Voice interaction method and device

Abstract

The invention provides a voice interaction method and device. The method comprises the following steps: acquiring a body health condition of a target user; performing voice recognition according to influence factors corresponding to the language system in the body health condition of the target user to obtain target data corresponding to the target user; determining instruction information corresponding to the target user according to the target data, wherein the instruction information is used for controlling household equipment; determining feedback information according to the instruction information and the body health condition of the target user, wherein the feedback information comprises equipment control confirmation information; and performing voice feedback to the target user according to the feedback information. Therefore, the accuracy of voice recognition of the target user can be improved.

Description

Technical Field

[0001] The present application relates to the field of voice interaction technology, and in particular to a voice interaction method and device. Background Art

[0002] Voice interaction refers to the process of users communicating and interacting with devices through voice. Voice interaction technology is mainly divided into four key steps: voice recognition, language understanding, dialogue management, and voice synthesis. It can be seen that voice recognition is a very important part of voice interaction, and voice recognition affects the subsequent voice data processing and even the voice synthesis process of voice interaction. In the application process of voice recognition, it is found that for some people with diseases that affect language function, their language function is different from that of normal people, so conventional language recognition will result in low accuracy. Therefore, for such situations, how to improve the accuracy of voice recognition is a technical problem that needs to be solved urgently in this field. Summary of the invention

[0003] The present application provides a voice interaction method and device, which performs voice recognition based on the influencing factors corresponding to the language system in the physical health condition of the target user, thereby improving the accuracy of voice recognition for the target user.

[0004] In a first aspect, the present application provides a voice interaction method, which is applied to a voice interaction module in a home intelligent system, and the method comprises:

[0005] Obtain the physical health status of target users;

[0006] Perform speech recognition based on the influencing factors corresponding to the language system in the physical health of the target user to obtain target data corresponding to the target user;

[0007] Determine the instruction information corresponding to the target user according to the target data, and the instruction information is used to control the home appliance;

[0008] Determine feedback information according to the instruction information and the physical health condition of the target user, the feedback information including device control confirmation information;

[0009] Provide voice feedback to the target user based on the feedback information.

[0010] It can be seen that in this application, the influencing factors of the target user's diseases that affect the voice system are taken into account during the target data acquisition stage, which is highly targeted and can improve the accuracy of voice recognition for the target user. At the same time, when performing subsequent device control confirmation information feedback based on the target data, the physical health of the target user is also taken into account, which is beneficial to the physical health of the target user and thus improves the intelligence of voice interaction.

[0011] In a feasible example, the target data of the target user is obtained based on the influencing factors corresponding to the language system in the target user's physical health condition, including: determining whether the target user has a disease that affects the language system based on the target user's physical health condition; if it is determined that the target user has a disease that affects the language system, determining the influencing factors corresponding to the disease that affects the language system; and performing speech recognition based on the influencing factors to obtain the target data of the target user.

[0012] In the present application, speech recognition is performed based on the influencing factors corresponding to the diseases that affect the language system in combination with the physical health of the target user, thereby improving the accuracy of speech recognition.

[0013] In a feasible example, the home smart system includes a data management module, which stores parameter data and historical device control data of home appliances, and determines the instruction information corresponding to the target user based on the target data, including: obtaining the historical device control data and parameter data of home appliances corresponding to the target user through the data management module; extracting instruction information based on the historical device control data, parameter data of home appliances and target data, and determining the instruction information corresponding to the target user.

[0014] In the present application, when determining the instruction information based on the target data, the historical device control data and the parameter data of the home appliance are combined, which can improve the accuracy of determining the instruction information.

[0015] In a feasible example, feedback information is determined based on the instruction information and the physical health condition of the target user, including: determining the sleep time period corresponding to the target user according to the physical health condition of the target user; if it is determined that the target home device corresponding to the instruction information has an impact on sleep, and it is determined that the current moment is in the sleep time period or the duration between the current moment and the starting end point of the sleep time period is less than a first preset duration, then determining a second device control instruction based on the impact of the target home device on sleep and the first device control instruction in the instruction information, so that the impact of controlling the target home device according to the second device control instruction on sleep is less than the impact of controlling the target home device according to the first device control instruction on sleep; determining feedback information based on the second device control instruction and the first prompt information, the first prompt information being used for sleep prompting; if it is determined that the target home device corresponding to the instruction information has no impact on sleep, determining feedback information based on the instruction information.

[0016] In the present application, when the target home device in the command information will affect the user's sleep, a control method with less impact is determined to generate feedback information, thereby reducing the impact of the use of the device on the user's sleep and improving the intelligence of the voice interaction.

[0017] In a feasible example, feedback information is determined based on the instruction information and the physical health condition of the target user, including: determining the target home device and the first device control instruction corresponding to the instruction information; if it is determined that after the target home device is controlled based on the first device control instruction, there are multiple third device control instructions at the next level, then based on the influence relationship between the adverse condition in the physical health condition and the multiple third device control instructions, a third target device control instruction is determined from the multiple third device control instructions, the third target device control instruction being the control instruction with the least influence relationship with the adverse condition among the multiple third device control instructions; feedback information is determined based on the third target device control instruction and the second prompt information, the second prompt information being used to prompt the influence relationship between the adverse condition and the third target device control instruction; if it is determined that after the target home device is controlled based on the first device control instruction, there are no multiple third device control instructions at the next level, then feedback information is determined based on the first device control instruction.

[0018] In the present application, by analyzing the relationship between the next-level instructions corresponding to the user's instructions and the impact of adverse conditions on physical health, the instructions at the next level with the least impact on the adverse conditions are automatically selected. This is beneficial to the user's physical health and further improves the intelligence of voice interaction.

[0019] In a feasible example, the home intelligent system also includes a data management module, which stores voice interaction data corresponding to multiple users, and provides voice feedback to the target user based on the feedback information, including: if it is determined that the target user has an unfavorable health condition in his physical health, determining the target user's emotional information based on the voice data corresponding to the target data; if it is determined that the target user's emotional information is a bad emotion, obtaining the voice interaction data corresponding to the first user among multiple users through the data management module, the first user being the user with the largest amount of voice interaction data among the multiple users except the target user; determining the voice features of the first user based on the voice interaction data corresponding to the first user; and providing voice feedback to the target user based on the voice features of the first user.

[0020] In the present application, when the user is in poor health and in a bad mood, voice feedback can be given to the user by simulating the voice characteristics of family members, which can provide certain emotional support to the user and further improve the intelligence of voice interaction.

