Control method and device of intelligent device, equipment and medium

Abstract

The embodiment of the invention discloses a control method and device of an intelligent device, equipment and a medium. The method comprises the following steps: acquiring a running state data set of all intelligent equipment in a target area; classifying all the intelligent devices according to the operation state to obtain a first intelligent device set; calling a preset recognition model, and configuring the preset recognition model to each intelligent device in the first intelligent device set to obtain a target device; controlling the target device to obtain the user request information, and obtaining a first identification result of the target device for the user request information; and generating a control instruction according to the first identification result to control an intelligent device corresponding to the user request information. The intelligent device serves as a control center, the calculation pressure of a single control center is reduced, and the control efficiency of the intelligent device is improved.

Description

Technical Field

[0001] The present invention relates to the field of smart home technology, and in particular to a control method, device, equipment and medium for a smart device. Background Art

[0002] With the rapid development of intelligent technologies such as automation and the Internet of Things, smart homes are becoming more and more convenient for people's lives. However, in the existing technology, the process of realizing smart homes is often carried out through one or a fixed number (the fixed number is greater than or equal to 2) of control centers to perform data calculations to control the smart devices in the network, and a single device receives user instructions in a fixed manner. However, when data calculations are performed through one or a fixed number of control centers to control the smart devices in the network, there is often a large amount of data calculation, and the calculation pressure of one control center for data calculation is large and the efficiency is low, while other electronic devices with data receiving and data calculation capabilities are idle or have little calculation pressure, which also causes a waste of resources. If data calculations are performed through a fixed number (the fixed number is greater than or equal to 2) of control centers, the control center will be unable to process the data, and the control center will be unable to process the data. The cost of controlling the networked smart devices by calculating data increases, and there is a problem of idle control centers when the amount of calculation is small. At the same time, when a control center performs data calculation to control the networked smart devices, it often uses a single model (algorithm) to identify the user's intention, which is easily disturbed and causes inaccurate recognition. When a fixed number (fixed number is greater than or equal to 2) of control centers perform data calculation to control the networked smart devices, although multiple models (algorithms) can be used to identify the user's intention at the same time, when a single device receives user instructions in a fixed manner, the difference in the advantages and disadvantages of the existing intention recognition models is not obvious, so it is not meaningful to use multiple models (algorithms) to identify the user's intention, and there is still an inaccurate recognition problem. When a single device receives user instructions in a fixed manner, if the device receiving the user's instructions is a non-portable electronic device, such as a smart speaker, it needs to be placed in a fixed position. When the user needs to control the smart device, it needs to move close to the smart speaker, causing inconvenience.

[0003] Cooking is an indispensable task related to human survival and development. From ancient times to the present, people have to cook once or more times every day. The cooking utensils, ingredients, seasonings, and processes used in different dishes in a meal are also varied. If a person only follows the steps to complete a dish each time, it often takes a long time to cook a meal. With the continuous progress of society, although there have been great improvements in various cooking utensils, saving a certain amount of processing time, the preparation of dishes still needs to be completed manually according to the steps, which undoubtedly cannot meet the fast pace of life of people today. With the rapid development of intelligent technologies such as automation and the Internet of Things, smart cooking and smart kitchens are becoming more and more popular. When smart cooking equipment and smart kitchen equipment are connected to the local area network to realize smart home, the above problems also exist. Summary of the invention

[0004] In view of this, the present invention provides a control method, device, equipment and medium for an intelligent device, which are used to solve the problems of inaccurate control of intelligent devices and low control efficiency of intelligent devices in the prior art.

[0005] To achieve one, part, or all of the above purposes or other purposes, the present invention provides a control method for an intelligent device, comprising:

[0006] Acquire an operation status data set of all smart devices in a target area, wherein the smart device is an electronic device having a data transceiver function and a data calculation function, and the operation status data set includes an operation status of each of the smart devices, and the operation status includes an on state, a standby state, and an off state;

[0007] Classify all smart devices according to the operating status to obtain a first smart device set, a second smart device set, and a third smart device set;

[0008] Calling a preset recognition model in a preset model library, and configuring the preset recognition model on a smart device in the first smart device set to obtain a target device, wherein the preset recognition model is an intention recognition model, and the preset model library includes at least two preset recognition models with different algorithms and feature values ​​corresponding to the preset recognition models;

[0009] Controlling the target device to obtain user request information, and obtaining a first recognition result of the target device for the user request information;

[0010] A control instruction is generated according to the first recognition result to control the smart device corresponding to the user request information.

[0011] Optionally, the step of obtaining a data set of operating status of all smart devices in the target area includes:

[0012] Divide the user's space into at least two sub-areas according to the building structure;

[0013] Acquire image data of each sub-region, and input the image data into a human body recognition model to obtain a second recognition result;

[0014] Determine the sub-area where the user is located based on the second recognition result as the target area;

[0015] The image data corresponding to the target area is used as the target image data, and the operation status data set of all the smart devices in the target area is obtained according to the target image data.

