Interaction method and device of smart home equipment

Abstract

The invention relates to an interaction method and device of smart home equipment. The method comprises the steps of triggering a task processing request in response to a user instruction; in response to the task processing request, determining a task triggering scene; wherein the task triggering scene is used for describing the scene of the moment when the user instruction is received; analyzing the task triggering scene, and determining emotion influence scene information in multiple pieces of scene information of the task triggering scene; wherein the emotion influence scene information is scene information influencing the emotion of the user; generating interaction information according to the emotion influence scene information; wherein the interaction information is at least used for performing care type interaction with the user according to the emotion influence scene information; and sending the task processing request and the interaction information to the corresponding smart home device so as to output the interaction information when the smart home device executes a task corresponding to the task processing request. Through the method, care type interaction information is provided for the user when the intelligent household equipment interacts with the user.

Description

Technical Field

[0001] The present application relates to the field of smart home, and in particular to an interaction method and device for smart home devices. Background Art

[0002] With the popularity of smart home devices, users have higher requirements for the interaction methods between smart home devices. Currently, users can interact with smart home devices through buttons, touch screens, voice, etc.

[0003] When existing smart home devices interact with users, they mostly focus on executing tasks corresponding to user instructions, and rarely involve interaction with users on an emotional level, making it difficult to meet users' psychological needs for care and companionship. Summary of the invention

[0004] The present application provides an interaction method and device for a smart home device to solve the technical problem that it is difficult for a smart home device to meet the user's psychological needs for care and companionship when interacting with the user.

[0005] In a first aspect, the present application provides an interaction method for a smart home device, the method comprising:

[0006] triggering a task processing request in response to a user instruction;

[0007] In response to the task processing request, determining a task triggering scenario; wherein the task triggering scenario is used to describe the scenario at the moment of receiving the user instruction, and the task triggering scenario includes a plurality of scenario information;

[0008] Parsing the task triggering scenario, and determining at least one emotion-affecting scenario information from the plurality of scenario information of the task triggering scenario; wherein the emotion-affecting scenario information is the scenario information that affects the user's emotions;

[0009] Generate interaction information according to the emotion-affecting scenario information; wherein the interaction information is at least used to perform caring interaction with the user with respect to the emotion-affecting scenario information;

[0010] The task processing request and the interaction information are sent to the corresponding smart home device, so that the interaction information is output when the smart home device executes the task corresponding to the task processing request.

[0011] In a feasible embodiment of the present application, determining a task triggering scenario includes:

[0012] Determining environmental context information in response to the task processing request; wherein the environmental context information at least includes weather information and / or temperature information and / or humidity information;

[0013] Determining time context information in response to the task processing request; wherein the time context information at least includes trigger time information;

[0014] The task triggering scenario is determined according to the environmental scenario information and the time scenario information.

[0015] In a feasible embodiment of the present application, the task triggering scenario is parsed, and at least one emotion-affecting scenario information is determined from the multiple scenario information of the task triggering scenario, including:

[0016] Determine the emotion impact weight corresponding to each of the scenario information; wherein the greater the impact of the scenario information on the user's emotions, the greater the emotion impact weight corresponding to the scenario information;

[0017] The context information whose emotion impact weight is greater than a preset weight threshold is determined as the emotion impact context information.

[0018] In a feasible embodiment of the present application, determining the emotion impact weight corresponding to each of the situation information includes:

[0019] determining a first degree of deviation between the time context information and the target time information;

[0020] The emotion impact weight of the time context information is determined according to the first deviation degree; wherein, the smaller the first deviation degree is, the greater the emotion impact weight of the time context information is.

[0021] In a feasible embodiment of the present application, determining the emotion impact weight corresponding to each of the situation information includes:

[0022] Determining a second degree of deviation between the environmental scenario information and the standard environmental information; wherein the standard environmental information at least includes a standard temperature value, a standard humidity value, and a standard weather condition, the standard temperature value is an average temperature value of the user's location within a preset time, the standard humidity value is an average humidity value of the user's location within the preset time, and the standard weather condition is a sunny day;

[0023] The emotion impact weight of the environmental context information is determined according to the second deviation degree; wherein, the greater the second deviation degree is, the greater the emotion impact weight of the environmental context information is.

[0024] In a feasible embodiment of the present application, generating interaction information according to the emotion impact scenario information includes:

[0025] Get the preset processing model;

[0026] The emotion-affecting scenario information is processed by the processing model to generate the interaction information corresponding to the emotion-affecting scenario information.

