Control method and device of intelligent cooking device, equipment and medium

Abstract

The embodiment of the invention discloses a control method and device for an intelligent cooking device, equipment and a medium, and the method comprises the steps: obtaining a sound signal for the intelligent cooking device, separating the sound signal into sub-sound signals from different sound sources, and obtaining a sub-sound signal set; classifying each sub-sound signal in the sub-sound signal set according to a preset voiceprint feature to obtain a sub-sound signal matched with the preset voiceprint feature as a first sound signal and a sub-sound signal not matched with the preset voiceprint feature as a second sound signal; generating an initial control instruction for the intelligent cooking device based on first content information of the first sound signal; second content information of the second sound signal is obtained, the correlation degree between the second content information and a preset keyword is calculated, if the correlation degree is larger than or equal to a threshold value, the initial control instruction is updated according to the second content information, a target control instruction is obtained, and control over the intelligent cooking device is completed.

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 cooking 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. 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 a day. The cooking utensils, ingredients, seasonings, and processes used in different dishes in a meal are also diverse. 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, or the intelligent cooking equipment can only complete the preparation of dishes according to the preset fixed steps, making the dishes single, and solving the problem of single dishes often requires setting various preset steps to correspond to different dishes, but setting various preset steps brings a lot of preset work and a lot of storage pressure, which undoubtedly can no longer meet the fast pace of life of people today.

[0003] At the same time, the control method of smart equipment is becoming more and more simple. Now it is common to send instructions to smart equipment by voice. However, when a user sends a voice instruction to a smart device, what the smart device receives is often not a single voice instruction of the user. For example, when a user is watching a dish making video, he sends a voice instruction to a smart cooking device. What the smart cooking device receives is the sound of the dish making video and the voice of the user. However, the sound of the dish making video can easily generate erroneous instructions, causing the smart cooking device to operate incorrectly. Summary of the invention

[0004] In view of this, the present invention provides a control method, device, equipment and medium for an intelligent cooking device, which are used to solve the problem in the prior art that the intelligent cooking device is not very intelligent and is easily disturbed when receiving voice commands.

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

[0006] Acquire a sound signal for the intelligent cooking device, and separate the sound signal into sub-sound signals originating from different sound sources to obtain a sub-sound signal set corresponding to the sound signal;

[0007] Classifying each sub-sound signal in the sub-sound signal set according to a preset voiceprint feature, obtaining a sub-sound signal matching the preset voiceprint feature as a first sound signal, and a sub-sound signal not matching the preset voiceprint feature as a second sound signal;

[0008] generating an initial control instruction for the intelligent cooking device based on the first content information of the first sound signal;

[0009] Acquiring second content information of the second sound signal, and calculating a correlation between the second content information and a preset keyword;

[0010] If the correlation degree is greater than or equal to a threshold, the initial control instruction is updated according to the second content information to obtain a target control instruction, and the target control instruction is used to control the intelligent cooking device.

[0011] Optionally, the step of acquiring a sound signal for the intelligent cooking device 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 recognition result;

[0014] Determine the sub-area where the user is located based on the 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 of all the smart devices in the target area are obtained according to the target image data to obtain an operation status data set, wherein 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, and the smart device is an electronic device with a sound receiving function and a data computing function;

[0016] 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, wherein the operating status of each smart device in the first smart device set is an on state;

[0017] A sound signal for a smart cooking device is obtained based on each smart device in the first smart device set.

[0018] Optionally, the step of separating the sound signal into sub-sound signals originating from different sound sources to obtain a sub-sound signal set corresponding to the sound signal comprises:

[0019] Separating the sound signal into first sub-sound signals originating from different sound sources by using independent component analysis technology to obtain a first sub-sound signal set;

[0020] Separating the sound signal into second sub-sound signals originating from different sound sources by a small amount of overlap between time-frequency components to obtain a second sub-sound signal set;

[0021] The second sub-sound signal set is modified based on the first sub-sound signal set to obtain a sub-sound signal set corresponding to the sound signal.

[0022] Optionally, the step of classifying the sub-sound signals in the sub-sound signal set according to a preset voiceprint feature to obtain the sub-sound signals matching the preset voiceprint feature as the first sound signal, and the sub-sound signals not matching the preset voiceprint feature as the second sound signal includes:

[0023] Inputting each sub-sound signal in the sub-sound signal set into a preset voiceprint recognition decision model to obtain a recognition score of each sub-sound signal in the sub-sound signal set, wherein the preset voiceprint recognition decision model is a support vector machine model having the preset voiceprint features;

[0024] taking the sub-sound signal in the sub-sound signal set whose recognition score is greater than or equal to the recognition threshold as the first sound signal matching the preset voiceprint feature;

[0025] The sub-sound signal in the sub-sound signal set whose recognition score is less than the recognition threshold is used as a second sound signal that does not match the preset voiceprint feature.

[0026] Optionally, the step of generating an initial control instruction for the intelligent cooking device based on the first content information of the first sound signal includes:

[0027] Acquire first content information of the first sound signal, and determine identity information and control information of the cooking device to be controlled based on the first content information;

[0028] The identity information and the control information are input into a preset control instruction template to obtain an initial control instruction for the intelligent cooking device. The preset control instruction template includes basic information for constructing the control instruction and control content information for implementing the control process. The control content information includes preset identity information, preset control information and preset operation information of the cooking device to be controlled.