[0016] Optionally, the step of using the image data corresponding to the target area as target image data, and acquiring the operating status data set of all smart devices in the target area according to the target image data includes:

[0017] Using the image data corresponding to the target area as target image data, and identifying the type information of each smart device displayed by the target image data;

[0018] The operating status of each smart device is determined based on the type information of each smart device, the power consumption data of each smart device, and the flow data of each smart device, so as to obtain an operating status data set of all smart devices in the target area.

[0019] Optionally, the step of calling a preset recognition model in a preset model library, configuring the preset recognition model in a smart device in the first smart device set, obtaining a target device, the preset recognition model being an intention recognition model, and the preset model library including at least two preset recognition models with different algorithms and feature values ​​corresponding to the preset recognition models, comprises:

[0020] Acquire a metadata set of all preset recognition models in the preset model library, wherein the metadata set includes metadata of each preset recognition model, and the metadata includes a model feature mapping relationship;

[0021] According to the model feature mapping relationship, a feature identifier of the feature on which each preset recognition model depends is obtained;

[0022] Acquire the feature value of the feature that each preset recognition model depends on according to the feature identifier to obtain a feature value set;

[0023] A preset recognition model is called out from the preset model library according to the feature value set, and the called out preset recognition model is configured on a smart device in the first smart device set to obtain a target device.

[0024] Optionally, the step of calling a preset recognition model in a preset model library according to the feature value set, and configuring the called preset recognition model on a smart device in the first smart device set to obtain a target device includes:

[0025] Calling out a preset recognition model in a preset model library according to the feature value set;

[0026] Counting the number of called preset recognition models as a first number;

[0027] Counting the number of smart devices in the first smart device set as a second number;

[0028] Compare the first number with the second number, and select the smaller number between the first number and the second number as the target number;

[0029] Selecting a target number of the preset recognition models by a random sampling method, and selecting a target number of smart devices to be configured from the first smart device set;

[0030] The selected preset recognition model is configured on the selected smart device to be configured according to the preset rule to obtain the target device, wherein the preset rule is configured for any preset recognition model and is only configured on one smart device to be configured.

[0031] Optionally, the step of controlling the target device to obtain user request information and obtaining a recognition result of the target device for the user request information includes:

[0032] Acquire a human-computer interaction rule formulated for the target device, and control the target device to acquire user request information according to the human-computer interaction rule;

[0033] A first recognition result of the target device for the user request information is obtained, where the first recognition result includes a to-be-controlled smart device corresponding to the user request information and a control instruction for the to-be-controlled smart device.

[0034] Optionally, the method further includes:

[0035] Calling a preset recognition model in the preset model library, and configuring the preset recognition model on a smart device in the second smart device set to obtain a candidate device;

[0036] Controlling the candidate device to obtain user request information, and obtaining a third recognition result of the candidate device for the user request information;

[0037] A control instruction is generated based on the first recognition result and the third recognition result to control the smart device corresponding to the user request information.

[0038] On the other hand, an embodiment of the present application provides a control device for an intelligent device, the control device comprising:

[0039] A data acquisition module is used to obtain an operation status data set of all smart devices in the target area, wherein the smart device is an electronic device with data receiving and sending functions and data computing functions, and the operation status data set includes the operation status of each smart device, and the operation status includes an on state, a standby state, and an off state;

[0040] A classification module, used for classifying all the smart devices according to the operating status to obtain a first smart device set, a second smart device set and a third smart device set;

[0041] A calling module, used to call a preset recognition model in a preset model library, and configure the preset recognition model to a smart device in the first smart device set to obtain a target device, wherein the preset recognition model is an intention recognition model, and the preset model library includes at least two preset recognition models with different algorithms and feature values ​​corresponding to the preset recognition models;

[0042] an identification module, used to control the target device to obtain user request information, and obtain a first identification result of the target device for the user request information;

[0043] A control module is used to generate a control instruction according to the first recognition result to control the smart device corresponding to the user request information.

[0044] On the other hand, an embodiment of the present application provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the control method of the intelligent device as described above are performed.

[0045] On the other hand, an embodiment of the present application provides a computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the control method of the intelligent device as described above are executed.

[0046] Implementing the embodiments of the present invention will have the following beneficial effects:

[0047] By acquiring an operation status data set of all smart devices in a target area, wherein the smart device is an electronic device with data receiving and sending functions and data computing functions, and the operation status data set includes the operation status of each of the smart devices, and the operation status includes an on state, a standby state and an off state; classifying all smart devices according to the operation status to obtain a first smart device set, a second smart device set and a third smart device set; calling a preset recognition model in a preset model library, and configuring the preset recognition model to the smart devices in the first smart device set to obtain a target device, the preset recognition model is an intention recognition model, and the preset model library includes at least two preset recognition models with different algorithms and feature values ​​corresponding to the preset recognition models; controlling the target device to obtain user request information, and obtaining a first recognition result of the target device for the user request information; generating a control instruction according to the first recognition result to control the smart device corresponding to the user request information. Using smart devices as control centers reduces the computing pressure of a single control center and improves the control efficiency of smart devices. When the first smart device set includes at least two smart devices, at least two smart devices are used to receive user instructions (voice instructions, gesture instructions, text instructions, etc.) in different ways, and recognize the user's intentions through different preset recognition models, which can ensure the accuracy of user intention recognition. Since the positions of different smart devices are different, different user instructions can be obtained, and different preset recognition models can be used to recognize different user instructions, which further ensures the accuracy of user intention recognition. At the same time, the position of the device that receives the user's instructions is not fixed, which can facilitate the user to complete the control of any smart device in the smart home network in any area covered by the smart home, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] 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, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] in:

