Method and device for calculating wake-up word recommendation degree, electronic equipment and storage medium

Abstract

The application discloses a kind of calculation methods, device, electronic equipment and storage medium of wake-up word recommendation degree, belong to voice interaction technical field.Therein, the method includes: obtaining input custom wake-up word;Determine the influence factor that influences the availability of the custom wake-up word;According to the influence factor, the recommendation degree of the custom wake-up word is calculated, wherein the recommendation degree is used to represent the matching degree of the custom wake-up word and voice wake-up device.Through the application, the technical problem that the availability of custom wake-up word is lower in related art is solved.

Description

Technical Field

[0001] This invention relates to the field of voice interaction technology, and more specifically, to a method, apparatus, electronic device, and storage medium for calculating wake word recommendation. Background Technology

[0002] The rapid development of intelligent voice interaction technology has provided people with many conveniences. Voice interaction often involves voice wake words, which are used to perform various functions. Currently, it has evolved from fixed wake words to user-customizable wake words. However, users are not aware of some issues related to custom wake words, such as sensitive words and repeated words, which can affect the subsequent wake-up rate and the areas that need to be avoided. This may lead to lower usability when using custom wake words.

[0003] There are currently no effective solutions to the aforementioned problems in the relevant technologies. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for calculating wake word recommendation, in order to solve the technical problem of low usability of custom wake words in related technologies.

[0005] According to one aspect of the embodiments of this application, a method for calculating the recommendation degree of a wake-up word is provided, comprising: obtaining an input custom wake-up word; determining influencing factors affecting the usability of the custom wake-up word; and calculating the recommendation degree of the custom wake-up word based on the influencing factors, wherein the recommendation degree is used to characterize the matching degree between the custom wake-up word and a voice wake-up device.

[0006] Furthermore, calculating the recommendation degree of the custom wake-up word based on the influencing factors includes: obtaining the baseline value corresponding to each of the influencing factors; determining the device type of the voice wake-up device, and determining the weight of each of the influencing factors based on the device type; and calculating the recommendation degree of the custom wake-up word based on the baseline value and weight of each of the influencing factors.

[0007] Furthermore, determining the device type of the voice wake-up device and determining the weight of each influencing factor based on the device type includes: for each influencing factor of the device type, obtaining the attention level of the corresponding influencing factor, wherein the attention level is used to represent the user's expected proportion of each influencing factor; and calculating the weight of each influencing factor using the corresponding attention level.

[0008] Furthermore, the influencing factors include wake-up rate, false wake-up rate, response time, and power consumption. Determining the device type of the voice wake-up device and assigning weights to each influencing factor based on the device type includes: if the power consumption of the device type is greater than a first preset threshold, assigning a first weight to the wake-up rate, false wake-up rate, and response time, and assigning a second weight to the power consumption, wherein the first weight is greater than the second weight; if the power consumption of the device type is less than a second preset threshold, assigning a third weight to the wake-up rate, false wake-up rate, and response time, and assigning a fourth weight to the power consumption, wherein the third weight is less than the fourth weight.

[0009] Furthermore, calculating the recommendation degree of the custom wake word based on the baseline value and weight of each of the influencing factors includes: multiplying the baseline value of each of the influencing factors by its weight to obtain the product between the baseline value and weight of each of the influencing factors; summing the products between the baseline value and weight of each of the influencing factors, and using the calculation result as the recommendation degree of the custom wake word.

[0010] Furthermore, after calculating the recommendation level of the custom wake word based on the influencing factors, the method further includes: obtaining the calculation standard and scoring suggestion corresponding to the recommendation level; and outputting the calculation standard and scoring suggestion.

[0011] Furthermore, obtaining the rating suggestion corresponding to the recommendation degree includes: if the recommendation degree is less than a preset score, then obtaining at least one recommended wake word related to the custom wake word; and using the recommended wake word as a rating suggestion.

