated to remove duplicate target words, and then the number of target words in the deduplicated text data is determined, and the number is used as the total amount of intent in the text data.

[0081] After obtaining the total amount of intent of the text data, the number of intents of the wake-up words is divided by the number of intents to obtain a second ratio, which can reflect the proportion of the intent of the wake-up words to the total intent of the text data.

[0082] As an example, usually the wake-up word has only one intention, which is to wake up the device, so 1 can be divided by the total number of intentions to obtain the second ratio, as shown in the following formula:

[0083] P 2 =1 / M 3

[0084] Among them, P 2Represents the second ratio, M 3 The total amount of intent representing text data.

[0085] S23. Determine the position weight of the wake-up word in the text data.

[0086] Usually, when interacting with a device by voice, the device needs to be woken up first. So when the user intends to interact with the device by voice, the wake-up word will be spoken first to wake up the device. Therefore, in the voice data sent when the user intends to wake up the device, the wake-up word is usually located at the beginning of the voice data. The wake-up word that appears in the middle or at the end of the voice data is generally not for wake-up. Therefore, the position of the wake-up word in the text data corresponding to the voice data can also reflect the strength of the user's wake-up intention.

[0087] As an embodiment, when determining the position weight of the wake-up word in the text data, the position of the wake-up word in the text data can be determined. If it is determined that the wake-up word is located at the beginning of a sentence in the text data, the position weight of the wake-up word in the text data is determined to be a preset first value; if it is determined that the wake-up word is not located at the beginning of a sentence in the text data, the position weight of the wake-up word in the text data is determined to be a preset second value, wherein the first value is greater than the second value, for example, the first value is 1 and the second value is 0.

[0088] S24. Determine the number of specific words in the text data.

[0089] In an embodiment of the present application, the specific word may be a word pre-set based on the user's historical behavior data or experience. For example, the specific word may be a word that is often used with the wake-up word, such as "Are you there?", "Hello?", "Excuse me?", "Please answer", etc.

[0090] As an embodiment, a specific word library for storing specific words can be pre-set in the device. When calculating the characteristic value of the wake-up word in the text data, the specific word is obtained from the specific word library, and then the text data is recognized based on the specific word to determine the number of specific words contained in the text data.

[0091] As an embodiment, text data is identified based on specific words. For each specific word, the specific word can be compared with the text data. If the text data is found to contain a word consistent with the word, it is determined that the text data contains the specific word. If the text data is not found to contain a word consistent with the word, it is determined that the text data does not contain the specific word. Based on the above method, after all the specific words contained in the text data are determined, the number of specific words contained in the text data is counted.

[0092] S25. Determine the specificity value of the preset wake-up word in the text data based on the first ratio, the second ratio, the position weight and the number of specific words.

[0093] As an embodiment, after respectively determining the first ratio, the second ratio, the position weight, and the number of specific words, the specificity value of the wake-up word in the text data may be calculated according to the following formula:

[0094] S=P 1 +P 2 +P 3 +M 4

[0095] Among them, S represents the specificity value of the wake-up word in the text data, P 3 represents the position weight, M 4 Indicates the number of specific words.

[0096] At this point, the calculation of the specificity value of the wake-up word in the text data is completed.

[0097] See also Figure 3 , is a schematic diagram of a device wake-up apparatus provided in an embodiment of the present application, such as Figure 3 As shown, the device may include:

[0098] An acquisition module 301 is used to acquire audio data;

[0099] A conversion module 302, used to convert audio data into text data;

[0100] A specificity determination module 303 is used to determine the specificity value of the wake-up word in the text data if it is determined that the text data contains a preset wake-up word, and the specificity value is positively correlated with the intensity of the user's wake-up intention for the device;

[0101] The wake-up module 304 is configured to wake up the device if it is determined that the specificity value belongs to a preset interval.

[0102] As a possible implementation, the above device may further include ( Figure 3 Not shown):

[0103] The discarding module is used to discard the audio data when it is determined that the text data does not contain the wake-up word.