[0050] Figure 1 is a flow chart of a control method of an intelligent device provided in an embodiment of the present application;

[0051] Figure 2 is a flow chart of another control method of an intelligent device provided in an embodiment of the present application;

[0052] Figure 3is a structural schematic diagram of a control device of an intelligent device provided in an embodiment of the present application;

[0053] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0054] Figure 5 It is a structural schematic diagram of a computer-readable storage medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] like Figure 1 As shown, the embodiment of the present application provides a control method of an intelligent device, including:

[0057] S101, obtaining an operation status data set of all smart devices in a target area, wherein the smart device is an electronic device having a data transceiver function and a data calculation function, and the operation status data set includes an operation status of each of the smart devices, and the operation status includes an on state, a standby state, and an off state;

[0058] Exemplarily, the area where the user is located is taken as the target area, and an operating status data set of all smart devices in the area where the user is located is obtained. The smart device is an electronic device with data receiving and sending functions and data calculation functions, for example, a smart TV, which can receive display data (programs) sent by a server, send request data to the server, and parse instructions to adjust the display content. The operating status data set includes the operating status of each of the smart devices, and the operating status includes an on state, a standby state, and an off state.

[0059] S102, classifying all smart devices according to the operating status to obtain a first smart device set, a second smart device set, and a third smart device set;

[0060] Exemplarily, all smart devices are classified according to the operating status to obtain a device set of smart devices in an on state (a first smart device set), a device set of smart devices in a standby state (a second smart device set), and a device set of smart devices in an off state (a third smart device set).

[0061] S103, calling a preset recognition model in a preset model library, and configuring the preset recognition model on a smart device in the first smart device set to obtain a target device, wherein the preset recognition model is an intention recognition model, and the preset model library includes at least two preset recognition models with different algorithms and feature values ​​corresponding to the preset recognition models;

[0062] Exemplarily, the preset model library is stored in the cloud to reduce the resource usage of the local area network, and a call request is sent to the cloud. The preset recognition model is extracted from the preset model library according to the call request, and the preset recognition model is configured in the smart devices in the first smart device set (the device set of smart devices in the turned-on state) to obtain the target device.

[0063] Exemplarily, the preset model library includes at least two preset recognition models with different algorithms, and also includes preset recognition models with the same algorithm but different model training methods.

[0064] S104, controlling the target device to obtain user request information, and obtaining a first recognition result of the target device for the user request information;

[0065] Exemplarily, when controlling the target device to obtain user request information, due to the different types of information that the target device can receive, the way of controlling the target device to obtain the user request information is also different. For example, when the target device is a monitoring device, the monitoring device is controlled to obtain the user's image (posture image, lip shape image) as the user request information; when the target device is an audio device, the audio device is controlled to obtain the user's voice data as the user request information.

[0066] Exemplarily, since different target devices obtain user request information in different data formats, different intent recognition models are needed to process the user request information. For example, when obtaining a user's image (gesture image, lip shape image) as user request information, the target device obtains a recognition result for the user request information through image recognition; when obtaining the user's voice data as user request information, the target device obtains a recognition result for the user request information through voice recognition.

[0067] S105: Generate a control instruction according to the first recognition result to control the smart device corresponding to the user request information.

[0068] Exemplarily, the first recognition result (user intention) is "start cooking". Since the smart device associated with "cooking" is a smart cooking device, the smart cooking device is determined to be the smart device corresponding to the user request information, and "start" is used as the control information to generate a control instruction. Among them, the smart device as the target device is an electronic device with data receiving and sending functions and data calculation functions, that is, in the embodiment of the present application, the smart device as the target device needs to perform data collection work (equivalent to the device that receives user instructions) and data calculation work (equivalent to the control center), and the smart device (the smart device corresponding to the user request information) is a controlled device, which does not need to directly receive user instructions, but indirectly receives user instructions in the form of receiving control instructions, and the smart device controls the smart device according to the user instructions.