[0012] According to another aspect of the embodiments of this application, a device for calculating the recommendation degree of a wake-up word is also provided, comprising: an acquisition module for acquiring an input custom wake-up word; a factor determination module for determining influencing factors affecting the usability of the custom wake-up word; and a calculation module for calculating the recommendation degree of the custom wake-up word based on the influencing factors, wherein the recommendation degree is used to characterize the matching degree between the custom wake-up word and a voice wake-up device.

[0013] Furthermore, the calculation module includes a recommendation calculation module, which is used to obtain the baseline value corresponding to each of the influencing factors; determine the device type of the voice wake-up device, and determine the weight of each of the influencing factors according to the device type; and calculate the recommendation degree of the custom wake-up word according to the baseline value and weight of each of the influencing factors.

[0014] Furthermore, the influencing factors include wake-up rate, false wake-up rate, response time, and power consumption. The recommendation calculation module includes a first weight calculation module, which is used to obtain the attention level of each influencing factor for each influencing factor of the device type. The attention level is used to characterize the user's expected proportion of each influencing factor. For each influencing factor, the corresponding attention level is used to calculate the weight.

[0015] Furthermore, the recommendation calculation module includes a second weight calculation module. The second weight calculation module is used to assign a first weight to the wake-up rate, the false wake-up rate, and the response time, and to assign a second weight to the power consumption if the power consumption of the device type is greater than a first preset threshold, wherein the first weight is greater than the second weight; if the power consumption of the device type is less than a second preset threshold, it assigns a third weight to the wake-up rate, the false wake-up rate, and the response time, and to assign a fourth weight to the power consumption, wherein the third weight is less than the fourth weight.

[0016] Furthermore, the recommendation calculation module includes a recommendation calculation submodule, which is used to multiply the baseline value of each of the influencing factors by its weight to obtain the product between the baseline value and the weight of each of the influencing factors; to accumulate the products between the baseline value and the weight of each of the influencing factors, and to use the calculation result as the recommendation degree of the custom wake word.

[0017] Furthermore, the device for calculating the wake word recommendation score also includes an output module, which is used to obtain the calculation criteria and scoring suggestions corresponding to the recommendation score; and output the calculation criteria and scoring suggestions.

[0018] Furthermore, the output module includes a rating suggestion acquisition module, which is used to acquire at least one recommended wake word related to the custom wake word if the recommendation score is less than a preset score; and use the recommended wake word as a rating suggestion.

[0019] According to another aspect of the embodiments of this application, a storage medium is also provided, the storage medium including a stored program that executes the above steps when the program is run.

[0020] According to another aspect of the embodiments of this application, an electronic device is also provided, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; wherein: the memory is used to store computer programs; and the processor is used to execute the steps in the above method by running the programs stored in the memory.

[0021] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the steps in the above-described method.

[0022] This invention obtains the input of a custom wake-up word; identifies the factors affecting the usability of the custom wake-up word; and calculates the recommendation degree of the custom wake-up word based on these factors. The recommendation degree characterizes the matching degree between the custom wake-up word and the voice wake-up device. By calculating the recommendation degree of the user-defined wake-up word based on the factors affecting its usability when the user defines it, and evaluating the user-defined wake-up word based on the recommendation degree, this invention assists users in setting custom wake-up words, solving the technical problem of low usability of custom wake-up words in related technologies and improving the user experience. Attached Figure Description

[0023] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0024] Figure 1 This is a hardware structure block diagram of a computer according to an embodiment of the present invention;

[0025] Figure 2 This is a flowchart of a method for calculating the recommendation score of wake words according to an embodiment of the present invention;

[0026] Figure 3 This is a schematic diagram of an application scenario according to an embodiment of the present invention;

[0027] Figure 4 This is a structural block diagram of a device for calculating wake word recommendation according to an embodiment of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all of them. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present application. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of the present application can be combined with each other.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] Example 1