[0029] Optionally, the step of acquiring the second content information of the second sound signal and calculating the relevance between the second content information and a preset keyword includes:

[0030] Acquiring second content information of the second sound signal by using a text recognition technology;

[0031] Performing word segmentation processing on the content information to obtain a phrase set corresponding to the content information;

[0032] The association degree between the preset keyword and the phrase set is calculated as the association degree between the content information and the preset keyword.

[0033] Optionally, if the correlation degree is greater than or equal to a threshold, the step of updating the initial control instruction according to the second content information to obtain a target control instruction includes:

[0034] If the relevance is greater than or equal to a threshold, sorting the phrases in the phrase set in chronological order to obtain a target phrase set;

[0035] Using the verbs in the target phrase set as separators to generate a phrase set;

[0036] generating operation information for the intelligent cooking device according to the phrase set;

[0037] The initial control instruction is updated based on the operation information to obtain a target control instruction.

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

[0039] A data acquisition module, used for acquiring a sound signal for the intelligent cooking device, and separating the sound signal into sub-sound signals originating from different sound sources to obtain a sub-sound signal set;

[0040] a voice recognition module, configured to classify each sub-sound signal in the sub-sound signal set according to a preset voiceprint feature, obtain a sub-sound signal matching the preset voiceprint feature as a first sound signal, and obtain a sub-sound signal not matching the preset voiceprint feature as a second sound signal;

[0041] An instruction generating module, configured to generate an initial control instruction for the intelligent cooking device based on the first content information of the first sound signal;

[0042] an identification module, configured to obtain second content information of the second sound signal, and calculate a correlation between the second content information and a preset keyword;

[0043] A control module is used to update the initial control instruction according to the second content information to obtain a target control instruction if the correlation degree is greater than or equal to a threshold, and the target control instruction is used to control the intelligent cooking device.

[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 cooking 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 cooking device as described above are executed.

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

[0047] A sound signal for an intelligent cooking device is obtained, and the sound signal is separated into sub-sound signals originating from different sound sources, so as to obtain a sub-sound signal set corresponding to the sound signal; each sub-sound signal in the sub-sound signal set is classified according to a preset voiceprint feature, so as to obtain a sub-sound signal matching the preset voiceprint feature as a first sound signal, and a sub-sound signal not matching the preset voiceprint feature as a second sound signal; an initial control instruction for the intelligent cooking device is generated based on the first content information of the first sound signal; the second content information of the second sound signal is obtained, and the correlation between the second content information and a preset keyword is calculated; if the correlation is greater than or equal to a threshold, the initial control instruction is updated according to the second content information to obtain a target control instruction, and the target control instruction is used to control the intelligent cooking device. The sound signal is separated into sub-sound signals originating from different sound sources, that is, the user sound information and the interference sound (background sound, sound emitted by other equipment, etc.) are separated, and the influence of the interference sound on the intelligent cooking device is avoided by only responding to the user sound information, thereby reducing the false triggering of the intelligent cooking device. An initial control instruction for the intelligent cooking device is generated based on the first sound signal, that is, the intelligent cooking device to be controlled is determined by the user sound information, and it is determined whether to start the intelligent cooking device to be controlled. If the correlation is greater than or equal to a threshold, the initial control instruction is updated according to the second content information, that is, the initial control instruction is updated by the interference sound (the sound of the dish making video), so that the intelligent cooking device to be controlled learns the dish making process without manual operation, thereby improving the intelligence of the intelligent cooking process. 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 This is an application scenario diagram of a control method for an intelligent cooking device provided in an embodiment of the present application;

[0051] Figure 2 It is a scene diagram of human-computer interaction in a control method of an intelligent cooking device provided in an embodiment of the present application;

[0052] Figure 3 is a flow chart of a control method of an intelligent cooking device provided in an embodiment of the present application;

[0053] Figure 4 This is an application scenario diagram of a control method for an intelligent cooking device provided in an embodiment of the present application;

[0054] Figure 5 This is an application interface diagram of a control method for an intelligent cooking device provided in an embodiment of the present application;

[0055] Figure 6 This is an application scenario diagram of a control method for an intelligent cooking device provided in an embodiment of the present application;

[0056] Figure 7 is a structural schematic diagram of a control device of an intelligent cooking device provided in an embodiment of the present application;

[0057] Figure 8 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0058] Fig. 9 It is a structural schematic diagram of a computer-readable storage medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] 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.

[0060] like Figure 1As shown, the embodiment of the present application provides an application scenario of a control method for an intelligent cooking device, and the application scenario includes: an intelligent device 101, a server 102, a gateway 104, an intelligent cooking device 103, and a router 105. Among them, the intelligent device 101 can be any electronic device with communication and sound receiving functions, such as: a smart phone, a desktop computer, a laptop computer, a tablet computer or other intelligent communication devices with network connection functions. The server 102 can be a network access server, a database server, a cloud server, etc.

[0061] Exemplarily, the gateway 104 can be built based on a standard wireless technology (ZigBee) protocol, and the smart cooking device 103 can be a device pre-added to the gateway 104. For example, the smart cooking device 103 can be a device in the kit to which the gateway 104 belongs when the gateway 104 leaves the factory; or it can be a device subsequently connected to the gateway 104 through user operation.

[0062] Exemplarily, a client capable of managing a smart home is installed in the smart device 101 , and the client may be an application client (such as mobile phone software) or a web client, which is not limited here, and the user interacts with the smart device 101 .

[0063] Exemplarily, the smart device 101 may be an electronic device having a sound receiving function and a data computing function, that is, an electronic device having a function of acquiring a sound signal for a smart cooking device.

