Voice function optimization method and device of smart home device

Abstract

The application relates to the technical field of smart home devices, and provides a voice function optimization method and device for a smart home device, which comprises the following steps: determining human body posture attribute information in at least one home layout drawing, setting attribute information of a smart home device, and acquiring voice data corresponding to the human body posture attribute information collected by the smart home device under the setting attribute information; determining a voice interaction success rate under the condition of the human body posture attribute information in the home layout drawing and the setting attribute information of the smart home device based on the voice data; and performing optimization processing on the smart home device based on the voice interaction success rate. The method provided by the application can effectively improve the efficiency of voice interaction optimization processing of the smart home device.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart home devices, and particularly relates to a voice function optimization method and device for a smart home device, and further relates to an electronic device and a non-transitory computer-readable storage medium. BACKGROUND

[0002] With the continuous development of artificial intelligence technology, various smart home devices are increasingly widely used in people's daily life, and smart home devices have become an indispensable part of people's daily life. However, the existing smart home devices still have some problems in voice interaction, such as insensitive voice wake-up, unsmooth voice interaction, and low voice distributed success rate. At present, the voice function optimization method of the existing smart home device is low in efficiency, which leads to the inability to quickly evaluate and optimize the performance of the smart home device. Therefore, how to provide a more accurate and efficient voice function optimization scheme for a smart home device has become a difficult problem to be solved. SUMMARY

[0003] The present application provides a voice function optimization method for a smart home device to solve the defect that the voice interaction processing scheme of the smart home device in the prior art is low in efficiency.

[0004] The present application provides a voice function optimization method for a smart home device, comprising: determining human posture attribute information in at least one home floor plan, setting attribute information of a smart home device, and obtaining voice data corresponding to the human posture attribute information collected by the smart home device under the setting attribute information; based on the voice data, determining a voice interaction success rate under the condition that the human posture attribute information in the home floor plan and the setting attribute information of the smart home device; and based on the voice interaction success rate, optimizing the smart home device.

[0005] The voice function optimization method of the smart home device provided by the application, the voice interaction success rate includes a single voice interaction success rate and a distributed voice interaction success rate; the voice data is analyzed statistically to record the success times and failure times of voice interaction between the human body and a single device and the success times and failure times of voice interaction between the human body and multiple distributed devices; the success times and failure times of voice interaction between the human body and a single device are used to calculate the single voice interaction success rate in the case of human body posture attribute information and setting attribute information of the smart home device in the home layout; wherein the single voice interaction success rate is the success rate of voice interaction between the human body and a single smart home device in a target space environment; the success times and failure times of voice interaction between the human body and multiple distributed devices are used to calculate the distributed voice interaction success rate in the case of human body posture attribute information and setting attribute information of the smart home device in the home layout; wherein the distributed voice interaction success rate is the success rate of voice interaction between the human body and multiple smart home devices distributed respectively in a target space environment.

[0006] The voice function optimization method of the smart home device provided by the application, the voice interaction success rate includes a single voice interaction success rate and a distributed voice interaction success rate; the voice data is analyzed statistically to record the success times and failure times of voice interaction between the human body and a single device and the success times and failure times of voice interaction between the human body and multiple distributed devices; the success times and failure times of voice interaction between the human body and a single device are used to calculate the single voice interaction success rate in the case of human body posture attribute information and setting attribute information of the smart home device in the home layout; wherein the single voice interaction success rate is the success rate of voice interaction between the human body and a single smart home device in a target space environment; the success times and failure times of voice interaction between the human body and multiple distributed devices are used to calculate the distributed voice interaction success rate in the case of human body posture attribute information and setting attribute information of the smart home device in the home layout; wherein the distributed voice interaction success rate is the success rate of voice interaction between the human body and multiple smart home devices distributed respectively in a target space environment.

[0007] The voice function optimization method of the smart home device provided in the application further comprises: obtaining human body posture attribute information and smart home device setting attribute information collected under a target space environment; generating an initial house type drawing corresponding to the target space environment; marking the human body posture attribute information and the smart home device setting attribute information into the initial house type drawing to obtain at least one house type drawing.

[0008] The voice function optimization method of the smart home device provided in the application further comprises: identifying target space elements in the house type drawing and human body node information under different human body postures; determining the smart home device setting attribute information based on the target space elements and determining the human body posture attribute information based on the human body node information under different human body postures.

[0009] The voice function optimization method of the smart home device provided in the application further comprises: determining the relative position relationship between the target space elements and the smart home device, determining the orientation and installation position of the smart home device based on the relative position relationship between the target space elements and the smart home device; and taking the orientation and installation position of the smart home device as the smart home device setting attribute information.