[0031] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile phone, computer, tablet, or similar computing device. Taking running on a computer as an example, Figure 1 This is a hardware structure block diagram of a computer according to an embodiment of the present invention. For example... Figure 1 As shown, a computer may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. Optionally, the computer may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the computer described above. For example, the computer may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0032] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to a video motion rate recognition method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the aforementioned method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0033] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by a computer's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0034] This embodiment provides a method for calculating the recommendation score of wake words. Figure 2 This is a flowchart illustrating a method for calculating wake word recommendation scores according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0035] Step S10: Obtain the input custom wake word;

[0036] The wake word recommendation method in this embodiment can be applied to smart terminals such as smart homes, smart robots, in-vehicle terminals, and smartphones to obtain input custom wake words. The input custom wake word can be a single character, a phrase, or a sentence. For example, a user can input "I'm home" as a wake word.

[0037] Step S20: Determine the factors affecting the availability of the custom wake word;

[0038] Factors affecting the usability of custom wake words are identified, including wake-up rate, false wake-up rate, response time, and power consumption. Wake-up rate is the probability of being activated by the wake word; a higher wake-up rate indicates better usability, usually expressed as a percentage. False wake-up rate is the probability of being activated by a non-wake word; a higher false wake-up rate indicates poorer usability. Response time is the time difference between when the user says the wake word and when the voice wake-up device provides feedback based on the wake word. Power consumption refers to the power consumption of the voice system in the voice wake-up device. The wake-up rate and false wake-up rate of custom wake words can be obtained by performing sensitive word detection, repeated word detection, colloquial word detection, and incomplete pronunciation detection on the custom wake words. The wake-up rate and false wake-up rate can also be determined by obtaining the pronunciation sequence of the custom wake words and comparing it with common pronunciations to determine the overlap between the pronunciation of the custom wake words and common pronunciations. The methods for obtaining response time and power consumption can refer to existing technologies.

[0039] Step S30: Calculate the recommendation degree of the custom wake-up word based on the influencing factors, wherein the recommendation degree is used to characterize the matching degree between the custom wake-up word and the voice wake-up device.

[0040] Based on influencing factors, the recommendation score of a custom wake-up word is calculated, where the recommendation score characterizes the matching degree between the custom wake-up word and the voice wake-up device. The recommendation score is directly proportional to the matching degree; that is, the higher the matching degree between the custom wake-up word and the voice wake-up device, the higher the recommendation score, and vice versa. Understandably, this embodiment integrates the aforementioned influencing factors to calculate the recommendation score of the custom wake-up word to score it. A higher recommendation score results in a higher score, meaning it is more recommended for users to use. Conversely, a lower recommendation score results in a lower score, indicating that the user-defined wake-up word may have some issues and is less recommended for use. In such cases, users can modify or replace their custom wake-up word based on the calculated recommendation score.

[0041] In one embodiment of this example, calculating the recommendation degree of the custom wake word based on the influencing factors includes:

[0042] Step S301: Obtain the baseline value corresponding to each of the aforementioned influencing factors;

[0043] Step S302: Determine the device type of the voice wake-up device, and determine the weight of each influencing factor based on the device type;

[0044] Step S303: Calculate the recommendation degree of the custom wake word based on the baseline value and weight of each of the influencing factors.

[0045] Obtain the baseline values ​​for each influencing factor. These baseline values ​​can be on a ten-point scale or a percentage scale, and can be obtained using existing technologies, which will not be elaborated upon here. For example... Figure 3As shown, the baseline values ​​for wake-up rate, false wake-up rate, response time, and power consumption are X1, X2, X3, and X4, respectively. The values ​​of X1, X2, X3, and X4 range from [0, 100]. This determines the device type of the voice wake-up device. The device type can be determined according to the device's purpose, size, or power consumption. Considering that different devices are suitable for voice wake-up differently, the weights of each influencing factor are determined according to the device type. The proportions of influencing factors for different device types will vary. Therefore, the weights of influencing factors for different device types are calculated. Based on the baseline values ​​and weights of each influencing factor, the recommendation degree of the custom wake-up word is calculated. This is the recommendation degree calculation for custom wake-up words on different devices, to obtain a more accurate evaluation of custom wake-up words, so that users can understand whether the custom content is suitable as a wake-up word, thereby improving the usability of subsequent custom wake-up words.