[0064] Exemplarily, the intelligent cooking device 103 can establish a network connection with the gateway 104 based on the ZigBee protocol, thereby joining the ZigBee network.

[0065] The gateway 104 and the smart device 101 can be connected to the router 105 and connected to the Ethernet through the router 105. The router 105 can access the server through a wired or wireless communication connection. For example, the gateway 104 and the smart device 101 can store the acquired sound information in the server 102. Optionally, the smart device 101 can also establish a network connection with the server 102 through mobile phone communication technology (2G / 3G / 4G / 5G), wireless communication (WiFi), etc., so as to obtain data sent by the server 102.

[0066] For example, Figure 1 The LAN path shown indicates that the smart device 101 is in the same LAN as the router 105 and the gateway 104, and the WAN path indicates that the smart device 101 is in the same LAN as the router 105 and the gateway 104. When the smart device 101 is in the same LAN as the router 105 and the gateway 104, the smart device 101 can Figure 1 The local area network path shown interacts with the gateway 104 and the smart cooking device 103 connected to the gateway 104; Figure 1 The wide area network path shown interacts with the gateway 104 and the smart cooking device 103 connected to the gateway 104. When the smart device 101 is not in the same local area network as the router 105 and the gateway 104, the smart device 101 can communicate with the router 105 through the following example: Figure 1 The wide area network path shown interacts with the gateway 104 and the smart cooking device 103 connected to the gateway 104.

[0067] In one scenario, Figure 2 As shown, the human-computer interaction process is as follows: the smart device 101 obtains a sound signal for the smart cooking device, and separates the sound signal into sub-sound signals originating from different sound sources to obtain a sub-sound signal set corresponding to the sound signal; classifies each sub-sound signal in the sub-sound signal set according to a preset voiceprint feature, obtains a sub-sound signal matching the preset voiceprint feature as a first sound signal, and a sub-sound signal not matching the preset voiceprint feature as a second sound signal; generates an initial control instruction for the smart cooking device based on the first content information of the first sound signal, the initial control instruction includes the smart cooking device and control information targeted by the first sound signal; obtains the second content information of the second sound signal, and calculates the correlation between the second content information and the preset keyword; if the correlation is greater than or equal to a threshold, generates operation information according to the second content information, and updates the initial control instruction to obtain a target control instruction, and the target control instruction is used to control the smart cooking device.

[0068] In one scenario, the server 102 is used for data interaction between the smart device 101 and the smart cooking device 103; at the same time, in order to reduce the computing pressure of the smart device 101, a sound signal for the smart cooking device is obtained, and the sound signal is separated into sub-sound signals originating from different sound sources to obtain a sub-sound signal set corresponding to the sound signal; each sub-sound signal in the sub-sound signal set is classified according to a preset voiceprint feature to obtain a sub-sound signal matching the preset voiceprint feature as a first sound signal, and a sub-sound signal not matching the preset voiceprint feature as a second sound signal; an initial control instruction for the smart cooking device is generated based on the first content information of the first sound signal; the second content information of the second sound signal is obtained, and the correlation between the second content information and the preset keyword is calculated; if the correlation is greater than or equal to a threshold, the initial control instruction is updated according to the second content information to obtain a target control instruction, and the process of using the target control instruction to control the smart cooking device can also be performed in the server 102.

[0069] In one scenario, the smart device 101 may directly interact with the smart cooking device 103 for data, and the smart device 101 may also forward data through the server 102 to interact with the smart cooking device 103 indirectly for data.

[0070] like Figure 3 As shown, the embodiment of the present application provides a control method of an intelligent cooking device, including:

[0071] S101, obtaining a sound signal for an intelligent cooking device, and separating the sound signal into sub-sound signals originating from different sound sources, to obtain a sub-sound signal set corresponding to the sound signal;

[0072] Exemplarily, when obtaining a sound signal for a smart cooking device, the sound signal for the smart cooking device can be obtained based on the wake-up method of the smart cooking device. For example, the smart cooking device needs to detect whether there is a user in a preset area (when the user is in front of the smart cooking device), and the smart cooking device is awakened and enters a data collection mode, thereby obtaining the sound signal for the smart cooking device.

[0073] Exemplarily, when obtaining sound signals for smart cooking devices, an intention recognition method can also be used to identify the user's intention. When the user's intention is related to cooking, a sound signal for the smart cooking device is obtained. For example, when the user's intention is recognized as "eating", the sound command sent by the user is considered to be a sound command for the smart cooking device, and then the sound signal for the smart cooking device is obtained. The smart cooking device is a smart device related to cooking, such as a smart rice cooker, a smart cooking machine, etc.

[0074] Exemplarily, when acquiring a sound signal for a smart cooking device, an initial sound signal may also be collected, and it may be identified whether the initial sound signal includes specific smart cooking equipment. For example, if the collected initial sound signal includes "start the smart rice cooker after twenty minutes", where "smart rice cooker" is a specific smart cooking equipment, the collected initial sound signal may be used as a sound signal for the smart cooking device.

[0075] Exemplarily, assuming that the sound signal is a mixed sound composed of the user's voice and the sound of a TV program, the sound signal is separated into the user's voice (the sound source is the user's sub-sound signal) and the sound of the TV program (the sound source is the TV's sub-sound signal) through sound separation technology.