[0021] In a feasible example, after providing voice feedback to the target user based on the feedback information, the method also includes: determining the recommended usage time of the target home device corresponding to the feedback information based on the physical health condition of the target user and the feedback information; generating a third prompt message when the target home device is used for the recommended usage time, the third prompt message being used to prompt a suggestion to stop using the target home device; and providing voice feedback to the target user based on the third prompt message.

[0022] In this application, the recommended usage time of the target home equipment is determined based on the physical health condition and feedback information of the target user, and the user is prompted after the target home equipment is used for the recommended usage time. This is beneficial to the physical health of the target user and thus improves the intelligence of voice interaction.

[0023] In a feasible example, the emotional information of the target user is determined according to the voice data corresponding to the target data, including: determining at least one first emotional information according to the voice features corresponding to the voice data; if it is determined that at least one first emotional information is single, then determining the first emotional information as the emotional information corresponding to the target user; if it is determined that at least one first emotional information is multiple, and it is determined that the current moment is in the target time period, then obtaining the previous sleep condition of the target user, and the target time period is used to characterize the time period that will be affected by the previous sleep condition; if the previous sleep condition is a good sleep, then determining the second emotional information among the multiple first emotional information as the emotional information corresponding to the target user, and the second emotional information is used to characterize the best emotional information among the multiple first emotional information; if the previous sleep condition is a bad sleep, then determining the third emotional information among the multiple first emotional information as the emotional information corresponding to the target user, and the third emotional information is used to characterize the worst emotional information among the multiple first emotional information.

[0024] In the present application, the emotional information of the target user is comprehensively judged in combination with the target user's sleep condition, so that the accuracy of determining the emotional information of the target user can be improved.

[0025] In a feasible example, training data is obtained, and the training data includes speech data, influencing factors, text data corresponding to the speech data, physical health characteristics, instruction information corresponding to the speech data, and feedback information corresponding to the speech data; model training of an initial speech recognition network is performed based on the speech data, influencing factors, and text data in the training data to obtain a speech recognition network, and the speech recognition network obtains text data based on the speech data and the influencing factors; model training of an initial instruction information extraction network is performed based on the text data corresponding to the speech data in the training data and the instruction information corresponding to the speech data to obtain an instruction information extraction network, and the instruction information extraction network is used to obtain instruction information based on the text data; model training of an initial feedback information acquisition network is performed based on the physical health characteristics in the training data, the instruction information corresponding to the speech data, and the feedback information corresponding to the speech data to obtain a feedback information acquisition network, and the feedback information acquisition network obtains feedback information based on the physical health characteristics and the instruction information; the speech recognition network, the instruction information extraction network, and the feedback information acquisition network constitute a speech interaction model.

[0026] In this application, a machine learning model is combined with voice interaction, and networks at different stages are trained independently, which helps the model learn more features of voice interaction, thereby improving the accuracy of voice interaction.

[0027] In a second aspect, the present application provides a voice interaction device, which is applied to a voice interaction module in a home intelligent system, and the device includes:

[0028] An acquisition unit, used to acquire the physical health status of the target user;

[0029] A processing unit, configured to perform speech recognition according to the influencing factors corresponding to the language system in the physical health condition of the target user, and obtain target data corresponding to the target user;

[0030] The processing unit is further used to determine instruction information corresponding to the target user according to the target data, and the instruction information is used to control the home appliance;

[0031] The processing unit is further used to determine feedback information according to the instruction information and the physical health condition of the target user, wherein the feedback information includes device control confirmation information;

[0032] The feedback unit is used to provide voice feedback to the target user according to the feedback information.

[0033] In a third aspect, the present application provides an electronic device comprising a processor, a memory, and a communication interface. The processor, the memory, and the communication interface are interconnected and perform communication with each other. The memory stores executable program code, the communication interface is used for wireless communication, and the processor is used to call the executable program code stored in the memory to execute, for example, some or all of the steps described in any method of the first aspect.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium, in which electronic data is stored. When the electronic data is executed by a processor, it is used to execute the electronic data to implement some or all of the steps described in the first aspect of the present application.

[0035] In a fifth aspect, the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the present application. The computer program product may be a software installation package. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A schematic diagram of the structure of a home intelligent system provided in an embodiment of the present application;

[0038] Figure 2 A flowchart of a voice interaction method provided in an embodiment of the present application;

[0039] Figure 3 A flow chart of a speech recognition network training process provided in an embodiment of the present application;

[0040] Figure 4 A schematic diagram of a flow chart for determining instruction information provided in an embodiment of the present application;

[0041] Figure 5 A schematic diagram of a structure of a single-day time period provided in an embodiment of the present application;

[0042] Figure 6 A flow chart of a speech interaction model training process provided in an embodiment of the present application;

[0043] Figure 7A block diagram of the functional units of a voice interaction device provided in an embodiment of the present application;

[0044] Figure 8 A block diagram of the functional units of another voice interaction device provided in an embodiment of the present application;

[0045] Fig. 9 A structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0047] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps is not limited to the listed steps, but optionally includes steps that are not listed, or optionally includes other steps inherent to these processes, methods, products or devices.

[0048] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0049] At present, voice interaction usually refers to the process of communicating with the system through voice recognition and synthesis technology. Voice interaction is mainly used for the control of furniture equipment in home scenarios. It can be seen that voice recognition is a very important part of voice interaction. Voice recognition affects the subsequent voice data processing and even the voice synthesis process of voice interaction. Therefore, the accuracy of voice recognition is particularly important in voice interaction. For some people with diseases that affect language function, their language function is different from that of normal people, so conventional language recognition will result in lower accuracy.

[0050] In this case, the general approach is to obtain a large amount of speech data from people with diseases that affect language function to train speech recognition models, so as to adapt to this group of people. However, this will limit the recognition accuracy due to the amount and type of training data.

[0051] Based on this, the present application provides a voice interaction method, which obtains the physical health status of the target user, and performs voice recognition according to the influencing factors in the physical health status of the target user corresponding to the language system, and obtains the target data corresponding to the target user. In this way, the voice recognition can be focused on specific disease scenarios, thereby improving the accuracy of voice recognition.

[0052] See also Figure 1 , Figure 1 A schematic diagram of the structure of a home intelligent system provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the home intelligent system 100 includes a voice interaction module 101, a device control module 102 and a data management module 103.

[0053] The voice interaction module 101 is used to realize voice interaction with the target user. Specifically, the voice interaction module 101 may include a voice receiving device, a voice playing device and a processor. The voice receiving device may be a microphone, the voice playing device may be a speaker, a sound, etc., and the processor is used for language understanding and language synthesis.

