Method and apparatus for determining food storage information, storage medium, and electronic device

Abstract

The application discloses a food storage information determination method and device, a storage medium and an electronic device, relates to the technical field of smart homes, and the food storage information determination method comprises the following steps: obtaining a food storage query request; in response to the food storage query request, obtaining a group of food characteristics of a target food and a group of refrigerator state characteristics of a target refrigerator; querying a first group of knowledge nodes associated with the group of food characteristics in a preset target knowledge graph, and querying a second group of knowledge nodes associated with the group of refrigerator state characteristics in the target knowledge graph; finding at least one pair of knowledge nodes in the first group of knowledge nodes and the second group of knowledge nodes; in the case that at least one pair of knowledge nodes is found, generating food storage information according to the knowledge nodes belonging to the second group of knowledge nodes in each pair of knowledge nodes in the at least one pair of knowledge nodes, and the food storage information comprises storage parameters in one or more dimensions of the target food stored in the target refrigerator.

Description

Technical Field

[0001] This application relates to the field of smart home technology, and more specifically, to a method and apparatus for determining food storage information, a storage medium, and an electronic device. Background Technology

[0002] Using refrigerators to store food is becoming the preferred method for more and more modern families. However, proper storage is crucial for preserving the original nutrients of food. Currently, many refrigerator users rely on experience to store food without scientifically selecting storage compartments or considering relevant information, leading to nutrient loss or even rendering the food inedible.

[0003] There is currently no effective solution to the problem that related technologies cannot combine refrigerator information to provide food storage information.

[0004] Therefore, it is necessary to improve the relevant technology to overcome the aforementioned defects. Summary of the Invention

[0005] This invention provides a method and apparatus for determining food storage information, a storage medium, and an electronic device, to at least solve the problem of not being able to provide food storage information in conjunction with relevant information from a refrigerator.

[0006] According to one aspect of the present invention, a method for determining food storage information is provided, comprising: obtaining a food storage query request, wherein the food storage query request is used to request a query for storage parameters of a target food stored on a target refrigerator; in response to the food storage query request, obtaining a set of food features of the target food and a set of refrigerator status features of the target refrigerator; querying a first set of knowledge nodes associated with the set of food features in a preset target knowledge graph, and querying a second set of knowledge nodes associated with the set of refrigerator status features in the target knowledge graph; searching for at least one pair of knowledge nodes in the first set of knowledge nodes and the second set of knowledge nodes, wherein the two knowledge nodes in each pair of knowledge nodes are associated and belong to the first set of knowledge nodes and the second set of knowledge nodes, respectively; and, if the at least one pair of knowledge nodes is found, generating food storage information based on the knowledge nodes in each pair of knowledge nodes belonging to the second set of knowledge nodes, wherein the food storage information includes storage parameters in one or more dimensions of storing the target food on the target refrigerator.

[0007] In an exemplary embodiment, searching for at least one pair of knowledge nodes in the first group of knowledge nodes and the second group of knowledge nodes includes: searching for the at least one pair of knowledge nodes corresponding to the request intent feature in the first group of knowledge nodes and the second group of knowledge nodes, wherein the request intent feature is an intent feature obtained by performing intent recognition on the food storage query request.

[0008] In an exemplary embodiment, searching for at least one pair of knowledge nodes corresponding to the request intent feature in the first group of knowledge nodes and the second group of knowledge nodes includes: when the request intent feature indicates a storage temperature included in the storage parameters requested for query, searching for at least one pair of knowledge nodes corresponding to the storage temperature in the first group of knowledge nodes and the second group of knowledge nodes; and / or when the request intent feature indicates a storage humidity included in the storage parameters requested for query, searching for at least one pair of knowledge nodes corresponding to the storage humidity in the first group of knowledge nodes and the second group of knowledge nodes; and / or when the request intent feature indicates a storage area included in the storage parameters requested for query, searching for at least one pair of knowledge nodes corresponding to the storage area in the first group of knowledge nodes and the second group of knowledge nodes; and / or when the request intent feature indicates a storage number of days included in the storage parameters requested for query, searching for at least one pair of knowledge nodes corresponding to the storage number of days in the first group of knowledge nodes and the second group of knowledge nodes.

[0009] In an exemplary embodiment, the step of searching for at least one pair of knowledge nodes corresponding to the storage temperature in the first group of knowledge nodes and the second group of knowledge nodes includes: searching for a first knowledge node corresponding to the storage temperature in the first group of knowledge nodes, and searching for a set of knowledge nodes corresponding to the storage temperature in the second group of knowledge nodes, wherein the first knowledge node is used to represent the recommended storage temperature of the target food, and each knowledge node in the set of knowledge nodes is used to represent the working temperature or working temperature range of the storage area in the target refrigerator; searching for a second knowledge node in the set of knowledge nodes, wherein the working temperature or working temperature range represented by the second knowledge node corresponds to the recommended storage temperature, and the first knowledge node represents the recommended storage temperature of the target food. The first knowledge node and the second knowledge node are a found pair of knowledge nodes; or, the first knowledge node corresponding to the storage temperature is searched in the first group of knowledge nodes, and the group of knowledge nodes corresponding to the storage temperature is searched in the second group of knowledge nodes, wherein the first knowledge node is used to represent the recommended storage temperature range of the target food, and each knowledge node in the group of knowledge nodes is used to represent the working temperature or working temperature range of the storage area in the target refrigerator; the second knowledge node is searched in the group of knowledge nodes, wherein the working temperature or working temperature range represented by the second knowledge node corresponds to the recommended storage temperature range, and the first knowledge node and the second knowledge node are a found pair of knowledge nodes.