[0076] S102, classifying each sub-sound signal in the sub-sound signal set according to a preset voiceprint feature, obtaining a sub-sound signal matching the preset voiceprint feature as a first sound signal, and a sub-sound signal not matching the preset voiceprint feature as a second sound signal;

[0077] Exemplarily, the preset voiceprint feature may be a voiceprint feature, a voice color feature, a pronunciation habit feature, etc. When the preset voiceprint feature is a preset voiceprint feature, the first voiceprint feature of the user is obtained according to the sub-sound signal of the user, and the second voiceprint feature of the TV is obtained according to the sub-sound signal of the TV, and then the preset voiceprint feature is matched with the first voiceprint feature and the second voiceprint feature respectively to obtain a sub-sound signal that matches the preset voiceprint feature as the first sound signal, and a sub-sound signal that does not match the preset voiceprint feature as the second sound signal.

[0078] S103, generating an initial control instruction for the intelligent cooking device based on the first content information of the first sound signal;

[0079] Exemplarily, the initial control instruction for the intelligent cooking device is generated only in response to the sub-sound signal that matches the preset voiceprint feature, so as to avoid erroneous control of the intelligent cooking device by the sub-sound signal that does not match the preset voiceprint feature.

[0080] S104, obtaining second content information of the second sound signal, and calculating the relevance between the second content information and a preset keyword;

[0081] Exemplarily, the second sound signal is converted into text information (content information), and the correlation between the text information and the preset keywords is calculated, wherein the preset keywords are words related to cooking, such as fry, stir-fry, cook, deep-fry, heat, rice, oil, salt, etc.

[0082] For example, Figure 4 As shown, the second sound signal is converted into text information (content information), that is, the text information is "Help me make a dish of scrambled eggs with tomatoes", the text information is matched with the words in the preset vocabulary, and it is determined that the word associated with the preset vocabulary is "fry", and then the intelligent cooking device is controlled according to "fry", and the preset vocabulary is a data table established based on the preset keywords.

[0083] S105: If the correlation degree is greater than or equal to a threshold, update the initial control instruction according to the second content information to obtain a target control instruction, where the target control instruction is used to control the intelligent cooking device.

[0084] Exemplarily, if the degree of association is greater than or equal to a threshold, the second content information is considered to be information related to cooking, such as information about a dish making video, and the initial control instructions are then updated according to the information about the dish making video, so that the updated initial control instructions can control the intelligent cooking device according to a process corresponding to the information about the dish making video.

[0085] For example, Figure 5 As shown, the information of the dish making video is the information of the making video of scrambled eggs with tomatoes, and the interface of the updated initial control instruction includes: starting the intelligent cooking device (cooking device), the working steps of the intelligent cooking device, that is, adding oil, tomatoes, eggs, and salt to the intelligent cooking device in sequence.

[0086] A sound signal for an intelligent cooking device is obtained, and the sound signal is separated into sub-sound signals originating from different sound sources, so as to obtain a sub-sound signal set corresponding to the sound signal; each sub-sound signal in the sub-sound signal set is classified according to a preset voiceprint feature, so as to obtain a sub-sound signal matching the preset voiceprint feature as a first sound signal, and a sub-sound signal not matching the preset voiceprint feature as a second sound signal; an initial control instruction for the intelligent cooking device is generated based on the first content information of the first sound signal; the second content information of the second sound signal is obtained, and the correlation between the second content information and a preset keyword is calculated; if the correlation is greater than or equal to a threshold, the initial control instruction is updated according to the second content information to obtain a target control instruction, and the target control instruction is used to control the intelligent cooking device. The sound signal is separated into sub-sound signals originating from different sound sources, that is, the user sound information and the interference sound (background sound, sound emitted by other equipment, etc.) are separated, and the influence of the interference sound on the intelligent cooking device is avoided by only responding to the user sound information, thereby reducing the false triggering of the intelligent cooking device. An initial control instruction for the intelligent cooking device is generated based on the first sound signal, that is, the intelligent cooking device to be controlled is determined by the user sound information, and it is determined whether to start the intelligent cooking device to be controlled. If the correlation is greater than or equal to a threshold, the initial control instruction is updated according to the second content information, that is, the initial control instruction is updated by the interference sound (the sound of the dish making video), so that the intelligent cooking device to be controlled learns the dish making process without manual operation, thereby improving the intelligence of the intelligent cooking process.

[0087] In a possible implementation, the step of acquiring a sound signal for the intelligent cooking device includes:

[0088] Divide the user's space into at least two sub-areas according to the building structure;

[0089] Acquire image data of each sub-region, and input the image data into a human body recognition model to obtain a recognition result;

[0090] Determine the sub-area where the user is located based on the recognition result as the target area;

[0091] The image data corresponding to the target area is used as the target image data, and the operation status data of all the smart devices in the target area are obtained according to the target image data to obtain an operation status data set, wherein 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, and the smart device is an electronic device with a sound receiving function and a data computing function;

[0092] 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, wherein the operating status of each smart device in the first smart device set is an on state;

[0093] A sound signal for a smart cooking device is obtained based on each smart device in the first smart device set.

[0094] 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.

[0095] 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.

[0096] 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;

[0097] 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.

[0098] Exemplarily, the process of constructing a human body recognition model is: constructing a feature interaction network, a local feature enhancement network and a local feature optimization network, with a residual neural network as the backbone 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.

[0099] Exemplarily, electronic devices that are in the area where the user is located, in the started state, and capable of receiving sound are taken as target smart devices (each smart device in the first smart device set), and sound signals for the smart cooking device are obtained based on each smart device in the first smart device set, which facilitates the acquisition of sound signals and enables users to perform voice control on the smart cooking device in any space, that is, without receiving sound signals through fixed devices, and thus there is no need for users to deliberately approach the fixed devices, thereby improving user experience.

