Cooking guidance method and device, equipment and storage medium

Abstract

The invention relates to the technical field of intelligent household appliances, and discloses a cooking guidance method and device, equipment and a storage medium. The method comprises the following steps: receiving current menu inquiry voice information sent by a user; under the condition that the corresponding first menu information is obtained according to the menu database, the terminal equipment is controlled to present the first menu information; and under the condition that the corresponding first menu information is not obtained, obtaining corresponding second menu information through the generative household appliance model, and controlling the terminal equipment to present the second menu information. In this way, all questions and all answers about the menu information in the cooking process are achieved, and the intelligence of obtaining the menu information is improved.

Description

Technical Field

[0001] The present application relates to the field of smart home appliance technology, for example, to methods, devices, equipment and storage media for cooking guidance. Background Art

[0002] With the improvement of domestic living standards and the development of science and technology, people have an increasingly strong demand for intelligent and convenient home appliances. When cooking, we need some cooking guidance, and recipes are our right-hand man. In addition, when cooking according to a recipe, we sometimes forget a step or detail in the recipe. At this time, we need to use our mobile phone or kitchen appliances to query and obtain the corresponding recipe information.

[0003] Currently, information interaction and recipe information can be obtained through the device’s smart screen, but this method easily dirtys the screen, which is neither convenient nor smart enough, nor hygienic. Of course, recipe information can also be obtained through language interaction, but different users may express the same question in different ways. For example, one person may ask, “How do I cut an onion?”, while another person may ask, “How should onions be processed?” Although the meaning of these two questions is the same, for this method of obtaining recipe information, they are considered different questions and require different answers. There are thousands of different recipes in the recipe database, and everyone asks about recipes in different ways. Therefore, in order to accurately answer users’ questions, it is necessary to continuously expand the corpus to cover various different ways of asking questions. This requires a huge amount of work and time, and is extremely time-consuming.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to ordinary technicians in this field. Summary of the Invention

[0005] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical elements or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0006] The embodiments of the present disclosure provide a method, apparatus, device, and storage medium for cooking guidance to solve the technical problem that obtaining recipe information is time-consuming and the intelligence needs to be improved.

[0007] In some embodiments, the method comprises:

[0008] Receive the user's voice message asking about the current recipe;

[0009] When the corresponding first recipe information is obtained according to the recipe database, controlling the terminal device to present the first recipe information;

[0010] In the case where the corresponding first recipe information is not obtained, the corresponding second recipe information is obtained through the generative home appliance model, and the terminal device is controlled to present the second recipe information.

[0011] In some embodiments, receiving a voice message from a user asking for a current recipe includes:

[0012] When voice recipe information is being broadcast, a voice message of the current recipe inquiry sent by the user is received.

[0013] In this way, during the process of recipe broadcasting, you can consult at any time, which further improves the intelligence of obtaining recipe information.

[0014] In some embodiments, controlling the terminal device to present the first recipe information includes:

[0015] Convert the current recipe inquiry voice information into the current recipe inquiry text information;

[0016] In a case where the recipe database includes first current information matching the current recipe query text information, determining the first current information as first recipe information;

[0017] The first recipe information is converted into first voice recipe information, and the terminal device is controlled to broadcast it.

[0018] In this way, the corresponding recipe information can be directly obtained through the recipe database and reported, which is fast, simple and efficient.

[0019] In some embodiments, obtaining the corresponding second recipe information includes:

[0020] Convert the current recipe inquiry voice information into the current recipe inquiry text information, and parse the current recipe inquiry text information through the generative home appliance model to obtain the current generated text information;

[0021] In a case where the recipe database includes second current information matching the currently generated text information, the second current information is determined as second recipe information.

[0022] Of course, the generative home appliance model can also be used to analyze recipe query information, deeply understand the user's intentions and underlying needs, and further improve the intelligence of obtaining recipe information.

[0023] In some embodiments, obtaining the corresponding second recipe information further includes:

[0024] In the case that the second current information is not included in the recipe database, when the generative home appliance model searches for third current information matching the currently generated text information in the set field, the second recipe information is determined based on the third current information.

[0025] It can be seen that the corresponding recipe information can be obtained through the generative home appliance model. In this way, there is no need to expand a large amount of corpus in the recipe database, which saves resources. At the same time, personalized and targeted recipe information can be given according to the user's intentions and underlying needs, further improving the intelligence of obtaining recipe information.