[0027] In a feasible embodiment of the present application, the user instruction includes a user voice instruction, the processing model includes a first processing model and a second processing model, and the emotion impact scenario information is processed by the processing model to generate the interaction information corresponding to the emotion impact scenario information, including:

[0028] Inputting the emotion impact situation information into the first processing model to obtain first interaction information; wherein the first interaction information is used to perform caring interaction with the user with respect to the emotion impact situation information;

[0029] Determining user emotion information according to the user voice command; wherein the user emotion information is used to describe the current user emotion;

[0030] Inputting the user emotion information into the second processing model to obtain second interaction information; wherein the second interaction information is used to perform caring interaction with the user according to the user emotion information;

[0031] The interaction information is generated according to the first interaction information and the second interaction information.

[0032] In a second aspect, the present application provides an interactive device for a smart home device, the device comprising:

[0033] A trigger module, used to trigger a task processing request in response to a user instruction;

[0034] A determination module, configured to determine a task triggering scenario in response to the task processing request; wherein the task triggering scenario is used to describe the scenario at the moment of receiving the user instruction, and the task triggering scenario includes a plurality of scenario information;

[0035] An analysis module, used to analyze the task triggering scenario, and determine at least one emotion-affecting scenario information from the multiple scenario information of the task triggering scenario; wherein the emotion-affecting scenario information is the scenario information that affects the user's emotions;

[0036] A generating module, configured to generate interaction information according to the emotion-affecting scenario information; wherein the interaction information is at least used to perform caring interaction with the user with respect to the emotion-affecting scenario information;

[0037] A sending module is used to send the task processing request and the interaction information to the corresponding smart home device, so as to output the interaction information when the smart home device executes the task corresponding to the task processing request.

[0038] In a third aspect, the present application provides a smart home device, comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus, wherein the processor is configured to execute an interaction method for a smart home device as described in any one of the embodiments of the first aspect of the present application.

[0039] In a fourth aspect, the present application further provides a computer storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute an interaction method for a smart home device as described in any one of the embodiments of the first aspect of the present application.

[0040] The above technical solution provided by the embodiment of the present application has the following advantages compared with the prior art:

[0041] In the technical solution provided by the present application, a task processing request is triggered in response to a user instruction; in response to the task processing request, a task triggering scenario is determined; wherein the task triggering scenario is used to describe the scenario at the moment when the user instruction is received, and the task triggering scenario includes multiple scenario information; the task triggering scenario is parsed, and at least one emotion-affecting scenario information is determined from the multiple scenario information of the task triggering scenario; wherein the emotion-affecting scenario information is scenario information that affects the user's emotions; interaction information is generated according to the emotion-affecting scenario information; wherein the interaction information is at least used to interact with the user in a caring manner with respect to the emotion-affecting scenario information; the task processing request and the interaction information are sent to the corresponding smart home device, so that the interaction information is output when the smart home device executes the task corresponding to the task processing request. When the task corresponding to the task processing request is executed, the interaction information is output.

[0042] Through the technical solution provided by this application, when the user expects the device to perform a task, the smart home device perceives the relevant situational information, analyzes the current situational information that affects the user's emotions, and generates corresponding interactive information to interact with the user with reference to the current situational information that affects the user's emotions. It can be seen that the smart home device not only performs tasks, but also interacts with the user while performing tasks, and such interactive information is a text generated based on the information that affects the user's emotions and is relevant to the current situation in real time. Therefore, the technical solution provided by this application can interact with the user in a caring manner and meet the user's psychological needs for care and companionship. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0044] In order to more clearly illustrate the embodiments of the present invention 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0045] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0046] Figure 1 A schematic diagram of an implementation scenario of an interaction method for smart home devices provided in an embodiment of the present application;

[0047] Figure 2 A schematic diagram of a flow chart of an interaction method of a smart home device provided in an embodiment of the present application;

[0048] Figure 3 A schematic diagram of the structure of an interactive device for a smart home device provided in an embodiment of the present application;

[0049] Figure 4 A schematic diagram of the structure of a smart home device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, 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 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 making creative work are within the scope of protection of this application.

[0051] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0052] In order to solve the technical problem in the prior art that smart home devices are difficult to meet users' psychological needs for care and companionship when interacting with users, the present application provides an interaction method and device for smart home devices, which can generate interaction information corresponding to user emotional information and / or emotional impact scenario information, so as to interact with users in a caring manner.