[0046] Through the above steps, the user-inputted custom wake-up word is obtained; the influencing factors affecting the usability of the custom wake-up word are determined, including wake-up rate, false wake-up rate, response time, and power consumption; based on the influencing factors, the recommendation degree of the custom wake-up word is calculated, whereby the recommendation degree is used to characterize the matching degree between the custom wake-up word and the voice wake-up device. By calculating the recommendation degree of the user-defined wake-up word based on the influencing factors affecting its usability when the user defines the wake-up word, evaluating the user-defined wake-up word based on the recommendation degree, and assisting the user in setting the custom wake-up word based on the recommendation degree, the technical problem of low usability of custom wake-up words in related technologies is solved, and the user experience is improved.

[0047] In this embodiment, determining the device type of the voice wake-up device and determining the weight of each influencing factor based on the device type includes:

[0048] Step A: For each influencing factor of the device type, obtain the attention level of the corresponding influencing factor, where the attention level is used to characterize the expected proportion of users for each influencing factor;

[0049] Step B involves calculating the weight of each influencing factor based on its corresponding level of attention.

[0050] In this embodiment, for each influencing factor of the device type, the attention level of the corresponding influencing factor is obtained. The attention level represents the user's expected proportion of each influencing factor, and a weight is calculated for each influencing factor using the corresponding attention level. For example, if the device type of the voice wake-up device is determined to be a smart home device among powered devices, such as an air conditioner, range hood, refrigerator, or speaker, the attention level of each influencing factor for this device type is obtained. The attention level represents the user's expected proportion of each influencing factor. The attention level can be obtained by collecting the user's expected proportion of each influencing factor under this device type through methods such as questionnaires. That is, obtaining the user's attention level to factors such as wake-up rate, false wake-up rate, response time, and power consumption for different types of devices. Using a large amount of survey data, the weight of each influencing factor is calculated mathematically. For example... Figure 3 K1, K2, K3, and K4, as shown, represent the weight values ​​for wake-up rate, false wake-up rate, response time, and power consumption, respectively. The mathematical method used can be the least squares method, but other methods can also be used to calculate the weight of each influencing factor. It should be noted that the more survey data there is, the more accurate the weight value of each influencing factor will be, and the higher the accuracy of the custom wake-up word recommendation based on the weight value will be. This will be closer to the needs of most users and therefore have high reference value for users, improving the user experience.

[0051] In another embodiment of this example, determining the device type of the voice wake-up device and determining the weight of each influencing factor based on the device type includes:

[0052] Step C: If the power consumption of the device type is greater than a first preset threshold, a first weight is assigned to the wake-up rate, the false wake-up rate and the response time, and a second weight is assigned to the power consumption, wherein the first weight is greater than the second weight;

[0053] Step D: If the power consumption of the device type is less than the second preset threshold, a third weight is assigned to the wake-up rate, the false wake-up rate and the response time, and a fourth weight is assigned to the power consumption, wherein the third weight is less than the fourth weight.