[0026] In some embodiments, further comprising:

[0027] In the case where the second recipe information is not obtained, unsupported speech information is obtained and the terminal device is controlled to present it.

[0028] In this way, clear instructions are given to users, ensuring the integrity of information interaction.

[0029] In some embodiments, the apparatus comprises:

[0030] A receiving module is configured to receive a voice message from a user asking for a current recipe;

[0031] A first presentation module is configured to present the first recipe information when the corresponding first recipe information is obtained from the recipe database;

[0032] The second presentation module is configured to obtain the corresponding second recipe information through the generative home appliance model and present the second recipe information when the corresponding first recipe information is not obtained.

[0033] In some embodiments, the apparatus for cooking guidance includes a processor and a memory storing program instructions, and the processor is configured to perform the above-mentioned cooking guidance method when executing the program instructions.

[0034] In some embodiments, the apparatus comprises:

[0035] Equipment body;

[0036] The device for cooking guidance is installed on the device body.

[0037] In some embodiments, the storage medium stores program instructions, and when the program instructions are run, the above-mentioned method for cooking guidance is executed.

[0038] The method, apparatus, and device for cooking guidance provided by the embodiments of the present disclosure can achieve the following technical effects:

[0039] When a recipe inquiry voice message is received, if the recipe database can obtain the corresponding recipe information, it can be presented directly. If the recipe database cannot obtain the corresponding recipe information, the corresponding recipe information can be obtained and presented through the generative home appliance model, realizing a hundred questions and answers about recipe information during the cooking process, improving the intelligence of obtaining recipe information and the user experience.

[0040] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] One or more embodiments are exemplarily described by corresponding drawings. These exemplary descriptions and drawings do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements. The drawings do not constitute a scale limitation. In addition,

[0042] Figure 1 This is a schematic diagram of the structure of a smart home system for cooking guidance provided by an embodiment of the present disclosure;

[0043] Figure 2 is a flowchart of a cooking guidance method provided by an embodiment of the present disclosure;

[0044] Figure 3 is a signaling interaction diagram for a cooking guidance method provided by an embodiment of the present disclosure;

[0045] Figure 4 is a structural diagram of a cooking guidance device provided by an embodiment of the present disclosure;

[0046] Figure 5 is a structural diagram of a cooking guidance device provided by an embodiment of the present disclosure;

[0047] Figure 6 is a structural diagram of a cooking guidance device provided by an embodiment of the present disclosure;

[0048] Figure 7 It is a schematic diagram of a device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0049] In order to be able to understand the features and technical content of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The accompanying drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the sake of convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0050] In the description and claims of the embodiments of the present disclosure, as well as in the accompanying drawings, the terms "first," "second," and the like are used to distinguish similar items and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate to describe the embodiments of the present disclosure herein. In addition, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions.

[0051] Unless otherwise stated, the term "plurality" means two or more.

[0052] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0053] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0054] With the development of artificial intelligence (AI), AI technology has also been applied in smart homes. Figure 1 This is a schematic diagram of the structure of a smart home system for cooking guidance in an embodiment of the present disclosure. It is widely used in smart home (Smart Home), smart home, smart home device ecology, smart residential (Intelligence House) ecology and other whole-house intelligent digital control application scenarios. The cooking guidance method provided in the embodiment of the present disclosure can be applied to Figure 1 The hardware environment shown is composed of a cloud server device 100 and a terminal device 200.

[0055] like Figure 1 As shown, the cloud server device 100 can be connected to the terminal device 200 via a network and can be used to provide services (such as application services, etc.) for the terminal device or the client installed on the terminal device. A database can be set up on the cloud server or independently of the cloud server to provide data storage services for the cloud server device 100. Cloud computing and / or edge computing services can be configured on the cloud server device or independently of the cloud server device to provide data computing services for the cloud server device 100. The above-mentioned network may include, but is not limited to, at least one of the following: a wired network and a wireless network. The above-mentioned wired network may include, but is not limited to, at least one of the following: a wide area network, a metropolitan area network, and a local area network. The above-mentioned wireless network may include, but is not limited to, at least one of the following: WIFI (Wireless Fidelity) and Bluetooth.