[0069] Exemplarily, when the user wants to control the smart cooking device to perform cooking, the operating status of all smart devices near the user is obtained to obtain an operating status set. For example, the user is in the living room, and the smart devices near the user are a smart TV, a smart speaker, and a smart monitoring device. The smart TV is in an on state, the smart speaker is in a standby state, and the smart monitoring device is in an on state. Then the operating status set is "on, standby, on". All smart devices are classified according to the operating status of the smart devices to obtain a first smart device set (smart TV, smart monitoring device), a second smart device set (smart speaker), and a third smart device set (empty). The preset recognition model is called in the preset model library, and the preset recognition model is configured on the smart TV and the smart monitoring device. The configured smart TV and the configured smart monitoring device are both used as target devices, and the configured smart TV is controlled to obtain the user request information. , at this time, the user request information can be the key information input by the user through the key, and the intelligent monitoring device after the control configuration obtains the user request information. At this time, the user request information can be the image information of the user. The key information input by the user through the key is recognized by the first intention recognition model trained based on the key information and the target intention, and the first intention (controlling the intelligent cooking device to perform cooking work) is obtained. The image information of the user is recognized by the second intention recognition model trained based on the image information and the target intention, and the second intention (controlling the intelligent cooking device to perform cooking work) is obtained. The target intention generated based on the first intention and the second intention is used as the first recognition result. According to the first recognition result, a control instruction is generated to control the intelligent device corresponding to the user request information. The control instruction includes the intelligent equipment to be controlled (intelligent cooking device) and the instruction content (perform cooking work) for the intelligent equipment to be controlled (intelligent cooking device). No matter which area the user is in, any intelligent device can be controlled, that is, the above-mentioned user controls the intelligent cooking device in the living room. When the intelligent cooking device and the user are not in the same area, cross-area control is performed.

[0070] Exemplarily, when at least two target devices are determined, if the target devices are in different local area networks, the first intent or the second intent is transmitted through a data channel between different local area networks to implement a process of generating a target intent based on the first intent and the second intent.

[0071] By acquiring an operation status data set of all smart devices in a target area, wherein the smart device is an electronic device with data receiving and sending functions and data computing functions, and the operation status data set includes the operation status of each of the smart devices, and the operation status includes an on state, a standby state and an off state; classifying all smart devices according to the operation status to obtain a first smart device set, a second smart device set and a third smart device set; calling a preset recognition model in a preset model library, and configuring the preset recognition model to the smart devices in the first smart device set to obtain a target device, the preset recognition model is an intention recognition model, and the preset model library includes at least two preset recognition models with different algorithms and feature values ​​corresponding to the preset recognition models; controlling the target device to obtain user request information, and obtaining a first recognition result of the target device for the user request information; generating a control instruction according to the first recognition result to control the smart device corresponding to the user request information. Using smart devices as control centers reduces the computing pressure of a single control center and improves the control efficiency of smart devices. When the first smart device set includes at least two smart devices, at least two smart devices are used to receive user instructions (voice instructions, gesture instructions, text instructions, etc.) in different ways, and recognize the user's intentions through different preset recognition models, which can ensure the accuracy of user intention recognition. Since the positions of different smart devices are different, different user instructions can be obtained, and different preset recognition models can be used to recognize different user instructions, which further ensures the accuracy of user intention recognition. At the same time, the position of the device that receives the user's instructions is not fixed, which can facilitate the user to complete the control of any smart device in the smart home network in any area covered by the smart home, thereby improving the user experience.

[0072] In a possible implementation, the step of acquiring the operating status data set of all smart devices in the target area includes:

[0073] Divide the user's space into at least two sub-areas according to the building structure;

[0074] Acquire image data of each sub-region, and input the image data into a human body recognition model to obtain a second recognition result;

[0075] Determine the sub-area where the user is located based on the second recognition result as the target area;

[0076] The image data corresponding to the target area is used as the target image data, and the operation status data set of all the smart devices in the target area is obtained according to the target image data.

[0077] Exemplarily, the process of dividing the space where the user is located into at least two sub-areas according to the building structure, for example, dividing the house where the user is located (the space where the user is located) into sub-spaces such as a living room, a bedroom, and a kitchen according to the building structure.

[0078] Exemplarily, image data of each sub-area can be obtained through a camera device, and the image data can be input into a human body recognition model to obtain a second recognition result; infrared image data of each sub-area can also be obtained through an infrared sensing device, and the infrared image data can be input into a human body recognition model to obtain a second recognition result.

[0079] Exemplarily, the process of constructing a human body recognition model is as follows: constructing a feature interaction network, a local feature enhancement network and a local feature optimization network, using a residual neural network as a main network, followed by the feature interaction network, the local feature enhancement network and the local feature optimization network in sequence, to obtain a human body recognition model;

[0080] The training process of the human body recognition model is as follows: obtain a human body training data set, input the training samples in the human body training data set into the human body recognition model; output multiple stage features through the multiple stage networks of the residual neural network respectively; use the feature interaction network to perform feature fusion processing on the multiple stage features to obtain fusion features, and perform interaction processing on the multiple stage features and the fusion features to obtain total interaction features; use the local feature enhancement network to process the total interaction features to obtain sample features and multiple local features; based on the sample features and multiple local features, use the loss function to complete the training of the human body recognition model.