[0053] Figure 1 A schematic diagram of an implementation scenario of an interactive method for a smart home device provided in an embodiment of the present application, referring to Figure 1 , describes an implementation scenario of an interaction method for a smart home device provided in an embodiment of the present application.

[0054] An interaction method for smart home devices provided in an embodiment of the present application can be applied to a home scene with multiple smart home devices. The method can use any smart home device as the execution subject, and can also use the back-end server connected to these smart home devices as the execution subject.

[0055] The backend server of the smart home device is connected to the smart home device based on a communication network, and communicates with each other based on the communication network. In some practical examples, the smart home device can be a smart air conditioner, a smart speaker, a smart refrigerator, a smart bracelet, and the like.

[0056] The home scene also includes front-end interactive devices, which are used to interact with users. The front-end interactive devices can be set on smart home devices, or can be a smart home device connected to a communication network, such as a smart speaker or a smart display.

[0057] Figure 2 A flow chart of an interactive method for a smart home device provided in an embodiment of the present application, referring to Figure 2 The embodiment of the present application provides a method for interacting with a smart home device, which specifically includes the following steps:

[0058] S1: triggering a task processing request in response to a user instruction;

[0059] Specifically, user instructions may include user touch instructions and user voice instructions. Users can input user instructions through a front-end interactive device connected to the smart home device. The front-end interactive device may be a microphone, a touch screen, control buttons, and other devices.

[0060] For example, a user may input a user command through a touch screen provided on a smart home device. In this case, the user command is a user touch command. For another example, a user may speak a user command into a microphone connected to the smart home device. In this case, the user command is a user voice command.

[0061] The front-end interactive device of the smart home device receives the user's instructions and transmits the user's instructions to the back-end server of the smart home device. The back-end server recognizes the user's instructions and triggers the corresponding task processing request.

[0062] The task processing request is used to instruct the corresponding smart home device to perform the task. In a feasible embodiment of the present application, the task processing request may specifically include an execution object and an execution action. The execution object indicates the smart home device currently executing the task, and the execution action indicates the corresponding action of the currently executing task.

[0063] S2: In response to the task processing request, determine a task triggering scenario; wherein the task triggering scenario is used to describe the scenario at the moment of receiving the user instruction, and the task triggering scenario includes multiple scenario information;

[0064] Specifically, after the back-end server of the smart home device determines the task processing request, it takes the task processing request as the trigger node and starts to determine the task triggering scenario. The task triggering scenario is used to describe the scenario at the moment when the user instruction is received. The task triggering scenario includes multiple scenario information. One scenario information describes one aspect of the scenario at the moment when the user instruction is received.

[0065] In a feasible embodiment of the present application, determining a task triggering scenario includes:

[0066] Determining environmental context information in response to the task processing request; wherein the environmental context information at least includes weather information and / or temperature information and / or humidity information;

[0067] Determining time context information in response to the task processing request; wherein the time context information at least includes trigger time information;

[0068] The task triggering scenario is determined based on the environmental scenario information and the time scenario information.

[0069] Specifically, the environmental scenario information is used to describe the environmental scenario at the moment when the user instruction is received, and the environmental scenario information at least includes weather information and / or temperature information and / or humidity information.

[0070] In a feasible embodiment of the present application, the back-end server of the smart home device can obtain environmental scenario information through an environmental monitoring device connected to the same communication network, for example, temperature information can be obtained through a temperature sensor and humidity information can be obtained through a humidity sensor.

[0071] The time context information is used to describe the time context of the moment when the user instruction is received, and the time context information at least includes trigger time information.

[0072] In a feasible embodiment of the present application, the backend server of the smart home device can directly use the time when the user instruction is received as the trigger time information.

[0073] In a feasible embodiment of the present application, based on the trigger time information, the backend server of the smart home device can further analyze the trigger time information to obtain more time context information. For example, the current date, current season, current time period (morning, noon or evening), current festival, etc. can be determined based on the trigger time information.

[0074] In a feasible embodiment of the present application, the context information may further include character context information, and the character context information includes at least user identity information and user age information.

[0075] After determining the context information of the moment when the user instruction is received, the task triggering context is determined based on the context information. As a specific example, the task triggering context can be expressed as: who + in xx area + xx weather + xx temperature + xx festival + (morning, noon or evening) + controlled xx + performed xx task.