[0100] Exemplarily, the second smart device set and / or the third smart device set are used as alternative smart device sets, and electronic devices in the user's area, in standby mode and / or in shutdown mode, and capable of receiving sound are used as target smart devices (each smart device in the second smart device set and / or the third smart device set). Based on each smart device in the second smart device set and / or the third smart device set, sound signals for the smart cooking device are obtained to facilitate the acquisition of sound signals, so that the user can perform voice control on the smart cooking device in any space, and smart devices in the second smart device set and / or the third smart device set that are closer to the user can be selected to obtain sound signals for the smart cooking device to ensure the clarity of the sound signal.

[0101] In a possible implementation manner, the step of separating the sound signal into sub-sound signals originating from different sound sources to obtain a sub-sound signal set corresponding to the sound signal includes:

[0102] Separating the sound signal into first sub-sound signals originating from different sound sources by using independent component analysis technology to obtain a first sub-sound signal set;

[0103] Separating the sound signal into second sub-sound signals originating from different sound sources by a small amount of overlap between time-frequency components to obtain a second sub-sound signal set;

[0104] The second sub-sound signal set is modified based on the first sub-sound signal set to obtain a sub-sound signal set corresponding to the sound signal.

[0105] Exemplarily, independent component analysis (ICA) is a method of calculation using statistical principles, which is a linear transformation process that separates data or signals into linear combinations of statistically independent non-Gaussian signal sources, and then separates the sound signal into first sub-sound signals originating from different sound sources to obtain a first sub-sound signal set.

[0106] Exemplarily, in order to avoid accidental errors between the independent component analysis technology and the technology with a small amount of overlap between time-frequency components, the second sub-sound signal set is corrected based on the first sub-sound signal set. For example, the first sub-sound signal set includes the sub-sound signal of sound source A and the sub-sound signal of sound source B, and the second sub-sound signal set includes the sub-sound signal of sound source A, the sub-sound signal of sound source B, and the sub-sound signal of sound source C. The first sub-sound signal set and the second sub-sound signal set are merged to obtain a sub-sound signal set corresponding to the sound signal, and the sub-sound signal set corresponding to the sound signal includes the sub-sound signal of sound source A, the sub-sound signal of sound source B, and the sub-sound signal of sound source C.

[0107] In a possible implementation, the step of classifying the sub-sound signals in the sub-sound signal set according to the preset voiceprint feature, obtaining the sub-sound signals matching the preset voiceprint feature as the first sound signal, and the sub-sound signals not matching the preset voiceprint feature as the second sound signal, includes:

[0108] Inputting each sub-sound signal in the sub-sound signal set into a preset voiceprint recognition decision model to obtain a recognition score of each sub-sound signal in the sub-sound signal set, wherein the preset voiceprint recognition decision model is a support vector machine model having the preset voiceprint features;

[0109] taking the sub-sound signal in the sub-sound signal set whose recognition score is greater than or equal to the recognition threshold as the first sound signal matching the preset voiceprint feature;

[0110] The sub-sound signal in the sub-sound signal set whose recognition score is less than the recognition threshold is used as a second sound signal that does not match the preset voiceprint feature.

[0111] Exemplarily, the audio corresponding to the preset voiceprint feature is used as a positive training sample, and the audio played on TV, the audio of the device running, etc. are collected as negative training samples, and trained using a machine learning model to obtain a voiceprint recognition decision model, and the machine learning model is a support vector machine (SVM) model.

[0112] Exemplarily, each sub-sound signal in the sub-sound signal set is input into a preset voiceprint recognition decision model to obtain a recognition score for each sub-sound signal in the sub-sound signal set. For example, the recognition score of the sub-sound signal of sound source A is 80, when the recognition threshold is 70, the sub-sound signal of sound source A is considered to be the first sound signal that matches the preset voiceprint feature. The recognition score of the sub-sound signal of sound source B is 60, then the sub-sound signal of sound source B is considered to be the second sound signal that does not match the preset voiceprint feature.

[0113] For example, Figure 6 As shown, two users (user C and user D) speak in different directions in the same room, each sub-sound signal in the sub-sound signal set of user C is input into a preset voiceprint recognition decision model to obtain a third recognition score of each sub-sound signal in the sub-sound signal set, each sub-sound signal in the sub-sound signal set of user D is input into a preset voiceprint recognition decision model to obtain a fourth recognition score of each sub-sound signal in the sub-sound signal set, the third recognition score is compared with the fourth recognition score, and the sound with a higher recognition score value is selected as the sound to be responded to, and then it is determined which user's voice to respond to and the other user's voice is ignored. For example, if the third recognition score is greater than the fourth recognition score, the voice of user C is responded to.

[0114] In a possible implementation, the step of generating an initial control instruction for the intelligent cooking device based on the first content information of the first sound signal includes:

[0115] Acquire first content information of the first sound signal, and determine identity information and control information of the cooking device to be controlled based on the first content information;

[0116] The identity information and the control information are input into a preset control instruction template to obtain an initial control instruction for the intelligent cooking device. The preset control instruction template includes basic information for constructing the control instruction and control content information for implementing the control process. The control content information includes preset identity information, preset control information and preset operation information of the cooking device to be controlled.