[0054] The device control module 102 is used to realize intelligent control of home appliances, and the data management module 103 is used to manage various data of the voice interaction module 101, the device control module 102 and home appliances.

[0055] In the present application, the voice interaction module 101 is used to obtain the physical health condition of the target object, and obtain the target data of the target user according to the influencing factors corresponding to the language system in the physical health condition of the target user; determine the instruction information corresponding to the target user according to the target data, and the instruction information is used to control the home appliances; then determine the feedback information according to the instruction information and the physical health condition of the target user, and the feedback information includes the device control confirmation information; finally, provide voice feedback to the target user according to the feedback information.

[0056] In this way, the influencing factors of the target user's diseases that affect the voice system are taken into account during the target data acquisition stage, which can improve the accuracy of voice recognition. At the same time, when the subsequent device control confirmation information feedback is carried out according to the target data, the physical health of the target user is also taken into account, thereby improving the intelligence of voice interaction.

[0057] Based on this, an embodiment of the present application provides a voice interaction method, and the embodiment of the present application is described in detail below in conjunction with the accompanying drawings.

[0058] See also Figure 2 , Figure 2 A flow chart of a voice interaction method provided in an embodiment of the present application is shown, and the method is applied to the above-mentioned voice interaction module, such as Figure 2 As shown, the method comprises the following steps:

[0059] Step S201, obtaining the physical health status of the target user.

[0060] The target user's health status can be saved in the data management module after the family members are reminded to upload their health status when the home smart system is installed at home, or it can be saved in the data management module after the family members have their annual physical examinations by directly uploading the electronic files of the physical examination reports through the terminal device. Therefore, the target user's health status is obtained from the data management module.

[0061] It can be understood that this application corresponds to a home scenario, and the acquisition of user data and other data involved in this application should be obtained after user authorization.

[0062] Step S202: acquiring target data of the target user according to the influencing factors corresponding to the language system in the physical health condition of the target user.

[0063] Among them, the influencing factor corresponds to the normal speech feature, which is used to characterize the characteristics of speech produced under the language habits of ordinary people. Speech features may include speech speed, intonation, volume, pitch, language fluency, etc. The influencing factor may include slow speech speed, low volume, and pauses. It can be understood that the target data here refers to text data.

[0064] Specifically, in a feasible embodiment, the target data of the target user is obtained based on the influencing factors corresponding to the language system in the target user's physical health condition, including: determining whether the target user has a disease that affects the language system based on the target user's physical health condition; if it is determined that the target user has a disease that affects the language system, determining the influencing factors corresponding to the disease that affects the language system; and performing speech recognition based on the influencing factors to obtain the target data of the target user.

[0065] Among them, first of all, it is necessary to analyze whether the user has any disease that affects his language system based on the physical health of the target user. For example, diseases that affect the language system may include Parkinson's disease, pharyngitis, functional pronunciation disorders, etc. If it is found that the target user does have a disease that affects the language system, then determine how these diseases specifically affect the function of the language system, so as to determine the corresponding influencing factors. Continuing with the previous example, Parkinson's disease can cause uncoordinated muscle movements of the pronunciation organs, so the corresponding influencing factors may include slow speech speed and abnormal intonation. Pharyngitis can affect the normal vibration of the vocal cords, so the corresponding influencing factors may include low volume. Finally, according to the influencing factors of these diseases, adjust the speech recognition process to obtain accurate speech data of the target user and ensure that speech recognition can effectively respond to the user's special language needs.

[0066] For example, the following describes speech recognition in detail in combination with a machine learning model. Figure 3 , Figure 3 A flow chart of a speech recognition network training process provided in an embodiment of the present application is as follows: Figure 3 As shown, it includes: obtaining the physical health condition of the target user, and determining the influencing factors corresponding to the voice system according to the physical health condition; determining the corresponding voice data and text data according to the influencing factors; inputting the voice data and text data into the initial voice recognition network, and here the influencing factors can also be combined with the voice data for feature fusion and then input into the initial voice recognition network; using the text data as the training target, performing model training, and obtaining the voice recognition network.

[0067] In the present application, speech recognition is performed based on the influencing factors corresponding to the diseases that affect the language system in combination with the physical health of the target user, thereby improving the accuracy of speech recognition.

[0068] Step S203: determining instruction information corresponding to the target user according to the target data.

[0069] Among them, since in the home scenario, the target user's voice interaction is generally used to control home appliances, it is necessary to understand the language of the target data in order to determine the corresponding device control requirements in the target data, and then determine the corresponding command information based on the device control requirements.

[0070] Specifically, in a feasible embodiment, the home intelligent system includes a data management module, which stores parameter data and historical device control data of home appliances, and determines the instruction information corresponding to the target user according to the target data, including: obtaining the historical device control data and parameter data of home appliances corresponding to the target user through the data management module; extracting instruction information according to the historical device control data, parameter data of home appliances and target data, and determining the instruction information corresponding to the target user.

[0071] Among them, in the scenario based on home appliance control, the instruction information must correspond to a certain home appliance in the home. At the same time, considering that the target user has a disease that affects the language system, the accuracy of the target data obtained by voice recognition may be affected. Therefore, when determining the instruction information based on the target data, this embodiment obtains the historical device control data corresponding to the target user and the parameter data of the home appliance from the data management module of the home intelligent system, and then extracts the instruction information based on the target data, the historical device control data and the parameter data of the home appliance to determine the corresponding instruction information. The data management module is used to manage all data and personal data of the devices in the home intelligent system.

[0072] For example, see Figure 4 , Figure 4 A flowchart of determining instruction information provided in an embodiment of the present application is shown as follows: Figure 4 As shown, the target data obtained includes "Please turn on the air conditioner and set the temperature to 26 degrees", and the parameter data of the household equipment includes air conditioner (parameter: ***), refrigerator (parameter: ***), and TV (parameter: ***). When extracting the instruction, the corresponding object is determined to be "empty" based on semantic analysis, and it is recognized to be similar to "air conditioner" in the household equipment, so it is replaced with "air conditioner", and the control mode is determined to be turned on and the temperature is 26 degrees. Therefore, the instruction information finally obtained includes that the control target is the air conditioner, and the control mode is turned on, cooled, and 26 degrees.

[0073] In the present application, when determining the instruction information based on the target data, the historical device control data and the parameter data of the home appliance are combined, which can improve the accuracy of determining the instruction information.