[0010] In an exemplary embodiment, generating food storage information based on knowledge nodes belonging to the second group of knowledge nodes in each of the at least one pair of knowledge nodes includes: if at least one pair of knowledge nodes corresponding to each intent feature in the request intent feature is found in the first group of knowledge nodes and the second group of knowledge nodes, determining the storage parameters represented by some or all of the knowledge nodes belonging to the second group of knowledge nodes in each of the at least one pair of knowledge nodes as storage parameters included in the food storage information, wherein the request intent feature is an intent feature obtained by performing intent recognition on the food storage query request; if at least one pair of knowledge nodes corresponding to some intent features in the request intent feature is found in the first group of knowledge nodes and the second group of knowledge nodes, searching for target knowledge nodes that are associated with candidate knowledge nodes in the target knowledge graph, wherein the candidate knowledge nodes are some or all of the knowledge nodes belonging to the second group of knowledge nodes in each of the at least one pair of knowledge nodes; determining the storage parameters represented by the candidate knowledge nodes and the target knowledge nodes as storage parameters included in the food storage information, wherein the request intent feature is an intent feature obtained by performing intent recognition on the food storage query request.

[0011] In an exemplary embodiment, the step of searching for target knowledge nodes that are associated with candidate knowledge nodes in the target knowledge graph includes: when the request intent feature is used to indicate the storage parameters included in the requested query, such as storage temperature, storage area, and storage days, and the partial intent feature is used to indicate the storage temperature and the storage days, searching for target knowledge nodes that are associated with candidate knowledge nodes in the target knowledge graph, wherein the candidate knowledge nodes are knowledge nodes representing the target operating temperature or target operating temperature range in the second group of knowledge nodes and knowledge nodes representing the target storage days or target storage day range in the second group of knowledge nodes, and the target knowledge nodes are used to represent the target storage area in the target refrigerator.

[0012] In an exemplary embodiment, the step of searching for a target knowledge node in the target knowledge graph that is associated with a candidate knowledge node includes: when the request intent feature is used to indicate the storage parameters included in the requested query, such as storage temperature, storage humidity, and storage area, and the partial intent feature is used to indicate the storage temperature and the storage humidity, searching for the target knowledge node in the target knowledge graph that is associated with the candidate knowledge node, wherein the candidate knowledge node is a knowledge node in the second group of knowledge nodes that represents the target operating temperature or the target operating temperature range and a knowledge node in the second group of knowledge nodes that represents the target storage humidity or the target storage humidity range, and the target knowledge node is used to represent the target storage area in the target refrigerator.

[0013] According to another aspect of the present invention, a device for determining food storage information is also provided, comprising: a first acquisition module, configured to acquire a food storage query request, wherein the food storage query request is used to request a query for storage parameters of a target food stored on a target refrigerator; a second acquisition module, configured to, in response to the food storage query request, acquire a set of food features of the target food and a set of refrigerator status features of the target refrigerator; a query module, configured to query a first set of knowledge nodes associated with the set of food features in a preset target knowledge graph, and query a second set of knowledge nodes associated with the set of refrigerator status features in the target knowledge graph; a search module, configured to search for at least one pair of knowledge nodes in the first set of knowledge nodes and the second set of knowledge nodes, wherein the two knowledge nodes in each pair of knowledge nodes are associated and belong to the first set of knowledge nodes and the second set of knowledge nodes, respectively; and a generation module, configured to, when the at least one pair of knowledge nodes is found, generate food storage information based on the knowledge nodes in each pair of knowledge nodes belonging to the second set of knowledge nodes, wherein the food storage information includes storage parameters in one or more dimensions of storing the target food on the target refrigerator.

[0014] According to another aspect of the present invention, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer program, wherein the computer program is configured to execute the above-described method for determining food storage information when it is run.

[0015] According to another aspect of the present invention, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the method for determining the food storage information via the computer program.

[0016] This invention, in response to a food storage query request, acquires a set of food characteristics of the target food and a set of refrigerator status characteristics of the target refrigerator. It then queries a preset target knowledge graph for a first set of knowledge nodes associated with the set of food characteristics and a second set of knowledge nodes associated with the set of refrigerator status characteristics. Next, it searches for at least one pair of knowledge nodes in the first and second sets of knowledge nodes. If at least one pair of knowledge nodes is found, food storage information is generated based on the knowledge nodes belonging to the second set of knowledge nodes in each pair. This technical solution allows users to obtain relevant food storage information when storing food in the refrigerator, enabling scientific food storage and solving the problem of not being able to provide food storage information by combining relevant refrigerator information. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the hardware environment for a method of determining food storage information according to an embodiment of this application.