[0104] As a possible implementation, the specificity determination module 303 includes:

[0105] A first calculation unit, used to calculate a first ratio of the length of the wake-up word to the length of the text data;

[0106] A second calculation unit is used to determine the total amount of intentions of the text data, and determine the ratio of the number of intentions of the wake-up word to the total amount of intentions as a second ratio;

[0107] A third calculation unit, used to determine the position weight of the wake-up word in the text data;

[0108] a fourth calculation unit, for determining the number of specific words in the text data;

[0109] The fifth calculation unit is used to determine the specificity value of the wake-up word in the text data according to the first ratio, the second ratio, the position weight and the number of specific words.

[0110] As a possible implementation manner, the first computing unit is specifically configured to:

[0111] Determine the number of words in the wake-up word;

[0112] Determine the word count of text data;

[0113] The ratio of the number of words in the wake-up word to the number of words in the text data is taken as the first ratio.

[0114] As a possible implementation manner, the second computing unit determines the total amount of the intention of the text data, including:

[0115] Perform word segmentation on the text data to obtain at least one word;

[0116] For each word, determine whether there is an intent corresponding to the word in the preset mapping relationship table between words and intents;

[0117] If it is determined that there is an intention corresponding to the word, the word is determined to be the target word;

[0118] Remove duplicate target words from text data;

[0119] Determine the number of target words in the deduplicated text data;

[0120] The number of target words is taken as the total amount of intent in the text data.

[0121] As a possible implementation manner, the third computing unit is specifically configured to:

[0122] Determine the location of the wake-up word in the text data;

[0123] If it is determined that the wake-up word is located at the beginning of a sentence in the text data, then determining that the position weight of the wake-up word in the text data is a preset first value;

[0124] If it is determined that the wake-up word is not located at the beginning of the sentence of the text data, the position weight of the wake-up word in the text data is determined to be a preset second value.

[0125] As a possible implementation manner, the fourth computing unit is specifically configured to:

[0126] Get the preset specific words;

[0127] The text data is recognized based on the specific words, and the number of the specific words contained therein is determined.

[0128] See also Figure 4 , Figure 4 It is a structural schematic diagram of an electronic device provided by another embodiment of the present application.

[0129] like Figure 4 As shown, the electronic device provided in this embodiment includes: at least one processor 401, a memory 402, at least one network interface 403 and other user interfaces 404. The various components in the electronic device 400 are coupled together through a bus system 405. It can be understood that the bus system 405 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 405 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 4 Various buses are labeled as bus system 405 .

[0130] The user interface 404 may include a display, a keyboard, or a pointing device (eg, a mouse, a trackball, a touch pad, or a touch screen).

[0131] It can be understood that the memory 402 in the embodiment of the present invention can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 402 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0132] In some implementations, the memory 402 stores the following elements, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system 4021 and application programs 4022 .

[0133] The operating system 4021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 4022 includes various application programs, such as a media player (Media Player), a browser (Browser), etc., which are used to implement various application services. The program for implementing the method of the embodiment of the present invention can be included in the application 4022.

[0134] In the embodiment of the present invention, by calling the program or instruction stored in the memory 402, specifically, the program or instruction stored in the application 4022, the processor 401 is used to execute the method steps provided by each method embodiment, for example, including:

[0135] Get audio data;

[0136] Convert audio data into text data;

[0137] If it is determined that the text data contains a preset wake-up word, then the specificity value of the wake-up word in the text data is determined, and the specificity value is positively correlated with the intensity of the user's intention to wake up the device;

[0138] If it is determined that the specific value belongs to the preset range, the device is woken up.

[0139] The method disclosed in the above embodiment of the present invention can be applied to the processor 401, or implemented by the processor 401. The processor 401 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 401 or the instruction in the form of software. The above processor 401 can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present invention can be directly embodied as a hardware decoding processor to execute, or the hardware and software units in the decoding processor can be executed. The software unit can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 402, and the processor 401 reads the information in the memory 402 and completes the steps of the above method in combination with its hardware.

[0140] It is understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPDevice, DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), general purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions of the present application, or a combination thereof.

[0141] For software implementation, the technology of this article can be implemented by a unit that performs the functions of this article. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or outside the processor.