[0074] Step S204: determining feedback information according to the instruction information and the physical health condition of the target user.

[0075] The feedback information includes device control confirmation information, that is, device control information suitable for the current physical condition of the target user is determined based on the instruction information and the physical health condition of the target user, and feedback is given to the user in the form of confirmation.

[0076] At the same time, when the feedback information is determined, the corresponding device control instruction may have been executed, that is, the corresponding device control has been performed, and the device control instruction should correspond to the device control confirmation information written in the feedback information. Whether to execute the corresponding device control instruction when determining the feedback information can be determined based on whether the device control determination information carried in the feedback information corresponds to the instruction information. If the device control determination information carried in the feedback information corresponds to the instruction information, then the corresponding device control instruction can be executed when determining the feedback information; if the device control determination information carried in the feedback information does not correspond to the instruction information, then the corresponding device control instruction should not be executed when determining the feedback information.

[0077] The following is a detailed description of the current steps:

[0078] In a feasible embodiment, feedback information is determined based on the instruction information and the physical health condition of the target user, including: determining the sleep time period corresponding to the target user according to the physical health condition of the target user; if it is determined that the target home appliance corresponding to the instruction information has an impact on sleep, and it is determined that the current moment is in the sleep time period or the duration between the current moment and the starting end point of the sleep time period is less than a first preset duration, then determining a second device control instruction based on the impact of the target home appliance on sleep and the first device control instruction in the instruction information, so that the impact of controlling the target home appliance according to the second device control instruction on sleep is less than the impact of controlling the target home appliance according to the first device control instruction on sleep; determining feedback information based on the second device control instruction and the first prompt information, the first prompt information being used for sleep prompting; if it is determined that the target home appliance corresponding to the instruction information has no impact on sleep, determining feedback information based on the instruction information.

[0079] It is understandable that the quality of sleep has a great impact on the health of the target user, and a sufficient and good sleep is beneficial to the health of the target user. At the same time, if the user has certain diseases (such as heart disease, high blood pressure, etc.), sufficient and good sleep should be guaranteed every day. Therefore, this embodiment will consider the impact of the current device control on the sleep of the target user when determining the feedback information.

[0080] Specifically, this embodiment will first determine the sleep time period corresponding to the target user according to the physical health of the target user. Here, factors such as the age and living habits of the target user can be comprehensively considered. Specifically, the recommended sleep duration will be determined first according to the physical health of the target user. Specifically, various physical indicators can be scored, and finally the recommended sleep duration will be determined according to the total score and the sleep duration interval. The sleep duration interval can be set according to the empirical value. After determining the recommended sleep duration, the corresponding sleep time period will be determined according to the living habits of the target user. That is, the home intelligent system judges the living habits of the target user based on the historical sleep data of the user, so as to adaptively determine the sleep time period of the target user. The specific sleep time period can also be set by the target user himself. There is no restriction here.

[0081] After determining the corresponding sleep time period, it will be determined whether the target home appliance corresponding to the instruction information will have an impact on sleep, and whether the current moment is in the sleep time period, or whether it is close to the start time of the sleep time period. If it is determined that the target home appliance corresponding to the instruction information will have an impact on sleep, and the current moment is in the sleep time period or close to the start time of the sleep time period, then the control instructions for the target home appliance in the instruction information can be appropriately adjusted. Specifically, it can be judged according to the degree of impact of the control instruction on the target home appliance on sleep, and the adjustment is to determine the second device control instruction that has a smaller degree of impact than the current first device control instruction. For example, if the target user wants to play music during the sleep time period, then at this time, you can choose to turn down the volume to reduce the impact of music on sleep. The specific judgment of the size of the impact and whether there is an impact can be set by the manufacturer based on experience.

[0082] After the second device control instruction is determined, feedback information can be determined based on the second device control instruction and the first prompt information. The first prompt information is used for sleep prompting, and the second device control instruction is used to confirm the control to the user. This can further improve the intelligence of voice interaction. For example, the feedback information can be "Identify that you are currently in the sleep period. Do you want to lower the volume to 25%? It is recommended to go to bed early."

[0083] If it is determined that the target home appliance corresponding to the instruction information has no effect on sleep, the feedback information can be directly determined according to the instruction information, and the instruction information can also be directly executed. It is understandable that the feedback information can also be directly determined according to the execution result corresponding to the instruction information.

[0084] For example, see Figure 5 , Figure 5 A schematic diagram of a single-day time period provided in an embodiment of the present application is shown in FIG. Figure 5As shown, it includes the time period from 0:00 to 24:00 of a single day, and the current time period includes the corresponding sleep time period. When confirming the feedback information shown in the current embodiment, if it is determined that the target home appliance corresponding to the instruction information has an impact on sleep, it will be determined separately according to the position of the current time in the single-day time period. If the current time is located in the time period of the day within the sleep time period, the feedback information is determined according to the second device control instruction and the first prompt information; if the current time is not located in the time period of the day within the sleep time period, the feedback information is determined according to the instruction information.

[0085] In the present application, when the target home device in the command information will affect the user's sleep, a control method with less impact is determined to generate feedback information, thereby reducing the impact of the use of the device on the user's sleep and improving the intelligence of the voice interaction.

[0086] In addition, in another feasible embodiment, feedback information is determined based on the instruction information and the physical health condition of the target user, including: determining the target home device and the first device control instruction corresponding to the instruction information; if it is determined that after the target home device is controlled based on the first device control instruction, there are multiple third device control instructions at the next level, then based on the influence relationship between the adverse condition in the physical health condition and the multiple third device control instructions, a third target device control instruction is determined from the multiple third device control instructions, the third target device control instruction being the control instruction with the least influence relationship with the adverse condition among the multiple third device control instructions; feedback information is determined based on the third target device control instruction and the second prompt information, the second prompt information being used to prompt the influence relationship between the adverse condition and the third target device control instruction; if it is determined that after the target home device is controlled based on the first device control instruction, there are no multiple third device control instructions at the next level, then feedback information is determined based on the first device control instruction.

[0087] Among them, the instruction information is used to control household appliances, so the control target in the instruction information is the target household appliance, and the corresponding control method corresponds to the first device control instruction. After determining the first device control instruction, it is necessary to further determine whether a series of more detailed and specific control operations will be triggered after executing this first device control instruction, that is, whether there are multiple third device control instructions at the next level, and these third device control instructions may be automatic optimization or supplementary operations based on the first device control instruction. For example, if the first device control instruction is to turn on the air conditioner, then the corresponding third device control instruction can be to adjust the mode and temperature.