[0010] The voice function optimization method of the smart home device provided in the application further comprises: identifying the human body node information under different human body postures; extracting feature information for representing human body posture attributes from the human body node information; determining the active posture and current position of the human body based on the feature information; and taking the active posture and current position of the human body as the human body posture attribute information.

[0011] The application further provides a voice function optimization device for a smart home device, which comprises: a target information extraction unit configured to determine human body posture attribute information and smart home device setting attribute information in at least one house type drawing and to obtain voice data corresponding to the human body posture attribute information collected by the smart home device under the setting attribute information; an interactive success rate analysis unit configured to determine the voice interactive success rate under the human body posture attribute information and the smart home device setting attribute information in the house type drawing based on the voice data; and an optimization processing unit configured to perform optimization processing on the smart home device based on the voice interactive success rate.

[0012] The voice function optimization device of the smart home device provided by the application, the voice interaction success rate includes a single voice interaction success rate and a distributed voice interaction success rate; the interaction success rate analysis unit is specifically used for: statistically analyzing the voice data, recording the success times and failure times of voice interaction between the human body and a single device, and recording the success times and failure times of voice interaction between the human body and multiple distributed devices; based on the success times and failure times of voice interaction between the human body and a single device, the single voice interaction success rate in the case of human posture attribute information and setting attribute information of the smart home device in the home layout diagram is calculated; wherein the single voice interaction success rate is the success rate of voice interaction between the human body and a single smart home device in a target space environment; based on the success times and failure times of voice interaction between the human body and multiple distributed devices, the distributed voice interaction success rate in the case of human posture attribute information and setting attribute information of the smart home device in the home layout diagram is calculated; wherein the distributed voice interaction success rate is the success rate of voice interaction between the human body and multiple smart home devices distributed respectively in a target space environment.

[0013] The voice function optimization device of the smart home device provided by the application, the optimization processing unit is specifically used for: comparing the single voice interaction success rate with a first interaction success rate threshold to obtain a first comparison result; comparing the distributed voice interaction success rate with a second interaction success rate threshold to obtain a second comparison result; in the case that the first comparison result is that the single voice interaction success rate is less than or equal to the lower limit value of the first interaction success rate threshold, and / or the distributed voice interaction success rate is less than or equal to the lower limit value of the second interaction success rate threshold, the multiple voice function modules of the smart home device are subjected to overall optimization processing; in the case that the first comparison result is that the single voice interaction success rate is greater than the lower limit value of the first interaction success rate threshold and less than or equal to the upper limit value of the first interaction success rate threshold, and the distributed voice interaction success rate is greater than the lower limit value of the second interaction success rate threshold and less than or equal to the upper limit value of the second interaction success rate threshold, the multiple voice function modules of the smart home device are subjected to local optimization processing.

[0014] The voice function optimization device of the smart home device provided in the application further comprises a home layout obtaining unit, configured to: acquire the human body posture attribute information and the smart home device setting attribute information collected under a target space environment; generate an initial home layout corresponding to the target space environment; and mark the human body posture attribute information and the smart home device setting attribute information into the initial home layout to obtain at least one home layout.

[0015] The voice function optimization device of the smart home device provided in the application, the target information extraction unit is specifically configured to: identify target space elements in the home layout and human body node information under different human body postures; determine the smart home device setting attribute information based on the target space elements, and determine the human body posture attribute information based on the corresponding human body node information under the different human body postures.

[0016] The voice function optimization device of the smart home device provided in the application, the determination of the smart home device setting attribute information based on the target space elements specifically comprises: determining the relative position relationship between the target space elements and the smart home device, determining the orientation and installation position of the smart home device based on the relative position relationship between the target space elements and the smart home device; and taking the orientation and installation position of the smart home device as the smart home device setting attribute information.

[0017] The voice function optimization device of the smart home device provided in the application, the determination of the human body posture attribute information based on the corresponding human body node information under the different human body postures specifically comprises: identifying the corresponding human body node information under the different human body postures; extracting feature information for representing human body posture attributes from the human body node information, determining the active posture and current position of the human body based on the feature information, and taking the active posture and current position of the human body as the human body posture attribute information.

[0018] The application further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the voice function optimization method of the smart home device according to any one of the above-mentioned embodiments when executing the program.

[0019] The application further provides a non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program is executable on a processor to implement the steps of the voice function optimization method of the smart home device according to any one of the above-mentioned embodiments.