[0076] S3: parsing the task triggering scenario, and determining at least one emotion-affecting scenario information from multiple scenario information of the task triggering scenario; wherein the emotion-affecting scenario information is scenario information that affects the user's emotions;

[0077] Specifically, based on the analysis of the task triggering scenario, at least one emotion-influencing scenario information is determined from multiple scenario information of the task triggering scenario, and the emotion-influencing scenario information is scenario information that may currently affect the user's emotions.

[0078] In a feasible embodiment of the present application, the task triggering scenario is parsed, and at least one emotion-affecting scenario information is determined from multiple scenario information of the task triggering scenario, including:

[0079] Determine the emotion impact weight corresponding to each context information; wherein the greater the impact of the context information on the user's emotions, the greater the emotion impact weight corresponding to the context information;

[0080] The context information whose emotion impact weight is greater than a preset weight threshold is determined as emotion impact context information.

[0081] Specifically, after the back-end server of the smart home device determines the task triggering scenario, it calculates the emotional impact weight of each scenario information in the task triggering scenario. The size of the emotional impact weight of a scenario information is related to the impact of the scenario information on the user's emotions. In the embodiment provided in the present application, the greater the impact of the scenario information on the user's emotions, the greater the emotional impact weight corresponding to the scenario information.

[0082] The emotion impact weight of each scenario information is compared with a preset weight threshold, and the scenario information whose emotion impact weight is greater than the preset weight threshold is determined as the emotion impact scenario information. The weight threshold can be a threshold pre-set by a technician in a back-end server of the smart home device, or a threshold calculated in real time based on the emotion impact weight of each scenario information. For example, the weight threshold is obtained by multiplying the average value of the emotion impact weight of each scenario information by a proportional coefficient, and the proportional coefficient can be set to 1.2.

[0083] It can be understood that the emotion-impacting scenario information is a number of scenario information with a relatively large emotion-impacting weight.

[0084] In a feasible embodiment of the present application, each situation information can be processed by a preset sentiment analysis model to determine the emotional impact weight of each situation information. The sentiment analysis model uses a deep neural network (such as a convolutional neural network CNN, a recurrent neural network RNN ​​and its variants LSTM, GRU, etc.) to analyze the situation information, and measures each situation information by standards such as the degree of severity, degree of change, and degree of user bias, so as to determine the emotional impact weight of each situation information. In some specific examples, when a situation information is worse, more variable, and the user is more biased, the emotional impact weight of the situation information is greater.

[0085] In a feasible embodiment of the present application, determining the emotion impact weight corresponding to each piece of situation information includes:

[0086] determining a first degree of deviation between the temporal context information and the target temporal information;

[0087] The emotional impact weight of the time context information is determined according to the first deviation degree; wherein, the smaller the first deviation degree is, the greater the emotional impact weight of the time context information is.

[0088] Specifically, target time information is obtained, where the target time information is time information that has special meaning to the user.

[0089] In a feasible embodiment of the present application, the target time information can be obtained from a preset target time information list, which pre-stores time information that has special meanings, such as the dates of the Spring Festival, New Year's Day, Christmas, etc.

[0090] In a feasible embodiment of the present application, the target time information can also be set by the user. The user can set part of the time as special time on the front-end interactive device of the smart home device, and the time information of these times is also the target time information, for example, the working time limit set by the user, the travel departure time set by the user, and other target time information.

[0091] In a feasible embodiment of the present application, the target time information can also be determined based on the character context information. When determining the context information, the character context information is obtained, and the time information carried in the character context information is used as the target time information, for example, the user's birthday, the user's relative's birthday, and the user's wedding anniversary are used to obtain the target time information.

[0092] After the target time information is determined, the first deviation degree between the time scenario information and the target time information is determined, and the emotional impact weight of the time scenario information is determined according to the first deviation degree. When the first deviation degree is smaller, it means that the current time scenario information is more special, and the time scenario information may have a greater impact on the user's emotions, so the emotional impact weight of the time scenario information is set to be larger; on the contrary, when the first deviation degree is larger, it means that the current time scenario information is less special, and the time scenario information may have a smaller impact on the user's emotions, so the emotional impact weight of the time scenario information is set to be smaller.

[0093] In a feasible embodiment of the present application, determining the first degree of deviation between the time context information and the target time information may be achieved through a neural network model.