[0056] The terminal device 200 may be but is not limited to a PC, mobile phone, tablet computer, smart air conditioner, smart range hood, smart refrigerator, smart oven, smart stove, smart device, smart water heater, smart washing equipment, smart dishwasher, smart projection equipment, smart TV, smart clothes drying rack, smart curtains, smart audio and video, smart socket, smart audio, smart speaker, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart sweeping robot, smart window cleaning robot, smart mopping robot, smart air purification equipment, smart steamer, smart microwave oven, smart kitchen treasure, smart purifier, smart water dispenser, smart door lock, etc.

[0057] In the embodiment of the present disclosure, the terminal device 200 includes kitchen appliances with voice functions, such as: smart refrigerators, smart stoves, smart ovens, or smart speakers, etc., and the cloud server device 100 applies generative AI technology, configures and saves a generative home appliance model, and also saves a recipe database. In this way, when a recipe inquiry voice message is received, if the recipe database can obtain the corresponding recipe information, the server can send the recipe information to the terminal device for presentation. If the recipe database cannot obtain the corresponding recipe information, the corresponding recipe information can be obtained through the generative home appliance model and sent to the terminal device for presentation, thereby realizing a hundred questions and answers about recipe information during the cooking process, improving the intelligence of obtaining recipe information and the user experience.

[0058] Alternatively, in some embodiments, the cloud server device 100 applies generative AI technology, configures and saves a generative home appliance model. In addition, a recipe database is saved in the terminal device. In this way, when a recipe inquiry voice message is received, if the recipe database can obtain the corresponding recipe information, the terminal device can directly present it. If the recipe database cannot obtain the corresponding recipe information, it can be sent to the server. The server obtains the corresponding recipe information through the generative home appliance model and sends it to the terminal device for presentation, thereby realizing a hundred questions and answers about recipe information during the cooking process, improving the intelligence of obtaining recipe information and the user experience.

[0059] Figure 2 FIG. 1 is a flow chart of a cooking instruction method provided by an embodiment of the present disclosure. Figure 2 As shown, the process for cooking instructions may include:

[0060] Step 201: Receive a voice message from a user asking for the current recipe.

[0061] The terminal device can be configured with a voice module, which can receive voice information from users within the set range of the terminal device. For example, the user sends a current recipe inquiry voice message such as "Query the method of making Kung Pao Chicken" or "##, how to make Kung Pao Chicken?", etc. In this way, the recipe inquiry voice message is clearer and carries clear information such as "Kung Pao Chicken".

[0062] In some embodiments, the voice messages sent by users may be more personalized, more specific, or chat-like, such as "How to cut onions to avoid tears?" or "How many chicken wings do you need?" These voice messages are related to recipes and can also be voice messages asking for the current recipe.

[0063] In some embodiments, after receiving the voice message of the current recipe inquiry from the user, the terminal device can communicate with the server, so that the cloud server device receives the voice message of the current recipe inquiry from the user through the terminal device with a voice module.

[0064] Of course, users can make recipe inquiries at any time, regardless of whether the terminal device is currently displaying recipe information. Therefore, in some embodiments, while the voice recipe information is being displayed, a user's voice message for the current recipe inquiry is received. For example, while the terminal device is displaying the "Kung Pao Chicken" recipe, if the user speaks "How do I marinate chicken?" or "What is cornstarch?", the user's voice message for the current recipe inquiry is received by the terminal device while the voice recipe information is being displayed. Alternatively, while the voice recipe information is being displayed, the cloud server device receives the user's voice message for the current recipe inquiry via the terminal device.

[0065] Step 202: When corresponding first recipe information is obtained according to the recipe database, the terminal device is controlled to present the first recipe information.

[0066] In this embodiment, the terminal device locally stores a recipe database or the cloud server device stores a recipe database. Therefore, after the terminal device or the cloud server device receives the current recipe inquiry voice information sent by the user, presenting the first recipe information includes: converting the current recipe inquiry voice information into current recipe inquiry text information; when the recipe database includes first current information that matches the current recipe inquiry text information, determining the first current information as the first recipe information; converting the first recipe information into first voice recipe information, and controlling the terminal device to broadcast it.

[0067] Among them, when the terminal device controls the terminal device to broadcast, the terminal device directly makes corresponding voice broadcasts based on the first voice recipe information, and when the cloud server device controls the terminal device to broadcast, the cloud server device sends the first voice recipe information to the terminal device, and the terminal device makes corresponding voice broadcasts.