[0054] In this embodiment, the first and second preset thresholds can be preset according to actual conditions. If the power consumption is greater than the preset threshold, it indicates that the voice wake-up device may be a large power consumption device, such as a voice-activated air conditioner. If the power consumption is less than the preset threshold, it indicates that the voice wake-up device may be a small power consumption device, such as a small voice-activated toy. If the power consumption of the device type is greater than the first preset threshold, a first weight is assigned to the wake-up rate, false wake-up rate, and response time, and a second weight is assigned to the power consumption, wherein the first weight is greater than the second weight. For relatively power-consuming products, their usage frequency is relatively high, and their requirements for wake-up rate, false wake-up rate, and response time are also relatively high. For devices with high power consumption, such as small toy cars, the impact of power consumption on voice wake-up is relatively small, so the weight of power consumption as an influencing factor can be set relatively low. Therefore, in this embodiment, for devices with high power consumption, a first weight is assigned to wake-up rate, false wake-up rate, and response time, and a second weight is assigned to power consumption, which is less than the first weight. Similarly, for device types with low power consumption, such as small toy cars, power consumption has a greater impact, so the weight assigned to power consumption is larger, and the weight assigned to wake-up rate, false wake-up rate, and response time is smaller. That is, if the power consumption of a device type is less than a second preset threshold, a third weight is assigned to wake-up rate, false wake-up rate, and response time, and a fourth weight is assigned to power consumption, where the third weight is less than the fourth weight. In this embodiment, different weight ratio standards are specified for different device types based on the characteristics of power consumption. Based on the corresponding weights, an adaptive recommendation degree can be calculated for different device types of voice wake-up devices, further improving the accuracy of the recommendation degree and enhancing the user experience.

[0055] In another embodiment of this example, calculating the recommendation degree of the custom wake word based on the baseline value and weight of each of the influencing factors includes:

[0056] Step E: Multiply the baseline value of each influencing factor by its weight to obtain the product between the baseline value and the weight of each influencing factor.

[0057] Step F involves summing the products between the baseline values ​​and weights of each of the aforementioned influencing factors, and using the calculation results as the recommendation score of the custom wake word.

[0058] like Figure 3 As shown, the input wake word is obtained and processed to obtain the baseline values ​​X1, X2, X3, and X4 of the factors affecting wake-up rate, false wake-up rate, response time, and power consumption. Then, the weights K1, K2, K3, and K4 corresponding to each factor are determined. The baseline value of each influencing factor is multiplied by its weight to obtain the product between the baseline value and the weight of each influencing factor. The products between the baseline value and the weight of each influencing factor are accumulated and calculated. The calculation result is used as the recommendation degree of the custom wake word. Figure 3 The score in the formula is the recommendation level of the custom wake word. The formula for calculating the recommendation level of the custom wake word is Score=X1·K1+X2·K2+X3·K3+X4·K4, where Score is the recommendation level of the custom wake word.

[0059] In another embodiment of this example, after calculating the recommendation score of the custom wake word based on the influencing factors, the method further includes:

[0060] Step G: Obtain the calculation criteria and scoring suggestions corresponding to the recommendation score;

[0061] Step H: Output the calculation criteria and scoring recommendations.

[0062] After calculating the recommendation score of the custom wake word, the calculation criteria and scoring suggestions corresponding to the recommendation score are obtained, and then the calculation criteria and scoring suggestions are output. The calculation criteria include a 10-point scale and a 100-point scale to provide a reference for the calculated recommendation score, and the scoring suggestions are the result recommendations corresponding to the recommendation score.

[0063] Furthermore, obtaining the rating suggestions corresponding to the recommendation level includes:

[0064] Step g1: If the recommendation score is less than the preset score, then obtain at least one recommended wake word related to the custom wake word;

[0065] Step g2: Use the recommended wake-up word as a scoring suggestion.

[0066] If the recommendation score is less than the preset value, at least one recommended wake-up word related to the custom wake-up word is obtained and used as a scoring suggestion. Specifically, the user-input custom wake-up word can be split and recombined, or duplicate or sensitive words in the wake-up word can be deleted to obtain a new wake-up word, which is then used as a recommended wake-up word. Alternatively, the semantics of the custom wake-up word can be analyzed to match recommended wake-up words with the same semantics, which are then output as scoring suggestions. Further scoring suggestions also include a scoring description corresponding to the recommendation score. For example, if the recommendation score exceeds a preset value (e.g., 80), the scoring description corresponding to that recommendation score is determined to be recommended for use and has a good effect. If the recommended wake-up word can meet the wake-up rate requirements, it will help improve the wake-up rate of the custom wake-up word for voice wake-up devices and ensure that the custom wake-up word meets the user's usage habits.