[0094] In a feasible embodiment of the present application, determining the emotion impact weight corresponding to each piece of situation information includes:

[0095] Determining a second degree of deviation between the environmental scenario information and the standard environmental information; wherein the standard environmental information includes at least a standard temperature value, a standard humidity value, and a standard weather condition, the standard temperature value is an average temperature value of the user's location within a preset time, the standard humidity value is an average humidity value of the user's location within a preset time, and the standard weather condition is a sunny day;

[0096] The emotional impact weight of the environmental context information is determined according to the second deviation degree; wherein, the greater the second deviation degree is, the greater the emotional impact weight of the environmental context information is.

[0097] Specifically, standard environmental information is obtained, and the standard environmental information includes at least a standard temperature value, a standard humidity value, and a standard weather condition. The standard temperature value is the average temperature value of the user's location within a preset time, the standard humidity value is the average humidity value of the user's location within a preset time, and the standard weather condition is a sunny day.

[0098] In a feasible embodiment of the present application, standard environmental information can be obtained on a weather website via a communication network.

[0099] As a specific example, the temperature value of the user's location within 30 days is obtained to calculate the average temperature value, and the average temperature value is used as the standard temperature value; the humidity value of the user's location within 30 days is obtained to calculate the average temperature value, and the average humidity value is used as the standard humidity value; sunny day is set as the standard weather condition; standard environmental information is determined by determining the standard temperature value, standard humidity value and standard weather condition.

[0100] It is understandable that, as an example, the environmental context information includes weather information, temperature information and humidity information, so in this example, the standard environmental information includes a standard temperature value, a standard humidity value and a standard weather condition. In other examples, if other environmental context information is also included, the standard context information is also increased accordingly.

[0101] After determining the standard environmental information, determine the second degree of deviation between the environmental scenario information and the standard environmental information, and determine the emotional impact weight of the environmental scenario information according to the second degree of deviation. When the second degree of deviation is larger, it means that the current environmental scenario information deviates more from the standard, and the environmental scenario information may have a greater impact on the user's emotions, so the emotional impact weight of the environmental scenario information is set to be larger; on the contrary, when the second degree of deviation is smaller, it means that the current environmental scenario information deviates less from the standard, and the environmental scenario information may have a smaller impact on the user's emotions, so the emotional impact weight of the environmental scenario information is set to be smaller.

[0102] In a feasible embodiment of the present application, determining the second degree of deviation between the environmental context information and the standard environmental information may be achieved through a neural network model.

[0103] Through the various embodiments involved in S3 above, the emotion-affecting scenario information is determined in the task triggering scenario, and the factors that are most likely to affect the user's emotions in the current scenario are actually analyzed, and the factors are related to the current scenario in real time. Through the various embodiments above, the analysis of user emotions is realized, providing data support for subsequent interaction with the user.

[0104] S4: generating interaction information according to the emotion-affecting scenario information; wherein the interaction information is at least used to perform caring interaction with the user with respect to the emotion-affecting scenario information;

[0105] Specifically, corresponding interaction information is generated according to the emotion-affecting scenario information, and the content of the interaction information is to provide caring interaction for the user with respect to the emotion-affecting scenario information.

[0106] In a feasible embodiment of the present application, generating interaction information according to the emotion impact scenario information includes:

[0107] Get the preset processing model;

[0108] The emotion-affecting situation information is processed through a processing model to generate interaction information corresponding to the emotion-affecting situation information.

[0109] Specifically, the processing model may be a text generation model based on natural language processing, and the processing model generates corresponding interactive information with reference to a preset text template and input information.

[0110] The processing model has been pre-trained, and for any input emotional impact scenario information, the processing model outputs corresponding, caring interactive information. For example, if the emotional impact scenario information is determined to be weather information, and the weather at this time is heavy rain, the emotional impact scenario information is input to the processing model, and the interactive information generated can be "It's raining heavily outside, remember to bring an umbrella when you go out."

[0111] In a feasible embodiment of the present application, the processing model includes a first processing model and a second processing model, and the emotion-affecting scenario information is processed by the processing model to generate interaction information corresponding to the emotion-affecting scenario information, including:

[0112] Inputting emotion-affecting scenario information into the first processing model to obtain first interaction information; wherein the first interaction information is used to perform caring interaction with the user with respect to the emotion-affecting scenario information;

[0113] Determining user emotion information according to the user voice command; wherein the user emotion information is used to describe the current user emotion;

[0114] Inputting user emotion information into the second processing model to obtain second interaction information; wherein the second interaction information is used to perform caring interaction with the user based on the user emotion information;

[0115] The interaction information is generated according to the first interaction information and the second interaction information.