[0068] For example, if the current recipe inquiry voice message is "Looking for the recipe for braised chicken wings," the cloud server device or terminal device converts it into text instructions and then searches the locally stored recipe database for the corresponding first recipe information, including detailed information such as the recipe's preparation steps and required ingredients. Thus, after the terminal device obtains the first recipe information, or receives the first recipe information sent by the cloud server, it can convert it into voice format and play it. Of course, it can also be presented in text format or graphic format.

[0069] Step 203: If the corresponding first recipe information is not obtained, the corresponding second recipe information is obtained through the generative home appliance model, and the terminal device is controlled to present the second recipe information.

[0070] In some embodiments, the current recipe inquiry voice information may be voice information such as "How to cut onions to avoid tears" or "What is cornstarch", etc. At this time, the corresponding first recipe information may not be found directly through the recipe database. Therefore, the current recipe inquiry voice information can be generalized and context-intentionally analyzed through the generative home appliance model to obtain the corresponding current generated text information, and then, the second current information matching the current generated text information is searched through the recipe database, that is, the corresponding second recipe information is obtained, including: converting the current recipe inquiry voice information into the current recipe inquiry text information, and parsing the current recipe inquiry text information through the generative home appliance model to obtain the current generated text information; when the recipe database includes the second current information matching the current generated text information, the second current information is determined as the second recipe information.

[0071] Generative AI is an artificial intelligence model based on deep learning technology, mainly based on deep neural networks. By training large-scale data sets, it learns to abstract the essential laws and probability distribution of data, and uses generative models to generate new data.

[0072] In the embodiment of the present disclosure, Figure 1The cloud server device shown is configured with a generative home appliance model through generative AI technology. Therefore, after the cloud server device obtains the current recipe inquiry voice information and converts it into the current recipe inquiry text information, the generative home appliance model can be used to generalize the current recipe inquiry text information and parse the morning and afternoon intentions. That is, through the generative home appliance model, the corresponding current generated text information can be obtained, and the search can continue in the saved recipe database. If the second current information that matches the current generated text information is obtained, the second current information can be determined as the second recipe information.

[0073] Alternatively, the terminal device obtains the current recipe inquiry voice information, converts it into the current recipe inquiry text information, and sends it to the cloud server device. The cloud server device generalizes the current recipe inquiry text information and parses the morning and afternoon intentions through the generative home appliance model, obtains the corresponding current generated text information, and sends it to the terminal device. Thereby, the terminal device searches in the saved recipe database. If the second current information that matches the currently generated text information is obtained, the second current information can be determined as the second recipe information.

[0074] In some embodiments, when a terminal device or cloud server device cannot find the corresponding recipe information in a locally stored recipe database, generative AI technology can be used to search, obtain the corresponding recipe information, and control the terminal device to present it. Specifically, obtaining the corresponding second recipe information further includes: if the recipe database does not contain the second current information, using the generative appliance model to find third current information in a set field that matches the currently generated text information, determining the third current information as the second recipe information.

[0075] like Figure 1 The cloud server shown is configured with a generative home appliance model through generative AI technology. Therefore, the cloud server device searches in the saved recipe database. If the second current information that matches the currently generated text information is not obtained, the cloud server device calls the set resources through the interface of the generative home appliance model to search and learn in related knowledge, skills and other fields. If the third current information that matches the currently generated text information is found, the second recipe information is determined based on the third current information.

[0076] Alternatively, if the terminal device fails to obtain the second current information that matches the currently generated text information in the saved recipe database, it can notify the cloud server device, so that the cloud server device calls the set resources through the interface of the generative home appliance model, searches and learns in relevant knowledge, skills and other fields. If the third current information that matches the currently generated text information is found, the second recipe information is determined based on the third current information.

[0077] The set resources can be industry public data resources, academic public resources, etc., or some commercial paid resources, etc.

[0078] For example, the current recipe inquiry voice message may be "How to cut onions to avoid tears." After the cloud server device converts it into text information, it calls the set resources through the interface of the generative home appliance model to generalize the current voice information and analyze the context intent to obtain the current generated text information. Then, through the interface of the generative home appliance model, it finds the third current information that matches the current generated text information in the fields of onion characteristics, growth habits, etc., and can learn and determine the second recipe information based on the third current information.

[0079] Of course, there are many ways to control the terminal device to present the second recipe information. The control terminal device uses one or more ways such as voice broadcast, graphic display, and text display to present the second recipe information.