[0081] Exemplarily, the process of constructing a human body recognition model is as follows: constructing a feature interaction network, a local feature enhancement network and a local feature optimization network, using a residual neural network as a main network, followed by the feature interaction network, the local feature enhancement network and the local feature optimization network in sequence, to obtain a human body recognition model;

[0082] In a possible implementation, the step of using the image data corresponding to the target area as target image data, and acquiring the operating status data set of all smart devices in the target area according to the target image data, includes:

[0083] Using the image data corresponding to the target area as target image data, and identifying the type information of each smart device displayed by the target image data;

[0084] The operating status of each smart device is determined based on the type information of each smart device, the power consumption data of each smart device, and the flow data of each smart device, so as to obtain an operating status data set of all smart devices in the target area.

[0085] Exemplarily, the image data corresponding to the target area is used as target image data, and the target image data is input into a device recognition model to obtain all smart devices existing in the target area, and then obtain an operating status data set of all smart devices in the target area. The model algorithm and structure of the device recognition model are consistent with the human body recognition model, but the device recognition model is trained through device features and device names during training.

[0086] Exemplarily, the image data corresponding to the target area is used as target image data, and the target image data is input into a device recognition model to obtain all smart devices existing in the target area, and then obtain an operating status data set of all smart devices in the target area. The model algorithm and structure of the device recognition model are consistent with the human body recognition model, but the device recognition model is trained through device features and device names during training.

[0087] Exemplarily, the power consumption data of each smart device is obtained through a non-invasive measurement device, and the traffic data of each smart device is obtained through a network traffic statistics method, and then the power consumption characteristic patterns of the smart device in different operating states (on state, standby state and off state) are determined based on the type information of the smart device, and the operating state of the smart device is determined through the power consumption data and power consumption characteristic patterns of the smart device, and whether the determined operating state is reasonable is verified through the traffic data of the smart device. For example, it is determined that the operating state of the smart TV is on through the power consumption data and power consumption characteristic patterns of the smart TV, but the traffic data of the smart TV is zero, which is obviously unreasonable and the operating state of the smart TV needs to be re-judged.

[0088] In a possible implementation, the step of calling a preset recognition model in a preset model library, configuring the preset recognition model on a smart device in the first smart device set, obtaining a target device, wherein the preset recognition model is an intention recognition model, and the preset model library includes at least two preset recognition models with different algorithms and feature values ​​corresponding to the preset recognition models, comprises:

[0089] Obtaining a metadata set of all preset recognition models in a preset model library, wherein the metadata set includes metadata of each preset recognition model, and the metadata includes a model feature mapping relationship;

[0090] According to the model feature mapping relationship, a feature identifier of the feature on which each preset recognition model depends is obtained;

[0091] Acquire the feature value of the feature that each preset recognition model depends on according to the feature identifier to obtain a feature value set;

[0092] A preset recognition model is called out from the preset model library according to the feature value set, and the called out preset recognition model is configured on a smart device in the first smart device set to obtain a target device.

[0093] For example, Figure 2 As shown, the calling process includes: in response to a model calling request, obtaining the metadata of the model, wherein the metadata of the model includes a model feature mapping relationship; specifically, in response to the model calling request, obtaining the metadata of the model called in the model calling request. Further specifically, the model calling request includes a model identifier of the called model, and according to the model identifier, the metadata of the corresponding model is obtained, wherein the metadata of the model includes a model feature mapping relationship, and the model feature mapping relationship is used to identify the features required by the current version of the model, i.e., the features that the model depends on. The model identifier here can be the name of the model or the number of the model, and can be used to uniquely identify the model;

[0094] According to the model feature mapping relationship, the feature identifiers of the features on which the model depends are obtained; specifically, the model feature mapping relationship is obtained to obtain the feature identifiers of the features on which the model depends.

[0095] According to the feature identifier, the feature value of the feature that the model depends on is obtained; specifically, according to the feature identifier and the metadata of the feature corresponding to the feature identifier, the feature value corresponding to the feature identifier is obtained, and the metadata of the feature includes the storage information of the feature value. According to the storage information, the required feature value can be obtained. The metadata of the feature includes: feature name, dimension, data type, default value and feature pool storage information. The metadata of the feature can be feature identifier, carrier object type, feature name, feature data format, feature storage medium information, etc.

[0096] The model is called according to the feature values ​​of the features on which the model depends; specifically, the feature values ​​of the features on which the model depends are obtained, the model service is called, and the model calculation results are returned.

[0097] In a possible implementation, the step of calling a preset recognition model in a preset model library according to the feature value set, and configuring the called preset recognition model in a smart device in the first smart device set to obtain a target device includes:

[0098] Calling out a preset recognition model in a preset model library according to the feature value set;

[0099] Counting the number of called preset recognition models as a first number;

[0100] Counting the number of smart devices in the first smart device set as a second number;

[0101] Compare the first number with the second number, and select the smaller number between the first number and the second number as the target number;

[0102] Selecting a target number of the preset recognition models by a random sampling method, and selecting a target number of smart devices to be configured from the first smart device set;

[0103] The selected preset recognition model is configured on the selected smart device to be configured according to the preset rule to obtain the target device, wherein the preset rule is configured for any preset recognition model and is only configured on one smart device to be configured.