[0020] Figure 2 This is a flowchart of a method for determining food storage information according to an embodiment of the present invention;

[0021] Figure 3 This is a schematic diagram of a knowledge graph according to an embodiment of the present invention;

[0022] Figure 4 This is an application scenario diagram of the method for determining food storage information according to an embodiment of the present invention;

[0023] Figure 5 This is a structural block diagram of a device for determining food storage information according to an embodiment of the present invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] According to one aspect of the embodiments of this application, a method for determining food storage information is provided. This method for determining food storage information is widely applicable to whole-house intelligent digital control application scenarios such as smart homes, smart home ecosystems, and intelligencehouse ecosystems. Optionally, in this embodiment, the above-mentioned method for determining food storage information can be applied to, for example... Figure 1 The hardware environment shown consists of terminal device 102 and server 104. For example... Figure 1 As shown, server 104 is connected to terminal device 102 via a network and can be used to provide services (such as application services) to the terminal or clients installed on the terminal. A database can be set up on the server or independently of the server to provide data storage services for server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data processing services for server 104.

[0027] The aforementioned network may include, but is not limited to, at least one of the following: wired network, wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network, metropolitan area network, local area network. The aforementioned wireless network may include, but is not limited to, at least one of the following: Wi-Fi (Wireless Fidelity), Bluetooth. The terminal device 102 may not be limited to PC, mobile phone, tablet computer, smart air conditioner, smart range hood, smart refrigerator, smart oven, smart stove, smart washing machine, smart water heater, smart washing equipment, smart dishwasher, smart projector, smart TV, smart clothes rack, smart curtains, smart audio-visual equipment, smart socket, smart speaker, smart speaker box, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart robot vacuum cleaner, smart window cleaning robot, smart mopping robot, smart air purifier, smart steam oven, smart microwave oven, smart water heater, smart air purifier, smart water dispenser, smart door lock, etc.

[0028] To address the aforementioned issues, this embodiment provides a method for determining food storage information, including but not limited to applications on cloud servers or refrigerators. Figure 2 This is a flowchart of a method for determining food storage information according to an embodiment of the present invention, the process including the following steps:

[0029] Step S202: Obtain a food storage query request, wherein the food storage query request is used to request and query the storage parameters of the target food stored on the target refrigerator;

[0030] In one exemplary embodiment, the food storage query request may be in the form of speech, and then the speech may be recognized by natural speech processing technology to determine the specific intent expressed by the food storage query request.

[0031] In one exemplary embodiment, a food storage query request could be "How should apples be stored in refrigerator A?".

[0032] Step S204: In response to the food storage query request, obtain a set of food characteristics of the target food and a set of refrigerator status characteristics of the target refrigerator;

[0033] In an exemplary embodiment, an image of the target food can be acquired to obtain a set of food features of the target food. The set of food features of the target food may include, but is not limited to: food type, food color, current state of the food, and food size.

[0034] In one exemplary embodiment, a set of refrigerator status characteristics of the target refrigerator includes, but is not limited to, the refrigerator model and the refrigerator's current storage status. It should be noted that once the refrigerator model is determined, the refrigerator's functions, the number of storage areas, and the corresponding operating parameters of each storage area can be determined.

[0035] Step S206: Query the first set of knowledge nodes associated with the set of food features in the preset target knowledge graph, and query the second set of knowledge nodes associated with the set of refrigerator status features in the target knowledge graph;

[0036] In one exemplary embodiment, Figure 3 This is a schematic diagram of a knowledge graph according to an embodiment of the present invention. The target knowledge graph is specifically as follows: Figure 3 As shown, the target knowledge graph in this embodiment includes, but is not limited to, a refrigerator knowledge graph and a food knowledge graph. Figure 3 The document describes the backend data storage and support architecture supported by a refrigerator knowledge graph and a food knowledge graph. The refrigerator knowledge graph represents the attributes of the refrigerator itself and the attributes of each compartment. The compartment attributes include the range of temperature and humidity regulation, as well as the function of each compartment. The food knowledge graph represents the nutritional components and other attributes of the food itself, and the storage time varies under different temperature and humidity scenarios.

[0037] Step S208: Find at least one pair of knowledge nodes in the first group of knowledge nodes and the second group of knowledge nodes, wherein the two knowledge nodes in each pair of knowledge nodes are related and belong to the first group of knowledge nodes and the second group of knowledge nodes respectively.

[0038] In an exemplary embodiment, step S208 can be implemented as follows: searching for at least one pair of knowledge nodes corresponding to the request intent feature in the first group of knowledge nodes and the second group of knowledge nodes, wherein the request intent feature is the intent feature obtained by performing intent recognition on the food storage query request.

[0039] In an exemplary embodiment, searching for the at least one pair of knowledge nodes corresponding to the request intent feature in the first group of knowledge nodes and the second group of knowledge nodes can be achieved in the following ways: when the request intent feature is used to indicate the storage temperature included in the storage parameters requested for query, at least one pair of knowledge nodes corresponding to the storage temperature is searched in the first group of knowledge nodes and the second group of knowledge nodes; and / or when the request intent feature is used to indicate the storage humidity included in the storage parameters requested for query, at least one pair of knowledge nodes corresponding to the storage humidity is searched in the first group of knowledge nodes and the second group of knowledge nodes; and / or when the request intent feature is used to indicate the storage area included in the storage parameters requested for query, at least one pair of knowledge nodes corresponding to the storage area is searched in the first group of knowledge nodes and the second group of knowledge nodes; and / or when the request intent feature is used to indicate the number of storage days included in the storage parameters requested for query, at least one pair of knowledge nodes corresponding to the number of storage days is searched in the first group of knowledge nodes and the second group of knowledge nodes.