[0117] Exemplarily, the first sound signal is converted into text information (first content information), for example, "start cooking", then the cooking device to be controlled is a smart device related to "cooking" (smart rice cooker, smart range hood, smart cooking equipment, etc.), and then the identity information of the smart rice cooker, smart range hood, smart cooking equipment, etc. is determined, and "start" is used as the control information.

[0118] Exemplarily, the preset control instruction template is, for example, “preset identity information of the cooking device to be controlled - preset control information - preset operation information”, wherein “-” represents basic information for constructing the control instruction, such as a general code.

[0119] Exemplarily, by constructing the process of initial control instructions through preset control instruction templates, the writing of general code is reduced, thereby reducing the time required to generate initial control instructions, improving the efficiency of generating initial control instructions, and also reducing the amount of data calculation. For example, the writing of code requires testing, while the code that has been tested does not need testing.

[0120] In a possible implementation manner, the step of acquiring the second content information of the second sound signal and calculating the relevance between the second content information and a preset keyword includes:

[0121] Acquiring second content information of the second sound signal by using a text recognition technology;

[0122] Performing word segmentation processing on the content information to obtain a phrase set corresponding to the content information;

[0123] The association degree between the preset keyword and the phrase set is calculated as the association degree between the content information and the preset keyword.

[0124] Exemplarily, the second content information of the second sound signal is obtained through text recognition technology (speech-to-text conversion technology), and the content information is segmented according to parts of speech. For example, verbs in the content information are extracted to obtain a verb set, and nouns in the content information are extracted to obtain a noun set. The verb set and the noun set are then merged to obtain a phrase set corresponding to the content information.

[0125] Exemplarily, the preset keywords can be set according to actual needs, for example, the preset keywords can be set according to regional dietary habit data, or the preset keywords can be set according to user dietary habit data. The process of calculating the association between the preset keywords and the phrase set can be a statistical process. For example, the number of first appearances of the first preset keyword (fry) in the phrase set is counted, and the number of second appearances of the second preset keyword (salt) in the phrase set is counted. The sum of the first number and the second number is used as the dividend, and the number of all words in the phrase set is used as the divisor to obtain the quotient, and the quotient is used as the association between the content information and the preset keywords.

[0126] In a possible implementation manner, if the correlation degree is greater than or equal to a threshold, the step of updating the initial control instruction according to the second content information to obtain a target control instruction includes:

[0127] If the relevance is greater than or equal to a threshold, sorting the phrases in the phrase set in chronological order to obtain a target phrase set;

[0128] Using the verbs in the target phrase set as separators to generate a phrase set;

[0129] generating operation information for the intelligent cooking device according to the phrase set;

[0130] The initial control instruction is updated based on the operation information to obtain a target control instruction.

[0131] Exemplarily, if the correlation is greater than or equal to a threshold, the phrases in the phrase set are sorted in the chronological order of their appearance to obtain a target phrase set. For example, if the phrase set is "fry, add, add, salt, vinegar", the phrases in the phrase set are sorted in the chronological order of their appearance to obtain a target phrase set "add, salt, add, vinegar, fry".

[0132] Exemplarily, the verbs in the target phrase set "add salt, add vinegar, stir-fry" are used as separators to generate a phrase set of "(add salt), (add vinegar), (stir-fry)", and then the operation information for the intelligent cooking device is generated according to the phrase set, which is to add salt first, then add vinegar, and then stir-fry. The initial control instruction ("identity information of the cooking device to be controlled - control information - preset operation information") is updated based on the operation information to obtain the target control instruction ("identity information of the cooking device to be controlled - control information - add salt first, then add vinegar, and then stir-fry").

[0133] Exemplarily, the initial control instruction is updated through the second sound information (the sound of the dish making video, etc.), so that the intelligent cooking device to be controlled learns the dish making process without manual operation, thereby improving the intelligence of the intelligent cooking process.

[0134] In a possible implementation, Figure 7 As shown, an embodiment of the present application provides a control device for an intelligent cooking device, the device comprising:

[0135] The data acquisition module 201 is used to obtain a sound signal for the intelligent cooking device, and separate the sound signal into sub-sound signals originating from different sound sources to obtain a sub-sound signal set;

[0136] A voice recognition module 202 is used to classify each sub-sound signal in the sub-sound signal set according to a preset voiceprint feature, obtain a sub-sound signal matching the preset voiceprint feature as a first sound signal, and obtain a sub-sound signal not matching the preset voiceprint feature as a second sound signal;

[0137] An instruction generating module 203, configured to generate an initial control instruction for the intelligent cooking device based on the first content information of the first sound signal;

[0138] The recognition module 204 is used to obtain the second content information of the second sound signal and calculate the relevance between the second content information and the preset keyword;

[0139] The control module 205 is configured to update the initial control instruction according to the second content information to obtain a target control instruction if the correlation degree is greater than or equal to a threshold, and the target control instruction is used to control the intelligent cooking device.