[0104] Exemplarily, in real applications, the number of the preset recognition models and the number of smart devices in the first smart device set are mostly different. For example, the number of the preset recognition models is 5, and the number of smart devices in the first smart device set is 8. Then 5 is taken as the target number, and 5 smart devices to be configured are selected from the first smart device set by random sampling. The 5 preset recognition models are non-repetitively configured on the 5 smart devices to be configured, that is, the preset rule is configured for any preset recognition model and only configured on one smart device to be configured to obtain the target device.

[0105] In a possible implementation manner, the step of controlling the target device to obtain the user request information and obtaining a first recognition result of the target device for the user request information includes:

[0106] Acquire a human-computer interaction rule formulated for the target device, and control the target device to acquire user request information according to the human-computer interaction rule;

[0107] A first recognition result of the target device for the user request information is obtained, where the first recognition result includes a to-be-controlled smart device corresponding to the user request information and a control instruction for the to-be-controlled smart device.

[0108] Exemplarily, since different target devices obtain user request information in different data formats, for example, in the living room, the monitoring device in the living room is used as the target device. Since the function of the monitoring device is to obtain images, the formulated human-computer interaction rules are to select the smart device to be controlled based on the user's first specific gesture (posture), and to control the smart device to be controlled based on the user's second specific gesture (posture).

[0109] In a possible implementation, the method further includes:

[0110] Calling a preset recognition model in the preset model library, and configuring the preset recognition model on a smart device in the second smart device set to obtain a candidate device;

[0111] Controlling the candidate device to obtain user request information, and obtaining a third recognition result of the candidate device for the user request information;

[0112] A control instruction is generated based on the first recognition result and the third recognition result to control the smart device corresponding to the user request information.

[0113] Exemplarily, in order to improve the accuracy of recognition, the preset recognition model is configured on the smart devices in the second smart device set (the device set in standby mode) to obtain alternative devices, and then control instructions are generated through more different user request information to control the smart devices corresponding to the user request information.

[0114] In a possible implementation, Figure 3 As shown, an embodiment of the present application provides a control device for an intelligent device, the control device comprising:

[0115] The data collection module 201 is used to obtain the operation status data set of all smart devices in the target area, wherein the smart device is an electronic device with data receiving and sending functions and data calculation functions, and the operation status data set includes the operation status of each smart device, and the operation status includes an on state, a standby state, and an off state;

[0116] A classification module 202, configured to classify all smart devices according to the operating status to obtain a first smart device set, a second smart device set, and a third smart device set;

[0117] The calling module 203 is used to call a preset recognition model in a preset model library, and configure the preset recognition model to the smart device in the first smart device set to obtain a target device, wherein the preset recognition model is an intention recognition model, and the preset model library includes at least two preset recognition models with different algorithms and feature values ​​corresponding to the preset recognition models;

[0118] The identification module 204 is used to control the target device to obtain the user request information, and obtain a first identification result of the target device for the user request information;

[0119] The control module 205 is used to generate a control instruction according to the first recognition result to control the smart device corresponding to the user request information.

[0120] By acquiring an operation status data set of all smart devices in a target area, wherein the smart device is an electronic device with data receiving and sending functions and data computing functions, and the operation status data set includes the operation status of each of the smart devices, and the operation status includes an on state, a standby state and an off state; classifying all smart devices according to the operation status to obtain a first smart device set, a second smart device set and a third smart device set; calling a preset recognition model in a preset model library, and configuring the preset recognition model to the smart devices in the first smart device set to obtain a target device, the preset recognition model is an intention recognition model, and the preset model library includes at least two preset recognition models with different algorithms and feature values ​​corresponding to the preset recognition models; controlling the target device to obtain user request information, and obtaining a first recognition result of the target device for the user request information; generating a control instruction according to the first recognition result to control the smart device corresponding to the user request information. Using smart devices as control centers reduces the computing pressure of a single control center and improves the control efficiency of smart devices. When the first smart device set includes at least two smart devices, at least two smart devices are used to receive user instructions (voice instructions, gesture instructions, text instructions, etc.) in different ways, and recognize the user's intentions through different preset recognition models, which can ensure the accuracy of user intention recognition. Since the positions of different smart devices are different, different user instructions can be obtained, and different preset recognition models can be used to recognize different user instructions, which further ensures the accuracy of user intention recognition. At the same time, the position of the device that receives the user's instructions is not fixed, which can facilitate the user to complete the control of any smart device in the smart home network in any area covered by the smart home, thereby improving the user experience.