[0088] If it is determined that after the target home device is controlled based on the first device control instruction, there are multiple third device control instructions at the next level, the third target device control instruction will be determined from the multiple third device control instructions based on the impact relationship between the adverse condition of the target user's physical health and the multiple third device control instructions. The third target device control instruction can be the control instruction with the least impact on the adverse condition among the multiple third device control instructions. Similarly, the impact relationship can be preset based on an empirical value.

[0089] For example, if the user has a respiratory disease and the patient is not suitable for breathing cold air, and the target home device corresponds to an air conditioner, and the first device control instruction is to turn on the cooling, then the third device control instruction can be to adjust the wind speed and temperature. At this time, the corresponding third target device control instruction can be the lowest wind speed and the general maximum temperature. The general maximum temperature is not the highest temperature that can be adjusted, but the highest temperature in the temperature range corresponding to the cooling set according to the empirical value, such as the general maximum temperature is twenty-eight degrees.

[0090] After the third target device control instruction is determined, feedback information is generated according to the third device control instruction and the second prompt information. The second prompt information is used to prompt the influence relationship between the adverse situation and the third target device control instruction. In other words, the second prompt information is used to explain to the user why this particular second target control instruction is selected. For example, the feedback information may be "considering that too low a temperature is not conducive to respiratory diseases, do you need to raise the temperature to 28 degrees?"

[0091] If it is determined that there are no multiple third device control instructions at the next level after executing the first device control instruction, feedback information is directly generated to the user based on the instruction information without performing additional health impact analysis and selection process. It is understandable that the feedback information can also be determined directly based on the execution result corresponding to the instruction information.

[0092] In the present application, by analyzing the relationship between the next-level instructions corresponding to the user's instructions and the impact of adverse conditions on physical health, the instructions at the next level with the least impact on the adverse conditions are automatically selected. This is beneficial to the user's physical health and further improves the intelligence of voice interaction.

[0093] Step S205: providing voice feedback to the target user according to the feedback information.

[0094] Among them, after voice feedback is given to the target user according to the feedback information, if the feedback information carries device control confirmation information, the voice data corresponding to the target user will continue to be received. After receiving the voice data used by the user to indicate confirmation, the corresponding device control will be executed.

[0095] In addition, in a feasible embodiment, the home intelligent system also includes a data management module, which stores voice interaction data corresponding to multiple users, and provides voice feedback to the target user based on the feedback information, including: if it is determined that the target user has an unfavorable health condition in his physical health, then determining the target user's emotional information based on the voice data corresponding to the target data; if it is determined that the target user's emotional information is a bad emotion, then obtaining the voice interaction data corresponding to the first user among the multiple users through the data management module, the first user being the user with the largest amount of voice interaction data among the multiple users except the target user; determining the voice features of the first user based on the voice interaction data corresponding to the first user; and based on the voice features of the first user, providing voice feedback to the target user.

[0096] Among them, when it is determined that there is an adverse health condition in the physical health of the target user, the emotional information of the target user can be determined according to the voice data corresponding to the target data. The voice data corresponding to the target data refers to the voice data obtained in the previous voice recognition process. The determination of emotional information based on voice data can be based on voice features, specifically based on a combination of machine learning, deep learning and voice processing technology. The reason why it is necessary to analyze the emotional information of the target user is that emotions also have a certain impact on the physical health of the target user. Good emotions are beneficial to the physical health of the target user, while bad emotions are not conducive to the physical health of the target user.

[0097] If the target user's emotional information is determined to be negative, the user can be fed back by simulating the voice characteristics of family members during voice feedback. This can provide certain emotional support and quickly narrow the distance between the target user and voice interaction. In addition, when the target user is in a bad mood, a familiar voice can bring a sense of warmth and comfort, which is helpful to alleviate the target user's negative emotions.

[0098] When determining the voice characteristics of family members, this embodiment obtains the voice interaction data of the first user with the largest amount of voice interaction data other than the target user among the voice interaction data of multiple users previously stored in the family through the data management module. The largest amount of voice interaction data indicates that the user has lived in the family for the longest time and may have the closest relationship with the target user. The voice characteristics of the first user are then determined based on the voice interaction data corresponding to the first user, and finally, based on the voice characteristics of the first user, feedback information is provided to the target user in voice feedback. The voice characteristics may include timbre, pitch, speech speed, etc.

[0099] In the present application, when the user is in poor health and in a bad mood, voice feedback can be given to the user by simulating the voice characteristics of family members, which can provide certain emotional support to the user and further improve the intelligence of voice interaction.

[0100] Furthermore, in a feasible embodiment, the emotional information of the target user is determined according to the voice data corresponding to the target data, including: determining at least one first emotional information according to the voice features corresponding to the voice data; if it is determined that at least one first emotional information is single, determining the first emotional information as the emotional information corresponding to the target user; if it is determined that at least one first emotional information is multiple, and it is determined that the current moment is in the target time period, obtaining the previous sleep condition of the target user, and the target time period is used to characterize the time period that will be affected by the previous sleep condition; if the previous sleep condition is good sleep, determining the second emotional information among the multiple first emotional information as the emotional information corresponding to the target user, and the second emotional information is used to characterize the best emotional information among the multiple first emotional information; if the previous sleep condition is bad sleep, determining the third emotional information among the multiple first emotional information as the emotional information corresponding to the target user, and the third emotional information is used to characterize the worst emotional information among the multiple first emotional information.

[0101] Among them, the determination of emotional information can be comprehensively judged in combination with the target user's previous sleep condition. When there is only one at least one first emotional information determined according to the voice feature, it can only be determined that the first emotional information is the emotional information corresponding to the target user. When there are multiple at least one first emotional information determined according to the voice feature, the emotional information corresponding to the target user can be selected from the multiple first emotional information in combination with the sleep condition. Specifically, it is first determined whether the current moment is in the target time period. The target time period refers to the time period that will be affected by the previous sleep condition. The target time period here is set based on the experience value. For example, the user's sleep time period is generally from 12 o'clock to 8 o'clock, then the time period from 8 o'clock to 9 o'clock in the morning can be the target time period. For example, if the user has a lunch break, the time period corresponding to half an hour after the lunch break can also be the target time period. It can be understood that the target time period here can be determined separately according to different user situations.