[0040] In an exemplary embodiment, finding at least one pair of knowledge nodes corresponding to the storage temperature in the first group of knowledge nodes and the second group of knowledge nodes can be achieved as follows: Finding a first knowledge node corresponding to the storage temperature in the first group of knowledge nodes, and finding a set of knowledge nodes corresponding to the storage temperature in the second group of knowledge nodes, wherein the first knowledge node represents the recommended storage temperature of the target food, and each knowledge node in the set of knowledge nodes represents the working temperature or working temperature range within the storage area of ​​the target refrigerator; finding a second knowledge node in the set of knowledge nodes, wherein the working temperature or working temperature range represented by the second knowledge node corresponds to the recommended storage temperature. The first knowledge node and the second knowledge node are a found pair of knowledge nodes; or, the first knowledge node corresponding to the storage temperature is searched in the first group of knowledge nodes, and the group of knowledge nodes corresponding to the storage temperature is searched in the second group of knowledge nodes, wherein the first knowledge node is used to represent the recommended storage temperature range of the target food, and each knowledge node in the group of knowledge nodes is used to represent the working temperature or working temperature range of the storage area in the target refrigerator; the second knowledge node is searched in the group of knowledge nodes, wherein the working temperature or working temperature range represented by the second knowledge node corresponds to the recommended storage temperature range, and the first knowledge node and the second knowledge node are a found pair of knowledge nodes.

[0041] It should be noted that the operating temperature or operating temperature range represented by the second knowledge node corresponds to, but is not limited to, the following: the operating temperature is equal to the recommended storage temperature, and the recommended storage temperature is within the operating temperature range.

[0042] It should be noted that in the process of determining the second knowledge node from a set of knowledge nodes corresponding to the storage temperature, if there is a second knowledge node that represents a working temperature or working temperature range that corresponds to the recommended temperature range of the first knowledge node, but the storage area corresponding to the second knowledge node does not have space for storing food, then a second knowledge node can be determined again from the set of knowledge nodes corresponding to the storage temperature in the manner described above. The second knowledge node determined again has space for storing food.

[0043] In an exemplary embodiment, finding at least one pair of knowledge nodes corresponding to the storage humidity in the first group of knowledge nodes and the second group of knowledge nodes can be achieved as follows: A third knowledge node corresponding to the storage humidity is found in the first group of knowledge nodes, and a set of knowledge nodes corresponding to the storage humidity is found in the second group of knowledge nodes. The first knowledge node represents the recommended storage humidity for the target food, and each knowledge node in the set of knowledge nodes corresponding to the storage humidity represents the working humidity or working humidity range within the storage area of ​​the target refrigerator. A fourth knowledge node is found in the set of knowledge nodes corresponding to the storage humidity, wherein the fourth knowledge node represents a working humidity or working humidity range that corresponds to the recommended storage humidity. The third knowledge node and the fourth knowledge node are a pair of knowledge nodes found; or the third knowledge node corresponding to the storage humidity is searched in the first group of knowledge nodes, and the group of knowledge nodes corresponding to the storage humidity is searched in the second group of knowledge nodes, wherein the third knowledge node is used to represent the recommended storage humidity range of the target food, and each knowledge node in the group of knowledge nodes corresponding to the storage humidity is used to represent the working humidity or working humidity range in the storage area of ​​the target refrigerator; the fourth knowledge node is searched in the group of knowledge nodes corresponding to the storage humidity, wherein the working humidity or working humidity range represented by the fourth knowledge node corresponds to the recommended storage humidity range, and the third knowledge node and the fourth knowledge node are a pair of knowledge nodes found.

[0044] It should be noted that the fourth knowledge node represents the working humidity or working humidity range corresponding to the recommended storage humidity, including but not limited to: the working humidity being equal to the recommended storage humidity, and the recommended storage humidity being within the working humidity range.

[0045] In an exemplary embodiment, finding at least one pair of knowledge nodes corresponding to the storage area in the first group of knowledge nodes and the second group of knowledge nodes can be achieved as follows: finding a fifth knowledge node corresponding to the storage area in the first group of knowledge nodes, and finding a group of knowledge nodes corresponding to the storage area in the second group of knowledge nodes, wherein the fifth knowledge node is used to represent the recommended storage area of ​​the target food, and each knowledge node in the group of knowledge nodes corresponding to the storage area is used to represent a storage area in the target refrigerator; finding a sixth knowledge node in the group of knowledge nodes corresponding to the storage area, wherein the storage area represented by the sixth knowledge node corresponds to the recommended storage area, and the fifth knowledge node and the sixth knowledge node are a found pair of knowledge nodes.

[0046] In an exemplary embodiment, finding at least one pair of knowledge nodes corresponding to the storage days in the first group of knowledge nodes and the second group of knowledge nodes can be achieved as follows: Finding a seventh knowledge node corresponding to the storage area in the first group of knowledge nodes, and finding a group of knowledge nodes corresponding to the storage days in the second group of knowledge nodes, wherein the seventh knowledge node represents the recommended storage days for the target food, and each knowledge node in the group of knowledge nodes corresponding to the storage days represents the target storage days or a range of target storage days; finding an eighth knowledge node in the group of knowledge nodes corresponding to the storage days, wherein the target storage days or range of target storage days represented by the eighth knowledge node corresponds to the recommended storage days, and the seventh knowledge node and the eighth knowledge node are a found pair of knowledge nodes.