[0020] The present invention provides a method for optimizing the voice function of smart home devices. This method involves determining human posture attribute information in at least one floor plan and setting attribute information of the smart home device, and acquiring voice data corresponding to the human posture attribute information collected by the smart home device under the setting attribute information. Based on the voice data, the method determines the voice interaction success rate under the conditions of the human posture attribute information in the floor plan and the setting attribute information of the smart home device. Based on the voice interaction success rate, the method optimizes the smart home device, effectively improving the efficiency of voice interaction optimization processing for smart home devices. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of the hardware environment for a method of optimizing the voice function of a smart home device according to an embodiment of this application.

[0023] Figure 2 This is a flowchart illustrating the method for optimizing the voice function of smart home devices provided by the present invention.

[0024] Figure 3 This is a complete flowchart illustrating the method for optimizing the voice function of smart home devices provided by the present invention.

[0025] Figure 4 This is a schematic diagram of the structure of the voice function optimization device for smart home devices provided by the present invention.

[0026] Figure 5 This is a schematic diagram of the electronic device provided by the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0028] The following is combined Figures 1-5 This invention describes a method and apparatus for optimizing the voice function of smart home devices.

[0029] Figure 1 This is a schematic diagram of the hardware environment for the voice function optimization method of the smart home device provided by the present invention.

[0030] According to one aspect of the embodiments of this application, a method for optimizing the voice function of a smart home device is provided. This method for optimizing the voice function of a smart home device is widely applicable to whole-house intelligent digital control application scenarios such as smart homes, smart home ecosystems, and intelligence house ecosystems. Optionally, in this embodiment, the above-mentioned method for optimizing the voice function of a smart home device can be applied to, for example... Figure 1 The hardware environment shown consists of terminal device 102 and server 104. For example... Figure 1 As shown, server 104 is connected to terminal device 102 via a network and can be used to provide services (such as application services) to the terminal or clients installed on the terminal. A database can be set up on the server or independently of the server to provide data storage services for server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data processing services for server 104.

[0031] The aforementioned network may include, but is not limited to, at least one of the following: wired network, wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network, metropolitan area network, local area network. The aforementioned wireless network may include, but is not limited to, at least one of the following: Wi-Fi (Wireless Fidelity), Bluetooth. The terminal device 102 may not be limited to PC, mobile phone, tablet computer, smart air conditioner, smart range hood, smart refrigerator, smart oven, smart stove, smart washing machine, smart water heater, smart washing equipment, smart dishwasher, smart projector, smart TV, smart clothes rack, smart curtains, smart audio-visual equipment, smart socket, smart speaker, smart speaker box, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart robot vacuum cleaner, smart window cleaning robot, smart mopping robot, smart air purifier, smart steam oven, smart microwave oven, smart water heater, smart air purifier, smart water dispenser, smart door lock, etc.

[0032] The following is a detailed description of embodiments of the voice function optimization method for smart home devices based on the present invention. For example... Figure 2 The diagram shown is a flowchart illustrating the voice function optimization method for smart home devices provided by this invention. The specific implementation process includes the following steps:

[0033] In step 110, the body posture attribute information in at least one home layout diagram, the setting attribute information of the smart home device, and voice data corresponding to the body posture attribute information collected by the smart home device under the setting attribute information are determined.

[0034] In the embodiment of the present application, before the body posture attribute information in at least one home layout diagram and the setting attribute information of the smart home device are determined, the body posture attribute information and the setting attribute information of the smart home device collected under the target space environment are acquired in advance through the camera and microphone array arranged in the target space environment. The body posture attribute information includes but is not limited to the active posture and current position of the human body, etc. The setting attribute information includes but is not limited to the orientation and installation position of the smart home device, etc.

[0035] Further, the initial layout diagram corresponding to the target space environment can be generated according to the actual situation of the target space environment, and the initial layout diagram can be a three-dimensional layout diagram structure. Then, the body posture attribute information and the setting attribute information of the smart home device are marked in the initial layout diagram to obtain at least one home layout diagram. The home layout diagram is a three-dimensional layout diagram structure, and different postures and current positions of the human body are marked therein, as well as different orientations and installation positions of the smart home device, etc.

[0036] In the implementation process of the present step, the determination of the body posture attribute information in at least one home layout diagram and the setting attribute information of the smart home device specifically includes:

[0037] In the process of optimizing and debugging the smart home device, after obtaining at least one home layout diagram, the target space elements in the home layout diagram and the body node information under different body postures are identified, the setting attribute information of the smart home device is determined based on the target space elements, and the body posture attribute information is determined based on the corresponding body node information under different body postures.

[0038] It should be noted that the target space elements can be doors and windows, wall lines, floors, roofs, directions, living room labels, bedroom labels, study room labels, etc., which can be used for reference to determine the orientation and actual position of the smart home device, and are not specifically limited herein.