[0102] Generally speaking, good sleep will make the user feel more positive. Therefore, when determining that the previous sleep condition is good sleep, the best emotion information among multiple first emotion information can be determined as the emotion information corresponding to the target user; while bad sleep will make the user feel more negative. Therefore, when determining that the previous sleep condition is bad sleep, the worst emotion information among multiple first emotion information can be determined as the emotion information corresponding to the target user. In the case that the target user is not in the target time period, the current posture of the target user can be combined for comprehensive judgment.

[0103] In the present application, the emotional information of the target user is comprehensively judged in combination with the target user's sleep condition, so that the accuracy of determining the emotional information of the target user can be improved.

[0104] In addition, in a feasible embodiment, after providing voice feedback to the target user based on the feedback information, the method also includes: determining the recommended usage time of the target home device corresponding to the feedback information based on the physical health condition of the target user and the feedback information; generating a third prompt information when the target home device is used for a period of time exceeding the recommended usage time, the third prompt information being used to prompt a suggestion to stop using the target home device; and providing voice feedback to the target user based on the third prompt information.

[0105] The recommended usage time of the target home appliance corresponding to the feedback information is determined according to the physical health of the target user and the feedback information. The adverse conditions in the physical health of the target user may be determined first, and the impact between the adverse conditions and the corresponding device control conditions in the feedback information is determined. Then, the recommended usage time of the target home appliance corresponding to the feedback information is determined comprehensively according to the magnitude of the impact and the usage time benchmark of the home appliance corresponding to the feedback information. The usage time benchmark may refer to the general usage time, and may also be determined in combination with the user's historical device usage data.

[0106] After determining that the use time of the target home appliance reaches the recommended use time, a third prompt message is generated, and voice feedback is provided to the target user according to the third prompt message, for prompting and suggesting to stop using the target home appliance.

[0107] In this application, the recommended usage time of the target home equipment is determined based on the physical health condition and feedback information of the target user, and the user is prompted after the target home equipment is used for the recommended usage time. This is beneficial to the physical health of the target user and thus improves the intelligence of voice interaction.

[0108] It is understandable that voice interaction can also be combined with a corresponding voice interaction model. The training and application of the voice interaction model are described in detail below:

[0109] In a feasible embodiment, training data is obtained, and the training data includes speech data, influencing factors, text data corresponding to the speech data, physical health characteristics, instruction information corresponding to the speech data, and feedback information corresponding to the speech data; model training of an initial speech recognition network is performed according to the speech data, influencing factors, and text data in the training data to obtain a speech recognition network, and the speech recognition network obtains text data according to the speech data and the influencing factors; model training of an initial instruction information extraction network is performed according to the text data corresponding to the speech data in the training data and the instruction information corresponding to the speech data to obtain an instruction information extraction network, and the instruction information extraction network is used to obtain instruction information according to the text data; model training of an initial feedback information acquisition network is performed according to the physical health characteristics in the training data, the instruction information corresponding to the speech data, and the feedback information corresponding to the speech data to obtain a feedback information acquisition network, and the feedback information acquisition network obtains feedback information according to the physical health characteristics and the instruction information; the speech recognition network, the instruction information extraction network, and the feedback information acquisition network constitute a speech interaction model.

[0110] In a feasible embodiment, voice data, influencing factors and physical health characteristics are input into a voice interaction model to obtain feedback information.

[0111] After determining the physical health of the target user, the influencing factors corresponding to the language system in the physical health of the target user are determined. At this time, the corresponding voice data and the text data corresponding to the voice data can be obtained in the database based on such influencing factors. Alternatively, based on the influencing factors, a pre-trained speech synthesis algorithm (such as a speech synthesis algorithm based on a convolutional neural network) or a speech enhancement algorithm can be used to simulate the possible pronunciation of the target user, thereby obtaining the corresponding voice data and the text data corresponding to the voice data.

[0112] It can be understood that the voice interaction model corresponds to a machine learning model. The aforementioned initial voice recognition network, initial command information extraction network, and initial feedback information acquisition network can be pre-trained networks, such as deep neural networks, recurrent neural networks, etc. At the same time, when performing model training for the initial command information extraction network, it can also be combined with the voice recognition network, but the voice recognition network will freeze the parameters during model training and will not participate in parameter optimization. When performing model training for the initial feedback information acquisition network, it can also be combined with the voice recognition network and the command information extraction network. Similarly, the voice recognition network and the command information extraction network will freeze the parameters during model training and will not participate in parameter optimization. In this way, independent training of networks at different stages is conducive to the model learning more features of voice interaction. In addition, the above-mentioned voice interaction model is also applicable to all embodiments shown in this application.

[0113] For example, see Figure 6 , Figure 6 A flow chart of a speech interaction model training process provided in an embodiment of the present application is as follows: Figure 6 As shown, voice data, influencing factors and text data are input into the initial voice recognition network for training to obtain a voice recognition network; text data and instruction information are input into the initial instruction information extraction network for training to obtain an instruction information extraction network; instruction information, physical health characteristics and feedback information are input into the initial feedback information acquisition network for training to obtain a feedback information acquisition network; finally, a voice interaction model is obtained by combining the voice recognition network, the instruction information extraction network and the feedback information acquisition network, wherein the output of the voice recognition network is used as the input of the instruction information extraction network, and the output of the instruction information extraction network plus the physical health characteristics are used as the input of the feedback information acquisition network.

[0114] It can be seen that in the embodiment of the present application, the influencing factors of the diseases of the target user that affect the voice system are taken into account in the target data acquisition stage, which is highly targeted and can improve the accuracy of voice recognition for the target user. At the same time, when performing subsequent device control confirmation information feedback based on the target data, the physical health of the target user is also taken into account, which is beneficial to the physical health of the target user and thus improves the intelligence of voice interaction.

[0115] In accordance with the above-mentioned embodiments, please refer to Figure 7 , Figure 7 This is a functional unit block diagram of a voice interaction device provided in an embodiment of the present application. The voice interaction device is the above-mentioned voice interaction module or a part of the voice interaction module, such as Figure 7 As shown, the voice interaction device 70 includes:

[0116] An acquisition unit 701 is used to acquire the physical health status of a target user;

[0117] The processing unit 702 is used to perform speech recognition according to the influencing factors corresponding to the language system in the physical health condition of the target user, and obtain target data corresponding to the target user;

[0118] The processing unit 702 is further used to determine the instruction information corresponding to the target user according to the target data, and the instruction information is used to control the home appliance;

[0119] The processing unit 702 is further used to determine feedback information according to the instruction information and the physical health condition of the target user, where the feedback information includes device control confirmation information;

[0120] The feedback unit 703 is used to provide voice feedback to the target user according to the feedback information.