[0080] It can be seen that in the embodiment of the present disclosure, when a recipe inquiry voice message is received, if the recipe database can obtain the corresponding recipe information, it can be presented directly; if the recipe database cannot obtain the corresponding recipe information, the corresponding recipe information can be obtained and presented through the generative home appliance model, thereby realizing a hundred questions and answers about recipe information during the cooking process, and obtaining the corresponding recipe information through the generative home appliance model. In this way, there is no need to expand a large amount of corpus in the recipe database, saving resources. At the same time, it can also deeply understand the user's intentions and the needs behind them, and provide personalized and targeted recipe information, further improving the intelligence of obtaining recipe information and the user experience.

[0081] Of course, in some embodiments, if the second recipe information is not obtained, unsupported wording information is obtained and the terminal device is controlled to present it. In this way, clear instructions are given to the user, ensuring the integrity of information interaction and further ensuring that all questions and answers about recipe information are answered.

[0082] Of course, in some embodiments, the generative home appliance model has the functions of self-learning and self-updating. Therefore, after the second current information is determined as the second recipe information, the correspondence between the current recipe inquiry text information and the second recipe information can be saved in the database. In this way, in the subsequent cooking guidance process, when the same current recipe inquiry voice information is received, the corresponding first recipe information can be obtained according to the recipe database. There is no need to use the generative home appliance model to call the set resources to parse the current recipe inquiry text information corresponding to the current recipe inquiry voice information, which simplifies the cooking guidance process and improves efficiency.

[0083] Similarly, in some embodiments, after determining the second recipe information based on the third current information, the correspondence between the current recipe inquiry text information corresponding to the current recipe inquiry voice information and the second recipe information can also be saved in the recipe database. In this way, in the subsequent cooking guidance process, when the same current recipe inquiry voice information is received, the corresponding first recipe information can be obtained according to the recipe database, without the need to use the generative home appliance model to call the set resources to search for the recipe information, which further simplifies the cooking guidance process and improves efficiency.

[0084] The following operation processes are grouped into specific embodiments to illustrate the cooking guidance process provided by the embodiments of the present invention.

[0085] In this embodiment, Figure 1 As shown, the terminal device can be a smart refrigerator with a voice module, and communicates with a cloud server device. The cloud server uses generative AI technology to save a generative home appliance model, which can be HomeGPT, and also saves a recipe database.

[0086] Figure 3 Schematic diagram of signaling interaction for a cooking guidance method provided by an embodiment of the present disclosure. Figure 3 , the cooking instruction process includes:

[0087] Step 301: The refrigerator receives a voice message from a user asking for the current recipe.

[0088] Among them, the current recipe inquiry voice information may include: "How to make ****?" or "What is the function of ## seasoning?" or "How to peel tomatoes?", etc., that is, voice information related to cooking can be the current recipe inquiry voice information.

[0089] Step 302: The refrigerator sends the current recipe inquiry voice message to the cloud server device.

[0090] Step 303: The cloud server device converts the current recipe inquiry voice information into the current recipe inquiry text information.

[0091] Step 304: The cloud server device determines whether the recipe database includes first current information that matches the current recipe query text information. If so, execute step 305; otherwise, execute step 307.

[0092] Based on the current recipe query text information, a search is performed in the recipe database, wherein the current recipe query text information can be parsed. If the current identity coding information ID of the current recipe query text information can be determined, the first current information matching the current identity coding information ID can be found in the recipe database, and step 305 can be executed.

[0093] Step 305: The cloud server device determines the first current information as the first recipe information, converts the first recipe information into first voice recipe information, and sends it to the refrigerator.

[0094] Step 306: The refrigerator makes an announcement based on the first voice recipe information.

[0095] Step 307: The cloud server device calls the setting resources through the generative home appliance model, generalizes and analyzes the context intent of the current recipe query text information, and obtains the current generative text information.

[0096] Step 308: The cloud server device determines whether the recipe database includes second current information that matches the currently generated text information. If so, execute step 309; otherwise, execute step 310.

[0097] Step 309: The cloud server device determines the second current information as the second recipe information, and saves the corresponding relationship between the previous recipe query text information and the second recipe information in the recipe database. Then, the process proceeds to step 313.