[0039] The human body node information can be position information of nodes corresponding to joints or component parts (such as a head, a foot, a hand, etc.) of the human body. Each node corresponds to a position of the human body, and the current state attribute of the human body can be determined by locating a plurality of nodes. The human body posture attribute information includes, but is not limited to, an active posture (such as standing, lying, sitting, etc.) and a current position of the human body, etc. It should be noted that the human body node information corresponding to the human body in different active postures is different. The human body node information can include information of different human body parts (such as a head, a foot, a hand, etc.) or different joints (such as an elbow joint, an ankle joint, etc.). Different human body node information can be used to determine different active postures and current positions of the human body, etc.

[0040] In the process of determining the setting attribute information of the smart home device based on the target space element, the relative positional relationship between the target space element and the smart home device can be identified by image recognition technology. The orientation and installation position of the smart home device are determined based on the relative positional relationship between the target space element and the smart home device, and the orientation and installation position of the smart home device are used as the setting attribute information of the smart home device.

[0041] In addition, in the process of determining the human body posture attribute information based on the human body node information corresponding to different human body postures, the feature information representing the human body posture attribute can be extracted from the human body node information by identifying the human body node information corresponding to different human body postures. The active posture and current position of the human body are determined based on the feature information, and the active posture and current position of the human body are used as the human body posture attribute information.

[0042] Specifically, a camera and a microphone can be placed in each room to collect information of user interaction (including but not limited to voice data input, gestures, line of sight direction, active posture, orientation, and interactive voice data, etc.). The collected data is transmitted to a server in real time for storage and analysis to form human body posture attribute information. The collected voice data is processed and analyzed by using a data analysis algorithm to extract useful information.

[0043] For example, the voice is converted into text by using voice recognition technology, and the text is processed by using natural language processing technology to extract the intention and demand of the user.

[0044] In addition, in order to solve the problem that the distributed voice test cannot be recorded, the data recording function can be collected on the camera and microphone device in each room, and the collected data is stored on the server in real time. The data record on the server is accessed by the distributed voice test system, and the voice interaction in each room is played back and tested. Through playback and testing, it can be checked whether the distributed voice is successfully implemented and whether there are problems. If there are problems, they can be repaired and optimized in time.

[0045] In addition, the generated home layout icon related information can be marked by the relevant data collected by the camera and microphone in the target space environment, and the home layout can be generated by using the relevant computer vision technology and artificial intelligence algorithm. The home layout is regarded as a large multi-dimensional network. The activity posture and current position of the human body, the orientation of the smart home device, and the receiving position (i.e. the installation position) and other information are marked on the home layout. These information can be extracted from the relevant data collected by the camera and microphone. The activity posture of the human body can be divided into standing posture, sitting posture, kneeling posture and dynamic posture. For example, when the activity posture of the human body is standing posture, the smart home device outputs voice, and after inputting different voices at different positions, the activity posture and current position of the human body, the voice data under the orientation and receiving position of different smart home devices are extracted.

[0046] Further, the marked related information can also be displayed in the form of animation on the home layout through abstract processing, so as to better understand and analyze the behavior and demand of the user. By placing cameras and microphones in each room of the user to collect data, the problem that the distributed voice test cannot be recorded can be solved.

[0047] Step 120, based on the voice data, determining the voice interaction success rate under the condition that the human posture attribute information in the home layout and the setting attribute information of the smart home device.

[0048] In the embodiment of the present application, the voice data can be statistically analyzed, and the success and failure times of voice interaction between the human body and a single device and the success and failure times of voice interaction between the human body and multiple distributed devices are recorded. Based on the success and failure times of voice interaction between the human body and a single device, the single voice interaction success rate under the condition that the human posture attribute information in the home layout and the setting attribute information of the smart home device are calculated.

[0049] The single voice interaction success rate is the success rate of the human body in the target space environment and the single smart home device (such as the A smart home device) for voice interaction, for example, if the human body sends an instruction to the A smart home device, the A smart home device answers the distributed voice interaction success, the success number is recorded, and if the A smart home device does not answer, it means that the distributed voice interaction fails, and the failure number is recorded. Based on the success number and the failure number of the human body and the plurality of distributed devices for voice interaction, the distributed voice interaction success rate under the condition of the human body posture attribute information and the setting attribute information of the smart home device in the home layout diagram is calculated.

[0050] It should be noted that the distributed voice interaction success rate is the success rate of the human body in the target space environment and the plurality of smart home devices (such as the A smart home device, the B smart home device, and the C smart home device) for voice interaction, for example, if the human body sends an instruction to the B smart home device, the C smart home device or the A smart home device answers the distributed voice interaction failure, and the failure number is recorded, and if the B smart home device answers, it means that the distributed voice interaction succeeds, and the success number is recorded. The voice data is the voice data collected by the smart home device under the condition of different human body postures and different setting attributes of the smart home device in the home layout diagram.