[0140] A sound signal for an intelligent cooking device is obtained, and the sound signal is separated into sub-sound signals originating from different sound sources, so as to obtain a sub-sound signal set corresponding to the sound signal; each sub-sound signal in the sub-sound signal set is classified according to a preset voiceprint feature, so as to obtain a sub-sound signal matching the preset voiceprint feature as a first sound signal, and a sub-sound signal not matching the preset voiceprint feature as a second sound signal; an initial control instruction for the intelligent cooking device is generated based on the first content information of the first sound signal; the second content information of the second sound signal is obtained, and the correlation between the second content information and a preset keyword is calculated; if the correlation is greater than or equal to a threshold, the initial control instruction is updated according to the second content information to obtain a target control instruction, and the target control instruction is used to control the intelligent cooking device. The sound signal is separated into sub-sound signals originating from different sound sources, that is, the user sound information and the interference sound (background sound, sound emitted by other equipment, etc.) are separated, and the influence of the interference sound on the intelligent cooking device is avoided by only responding to the user sound information, thereby reducing the false triggering of the intelligent cooking device. An initial control instruction for the intelligent cooking device is generated based on the first sound signal, that is, the intelligent cooking device to be controlled is determined by the user sound information, and it is determined whether to start the intelligent cooking device to be controlled. If the correlation is greater than or equal to a threshold, the initial control instruction is updated according to the second content information, that is, the initial control instruction is updated by the interference sound (the sound of the dish making video), so that the intelligent cooking device to be controlled learns the dish making process without manual operation, thereby improving the intelligence of the intelligent cooking process.

[0141] In a possible implementation, Figure 8As 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 a sound signal for an intelligent cooking device, and separating the sound signal into sub-sound signals originating from different sound sources to obtain a sub-sound signal set corresponding to the sound signal; classifying each sub-sound signal in the sub-sound signal set according to a preset voiceprint feature to obtain a sub-sound signal matching the preset voiceprint feature as a first sound signal, and a sub-sound signal not matching the preset voiceprint feature as a second sound signal; generating an initial control instruction for the intelligent cooking device based on first content information of the first sound signal; obtaining second content information of the second sound signal, and calculating a correlation between the second content information and a preset keyword; if the correlation is greater than or equal to a threshold, updating the initial control instruction according to the second content information to obtain a target control instruction, and the target control instruction is used to control the intelligent cooking device.

[0142] A sound signal for an intelligent cooking device is obtained, and the sound signal is separated into sub-sound signals originating from different sound sources, so as to obtain a sub-sound signal set corresponding to the sound signal; each sub-sound signal in the sub-sound signal set is classified according to a preset voiceprint feature, so as to obtain a sub-sound signal matching the preset voiceprint feature as a first sound signal, and a sub-sound signal not matching the preset voiceprint feature as a second sound signal; an initial control instruction for the intelligent cooking device is generated based on the first content information of the first sound signal; the second content information of the second sound signal is obtained, and the correlation between the second content information and a preset keyword is calculated; if the correlation is greater than or equal to a threshold, the initial control instruction is updated according to the second content information to obtain a target control instruction, and the target control instruction is used to control the intelligent cooking device. The sound signal is separated into sub-sound signals originating from different sound sources, that is, the user sound information and the interference sound (background sound, sound emitted by other equipment, etc.) are separated, and the influence of the interference sound on the intelligent cooking device is avoided by only responding to the user sound information, thereby reducing the false triggering of the intelligent cooking device. An initial control instruction for the intelligent cooking device is generated based on the first sound signal, that is, the intelligent cooking device to be controlled is determined by the user sound information, and it is determined whether to start the intelligent cooking device to be controlled. If the correlation is greater than or equal to a threshold, the initial control instruction is updated according to the second content information, that is, the initial control instruction is updated by the interference sound (the sound of the dish making video), so that the intelligent cooking device to be controlled learns the dish making process without manual operation, thereby improving the intelligence of the intelligent cooking process.

[0143] In a possible implementation, Fig. 9 As shown, an embodiment of the present application provides a computer-readable storage medium 400, on which a computer program 411 is stored. When the computer program 411 is executed by a processor, it is implemented as follows: obtaining a sound signal for an intelligent cooking device, and separating the sound signal into sub-sound signals originating from different sound sources, to obtain a sub-sound signal set corresponding to the sound signal; classifying each sub-sound signal in the sub-sound signal set according to a preset voiceprint feature, to obtain a sub-sound signal matching the preset voiceprint feature as a first sound signal, and a sub-sound signal not matching the preset voiceprint feature as a second sound signal; generating an initial control instruction for the intelligent cooking device based on first content information of the first sound signal; obtaining second content information of the second sound signal, and calculating a correlation between the second content information and a preset keyword; if the correlation is greater than or equal to a threshold, updating the initial control instruction according to the second content information to obtain a target control instruction, and the target control instruction is used to control the intelligent cooking device.

[0144] A sound signal for an intelligent cooking device is obtained, and the sound signal is separated into sub-sound signals originating from different sound sources, so as to obtain a sub-sound signal set corresponding to the sound signal; each sub-sound signal in the sub-sound signal set is classified according to a preset voiceprint feature, so as to obtain a sub-sound signal matching the preset voiceprint feature as a first sound signal, and a sub-sound signal not matching the preset voiceprint feature as a second sound signal; an initial control instruction for the intelligent cooking device is generated based on the first content information of the first sound signal; the second content information of the second sound signal is obtained, and the correlation between the second content information and a preset keyword is calculated; if the correlation is greater than or equal to a threshold, the initial control instruction is updated according to the second content information to obtain a target control instruction, and the target control instruction is used to control the intelligent cooking device. The sound signal is separated into sub-sound signals originating from different sound sources, that is, the user sound information and the interference sound (background sound, sound emitted by other equipment, etc.) are separated, and the influence of the interference sound on the intelligent cooking device is avoided by only responding to the user sound information, thereby reducing the false triggering of the intelligent cooking device. An initial control instruction for the intelligent cooking device is generated based on the first sound signal, that is, the intelligent cooking device to be controlled is determined by the user sound information, and it is determined whether to start the intelligent cooking device to be controlled. If the correlation is greater than or equal to a threshold, the initial control instruction is updated according to the second content information, that is, the initial control instruction is updated by the interference sound (the sound of the dish making video), so that the intelligent cooking device to be controlled learns the dish making process without manual operation, thereby improving the intelligence of the intelligent cooking process.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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 cooking device, characterized in that: include: Acquire a sound signal for the intelligent cooking device, and separate the sound signal into sub-sound signals originating from different sound sources to obtain a sub-sound signal set corresponding to the sound signal; Classifying each sub-sound signal in the sub-sound signal set according to a preset voiceprint feature, obtaining a sub-sound signal matching the preset voiceprint feature as a first sound signal, and a sub-sound signal not matching the preset voiceprint feature as a second sound signal; generating an initial control instruction for the intelligent cooking device based on the first content information of the first sound signal; Acquiring second content information of the second sound signal, and calculating a correlation between the second content information and a preset keyword; If the correlation degree is greater than or equal to a threshold, the initial control instruction is updated according to the second content information to obtain a target control instruction, and the target control instruction is used to control the intelligent cooking device.