[0121] In a possible implementation, Figure 4As shown, an embodiment of the present application provides an electronic device 300, including: a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, the following is achieved: obtaining an operation status data set of all smart devices in a target area, wherein the smart device is an electronic device having a data transceiver function and a data calculation function, and the operation status data set includes an operation status of each of the smart devices, and the operation status includes an on state, a standby state, and an off state; classifying all smart devices according to the operation status to obtain a first smart device set, a second smart device set, and a third smart device set; calling a preset recognition model in a preset model library, and configuring the preset recognition model to the smart devices in the first smart device set to obtain a target device, the preset recognition model is an intention recognition model, and the preset model library includes at least two preset recognition models with different algorithms and feature values ​​corresponding to the preset recognition models; controlling the target device to obtain user request information, and obtaining a first recognition result of the target device for the user request information; generating a control instruction according to the first recognition result to control the smart device corresponding to the user request information.

[0122] By acquiring an operation status data set of all smart devices in a target area, wherein the smart device is an electronic device with data receiving and sending functions and data computing functions, and the operation status data set includes the operation status of each of the smart devices, and the operation status includes an on state, a standby state and an off state; classifying all smart devices according to the operation status to obtain a first smart device set, a second smart device set and a third smart device set; calling a preset recognition model in the preset model library, and configuring the preset recognition model to the smart devices in the first smart device set to obtain a target device, the preset recognition model is an intention recognition model, and the preset model library includes at least two preset recognition models with different algorithms and feature values ​​corresponding to the preset recognition models; controlling the target device to obtain user request information, and obtaining a first recognition result of the target device for the user request information; generating a control instruction according to the first recognition result to control the smart device corresponding to the user request information. Using smart devices as control centers reduces the computing pressure of a single control center and improves the control efficiency of smart devices. When the first smart device set includes at least two smart devices, at least two smart devices are used to receive user instructions (voice instructions, gesture instructions, text instructions, etc.) in different ways, and recognize the user's intentions through different preset recognition models, which can ensure the accuracy of user intention recognition. Since the positions of different smart devices are different, different user instructions can be obtained, and different preset recognition models can be used to recognize different user instructions, which further ensures the accuracy of user intention recognition. At the same time, the position of the device that receives the user's instructions is not fixed, which can facilitate the user to complete the control of any smart device in the smart home network in any area covered by the smart home, thereby improving the user experience.

[0123] In a possible implementation, Figure 5As shown, an embodiment of the present application provides a computer-readable storage medium 400, on which a computer program 411 is stored, and when the computer program 411 is executed by a processor, it is implemented: obtaining an operation status data set of all smart devices in a target area, wherein the smart device is an electronic device with a data receiving and transmitting function and a data computing function, and the operation status data set includes the operation status of each of the smart devices, and the operation status includes an on state, a standby state, and an off state; classifying all smart devices according to the operation status to obtain a first smart device set, a second smart device set, and a third smart device set; calling a preset recognition model in a preset model library, and configuring the preset recognition model to the smart devices in the first smart device set to obtain a target device, the preset recognition model is an intention recognition model, and the preset model library includes at least two preset recognition models with different algorithms and feature values ​​corresponding to the preset recognition models; controlling the target device to obtain user request information, and obtaining a first recognition result of the target device for the user request information; generating a control instruction according to the first recognition result to control the smart device corresponding to the user request information.

[0124] By acquiring an operation status data set of all smart devices in a target area, wherein the smart device is an electronic device with data receiving and sending functions and data computing functions, and the operation status data set includes the operation status of each of the smart devices, and the operation status includes an on state, a standby state and an off state; classifying all smart devices according to the operation status to obtain a first smart device set, a second smart device set and a third smart device set; calling a preset recognition model in the preset model library, and configuring the preset recognition model to the smart devices in the first smart device set to obtain a target device, the preset recognition model is an intention recognition model, and the preset model library includes at least two preset recognition models with different algorithms and feature values ​​corresponding to the preset recognition models; controlling the target device to obtain user request information, and obtaining a first recognition result of the target device for the user request information; generating a control instruction according to the first recognition result to control the smart device corresponding to the user request information. Using smart devices as control centers reduces the computing pressure of a single control center and improves the control efficiency of smart devices. When the first smart device set includes at least two smart devices, at least two smart devices are used to receive user instructions (voice instructions, gesture instructions, text instructions, etc.) in different ways, and recognize the user's intentions through different preset recognition models, which can ensure the accuracy of user intention recognition. Since the positions of different smart devices are different, different user instructions can be obtained, and different preset recognition models can be used to recognize different user instructions, which further ensures the accuracy of user intention recognition. At the same time, the position of the device that receives the user's instructions is not fixed, which can facilitate the user to complete the control of any smart device in the smart home network in any area covered by the smart home, thereby improving the user experience.

[0125] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0126] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0127] The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, etc., or any suitable combination of the foregoing.