[0116] Specifically, in the above embodiment, the user's emotions may also be analyzed, and the interaction information may be further improved based on the obtained user emotion information, so that the interaction information has more caring implications.

[0117] The processing model specifically includes a first processing model and a second processing model. The first processing model outputs first interaction information, and the second processing model outputs second interaction information.

[0118] First, the emotion-affecting scenario information is processed by a first processing model to obtain first interaction information for performing caring interaction with the user with respect to the emotion-affecting scenario information.

[0119] When a user controls a smart home device by voice, the user voice command is obtained, and the user emotion information is determined according to the user voice command, and the user emotion information is used to describe the current user emotion. As an example, any one of multiple emotion keywords can be used as the user emotion information, and the emotion keywords include, for example, keywords such as happy, frustrated, angry, etc.

[0120] After acquiring the user emotion information, the user emotion information is processed by the second processing model to obtain second interaction information used for performing caring interaction with the user according to the user emotion information.

[0121] The first interaction information and the second interaction information are combined to obtain interaction information.

[0122] As an example, the currently analyzed user emotion information is "depressed", the currently determined emotion impact scenario information is the trigger time information, and the first deviation between the trigger time information and the Spring Festival is the smallest. Then the first interaction information can be generated as "Today is a good day for family reunion", and the second interaction information can be generated as "Cheer up, today is a good day for family reunion". Then the interaction information can be generated as "Cheer up, today is a good day for family reunion".

[0123] S5: sending the task processing request and the interaction information to the corresponding smart home device, so that the interaction information is output when the smart home device executes the task corresponding to the task processing request;

[0124] Specifically, after the back-end server of the smart home device generates the interaction information, it sends a task processing request and the interaction information to the corresponding smart home device. The smart home device executes the task corresponding to the task processing request and outputs the interaction information on the front-end interaction device of the smart home device to display the interaction information to the user.

[0125] In a feasible embodiment of the present application, the interactive information may be interactive voice, the smart home device executes the task corresponding to the task processing request, and outputs the interactive voice on the front-end interactive device of the smart home device.

[0126] In a feasible embodiment of the present application, the interactive information may also be an interactive text. The smart home device executes the task corresponding to the task processing request, and displays the interactive text on the front-end interactive device of the smart home device.

[0127] Through the technical solution provided by this application, when the user expects the device to perform a task, the smart home device perceives the relevant situational information, analyzes the current situational information that affects the user's emotions, and generates corresponding interactive information to interact with the user with reference to the current situational information that affects the user's emotions. It can be seen that the smart home device not only performs tasks, but also interacts with the user while performing tasks, and such interactive information is a text generated based on the information that affects the user's emotions and is relevant to the current situation in real time. Therefore, the technical solution provided by this application can interact with the user in a caring manner and meet the user's psychological needs for care and companionship.

[0128] Corresponding to the above method embodiment, the embodiment of the present application also provides an interactive device for smart home devices. Figure 3 A schematic diagram of a structure of an interactive device for a smart home device provided in an embodiment of the present application, referring to Figure 3 , an interactive device for a smart home device provided in an embodiment of the present application includes:

[0129] A trigger module 301, configured to trigger a task processing request in response to a user instruction;

[0130] The determination module 302 is used to determine the task triggering scenario in response to the task processing request; wherein the task triggering scenario is used to describe the scenario at the moment of receiving the user instruction, and the task triggering scenario includes multiple scenario information;

[0131] The analysis module 303 is used to analyze the task triggering scenario and determine at least one emotion-affecting scenario information from multiple scenario information of the task triggering scenario; wherein the emotion-affecting scenario information is scenario information that affects the user's emotions;

[0132] A generating module 304 is used to generate interaction information according to the emotion-affecting scenario information; wherein the interaction information is at least used to perform caring interaction with the user with respect to the emotion-affecting scenario information;

[0133] The sending module 305 is used to send the task processing request and the interaction information to the corresponding smart home device, so that the interaction information is output when the smart home device executes the task corresponding to the task processing request.