2. The control method of the intelligent cooking device according to claim 1, characterized in that: The step of obtaining a sound signal for the intelligent cooking device 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 recognition result; Determine the sub-area where the user is located based on the 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 of all the smart devices in the target area are obtained according to the target image data to obtain an operation status data set, wherein 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, and the smart device is an electronic device with a sound receiving function and a data computing function; 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, wherein the operating status of each smart device in the first smart device set is an on state; A sound signal for a smart cooking device is obtained based on each smart device in the first smart device set.

3. The control method of the intelligent cooking device according to claim 1, characterized in that: The step of separating the sound signal into sub-sound signals originating from different sound sources to obtain a sub-sound signal set corresponding to the sound signal comprises: Separating the sound signal into first sub-sound signals originating from different sound sources by using independent component analysis technology to obtain a first sub-sound signal set; Separating the sound signal into second sub-sound signals originating from different sound sources by a small amount of overlap between time-frequency components to obtain a second sub-sound signal set; The second sub-sound signal set is modified based on the first sub-sound signal set to obtain a sub-sound signal set corresponding to the sound signal.

4. The control method of the intelligent cooking device according to claim 1, characterized in that: The step of classifying the sub-sound signals in the sub-sound signal set according to the preset voiceprint feature, obtaining the sub-sound signals matching the preset voiceprint feature as the first sound signal, and the sub-sound signals not matching the preset voiceprint feature as the second sound signal, comprises: Inputting each sub-sound signal in the sub-sound signal set into a preset voiceprint recognition decision model to obtain a recognition score of each sub-sound signal in the sub-sound signal set, wherein the preset voiceprint recognition decision model is a support vector machine model having the preset voiceprint features; Taking the sub-sound signal in the sub-sound signal set whose recognition score is greater than or equal to the recognition threshold as the first sound signal matching the preset voiceprint feature; The sub-sound signal in the sub-sound signal set whose recognition score is less than the recognition threshold is used as a second sound signal that does not match the preset voiceprint feature.

5. The control method of the intelligent cooking device according to claim 1, characterized in that: The step of generating an initial control instruction for the intelligent cooking device based on the first content information of the first sound signal comprises: Acquire first content information of the first sound signal, and determine identity information and control information of the cooking device to be controlled based on the first content information; The identity information and the control information are input into a preset control instruction template to obtain an initial control instruction for the intelligent cooking device. The preset control instruction template includes basic information for constructing the control instruction and control content information for implementing the control process. The control content information includes preset identity information, preset control information and preset operation information of the cooking device to be controlled.

6. The control method of the intelligent cooking device according to claim 1, characterized in that: The step of acquiring the second content information of the second sound signal and calculating the relevance between the second content information and the preset keyword includes: Acquiring second content information of the second sound signal by using a text recognition technology; Performing word segmentation processing on the content information to obtain a phrase set corresponding to the content information; The association degree between the preset keyword and the phrase set is calculated as the association degree between the content information and the preset keyword.

7. The control method of the intelligent cooking device according to claim 6, characterized in that: If the correlation degree is greater than or equal to a threshold, the step of updating the initial control instruction according to the second content information to obtain a target control instruction includes: If the relevance is greater than or equal to a threshold, sorting the phrases in the phrase set in chronological order to obtain a target phrase set; Using the verbs in the target phrase set as separators to generate a phrase set; generating operation information for the intelligent cooking device according to the phrase set; The initial control instruction is updated based on the operation information to obtain a target control instruction.

8. A control device for an intelligent cooking device, characterized in that: The device comprises: A data acquisition module, used for acquiring a sound signal for the intelligent cooking device, and separating the sound signal into sub-sound signals originating from different sound sources to obtain a sub-sound signal set; a voice recognition module, configured to classify each sub-sound signal in the sub-sound signal set according to a preset voiceprint feature, obtain a sub-sound signal matching the preset voiceprint feature as a first sound signal, and obtain a sub-sound signal not matching the preset voiceprint feature as a second sound signal; An instruction generating module, configured to generate an initial control instruction for the intelligent cooking device based on the first content information of the first sound signal; an identification module, configured to obtain second content information of the second sound signal, and calculate a correlation between the second content information and a preset keyword; A control module is used to update the initial control instruction according to the second content information to obtain a target control instruction if the correlation degree is greater than or equal to a threshold, and the target control instruction is used to control the intelligent cooking device.

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 cooking 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 cooking device according to any one of claims 1 to 7 are executed.

Images