[0142] The embodiment of the present invention also provides a storage medium (computer-readable storage medium). The storage medium here stores one or more programs. The storage medium may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk or a solid-state drive; the memory may also include a combination of the above-mentioned types of memory.

[0143] When one or more programs in the storage medium can be executed by one or more processors, the device wake-up method executed on the electronic device side can be implemented.

[0144] The processor is used to execute the device wake-up program stored in the memory to implement the following steps of the device wake-up method performed on the electronic device side:

[0145] Get audio data;

[0146] Convert audio data into text data;

[0147] If it is determined that the text data contains a preset wake-up word, then the specificity value of the wake-up word in the text data is determined, and the specificity value is positively correlated with the intensity of the user's intention to wake up the device;

[0148] If it is determined that the specific value belongs to the preset range, the device is woken up.

[0149] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0150] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0151] It should be noted that, in the description of this application, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0152] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0153] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0154] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0155] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0156] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0157] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0158] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A device wake-up method, characterized in that: include: Get audio data; Converting the audio data into text data; If it is determined that the text data contains a preset wake-up word, then determine the specificity value of the wake-up word in the text data, the specificity value is positively correlated with the strength of the user's wake-up intention for the device, and the determination of the specificity value of the wake-up word in the text data includes: calculating a first ratio of the length of the wake-up word to the length of the text data; determining the total amount of intentions of the text data, and determining the ratio of the number of intentions of the wake-up word to the total amount of intentions as a second ratio; determining the position weight of the wake-up word in the text data; determining the number of specific words in the text data; and determining the specificity value of the wake-up word in the text data according to the first ratio, the second ratio, the position weight, and the number of specific words. If it is determined that the specificity value belongs to a preset interval, the device is woken up.

2. The method according to claim 1, characterized in that The method further comprises: If it is determined that the text data does not include the wake-up word, the audio data is discarded.

3. The method according to claim 1, characterized in that The calculating a first ratio of the length of the preset wake-up word to the length of the text data includes: Determining the number of words in the wake-up word; Determining the number of words in the text data; The ratio of the number of characters in the wake-up word to the number of characters in the text data is used as the first ratio.

4. The method according to claim 1, characterized in that The determining the total amount of the intention of the text data includes: Performing word segmentation processing on the text data to obtain at least one word; For each word, determine whether there is an intent corresponding to the word in a preset mapping relationship table between words and intents; If it is determined that there is an intention corresponding to the word, the word is determined to be a target word; and the target word in the text data is deduplicated; Determining the number of target words in the text data after deduplication processing; The number is regarded as the total amount of the intention of the text data.

5. The method according to claim 1, characterized in that The determining the position weight of the wake-up word in the text data includes: Determining a position of the wake-up word in the text data; If it is determined that the wake-up word is located at the beginning of the sentence of the text data, determining that the position weight of the wake-up word in the text data is a preset first value; If it is determined that the wake-up word is not located at the beginning of the sentence of the text data, the position weight of the wake-up word in the text data is determined to be a preset second value.

6. The method according to claim 1, characterized in that Determining the number of specific words in the text data includes: Get the preset specific words; The text data is identified based on the specific words, and the number of the specific words contained therein is determined.

7. A device waking up a device, characterized in that: include: An acquisition module, used to acquire audio data; A conversion module, used for converting the audio data into text data; A specificity determination module, for determining a specificity value of the wake-up word in the text data if it is determined that the text data contains a preset wake-up word, the specificity value being positively correlated with the strength of the user's wake-up intention for the device, the specificity value of the wake-up word in the text data comprising: calculating a first ratio of the length of the wake-up word to the length of the text data; determining the total amount of intentions of the text data, and determining the ratio of the number of intentions of the wake-up word to the total amount of intentions as a second ratio; determining a position weight of the wake-up word in the text data; determining the number of specific words in the text data; and determining the specificity value of the wake-up word in the text data according to the first ratio, the second ratio, the position weight, and the number of specific words. The wake-up module is used to wake up the device if it is determined that the specificity value belongs to a preset interval.

8. An electronic device, characterized in that: include: A processor and a memory, wherein the processor is used to execute a device wake-up program stored in the memory to implement the device wake-up method described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the device wake-up method described in any one of claims 1-6.

Images