[0098] Step 310: The cloud server device calls the setting resource through the generative home appliance model and searches for the third current information matching the currently generated text information in the setting field.

[0099] Step 311: The cloud server device determines whether the third current information is found. If so, step 312 is executed; otherwise, step 315 is executed.

[0100] Step 312: The cloud server device determines the second recipe information based on the third current information, and saves the corresponding relationship between the previous recipe query text information and the second recipe information in the recipe database. Then, the process proceeds to step 313.

[0101] Step 313: The cloud server device converts the second recipe information into second voice recipe information and sends it to the refrigerator.

[0102] Step 314: The refrigerator makes a voice announcement based on the second voice recipe information.

[0103] Step 315: The cloud server device obtains the unsupported speech information, converts it into corresponding unsupported voice information, and sends it to the refrigerator.

[0104] Step 316: The refrigerator makes a voice announcement based on the voice-unsupported information.

[0105] As can be seen, in this embodiment, the cloud server device stores a recipe database and is configured with HomeGTP. Thus, upon receiving a voice message requesting a recipe, if the recipe database can obtain the corresponding recipe information, it can be directly presented. If the recipe database cannot obtain the corresponding recipe information, the corresponding recipe information can be obtained and presented via HomeGTP. This enables a comprehensive range of questions and answers regarding recipe information during the cooking process. Furthermore, by obtaining the corresponding recipe information via HomeGTP, there is no need to expand the recipe database with massive amounts of data, saving resources. Furthermore, the system can deeply understand the user's intentions and underlying needs, providing personalized and targeted recipe information, further improving the intelligence of recipe information acquisition and the user experience. Furthermore, the recipe database can be updated based on the recipe information obtained via HomeGTP, further improving the efficiency of the cooking guidance process.

[0106] According to the above-mentioned process for cooking guidance, a device for cooking guidance can be constructed.

[0107] Figure 4 This is a schematic diagram of a cooking guidance device provided by an embodiment of the present disclosure. Figure 4 As shown, the cooking guidance device 400 can be applied to a terminal device or a cloud server device, and includes: a receiving module 410, a first presentation module 420 and a second presentation module 430.

[0108] The receiving module 410 is configured to receive a voice message from a user asking for a current recipe;

[0109] The first presentation module 420 is configured to control the terminal device to present the first recipe information when the corresponding first recipe information is obtained according to the recipe database.

[0110] The second presentation module 430 is configured to obtain the corresponding second recipe information through the generative home appliance model when the corresponding first recipe information is not obtained, and control the terminal device to present the second recipe information.

[0111] In some embodiments, the receiving module 410 is further configured to receive a current recipe inquiry voice message from a user when performing voice recipe information broadcasting.

[0112] In some embodiments, the first presentation module 420 is specifically configured to convert the current recipe inquiry voice information into the current recipe inquiry text information; when the recipe database includes the first current information that matches the current recipe inquiry text information, the first current information is determined as the first recipe information; the first recipe information is converted into the first voice recipe information, and the terminal device is controlled to broadcast it.

[0113] In some embodiments, the second presentation module 430 is specifically configured to convert the current recipe inquiry voice information into the current recipe inquiry text information, and parse the current recipe inquiry text information through the generative home appliance model to obtain the current generated text information; when the recipe database includes second current information that matches the current generated text information, the second current information is determined as the second recipe information.

[0114] In some embodiments, the second presentation module 430 is further configured to determine the second recipe information based on the third current information when the generative home appliance model finds the third current information that matches the currently generated text information in the set field when the second current information is not included in the recipe database.

[0115] In some embodiments, it also includes: a third presentation module, which is configured to obtain unsupported speech information when the second recipe information is not obtained, and control the terminal device to present it.

[0116] The following example illustrates a process of providing cooking guidance using the cooking guidance device provided in an embodiment of the present invention.

[0117] like Figure 1 As shown, the terminal device can be a smart stove, which communicates with the cloud server device, and the cloud server device saves the generative home appliance model through generative AI technology, and also saves the recipe database. Figure 5 This is a schematic diagram of a cooking guidance device provided by an embodiment of the present disclosure. Figure 5 As shown, the cooking guidance device 400 is applied to a cloud server device, and includes: a receiving module 410 , a first presentation module 420 , a second presentation module 430 and a third presentation module 440 .