[0134] In a feasible embodiment of the present application, the determination module 302 includes:

[0135] A first determining unit, configured to determine environmental context information in response to a task processing request; wherein the environmental context information at least includes weather information and / or temperature information and / or humidity information;

[0136] A second determining unit, configured to determine time context information in response to the task processing request; wherein the time context information at least includes trigger time information;

[0137] The third determining unit is used to determine the task triggering scenario according to the environmental scenario information and the time scenario information.

[0138] In a feasible embodiment of the present application, the analysis module 303 includes:

[0139] A fourth determining unit is used to determine the emotion impact weight corresponding to each piece of context information; wherein the greater the impact of the context information on the user's emotions, the greater the emotion impact weight corresponding to the context information;

[0140] The fifth determining unit is configured to determine the context information whose emotion impact weight is greater than a preset weight threshold as emotion impact context information.

[0141] In a feasible embodiment of the present application, the fourth determining unit includes:

[0142] A first determining subunit, used to determine a first deviation degree between the time context information and the target time information;

[0143] The second determining subunit is used to determine the emotion impact weight of the time context information according to the first deviation degree; wherein, the smaller the first deviation degree is, the greater the emotion impact weight of the time context information is.

[0144] In a feasible embodiment of the present application, the fourth determining unit includes:

[0145] The third determination subunit is used to determine a second deviation degree between the environmental scenario information and the standard environmental information; wherein the standard environmental information at least includes a standard temperature value, a standard humidity value and a standard weather condition, the standard temperature value is an average temperature value of the user's location within a preset time, the standard humidity value is an average humidity value of the user's location within a preset time, and the standard weather condition is a sunny day;

[0146] The fourth determination subunit is used to determine the emotional impact weight of the environmental context information according to the second deviation degree; wherein, the greater the second deviation degree, the greater the emotional impact weight of the environmental context information.

[0147] In a feasible embodiment of the present application, the generating module 304 includes:

[0148] An acquisition unit, used for acquiring a preset processing model;

[0149] The processing unit is used to process the emotion-affecting scenario information through a processing model to generate interaction information corresponding to the emotion-affecting scenario information.

[0150] In a feasible embodiment of the present application, the user instruction includes a user voice instruction, the processing model includes a first processing model and a second processing model, and the processing unit includes:

[0151] A first input subunit is used to input emotion-affecting scenario information into a first processing model to obtain first interaction information; wherein the first interaction information is used to perform caring interaction with a user with respect to the emotion-affecting scenario information;

[0152] A fifth determining subunit, configured to determine user emotion information according to the user voice command; wherein the user emotion information is used to describe the current user emotion;

[0153] A second input subunit is used to input the user emotion information into the second processing model to obtain second interaction information; wherein the second interaction information is used to perform caring interaction with the user according to the user emotion information;

[0154] The generating subunit is configured to generate interaction information according to the first interaction information and the second interaction information.

[0155] like Figure 4 As shown, the embodiment of the present application provides a smart home device, including a processor 401, a communication interface 402, a memory 403 and a communication bus 404, wherein the processor 401, the communication interface 402, and the memory 403 communicate with each other through the communication bus 404.

[0156] Memory 403, used for storing computer programs;

[0157] In one embodiment of the present application, the processor 401 is used to execute the program stored in the memory 403 to implement an interaction method of a smart home device provided by any of the above method embodiments, for example, including:

[0158] triggering a task processing request in response to a user instruction;

[0159] In response to the task processing request, determining a task triggering scenario; wherein the task triggering scenario is used to describe the scenario at the moment of receiving the user instruction, and the task triggering scenario includes multiple scenario information;

[0160] Analyze the task triggering scenario, and determine at least one emotion-affecting scenario information from multiple scenario information of the task triggering scenario; wherein the emotion-affecting scenario information is scenario information that affects the user's emotions;

[0161] Generate interactive information according to the emotion-affecting scenario information; wherein the interactive information is at least used to perform caring interaction with the user with respect to the emotion-affecting scenario information;

[0162] Send the task processing request and the interaction information to the corresponding smart home device, so that the interaction information is output when the smart home device executes the task corresponding to the task processing request.

[0163] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of a smart home device interaction method provided in any of the aforementioned method embodiments are implemented.