[0047] Step S210: If the at least one pair of knowledge nodes is found, food storage information is generated based on the knowledge nodes belonging to the second group of knowledge nodes in each of the at least one pair of knowledge nodes, wherein the food storage information includes storage parameters in one or more dimensions of storing the target food on the target refrigerator.

[0048] In an exemplary embodiment, step S210 can be implemented by the following steps S11-S12:

[0049] Step S11: If at least one pair of knowledge nodes corresponding to each intent feature in the request intent feature is found in the first group of knowledge nodes and the second group of knowledge nodes, the storage parameters represented by some or all of the knowledge nodes in the second group of knowledge nodes in each pair of knowledge nodes are determined as the storage parameters included in the food storage information, wherein the request intent feature is the intent feature obtained by performing intent recognition on the food storage query request.

[0050] In other words, if a food storage query request is used to query the storage humidity and storage temperature of food, and two pairs of knowledge nodes related to storage humidity and storage temperature are found in the first and second sets of knowledge nodes, then the storage parameters represented by some or all of the knowledge nodes belonging to the second set of knowledge nodes in the two pairs of knowledge nodes can be determined as the storage parameters included in the food storage information. For example, if the nodes belonging to the second set of knowledge nodes in the two pairs of knowledge nodes are the first node and the second node, where the first node represents a temperature of 10 degrees Celsius and the second node represents a relative humidity of 45%, then the generated storage parameters are 10 degrees Celsius and 45% relative humidity.

[0051] Step S12: If at least one pair of knowledge nodes corresponding to a portion of the intent features in the request intent features is found in the first group of knowledge nodes and the second group of knowledge nodes, a target knowledge node with an association relationship with the candidate knowledge node is searched in the target knowledge graph, wherein the candidate knowledge node is a portion or all of the knowledge nodes in the second group of knowledge nodes in each of the at least one pair of knowledge nodes; the storage parameters represented by the candidate knowledge node and the target knowledge node are determined as the storage parameters included in the food storage information, wherein the request intent features are the intent features obtained by performing intent recognition on the food storage query request.

[0052] It should be noted that the relationship between candidate knowledge nodes and target knowledge nodes in the target knowledge graph means that the candidate knowledge nodes and target knowledge nodes are directly or indirectly connected by edges in the target knowledge graph.

[0053] In an exemplary embodiment, searching for target knowledge nodes that are associated with candidate knowledge nodes in the target knowledge graph can be achieved in the following way: when the request intent feature is used to indicate the storage parameters included in the requested query, such as storage temperature, storage area, and storage days, and the partial intent feature is used to indicate the storage temperature and the storage days, the target knowledge nodes that are associated with the candidate knowledge nodes are searched in the target knowledge graph. The candidate knowledge nodes are knowledge nodes representing the target operating temperature or target operating temperature range from the second group of knowledge nodes, and knowledge nodes representing the target storage days or target storage day range from the second group of knowledge nodes. The target knowledge nodes are used to represent the target storage area in the target refrigerator.

[0054] In other words, if a food storage query request is used to query the storage temperature, storage area, and storage days of food, but only knowledge node pairs corresponding to storage temperature and storage days are found in the first and second sets of knowledge nodes, then it is necessary to query the target knowledge node corresponding to the storage area in the second set of knowledge nodes using the storage temperature and storage days. In an exemplary embodiment, in the second set of knowledge nodes, the target knowledge node corresponding to the storage area has a subordinate relationship with the candidate knowledge nodes corresponding to the storage temperature and storage days; that is, the storage area can be determined by the storage temperature and storage days.

[0055] In an exemplary embodiment, searching for target knowledge nodes that are associated with candidate knowledge nodes in the target knowledge graph can be achieved in the following way: when the request intent feature is used to indicate the storage parameters included in the requested query, such as storage temperature, storage humidity, and storage area, and the partial intent feature is used to indicate the storage temperature and the storage humidity, the target knowledge node that is associated with the candidate knowledge node is searched in the target knowledge graph. The candidate knowledge node is a knowledge node in the second group of knowledge nodes that represents the target operating temperature or the target operating temperature range, and a knowledge node in the second group of knowledge nodes that represents the target storage humidity or the target storage humidity range. The target knowledge node is used to represent the target storage area in the target refrigerator.

[0056] In other words, if a food storage query request is used to query the storage humidity, storage temperature, and storage area of ​​food, but only knowledge node pairs corresponding to storage humidity and storage temperature are found in the first and second sets of knowledge nodes, then it is necessary to query the target knowledge node corresponding to the storage area in the second set of knowledge nodes using storage humidity and storage temperature. In an exemplary embodiment, in the second set of knowledge nodes, there is a subordinate relationship between the target knowledge node corresponding to the storage area and the candidate knowledge nodes corresponding to storage humidity and storage temperature; that is, the storage area can be determined by storage humidity and storage temperature.

[0057] To better understand, in an exemplary embodiment, if a user issues a food storage query request indicating: What are the temperature, humidity, location, and number of days the apple is stored in refrigerator A? Then, through the above steps S202-S208, the user can be replied with "Stored in area A of the refrigerator, at a temperature of 10 degrees Celsius, a relative humidity of 45%, and for 3 days."