[0051] In the embodiment of the present application, as shown in Figure 3 The data analysis system of the server can be used to process and analyze the relevant information collected in the home layout diagram.

[0052] Specifically, the information marked on the home layout diagram is regarded as different data points in the multi-dimensional network, and the XPath and LXML methods are used for data extraction. The data marked in the home layout diagram is analyzed by the LXML parser, and the XPath is used to quickly locate the target space elements in the home layout diagram and the human body node information under the activity posture of different human bodies. Then, through a large amount of data, the potential voice mode and the correlation of different voice data are found, so as to extract the required data information, realize the extraction and retrieval of various data sources. Through the analysis of the interaction information and the voice information in the data, the interaction success rate (i.e. the single voice interaction success rate) and the success rate of the distributed voice (i.e. the distributed voice interaction success rate) can be calculated. For example, the success rate of interaction can be calculated by counting the success number and the failure number of each interaction, and the success rate of distributed voice can be calculated by counting whether the sending and receiving of each distributed voice is successful.

[0053] The specific steps of data analysis are as follows: the interaction information and voice information in the voice data are analyzed by using statistical methods or tools, and then the rules, trends and correlations of the voice data are found, and the distributed voice interaction success rate and the single voice interaction success rate are counted. The data analysis method includes: grouping analysis method, the data is classified according to the interaction information of the user and the device and the voice information of the smart home device to the user, and then each group of data is analyzed to find the success times and failure times of each interaction to calculate the single voice interaction success rate. Cross analysis method, by cross combination of two or more variables, such as time as the horizontal axis, the time difference of each distributed voice sending and receiving as the vertical axis, cross combination of the two variables, forming a cross table, and then the data in the cross table is counted and analyzed, so as to obtain the distributed voice interaction success rate.

[0054] Step 130, based on the voice interaction success rate, the smart home device is optimized.

[0055] In the embodiment of the application, the single voice interaction success rate can be compared with the first interaction success rate threshold to obtain a first comparison result; the distributed voice interaction success rate is compared with the second interaction success rate threshold to obtain a second comparison result.

[0056] In the case that the first comparison result is that the single voice interaction success rate is less than or equal to the lower limit value of the first interaction success rate threshold, and / or the distributed voice interaction success rate is less than or equal to the lower limit value of the second interaction success rate threshold, the multiple voice function modules of the smart home device are optimized as a whole.

[0057] In the case that the first comparison result is that the single voice interaction success rate is greater than the lower limit value of the first interaction success rate threshold and less than or equal to the upper limit value of the first interaction success rate threshold, and the distributed voice interaction success rate is greater than the lower limit value of the second interaction success rate threshold and less than or equal to the upper limit value of the second interaction success rate threshold, the multiple voice function modules of the smart home device are locally optimized.

[0058] For example: the first interaction success rate threshold can include 95% and 98%. The second interaction success rate threshold can include 95% and 98%. The first comparison result can include: the single voice interaction success rate is less than or equal to 95%, at this time the smart home device can be optimized as a whole, or the single voice interaction success rate is greater than 95% and less than or equal to 98%, at this time the smart home device can be locally optimized, or the single voice interaction success rate is greater than 98%, at this time the smart home device can not be optimized.

[0059] Correspondingly, the second comparison result can include: the distributed voice interaction success rate is less than or equal to 95%, at which time the smart home device can be subjected to overall optimization processing, or the distributed voice interaction success rate is greater than 95% and less than or equal to 98%, at which time the smart home device can be subjected to local optimization processing, or the distributed voice interaction success rate is greater than 98%, at which time the smart home device can be subjected to no optimization processing.

[0060] In the specific implementation process, the smart home device can be optimized and improved according to the statistical result. The overall optimization processing of the plurality of voice function modules of the smart home device includes hardware optimization, software adjustment, and distributed voice technology optimization. The hardware optimization includes but is not limited to replacing a microphone array with higher performance, increasing processor capability, and improving network connection quality; the software adjustment includes but is not limited to updating a voice recognition algorithm, optimizing a user interface, and enhancing an error processing mechanism; and the distributed voice technology optimization further includes dynamically adjusting the accuracy and response speed of voice recognition by using machine learning and deep learning technology.

[0061] The local optimization processing of the plurality of voice function modules of the smart home device includes hardware optimization, software adjustment, or distributed voice technology optimization. The hardware optimization includes but is not limited to replacing a microphone array with higher performance, increasing processor capability, and improving network connection quality; the software adjustment includes but is not limited to updating a voice recognition algorithm, optimizing a user interface, and enhancing an error processing mechanism; and the distributed voice technology optimization further includes dynamically adjusting the accuracy and response speed of voice recognition by using machine learning and deep learning technology.