[0128] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0129] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0130] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described above, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

[0131] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A control method for an intelligent device, characterized in that: include: Acquire an operation status data set of all smart devices in a target area, wherein the smart device is an electronic device having a data transceiver function and a data calculation function, and the operation status data set includes an operation status of each of the smart devices, and the operation status includes an on state, a standby state, and an off state; Classify all smart devices according to the operating status to obtain a first smart device set, a second smart device set, and a third smart device set; Calling a preset recognition model in a preset model library, and configuring the preset recognition model on a smart device in the first smart device set to obtain a target device, wherein the preset recognition model is an intention recognition model, and the preset model library includes at least two preset recognition models with different algorithms and feature values ​​corresponding to the preset recognition models; Controlling the target device to obtain user request information, and obtaining a first recognition result of the target device for the user request information; A control instruction is generated according to the first recognition result to control the smart device corresponding to the user request information.

2. The control method of the intelligent device according to claim 1, characterized in that: The step of obtaining the operating status data set of all smart devices in the target area includes: Divide the user's space into at least two sub-areas according to the building structure; Acquire image data of each sub-region, and input the image data into a human body recognition model to obtain a second recognition result; Determine the sub-area where the user is located based on the second recognition result as the target area; The image data corresponding to the target area is used as the target image data, and the operation status data set of all the smart devices in the target area is obtained according to the target image data.

3. The control method of the intelligent device according to claim 2, characterized in that: The step of using the image data corresponding to the target area as target image data and acquiring the operating status data set of all smart devices in the target area according to the target image data includes: Using the image data corresponding to the target area as target image data, and identifying the type information of each smart device displayed by the target image data; The operating status of each smart device is determined based on the type information of each smart device, the power consumption data of each smart device, and the flow data of each smart device, so as to obtain an operating status data set of all smart devices in the target area.

4. The control method of the intelligent device according to claim 1, characterized in that: The step of calling a preset recognition model in a preset model library, configuring the preset recognition model on a smart device in the first smart device set, obtaining a target device, wherein the preset recognition model is an intention recognition model, and the preset model library includes at least two preset recognition models with different algorithms and feature values ​​corresponding to the preset recognition models, comprises: Obtaining a metadata set of all preset recognition models in a preset model library, wherein the metadata set includes metadata of each preset recognition model, and the metadata includes a model feature mapping relationship; According to the model feature mapping relationship, a feature identifier of the feature on which each preset recognition model depends is obtained; Acquire the feature value of the feature that each preset recognition model depends on according to the feature identifier to obtain a feature value set; A preset recognition model is called out from the preset model library according to the feature value set, and the called out preset recognition model is configured on a smart device in the first smart device set to obtain a target device.

5. The control method of the intelligent device according to claim 4, characterized in that: The step of calling a preset recognition model in a preset model library according to the feature value set, and configuring the called preset recognition model to a smart device in the first smart device set to obtain a target device includes: Calling out a preset recognition model in a preset model library according to the feature value set; Counting the number of called preset recognition models as a first number; Counting the number of smart devices in the first smart device set as a second number; Compare the first number with the second number, and select the smaller number between the first number and the second number as the target number; Selecting a target number of preset recognition models by a random sampling method, and selecting a target number of smart devices to be configured from the first smart device set; The selected preset recognition model is configured on the selected smart device to be configured according to the preset rule to obtain the target device, wherein the preset rule is configured for any preset recognition model and is only configured on one smart device to be configured.

6. The control method of the intelligent device according to claim 1, characterized in that: The step of controlling the target device to obtain user request information and obtaining a first recognition result of the target device for the user request information includes: Acquire a human-computer interaction rule formulated for the target device, and control the target device to acquire user request information according to the human-computer interaction rule; A first recognition result of the target device for the user request information is obtained, where the first recognition result includes a to-be-controlled smart device corresponding to the user request information and a control instruction for the to-be-controlled smart device.

7. The control method of the intelligent device according to claim 1, characterized in that: The method further comprises: Calling a preset recognition model in a preset model library, and configuring the preset recognition model to a smart device in the second smart device set to obtain a candidate device; Controlling the candidate device to obtain user request information, and obtaining a third recognition result of the candidate device for the user request information; A control instruction is generated based on the first recognition result and the third recognition result to control the smart device corresponding to the user request information.

8. A control device for an intelligent device, characterized in that: The control device comprises: A data acquisition module is used to obtain an operation status data set of all smart devices in the target area, wherein the smart device is an electronic device with data receiving and sending functions and data computing functions, and the operation status data set includes the operation status of each smart device, and the operation status includes an on state, a standby state, and an off state; A classification module, used for classifying all the smart devices according to the operating status to obtain a first smart device set, a second smart device set and a third smart device set; A calling module, used to call a preset recognition model in a preset model library, and configure the preset recognition model to a smart device in the first smart device set to obtain a target device, wherein the preset recognition model is an intention recognition model, and the preset model library includes at least two preset recognition models with different algorithms and feature values ​​corresponding to the preset recognition models; an identification module, used to control the target device to obtain user request information, and obtain a first identification result of the target device for the user request information; A control module is used to generate a control instruction according to the first recognition result to control the smart device corresponding to the user request information.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the control method of the intelligent device as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the control method of the intelligent device according to any one of claims 1 to 7 are executed.

Images