[0058] Through the above steps, in response to a food storage query request, a set of food characteristics of the target food and a set of refrigerator status characteristics of the target refrigerator are obtained. Then, a first set of knowledge nodes associated with the set of food characteristics and a second set of knowledge nodes associated with the set of refrigerator status characteristics are queried in a preset target knowledge graph. Next, at least one pair of knowledge nodes is searched among the first and second sets of knowledge nodes. If at least one pair of knowledge nodes is found, food storage information is generated based on the knowledge nodes belonging to the second set of knowledge nodes in each pair of at least one pair of knowledge nodes. Using this technical solution, users can obtain relevant food storage information when storing food in the refrigerator, enabling scientific food storage and solving the problem of not being able to provide food storage information by combining relevant refrigerator information.

[0059] Obviously, the embodiments described above are merely some embodiments of the present invention, and not all embodiments. To better understand the above method, the following description, in conjunction with embodiments, illustrates the process, but is not intended to limit the technical solutions of the embodiments of the present invention. Specifically:

[0060] In an optional embodiment, the knowledge graph is a crucial component of intelligent interaction, providing services such as knowledge disambiguation and rapid retrieval during dialogue. This application will utilize refrigerator and food knowledge graphs to provide strong scientific evidence for food storage recommendations. On one hand, the refrigerator knowledge graph draws from real data on different types of refrigerators, while the food knowledge graph contains food and individual food data sourced from professional food research institutions. On the other hand, natural language processing technology is used to quickly retrieve food information and related refrigerator compartment data. Finally, intelligent technology will be employed to combine the knowledge graph with the user's actual refrigerator food situation for joint analysis, ultimately providing the user with information such as the optimal storage compartment and related temperatures, making food storage more rational and accurate.

[0061] like Figure 3 As shown, the overall architecture of the refrigerator and food knowledge graph is described, along with the backend data storage and support architecture supported by these two knowledge graphs. The refrigerator knowledge graph represents the refrigerator's inherent attributes and the attributes of each compartment, including temperature and humidity control ranges and the functions of each compartment. The food knowledge graph represents the nutritional components and other attributes of the food itself, noting that different storage times occur under different temperature and humidity conditions. Based on the temperature and humidity ranges of different compartments, the required storage conditions for the food, and considering the user's refrigerator model and the current food stored in the refrigerator, the system comprehensively determines the optimal storage location for the food. This provides strong data support for the user's food storage, maximizing the freshness of the food.

[0062] In other words, the knowledge graphs related to refrigerators and food ingredients provide the strongest basis for judgment in ensuring food storage; in addition, the knowledge graphs, as the storage of backend knowledge, combined with natural language, make related queries for application services faster.

[0063] Figure 4 This is an application scenario diagram of the method for determining food storage information according to an embodiment of the present invention, such as... Figure 4 As shown, the process of accessing the knowledge graph for food storage is described in the form of a question-and-answer service, and relevant parameters for food storage recommendations are given.

[0064] Figure 4 The upper part describes the service query statement and required conditions, and then proceeds through entity recognition, entity linking, relationship judgment, and answer generation. Figure 4The lower half of the graph illustrates the query process related to entities. The graph provides answers to upper-level services based on a combined analysis of known food storage conditions and refrigerator compartment diagrams. In summary, Figure 4 This document describes the architecture and service process of a refrigerator and food storage graph. The graph provides users with appropriate food storage recommendations in different scenarios, making refrigerator food storage Q&A more intelligent and convenient, thereby improving the user experience and increasing food utilization. Overall, it achieves a technical architecture that combines the relationship graph and food storage Q&A, significantly improving the overall service experience.

[0065] It should be noted that the embodiments of this application are based on the design and storage mode of refrigerator compartments and food map, as well as the joint storage of food storage scenarios and refrigerator compartments, and provide services based on the food and refrigerator architecture map system. Taking dialogue as an example, firstly, the keywords of food are found, combined with the user's actual refrigerator situation, and the food storage scenario, refrigerator compartment and current refrigerator status are logically analyzed to give the answer of the number of storage days under different compartments and different scenarios.

[0066] Furthermore, this application's embodiment utilizes a knowledge graph-based refrigerator food storage recommendation system. Through entity recognition and linking, entity relationship queries yield storage recommendation results. The stability and reliability of the food and refrigerator data within the knowledge graph provide a solid basis for the service's answers. The joint and rapid retrieval of the knowledge graph improves overall question-and-answer efficiency, making the correlation between food and refrigerator data more complete. Isolated data is linked by demand, and the same knowledge graph can connect its internal data and relationships, simplifying logical calculations and data queries. This improves the recommendation method that separates refrigerators and food, ensuring the integration of refrigerator and food recommendation services. It provides food storage times for different scenarios, effectively guaranteeing food freshness and improving food utilization. Furthermore, natural language processing technology is used to analyze questions and quickly retrieve answers from the knowledge graph, ensuring timely responses and improving service efficiency.

[0067] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0068] This embodiment also provides a device for determining food storage information, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementations, or a combination of software and hardware, are also possible and contemplated.