[0062] For example, the interaction success rate can be improved by improving the hardware or software of the device, and the distributed voice success rate can be improved by optimizing the algorithm of the distributed voice technology. In addition, the statistical results can be displayed in the form of charts or reports to better understand the use and performance of the smart home device. At the same time, the functions of the smart home device can be adjusted and optimized according to the statistical results. In addition, the position layout of the smart home device in the actual home scene of the user can be adjusted and optimized to improve the voice function feedback and receiving effect. By collecting and analyzing the voice data and user interaction information in the user environment, and according to the statistical interaction success rate, distributed voice and other indicators, the performance of the smart home device can be optimized, which can involve improving the hardware and software of the device, adjusting parameters, redesigning, and using these improvements to improve the performance of the device. By collecting and analyzing the voice data and user interaction information in the user environment, the voice wake-up success rate of the device can be effectively improved, the voice interaction experience can be optimized, and the distributed voice success rate can be improved. By recording and analyzing the voice data and interaction information in the user environment in real time, accurate data support is provided for the performance optimization of the device, and continuous improvement and upgrading of the device is realized.

[0063] In addition, a neural network model can be used to analyze and process the collected data to more accurately identify the user's intentions and needs. At the same time, the device performance can be optimized using corresponding algorithms and models to improve the response speed and user experience of the device. In addition, more flexible data storage and processing methods can be used to better meet the needs of different users and scenarios, which are not limited here.

[0064] The voice function optimization method of the smart home device provided by the application determines the human body posture attribute information in at least one home floor plan, the setting attribute information of the smart home device, and obtains the voice data corresponding to the human body posture attribute information collected by the smart home device under the setting attribute information. Based on the voice data, the voice interaction success rate under the condition of human body posture attribute information and setting attribute information of the smart home device in the home floor plan is determined, and the smart home device is optimized based on the voice interaction success rate. The efficiency of the voice interaction optimization process of the smart home device can be effectively improved, so it is suitable for optimizing a large number of smart home devices in the production and debugging process.

[0065] The voice function optimization device of the smart home device provided by the application is described below, and the voice function optimization device of the smart home device described below can be referred to each other. Reference Figure 4As shown, it is the structural schematic view of the voice function optimization device of the smart home device provided by the application. The voice function optimization device of the smart home device provided by the application specifically comprises the following parts:

[0066] The target information extraction unit 401 is used for determining the human body posture attribute information in at least one home floor plan and the setting attribute information of the smart home device, and obtaining the voice data corresponding to the human body posture attribute information collected by the smart home device under the setting attribute information.

[0067] The interaction success rate analysis unit 402 is used for determining the voice interaction success rate under the condition of the human body posture attribute information in the home floor plan and the setting attribute information of the smart home device based on the voice data.

[0068] The optimization processing unit 403 is used for performing optimization processing on the smart home device based on the voice interaction success rate.

[0069] According to the voice function optimization device of the smart home device provided by the application, the voice interaction success rate comprises a single voice interaction success rate and a distributed voice interaction success rate; the interaction success rate analysis unit is specifically used for: statistically analyzing the voice data, recording the success times and failure times of voice interaction between the human body and a single device, and recording the success times and failure times of voice interaction between the human body and multiple distributed devices; calculating the single voice interaction success rate under the condition of the human body posture attribute information in the home floor plan and the setting attribute information of the smart home device based on the success times and failure times of voice interaction between the human body and a single device; wherein the single voice interaction success rate is the success rate of voice interaction between the human body and a single smart home device in a target space environment; calculating the distributed voice interaction success rate under the condition of the human body posture attribute information in the home floor plan and the setting attribute information of the smart home device based on the success times and failure times of voice interaction between the human body and multiple distributed devices; wherein the distributed voice interaction success rate is the success rate of voice interaction between the human body and multiple smart home devices distributed in a target space environment.

[0070] The voice function optimization device of the smart home equipment provided by the application, the optimization processing unit is specifically used for: comparing the single voice interaction success rate with a first interaction success rate threshold to obtain a first comparison result; comparing the distributed voice interaction success rate with a second interaction success rate threshold to obtain a second comparison result; in the case that the first comparison result is that the single voice interaction success rate is less than or equal to the lower limit value of the first interaction success rate threshold and / or the distributed voice interaction success rate is less than or equal to the lower limit value of the second interaction success rate threshold, the plurality of voice function modules of the smart home equipment are subjected to overall optimization processing; in the case that the first comparison result is that the single voice interaction success rate is greater than the lower limit value of the first interaction success rate threshold and less than or equal to the upper limit value of the first interaction success rate threshold, and the distributed voice interaction success rate is greater than the lower limit value of the second interaction success rate threshold and less than or equal to the upper limit value of the second interaction success rate threshold, the plurality of voice function modules of the smart home equipment are subjected to local optimization processing.