[0121] In a feasible embodiment, in terms of acquiring the target data of the target user based on the influencing factors corresponding to the language system in the target user's physical health condition, the acquisition unit 701 is specifically used to: determine whether the target user has a disease that affects the language system based on the target user's physical health condition; if it is determined that the target user has a disease that affects the language system, determine the influencing factors corresponding to the disease that affects the language system; and perform speech recognition based on the influencing factors to acquire the target data of the target user.

[0122] In a feasible embodiment, the home intelligent system includes a data management module, which stores parameter data and historical device control data of home appliances. In terms of determining the instruction information corresponding to the target user based on the target data, the processing unit 702 is specifically used to: obtain the historical device control data and parameter data of the home appliances corresponding to the target user through the data management module; extract instruction information based on the historical device control data, the parameter data of the home appliances and the target data, and determine the instruction information corresponding to the target user.

[0123] In a feasible embodiment, in terms of determining feedback information based on instruction information and the physical health condition of the target user, the processing unit 702 is specifically used to: determine the sleep time period corresponding to the target user according to the physical health condition of the target user; if it is determined that the target home appliance corresponding to the instruction information has an impact on sleep, and it is determined that the current moment is in the sleep time period or the duration between the current moment and the starting end point of the sleep time period is less than a first preset duration, then determine a second device control instruction based on the impact of the target home appliance on sleep and the first device control instruction in the instruction information, so that the impact of controlling the target home appliance according to the second device control instruction on sleep is less than the impact of controlling the target home appliance according to the first device control instruction on sleep; determine feedback information according to the second device control instruction and the first prompt information, the first prompt information being used for sleep prompting; if it is determined that the target home appliance corresponding to the instruction information has no impact on sleep, determine feedback information according to the instruction information.

[0124] In a feasible embodiment, in terms of determining feedback information based on instruction information and the physical health condition of the target user, the processing unit 702 is specifically used to: determine the target home device and the first device control instruction corresponding to the instruction information; if it is determined that after the target home device is controlled based on the first device control instruction, there are multiple third device control instructions at the next level, then based on the influence relationship between the adverse condition in the physical health condition and the multiple third device control instructions, determine the third target device control instruction from the multiple third device control instructions, the third target device control instruction being the control instruction with the least influence relationship with the adverse condition among the multiple third device control instructions; determine feedback information based on the third target device control instruction and the second prompt information, the second prompt information being used to prompt the influence relationship between the adverse condition and the third target device control instruction; if it is determined that after the target home device is controlled based on the first device control instruction, there are no multiple third device control instructions at the next level, then determine feedback information based on the first device control instruction.

[0125] In a feasible embodiment, the home intelligent system also includes a data management module, which stores voice interaction data corresponding to multiple users. In terms of providing voice feedback to the target user based on the feedback information, the feedback unit 703 is specifically used to: if it is determined that the target user has an unfavorable health condition in his physical health condition, determine the target user's emotional information based on the voice data corresponding to the target data; if it is determined that the target user's emotional information is a bad emotion, obtain the voice interaction data corresponding to the first user among the multiple users through the data management module, the first user being the user with the largest amount of voice interaction data among the multiple users except the target user; determine the voice features of the first user based on the voice interaction data corresponding to the first user; and based on the voice features of the first user, provide voice feedback to the target user.

[0126] In a feasible embodiment, the voice interaction device 70 also includes: after the feedback unit 703 provides voice feedback to the target user based on the feedback information, the processing unit 702 is also used to determine the recommended usage time of the target home appliance corresponding to the feedback information based on the physical health condition of the target user and the feedback information; when the target home appliance is used for the recommended usage time, a third prompt information is generated, and the third prompt information is used to prompt and recommend to stop using the target home appliance; the feedback unit 703 is also used to provide voice feedback to the target user based on the third prompt information.

[0127] It can be understood that since the method embodiment and the device embodiment are different presentation forms of the same technical concept, the content of the method embodiment part in this application should be synchronously adapted to the device embodiment part and will not be repeated here.

[0128] In the case of an integrated unit, such as Figure 8 As shown, Figure 8 This is a block diagram of the functional units of another voice interaction device 70 provided in an embodiment of the present application. Figure 8 In the embodiment, the voice interaction device 70 includes: a processing module 812 and a communication module 811. The processing module 812 is used to control and manage the actions of the voice interaction device 70, for example, the steps of the acquisition unit 701, the processing unit 702 and the feedback unit 703, and / or other processes for executing the technology described herein. The communication module 811 is used to support the interaction between the voice interaction device 70 and other devices. Figure 8 As shown, the voice interaction device 70 may further include a storage module 813 , and the storage module 813 is used to store program codes and data of the voice interaction device 70 .

[0129] Among them, the processing module 812 can be a processor or a controller, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements a computing function, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication module 811 can be a transceiver, an RF circuit or a communication interface, and the like. The storage module 813 can be a memory.

[0130] Among them, all relevant contents of each scenario involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and will not be repeated here. The above voice interaction device 70 can execute the above Figure 2 The voice interaction method shown.

[0131] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center containing one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0132] Fig. 9 This is a structural block diagram of an electronic device provided in an embodiment of the present application. Fig. 9 As shown, the electronic device 900 may include one or more of the following components: a processor 901, a memory 902 and a communication interface 903. The processor 901, the memory 902 and the communication interface 903 are interconnected and perform communication work with each other, wherein the memory 902 may store one or more computer programs, and the one or more computer programs may be configured to implement the methods described in the above embodiments when executed by one or more processors 901.

[0133] The processor 901 may include one or more processing cores. The processor 901 uses various interfaces and lines to connect the various parts of the entire electronic device 900, and executes various functions and processes data of the electronic device 900 by running or executing instructions, programs, code sets or instruction sets stored in the memory 902, and calling data stored in the memory 902. Optionally, the processor 901 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 901 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processor (Graphics Processing Unit, GPU) and a modem. It can be understood that the above-mentioned modem may not be integrated into the processor 901, and can be implemented separately through a communication chip.

[0134] The memory 902 may include a random access memory (RAM) or a read-only memory (ROM). The memory 902 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 902 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc. The data storage area may also store data created by the electronic device 900 during use, etc.

[0135] It is understandable that the electronic device 900 may include more or fewer structural elements than those in the above structural block diagram, for example, a power module, physical buttons, a WiFi (Wireless Fidelity) module, a speaker, a Bluetooth module, a sensor, etc., which are not limited here.