[0069] Figure 5 This is a structural block diagram of a device for determining food storage information according to an embodiment of the present invention. The device includes:

[0070] The first acquisition module 50 is used to acquire a food storage query request, wherein the food storage query request is used to request the query of storage parameters for storing target food on the target refrigerator;

[0071] The second acquisition module 52 is used to acquire a set of food features of the target food and a set of refrigerator status features of the target refrigerator in response to the food storage query request.

[0072] The query module 54 is used to query a first set of knowledge nodes associated with the set of food features in a preset target knowledge graph, and to query a second set of knowledge nodes associated with the set of refrigerator status features in the target knowledge graph.

[0073] The search module 56 is used to search for at least one pair of knowledge nodes in the first group of knowledge nodes and the second group of knowledge nodes, wherein the two knowledge nodes in each pair of knowledge nodes are related and belong to the first group of knowledge nodes and the second group of knowledge nodes respectively.

[0074] The generation module 58 is configured to generate food storage information based on the knowledge nodes belonging to the second group of knowledge nodes in each of the at least one pair of knowledge nodes when the at least one pair of knowledge nodes is found, wherein the food storage information includes storage parameters in one or more dimensions of storing the target food on the target refrigerator.

[0075] The aforementioned device, in response to a food storage query request, acquires a set of food characteristics of the target food and a set of refrigerator status characteristics of the target refrigerator. It then queries a preset target knowledge graph for a first set of knowledge nodes associated with the set of food characteristics and a second set of knowledge nodes associated with the set of refrigerator status characteristics. Next, it searches for at least one pair of knowledge nodes between the first and second sets of knowledge nodes. If at least one pair of knowledge nodes is found, food storage information is generated based on the knowledge nodes belonging to the second set of knowledge nodes in each pair. This technical solution allows users to obtain relevant food storage information when storing food in the refrigerator, enabling scientific food storage and solving the problem of not being able to provide food storage information by combining relevant refrigerator information.

[0076] In an exemplary embodiment, the search module 56 is further configured to search for at least one pair of knowledge nodes corresponding to the request intent feature in the first group of knowledge nodes and the second group of knowledge nodes, wherein the request intent feature is an intent feature obtained by performing intent recognition on the food storage query request.

[0077] In an exemplary embodiment, the lookup module 56 is further configured to: when the request intent feature indicates that the storage parameters to be queried include a storage temperature, search for at least one pair of knowledge nodes corresponding to the storage temperature in the first group of knowledge nodes and the second group of knowledge nodes; and / or when the request intent feature indicates that the storage parameters to be queried include a storage humidity, search for at least one pair of knowledge nodes corresponding to the storage humidity in the first group of knowledge nodes and the second group of knowledge nodes; and / or when the request intent feature indicates that the storage parameters to be queried include a storage area, search for at least one pair of knowledge nodes corresponding to the storage area in the first group of knowledge nodes and the second group of knowledge nodes; and / or when the request intent feature indicates that the storage parameters to be queried include a storage number of days, search for at least one pair of knowledge nodes corresponding to the storage number of days in the first group of knowledge nodes and the second group of knowledge nodes.

[0078] In an exemplary embodiment, the lookup module 56 is further configured to: look up a first knowledge node corresponding to the storage temperature in the first group of knowledge nodes; and look up a group of knowledge nodes corresponding to the storage temperature in the second group of knowledge nodes, wherein the first knowledge node represents the recommended storage temperature of the target food, and each knowledge node in the group of knowledge nodes represents the working temperature or working temperature range within the storage area of ​​the target refrigerator; look up a second knowledge node in the group of knowledge nodes, wherein the working temperature or working temperature range represented by the second knowledge node corresponds to the recommended storage temperature, and the first knowledge node and the second knowledge node are a found pair of knowledge nodes; or look up the first knowledge node corresponding to the storage temperature in the first group of knowledge nodes; and look up the group of knowledge nodes corresponding to the storage temperature in the second group of knowledge nodes, wherein the first knowledge node represents the recommended storage temperature range of the target food, and each knowledge node in the group of knowledge nodes represents the working temperature or working temperature range within the storage area of ​​the target refrigerator; look up a second knowledge node in the group of knowledge nodes, wherein the working temperature or working temperature range represented by the second knowledge node corresponds to the recommended storage temperature range, and the first knowledge node and the second knowledge node are a found pair of knowledge nodes.

[0079] In an exemplary embodiment, the generation module 58 is further configured to: 1) When at least one pair of knowledge nodes corresponding to each intent feature in the request intent features is found in the first group of knowledge nodes and the second group of knowledge nodes, determine the storage parameters represented by some or all of the knowledge nodes belonging to the second group of knowledge nodes in each pair of knowledge nodes as storage parameters included in the food storage information; 2) When at least one pair of knowledge nodes corresponding to some intent features in the request intent features is found in the first group of knowledge nodes and the second group of knowledge nodes, search for target knowledge nodes that are associated with candidate knowledge nodes in the target knowledge graph; 3) When the candidate knowledge nodes are some or all of the knowledge nodes belonging to the second group of knowledge nodes in each pair of knowledge nodes in the at least one pair of knowledge nodes; 4) Determine the storage parameters represented by the candidate knowledge nodes and the target knowledge nodes as storage parameters included in the food storage information; 5) When the request intent features are obtained by intent recognition of the food storage query request.