[0071] The voice function optimization device of the smart home equipment provided by the application, before determining the human body posture attribute information and the setting attribute information of the smart home equipment in at least one home floor plan, further comprises a home floor plan obtaining unit, which is used for: acquiring human body posture attribute information and setting attribute information of a smart home equipment collected under a target space environment; generating an initial floor plan corresponding to the target space environment; marking the human body posture attribute information and the setting attribute information of the smart home equipment into the initial floor plan to obtain at least one home floor plan.

[0072] The voice function optimization device of the smart home equipment provided by the application, the target information extraction unit is specifically used for: identifying target space elements in the home floor plan and human body node information under different human body postures; determining the setting attribute information of the smart home equipment based on the target space elements, and determining the human body posture attribute information based on the corresponding human body node information under different human body postures.

[0073] The voice function optimization device of the smart home equipment provided by the application, the determination of the setting attribute information of the smart home equipment based on the target space elements specifically comprises: determining the relative position relationship between the target space elements and the smart home equipment, determining the orientation and installation position of the smart home equipment based on the relative position relationship between the target space elements and the smart home equipment; taking the orientation and installation position of the smart home equipment as the setting attribute information of the smart home equipment.

[0074] The voice function optimization device of the smart home equipment provided by the application determines the human body posture attribute information based on the human body node information corresponding to different human body postures, specifically includes: identifying the human body node information corresponding to different human body postures; extracting feature information for representing human body posture attributes from the human body node information, determining the active posture and the current position of the human body based on the feature information, and taking the active posture and the current position of the human body as the human body posture attribute information.

[0075] The voice function optimization device of the smart home equipment provided by the application determines the human body posture attribute information based on the human body node information corresponding to different human body postures, specifically includes: identifying the human body node information corresponding to different human body postures; extracting feature information for representing human body posture attributes from the human body node information, determining the active posture and the current position of the human body based on the feature information, and taking the active posture and the current position of the human body as the human body posture attribute information.

[0076] Figure 5 An example of an electronic device is shown in the physical structure diagram of the electronic device as shown in the figure, Figure 5 The electronic device can include a processor 501, a communication interface 504, a memory 502 and a communication bus 503, wherein the processor 501, the communication interface 504 and the memory 502 communicate with each other through the communication bus 503. The processor 501 can call the logical instructions in the memory 502 to execute the voice function optimization method of the smart home equipment, which includes: determining the human body posture attribute information in at least one home floor plan and the setting attribute information of the smart home equipment, and obtaining the voice data corresponding to the human body posture attribute information collected by the smart home equipment under the setting attribute information; based on the voice data, determining the voice interaction success rate under the condition that the human body posture attribute information in the home floor plan and the setting attribute information of the smart home equipment; based on the voice interaction success rate, the smart home equipment is optimized.

[0077] Further, the logic instructions in the memory 502 described above can be implemented in the form of software functional units and sold or used as independent products, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0078] In another aspect, the present application also provides a computer program product, which includes a computer program, the computer program can be stored in a computer readable storage medium, and the computer program is executed by a processor, so that the computer can execute the voice function optimization method of the smart home device provided by the above-mentioned methods. The method includes: determining the human body posture attribute information in at least one home floor plan and the setting attribute information of the smart home device, and obtaining the voice data corresponding to the human body posture attribute information collected by the smart home device under the setting attribute information; determining the voice interaction success rate under the condition of the human body posture attribute information and the setting attribute information of the smart home device in the home floor plan based on the voice data; and optimizing the smart home device based on the voice interaction success rate.

[0079] In another aspect, the present application also provides a computer readable storage medium, which includes a stored program, wherein the program runs to execute the voice function optimization method of the smart home device provided by the above-mentioned methods. The method includes: determining the human body posture attribute information in at least one home floor plan and the setting attribute information of the smart home device, and obtaining the voice data corresponding to the human body posture attribute information collected by the smart home device under the setting attribute information; determining the voice interaction success rate under the condition of the human body posture attribute information and the setting attribute information of the smart home device in the home floor plan based on the voice data; and optimizing the smart home device based on the voice interaction success rate.