[0164] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0165] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0166] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0167] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for interacting with smart home devices, characterized in that: The method comprises: triggering a task processing request in response to a user instruction; In response to the task processing request, determining a task triggering scenario; wherein the task triggering scenario is used to describe the scenario at the moment of receiving the user instruction, and the task triggering scenario includes a plurality of scenario information; Parsing the task triggering scenario, and determining at least one emotion-affecting scenario information from the plurality of scenario information of the task triggering scenario; wherein the emotion-affecting scenario information is the scenario information that affects the user's emotions; Generate interaction information according to the emotion-affecting scenario information; wherein the interaction information is at least used to perform caring interaction with the user with respect to the emotion-affecting scenario information; The task processing request and the interaction information are sent to the corresponding smart home device, so that the interaction information is output when the smart home device executes the task corresponding to the task processing request.

2. The method according to claim 1, characterized in that: Determine the task triggering scenario, including: Determining environmental context information in response to the task processing request; wherein the environmental context information at least includes weather information and / or temperature information and / or humidity information; Determining time context information in response to the task processing request; wherein the time context information at least includes trigger time information; The task triggering scenario is determined according to the environmental scenario information and the time scenario information.

3. The method according to claim 2, characterized in that Parsing the task triggering scenario and determining at least one emotion-affecting scenario information from a plurality of scenario information of the task triggering scenario includes: Determine the emotion impact weight corresponding to each of the scenario information; wherein the greater the impact of the scenario information on the user's emotions, the greater the emotion impact weight corresponding to the scenario information; The context information whose emotion impact weight is greater than a preset weight threshold is determined as the emotion impact context information.

4. The method according to claim 3, characterized in that Determining the emotional impact weight corresponding to each of the scenario information includes: determining a first degree of deviation between the time context information and the target time information; The emotion impact weight of the time context information is determined according to the first deviation degree; wherein, the smaller the first deviation degree is, the greater the emotion impact weight of the time context information is.

5. The method according to claim 3, characterized in that: Determining the emotional impact weight corresponding to each of the scenario information includes: Determining a second degree of deviation between the environmental scenario information and the standard environmental information; wherein the standard environmental information at least includes a standard temperature value, a standard humidity value, and a standard weather condition, the standard temperature value is an average temperature value of the user's location within a preset time, the standard humidity value is an average humidity value of the user's location within the preset time, and the standard weather condition is a sunny day; The emotion impact weight of the environmental context information is determined according to the second deviation degree; wherein, the greater the second deviation degree is, the greater the emotion impact weight of the environmental context information is.

6. The method according to claim 1, characterized in that Generate interactive information according to the emotion impact scenario information, including: Get the preset processing model; The emotion-affecting scenario information is processed by the processing model to generate the interaction information corresponding to the emotion-affecting scenario information.

7. The method according to claim 6, characterized in that The user instruction includes a user voice instruction, the processing model includes a first processing model and a second processing model, and the emotion-affecting scenario information is processed by the processing model to generate the interaction information corresponding to the emotion-affecting scenario information, including: Inputting the emotion impact situation information into the first processing model to obtain first interaction information; wherein the first interaction information is used to perform caring interaction with the user with respect to the emotion impact situation information; Determining user emotion information according to the user voice command; wherein the user emotion information is used to describe the current user emotion; Inputting the user emotion information into the second processing model to obtain second interaction information; wherein the second interaction information is used to perform caring interaction with the user according to the user emotion information; The interaction information is generated according to the first interaction information and the second interaction information.

8. An interactive device for smart home equipment, characterized in that: The device comprises: A trigger module, used to trigger a task processing request in response to a user instruction; A determination module, configured to determine a task triggering scenario in response to the task processing request; wherein the task triggering scenario is used to describe the scenario at the moment of receiving the user instruction, and the task triggering scenario includes a plurality of scenario information; An analysis module, used to analyze the task triggering scenario, and determine at least one emotion-affecting scenario information from the multiple scenario information of the task triggering scenario; wherein the emotion-affecting scenario information is the scenario information that affects the user's emotions; A generating module, configured to generate interaction information according to the emotion-affecting scenario information; wherein the interaction information is at least used to perform caring interaction with the user with respect to the emotion-affecting scenario information; A sending module is used to send the task processing request and the interaction information to the corresponding smart home device, so as to output the interaction information when the smart home device executes the task corresponding to the task processing request.

9. A smart home device, characterized in that: include: A processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; The memory is used to store a computer program; the processor is used to implement the interaction method of a smart home device as described in any one of claims 1 to 7 when executing the computer program.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for interacting with a smart home device described in any one of claims 1 to 7 is implemented.

Images