[0118] In this embodiment, the smart stove receives a user's voice message inquiring about a current recipe through a receiving module 410. The voice message inquiring about a current recipe may include, for example, "How do I make ****?", "What is the function of ## seasoning?", or "How do I marinate a dish?" In other words, any voice message related to cooking can be considered a voice message inquiring about a current recipe. This voice message is then converted into textual information. If the recipe database contains a first current message that matches the textual information, the first presentation module 420 identifies the first current message as the first recipe message, converts it into a first voice message, and then sends it to the smart stove for broadcast.

[0119] If the recipe database does not include the first current information that matches the current recipe query text information, the second presentation module 430 calls the setting resources through HomeGPT, generalizes and analyzes the current recipe query text information, obtains the current generated text information, and when the recipe database includes the second current information that matches the current generated text information, determines the second current information as the second recipe information, and converts the second recipe information into the corresponding second voice recipe information and sends it to the smart stove for broadcast.

[0120] In the case that the recipe database does not include the second current information that matches the currently generated text information, the second presentation module 430 continues to call the setting resource through HomeGPT, and finds the third current information that matches the currently generated text information in the setting field. When the third current information is found, the second recipe information is determined according to the third current information, and after converting the third recipe information into the corresponding second voice recipe information, it is sent to the smart stove for broadcast.

[0121] Of course, the second presentation module 430 can also save the correspondence between the previous recipe inquiry text information and the second recipe information in the recipe database. In this way, in the subsequent cooking guidance process, when the same current recipe inquiry voice information is received, the corresponding first recipe information can be obtained according to the recipe database. There is no need to use the generative home appliance model to call the set resources to search for recipe information, which further simplifies the cooking guidance process and improves efficiency.

[0122] When the third current information is not found, that is, the second recipe information is not obtained, the third presentation module 440 can obtain the unsupported speech information, convert it into corresponding unsupported voice information, and send it to the smart stove for broadcast.

[0123] As can be seen, in this embodiment, a recipe database is stored in the cloud server device and configured with HomeGTP. Thus, when the cooking guidance device receives a voice message requesting a recipe, if the recipe database can obtain the corresponding recipe information, it can directly present it. If the recipe database cannot obtain the corresponding recipe information, the corresponding recipe information can be obtained and presented via HomeGTP. This enables a comprehensive range of questions and answers regarding recipe information during the cooking process. Furthermore, by obtaining the corresponding recipe information via HomeGTP, there is no need to expand the recipe database with massive amounts of data, saving resources. Furthermore, the device can deeply understand the user's intentions and underlying needs, providing personalized and targeted recipe information, further improving the intelligence of recipe information acquisition and the user experience. Furthermore, the recipe database can be updated based on the recipe information obtained via HomeGTP, further improving the efficiency of the cooking guidance process.

[0124] The present disclosure provides a cooking instruction device 600, the structure of which is as follows: Figure 6 Shown, including:

[0125] Processor 1000 and memory 1001 may also include a communication interface 1002 and a bus 1003. Processor 1000, communication interface 1002, and memory 1001 may communicate with each other via bus 1003. Communication interface 1002 may be used for information transmission. Processor 1000 may invoke logic instructions in memory 1001 to execute the cooking guidance method of the above-described embodiment.

[0126] In addition, the logic instructions in the memory 1001 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0127] Memory 1001, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of the present disclosure. Processor 1000 executes the program instructions / modules stored in memory 1001 to perform functional applications and data processing, thereby implementing the cooking guidance method in the above-described method embodiments.

[0128] The memory 1001 may include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function; the data storage area may store data generated based on the use of the terminal device. Furthermore, the memory 1001 may include high-speed random access memory and non-volatile memory.

[0129] An embodiment of the present disclosure provides a cooking guidance device, comprising: a processor and a memory storing program instructions, wherein the processor is configured to execute a cooking guidance method when executing the program instructions.

[0130] Combine Figure 7, the embodiment of the present disclosure provides a device 700, which can be a terminal device or a cloud server device, including: a device body; the above-mentioned cooking guidance device 400 (600). The cooking guidance device 400 (600) is installed on the device body. The installation relationship described here is not limited to placement inside the product, but also includes installation connections with other components of the product, including but not limited to physical connections, electrical connections or signal transmission connections. It can be understood by those skilled in the art that the cooking guidance device 400 (600) can be adapted to a feasible device body, thereby realizing other feasible embodiments.