[0136] The electronic device 900 may be a voice interaction module or a part of a voice interaction module.

[0137] An embodiment of the present application provides a computer-readable storage medium, wherein program data is stored in the computer-readable storage medium, and when the program data is executed by a processor, the program data is used to execute part or all of the steps of any one of the voice interaction methods recorded in the above method embodiments.

[0138] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps of any voice interaction method described in the above method embodiment. The computer program product may be a software installation package.

[0139] It should be noted that for the method embodiments of any of the aforementioned voice interaction methods, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by this application.

[0140] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other variations of the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "one" does not exclude multiple situations. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0141] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the method embodiments of any of the above-mentioned voice interaction methods can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a disk or an optical disk, etc.

[0142] The above is a detailed introduction to the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of a voice interaction method and device of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, based on the idea of ​​a voice interaction method and device of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0143] The present application is described with reference to the flowcharts and / or block diagrams of the methods, hardware products, and computer program products of the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0144] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0145] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0146] It can be understood that any product that is controlled or configured to execute the processing method of the flowchart described in the method embodiment of a voice interaction method of the present application, such as the terminal and computer program product in the above flowchart, falls within the scope of the related products described in the present application.

[0147] Obviously, those skilled in the art can make various changes and modifications to the voice interaction method and device provided by the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A voice interaction method, characterized in that: The method is applied to a voice interaction module in a home intelligent system, and the method comprises: Obtain the physical health status of target users; Perform speech recognition according to the influencing factors corresponding to the language system in the physical health condition of the target user to obtain target data corresponding to the target user; Determine instruction information corresponding to the target user according to the target data, wherein the instruction information is used to control the home appliance; Determine feedback information according to the instruction information and the physical health condition of the target user, the feedback information including device control confirmation information; Providing voice feedback to the target user according to the feedback information.

2. The method according to claim 1, characterized in that The acquiring the target data of the target user according to the influencing factors corresponding to the language system in the physical health condition of the target user includes: Determining whether the target user has a disease that affects the language system according to the physical health of the target user; If it is determined that the target user has a disease that affects the language system, determining an influencing factor corresponding to the disease that affects the language system; Speech recognition is performed based on the influencing factors to obtain target data corresponding to the target user.

3. The method according to claim 2, characterized in that The home intelligent system includes a data management module, in which parameter data and historical device control data of the home device are stored. The step of determining the instruction information corresponding to the target user according to the target data includes: Acquire the historical device control data and parameter data of the home device corresponding to the target user through the data management module; The command information is extracted according to the historical device control data, the parameter data of the home device and the target data to determine the command information corresponding to the target user.

4. The method according to any one of claims 1 to 3, characterized in that: The step of determining feedback information according to the instruction information and the physical health condition of the target user includes: Determining a sleep time period corresponding to the target user according to the physical health condition of the target user; If it is determined that the target home appliance corresponding to the instruction information has an impact on sleep, and it is determined that the current moment is in the sleep time period or the duration between the current moment and the starting end point of the sleep time period is less than a first preset duration, a second device control instruction is determined based on the impact of the target home appliance on sleep and the first device control instruction in the instruction information, so that the impact of controlling the target home appliance according to the second device control instruction on sleep is less than the impact of controlling the target home appliance according to the first device control instruction on sleep; Determine the feedback information according to the second device control instruction and the first prompt information, wherein the first prompt information is used for providing a sleep prompt; If it is determined that the target home appliance corresponding to the instruction information has no impact on sleep, feedback information is determined according to the instruction information.

5. The method according to any one of claims 1 to 3, characterized in that: The step of determining feedback information according to the instruction information and the physical health condition of the target user includes: Determine a target home device and a first device control instruction corresponding to the instruction information; If it is determined that after the target home device is controlled based on the first device control instruction, there are multiple third device control instructions at the next level, then based on the influence relationship between the adverse condition in the physical health condition and the multiple third device control instructions, a third target device control instruction is determined from the multiple third device control instructions, and the third target device control instruction is the control instruction with the smallest influence relationship with the adverse condition among the multiple third device control instructions; Determining the feedback information according to the third target device control instruction and second prompt information, wherein the second prompt information is used to prompt the influence relationship between the bad situation and the third target device control instruction; If it is determined that after the target home device is controlled based on the first device control instruction, there are no multiple third device control instructions at the next level, the feedback information is determined according to the instruction information.

6. The method according to any one of claims 1 to 5, characterized in that: The home intelligent system further includes a data management module, in which voice interaction data corresponding to a plurality of users are stored. The voice feedback is provided to the target user according to the feedback information, including: If it is determined that the physical health of the target user has an unfavorable health condition, determining the emotional information of the target user according to the voice data corresponding to the target data; If it is determined that the emotional information of the target user is a negative emotion, the voice interaction data corresponding to the first user among the multiple users is obtained through the data management module, where the first user is the user with the largest amount of voice interaction data among the multiple users except the target user; determining a voice feature of the first user according to the voice interaction data corresponding to the first user; Based on the voice feature of the first user, the feedback information is provided to the target user in the form of voice feedback.

7. The method according to any one of claims 1 to 6, characterized in that: After providing voice feedback to the target user according to the feedback information, the method further includes: Determine the recommended usage time of the target home appliance corresponding to the feedback information according to the physical health condition of the target user and the feedback information; When the target home appliance is used for the recommended usage time, generating a third prompt message, wherein the third prompt message is used to prompt and recommend stopping the use of the target home appliance; Providing voice feedback to the target user according to the third prompt information.

8. A voice interaction device, characterized in that: The device is applied to a voice interaction module in a home intelligent system, and the device comprises: An acquisition unit, used to acquire the physical health status of the target user; A processing unit, configured to perform speech recognition according to the influencing factors corresponding to the language system in the physical health condition of the target user, and obtain target data corresponding to the target user; The processing unit is further used to determine the instruction information corresponding to the target user according to the target data, and the instruction information is used to control the home appliance; The processing unit is further used to determine feedback information according to the instruction information and the physical health condition of the target user, wherein the feedback information includes device control confirmation information; A feedback unit is used to provide voice feedback to the target user according to the feedback information.

9. An electronic device, characterized in that: The device comprises: A processor, a memory, and a communication interface, wherein the processor, the memory, and the communication interface are connected to each other and perform communication work between them; The memory stores executable program code, and the communication interface is used for wireless communication; The processor is used to call the executable program code stored in the memory to execute the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: A computer program for electronic data exchange is stored, wherein the computer program enables a computer to execute the method according to any one of claims 1 to 7.

Images