[0080] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0081] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and necessary general hardware platforms, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of software products, and the computer software products can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and include a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0082] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for optimizing the voice function of a smart home device, characterized in that, The method comprises the steps of: determining human posture attribute information in at least one home floor plan and setting attribute information of a smart home device, and obtaining voice data corresponding to the human posture attribute information collected by the smart home device under the setting attribute information; based on the voice data, determining the voice interaction success rate under the condition of the human posture attribute information in the home floor plan and the setting attribute information of the smart home device; based on the voice interaction success rate, optimizing the smart home device. 2.The method of optimizing a voice function of a smart home device according to claim 1, wherein, The voice interaction success rate includes a single voice interaction success rate and a distributed voice interaction success rate. The voice interaction success rate under the condition of the human posture attribute information in the home floor plan and the setting attribute information of the smart home device is determined based on the voice data, comprising: statistical analysis of the voice data, recording the success and failure times of voice interaction between the human body and a single device, and recording the success and failure times of voice interaction between the human body and multiple distributed devices; based on the success and failure times of voice interaction between the human body and a single device, the single voice interaction success rate under the condition of the human posture attribute information in the home floor plan and the setting attribute information of the smart home device is calculated; wherein the single voice interaction success rate is the success rate of voice interaction between the human body and a single smart home device in a target space environment; based on the success and failure times of voice interaction between the human body and multiple distributed devices, the distributed voice interaction success rate under the condition of the human posture attribute information in the home floor plan and the setting attribute information of the smart home device is calculated; wherein the distributed voice interaction success rate is the success rate of voice interaction between the human body and multiple smart home devices distributed in a target space environment. 3.The method of optimizing a voice function of a smart home device according to claim 2, wherein, The smart home device is optimized based on the voice interaction success rate, specifically comprising: comparing the single voice interaction success rate with a first interaction success rate threshold to obtain a first comparison result; comparing the distributed voice interaction success rate with a second interaction success rate threshold to obtain a second comparison result; in the case that the first comparison result is that the single voice interaction success rate is less than or equal to the lower limit value of the first interaction success rate threshold, and / or the distributed voice interaction success rate is less than or equal to the lower limit value of the second interaction success rate threshold, the multiple voice function modules of the smart home device are optimized as a whole; in the case that the first comparison result is that the single voice interaction success rate is greater than the lower limit value of the first interaction success rate threshold and less than or equal to the upper limit value of the first interaction success rate threshold, and the distributed voice interaction success rate is greater than the lower limit value of the second interaction success rate threshold and less than or equal to the upper limit value of the second interaction success rate threshold, the multiple voice function modules of the smart home device are optimized locally. 4.The method of optimizing a voice function of a smart home device according to claim 1, wherein, Before determining the human posture attribute information in at least one home floor plan and the setting attribute information of the smart home device, the method further comprises the steps of: Acquire human posture attribute information and smart home device setting attribute information collected in a target space environment; Generate an initial house type diagram corresponding to the target space environment; Mark the human posture attribute information and the smart home device setting attribute information in the initial house type diagram to obtain at least one home house type diagram. 5.The method of optimizing a voice function of a smart home device according to claim 1, wherein, The determination of the human posture attribute information and the smart home device setting attribute information in the at least one home house type diagram specifically includes: Identify target space elements in the home house type diagram and human node information in different human postures; Determine the smart home device setting attribute information based on the target space elements, and determine the human posture attribute information based on the corresponding human node information in different human postures. 6.The method of optimizing a voice function of a smart home device according to claim 5, wherein, The determination of the smart home device setting attribute information based on the target space elements specifically includes: Determine the relative position relationship between the target space elements and the smart home device, determine the orientation and installation position of the smart home device based on the relative position relationship between the target space elements and the smart home device, and take the orientation and installation position of the smart home device as the setting attribute information of the smart home device. 7.The method of optimizing a voice function of a smart home device according to claim 5, wherein, The determination of the human posture attribute information based on the corresponding human node information in different human postures specifically includes: Identify the corresponding human node information in different human postures; Extract feature information representing human posture attributes from the human node information, determine the active posture and current position of the human based on the feature information, and take the active posture and current position of the human as the human posture attribute information. 8.A voice function optimization apparatus of a smart home device, characterized by, It includes: A target information extraction unit is configured to determine human posture attribute information and smart home device setting attribute information in at least one home house type diagram, and acquire voice data corresponding to the human posture attribute information collected by the smart home device under the setting attribute information; An interaction success rate analysis unit is configured to determine the voice interaction success rate under the condition that the human posture attribute information and the smart home device setting attribute information in the home house type diagram based on the voice data; An optimization processing unit is configured to perform optimization processing on the smart home device based on the voice interaction success rate.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to realize the steps of the voice function optimization method of the smart home device according to any one of claims 1 to 7. 10.A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the voice function optimization method of the smart home device according to any one of claims 1 to 7.

Images