[0131] An embodiment of the present disclosure provides a storage medium storing program instructions, which, when executed, execute the above-mentioned method for cooking guidance.

[0132] An embodiment of the present disclosure provides a computer program product, which includes a computer program stored on a storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the above-mentioned cooking guidance method.

[0133] The aforementioned storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0134] The technical solution of the embodiments of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present disclosure. The aforementioned storage medium may be a non-transitory storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program code, or a transient storage medium.

[0135] The above description and accompanying drawings sufficiently illustrate the embodiments of the present disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, process, and other changes. The embodiments represent only possible variations. Unless expressly required, individual components and functions are optional, and the order of operations may vary. Portions and features of some embodiments may be included in or substituted for portions and features of other embodiments. The scope of the embodiments of the present disclosure includes the entire scope of the claims and all available equivalents thereof. When used in this application, although the terms "first," "second," etc. may be used in this application to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element can be called a second element, and similarly, a second element can be called a first element, without changing the meaning of the description, as long as all occurrences of "first element" are consistently renamed and all occurrences of "second element" are consistently renamed. The first element and the second element are both elements, but they may not be the same element. Furthermore, the terms used in this application are only used to describe the embodiments and are not intended to limit the claims. As used in the description of the embodiments and claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of one or more of the associated listings. In addition, when used in this application, the term "comprise" and its variations "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups of these. Without further limitation, an element defined by the phrase "comprising a..." does not exclude the presence of other identical elements in the process, method or apparatus comprising the element. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the embodiments can be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can be referred to the description of the method part.

[0136] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present disclosure. The technicians will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0137] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units can be merely a logical functional division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, and can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected to implement this embodiment according to actual needs. In addition, the functional units in the embodiments of the present disclosure may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0138] The flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to the embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a part of a model, program segment or code, and the part of the model, program segment or code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, which can depend on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in an order different from that disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified function or action, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for cooking instruction, characterized in that include: Receive the user's voice message asking about the current recipe; When the corresponding first recipe information is obtained according to the recipe database, controlling the terminal device to present the first recipe information; In the case where the corresponding first recipe information is not obtained, the corresponding second recipe information is obtained through the generative home appliance model, and the terminal device is controlled to present the second recipe information.

2. The method according to claim 1, characterized in that The receiving of the current recipe inquiry voice message sent by the user includes: When voice recipe information is being broadcast, a voice message of the current recipe inquiry sent by the user is received.

3. The method according to claim 1, characterized in that The controlling the terminal device to present the first recipe information includes: Convert the current recipe inquiry voice information into the current recipe inquiry text information; In a case where the recipe database includes first current information matching the current recipe query text information, determining the first current information as first recipe information; The first recipe information is converted into first voice recipe information, and the terminal device is controlled to broadcast it.

4. The method according to claim 1, wherein Obtaining the corresponding second recipe information includes: Convert the current recipe inquiry voice information into the current recipe inquiry text information, and parse the current recipe inquiry text information through the generative home appliance model to obtain the current generated text information; In a case where the recipe database includes second current information matching the currently generated text information, the second current information is determined as second recipe information.

5. The method according to claim 4, characterized in that The obtaining of the corresponding second recipe information further includes: In the case that the second current information is not included in the recipe database, when the generative home appliance model searches for third current information matching the currently generated text information in the set field, the second recipe information is determined based on the third current information.

6. The method according to any one of claims 1 to 5, characterized in that Also includes: In the case where the second recipe information is not obtained, unsupported speech information is obtained and the terminal device is controlled to present it.

7. A device for cooking guidance, characterized in that include: A receiving module is configured to receive a voice message from a user asking for a current recipe; The first presentation module is configured to control the terminal device to present the first recipe information when the corresponding first recipe information is obtained from the recipe database; The second presentation module is configured to obtain the corresponding second recipe information through the generative home appliance model when the corresponding first recipe information is not obtained, and control the terminal device to present the second recipe information.

8. A cooking instruction device comprising a processor and a memory storing program instructions, wherein: The processor is configured to perform the method for cooking guidance according to any one of claims 1 to 6 when executing the program instructions.

9. A device, characterized in that include: Equipment body; The device for cooking guidance according to claim 7 or 8 is installed on the device body.

10. A storage medium storing program instructions, characterized in that: When the program instructions are executed, the method for cooking guidance according to any one of claims 1 to 6 is executed.

Images