[0067] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0068] Example 2

[0069] This embodiment also provides a wake-word recommendation calculation device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0070] Figure 4 This is a structural block diagram of a wake-word recommendation calculation device according to an embodiment of the present invention, such as... Figure 4 As shown, the device includes: an acquisition module 40, a factor determination module 41, and a calculation module 42, wherein,

[0071] The acquisition module 40 is used to acquire the input custom wake word;

[0072] Factor determination module 41 is used to determine the influencing factors affecting the availability of the custom wake word;

[0073] The calculation module 42 is used to calculate the recommendation degree of the custom wake-up word based on the influencing factors, wherein the recommendation degree is used to characterize the matching degree between the custom wake-up word and the voice wake-up device.

[0074] Optionally, the calculation module includes a recommendation calculation module, which is used to obtain the baseline value corresponding to each of the influencing factors; determine the device type of the voice wake-up device, and determine the weight of each of the influencing factors according to the device type; and calculate the recommendation degree of the custom wake-up word according to the baseline value and weight of each of the influencing factors.

[0075] Optionally, the recommendation calculation module includes a first weight calculation module, which is used to obtain the attention level of each influencing factor for each influencing factor of the device type, wherein the attention level is used to characterize the expected proportion of users for each influencing factor; and to calculate the weight of each influencing factor using the corresponding attention level.

[0076] Optionally, the recommendation calculation module includes a second weight calculation module. The second weight calculation module is used to assign a first weight to the wake-up rate, the false wake-up rate, and the response time, and to assign a second weight to the power consumption if the power consumption of the device type is greater than a first preset threshold, wherein the first weight is greater than the second weight; if the power consumption of the device type is less than a second preset threshold, it assigns a third weight to the wake-up rate, the false wake-up rate, and the response time, and to assign a fourth weight to the power consumption, wherein the third weight is less than the fourth weight.

[0077] Optionally, the recommendation calculation module includes a recommendation calculation submodule, which is used to multiply the baseline value of each of the influencing factors by its weight to obtain the product between the baseline value and the weight of each of the influencing factors; to accumulate the products between the baseline value and the weight of each of the influencing factors, and to use the calculation result as the recommendation degree of the custom wake word.

[0078] Optionally, the device for calculating the wake word recommendation score further includes an output module, which is used to obtain the calculation criteria and scoring suggestions corresponding to the recommendation score; and output the calculation criteria and scoring suggestions.

[0079] Optionally, the output module includes a rating suggestion acquisition module, which is used to acquire at least one recommended wake word related to the custom wake word if the recommendation score is less than a preset score; and use the recommended wake word as a rating suggestion.

[0080] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0081] Example 3

[0082] Embodiments of the present invention also provide a storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.

[0083] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0084] S1, obtain the input custom wake word;

[0085] S2, determine the factors affecting the availability of the custom wake word;

[0086] S3. Calculate the recommendation degree of the custom wake-up word based on the influencing factors, wherein the recommendation degree is used to characterize the matching degree between the custom wake-up word and the voice wake-up device.

[0087] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0088] Embodiments of the present invention also provide an electronic device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0089] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0090] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0091] S1, obtain the input custom wake word;

[0092] S2, determine the factors affecting the availability of the custom wake word;

[0093] S3. Calculate the recommendation degree of the custom wake-up word based on the influencing factors, wherein the recommendation degree is used to characterize the matching degree between the custom wake-up word and the voice wake-up device.

[0094] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0095] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0096] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0097] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0098] 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 units can be selected to achieve the purpose of this embodiment according to actual needs.

[0099] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0100] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0101] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for calculating the recommendation degree of wake words, characterized in that, The method includes: Get the input custom wake word; Identify the factors affecting the availability of the custom wake word; Based on the aforementioned influencing factors, the recommendation degree of the custom wake-up word is calculated, wherein the recommendation degree is used to characterize the matching degree between the custom wake-up word and the voice wake-up device; Calculating the recommendation score of the custom wake word includes: Obtain the baseline values ​​corresponding to each of the aforementioned influencing factors; Determine the device type of the voice wake-up device, and determine the weight of each of the influencing factors based on the device type; The recommendation rate of the custom wake word is calculated based on the baseline value and weight of each of the aforementioned influencing factors; The influencing factors include wake-up rate, false wake-up rate, response time, and power consumption. The device type of the voice wake-up device is determined, and the weight of each influencing factor is determined based on the device type, including: If the power consumption of the device type is greater than a first preset threshold, the device type is a large power consumption device. A first weight is assigned to the wake-up rate, the false wake-up rate and the response time, and a second weight is assigned to the power consumption, wherein the first weight is greater than the second weight. If the power consumption of the device type is less than the second preset threshold, the device type is a small power consumption device, a third weight is assigned to the wake-up rate, the false wake-up rate and the response time, and a fourth weight is assigned to the power consumption, wherein the third weight is less than the fourth weight.

2. The method according to claim 1, characterized in that, The recommendation score of the custom wake word is calculated based on the baseline value and weight of each of the aforementioned influencing factors, including: Multiply the baseline value of each of the influencing factors by its weight to obtain the product between the baseline value and the weight of each of the influencing factors. The products of the baseline values ​​and weights of each of the aforementioned influencing factors are summed, and the calculation results are used as the recommendation score of the custom wake word.

3. The method according to claim 1, characterized in that, After calculating the recommendation rate of the custom wake word based on the aforementioned influencing factors, the method further includes: Obtain the calculation criteria and scoring suggestions corresponding to the recommendation score; Output the calculation criteria and scoring recommendations.

4. The method according to claim 3, characterized in that, Obtaining the rating suggestions corresponding to the recommendation level includes: If the recommendation score is less than the preset score, then at least one recommended wake word related to the custom wake word is obtained; The recommended wake words are used as scoring suggestions.

5. A device for calculating the recommendation degree of wake words, characterized in that, include: The acquisition module is used to acquire the input custom wake word; The factor determination module is used to determine the influencing factors affecting the availability of the custom wake word; The calculation module is used to calculate the recommendation degree of the custom wake-up word based on the influencing factors, wherein the recommendation degree is used to characterize the matching degree between the custom wake-up word and the voice wake-up device; The calculation module includes a recommendation calculation module, which is used to obtain the baseline value corresponding to each of the influencing factors; determine the device type of the voice wake-up device, and determine the weight of each of the influencing factors according to the device type; and calculate the recommendation degree of the custom wake-up word according to the baseline value and weight of each of the influencing factors. The recommendation calculation module includes a second weight calculation module. The influencing factors include wake-up rate, false wake-up rate, response time, and power consumption. The second weight calculation module is used to assign a first weight to the wake-up rate, false wake-up rate, and response time, and a second weight to the power consumption, if the power consumption of the device type is greater than a first preset threshold, and the device type is a large power consumption device; if the power consumption of the device type is less than a second preset threshold, and the device type is a small power consumption device, a third weight is assigned to the wake-up rate, false wake-up rate, and response time, and a fourth weight to the power consumption, wherein the third weight is less than the fourth weight.

6. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, communication interface, and memory communicate with each other through the communication bus; wherein: Memory, used to store computer programs; A processor for executing the method steps of any one of claims 1 to 4 by running a program stored in memory.

7. A storage medium, characterized in that, The storage medium includes a stored program, wherein the program executes the method steps of any one of claims 1 to 4 when it is run.

Images