[0080] In an exemplary embodiment, the generation module 58 is further configured to, when the request intent feature is used to indicate the storage temperature, storage area, and storage days included in the storage parameters requested for query, and the partial intent feature is used to indicate the storage temperature and the storage days, search in the target knowledge graph for a target knowledge node that is associated with the candidate knowledge node, wherein the candidate knowledge node is a knowledge node representing the target operating temperature or target operating temperature range in the second group of knowledge nodes and a knowledge node representing the target storage days or target storage days range in the second group of knowledge nodes, and the target knowledge node is used to represent the target storage area in the target refrigerator.

[0081] In an exemplary embodiment, the generation module 58 is further configured to, when the request intent feature is used to indicate the storage temperature, storage humidity, and storage area included in the storage parameters requested for query, and the partial intent feature is used to indicate the storage temperature and the storage humidity, search in the target knowledge graph for a target knowledge node that is associated with the candidate knowledge node, wherein the candidate knowledge node is a knowledge node representing the target operating temperature or target operating temperature range in the second group of knowledge nodes and a knowledge node representing the target storage humidity or target storage humidity range in the second group of knowledge nodes, and the target knowledge node is used to represent the target storage area in the target refrigerator.

[0082] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.

[0083] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0084] S1, Obtain a food storage query request, wherein the food storage query request is used to request and query the storage parameters of the target food stored on the target refrigerator;

[0085] S2, in response to the food storage query request, obtain a set of food characteristics of the target food and a set of refrigerator status characteristics of the target refrigerator;

[0086] S3, query the first set of knowledge nodes associated with the set of food features in the preset target knowledge graph, and query the second set of knowledge nodes associated with the set of refrigerator status features in the target knowledge graph;

[0087] S4, find at least one pair of knowledge nodes in the first group of knowledge nodes and the second group of knowledge nodes, wherein the two knowledge nodes in each pair of knowledge nodes are related and belong to the first group of knowledge nodes and the second group of knowledge nodes respectively.

[0088] S5, if the at least one pair of knowledge nodes is found, food storage information is generated based on the knowledge nodes belonging to the second group of knowledge nodes in each of the at least one pair of knowledge nodes, wherein the food storage information includes storage parameters in one or more dimensions of storing the target food on the target refrigerator.

[0089] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0090] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0091] Embodiments of the present invention also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0092] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0093] S1, Obtain a food storage query request, wherein the food storage query request is used to request and query the storage parameters of the target food stored on the target refrigerator;

[0094] S2, in response to the food storage query request, obtain a set of food characteristics of the target food and a set of refrigerator status characteristics of the target refrigerator;

[0095] S3, query the first set of knowledge nodes associated with the set of food features in the preset target knowledge graph, and query the second set of knowledge nodes associated with the set of refrigerator status features in the target knowledge graph;

[0096] S4, find at least one pair of knowledge nodes in the first group of knowledge nodes and the second group of knowledge nodes, wherein the two knowledge nodes in each pair of knowledge nodes are related and belong to the first group of knowledge nodes and the second group of knowledge nodes respectively.

[0097] S5, if the at least one pair of knowledge nodes is found, food storage information is generated based on the knowledge nodes belonging to the second group of knowledge nodes in each of the at least one pair of knowledge nodes, wherein the food storage information includes storage parameters in one or more dimensions of storing the target food on the target refrigerator.

[0098] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0099] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0100] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0101] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for determining food storage information, characterized in that, include: Obtain a food storage query request, wherein the food storage query request is used to request and query the storage parameters of the target food stored on the target refrigerator; In response to the food storage query request, a set of food characteristics of the target food and a set of refrigerator status characteristics of the target refrigerator are obtained; wherein, the set of refrigerator status characteristics includes the current storage status of the target refrigerator; In the preset target knowledge graph, query the first set of knowledge nodes associated with the set of food features, and in the target knowledge graph, query the second set of knowledge nodes associated with the set of refrigerator status features; Find at least one pair of knowledge nodes in the first group of knowledge nodes and the second group of knowledge nodes, wherein the two knowledge nodes in each pair of knowledge nodes are related and belong to the first group of knowledge nodes and the second group of knowledge nodes respectively; If the at least one pair of knowledge nodes is found, food storage information is generated based on the knowledge node in the second group of knowledge nodes in each of the at least one pair of knowledge nodes, wherein the food storage information includes storage parameters in one or more dimensions of storing the target food on the target refrigerator; The step of generating food storage information based on the knowledge nodes belonging to the second group of knowledge nodes in each of the at least one pair of knowledge nodes includes: If at least one pair of knowledge nodes corresponding to each intent feature in the request intent feature is found in the first group of knowledge nodes and the second group of knowledge nodes, the storage parameters represented by some or all of the knowledge nodes in the second group of knowledge nodes in each pair of knowledge nodes are determined as the storage parameters included in the food storage information, wherein the request intent feature is the intent feature obtained by performing intent recognition on the food storage query request. If at least one pair of knowledge nodes corresponding to a portion of the intent features in the request intent features is found in the first group of knowledge nodes and the second group of knowledge nodes, target knowledge nodes that are associated with the candidate knowledge nodes are searched in the target knowledge graph. The candidate knowledge nodes are some or all of the knowledge nodes in the second group of knowledge nodes in each of the at least one pair of knowledge nodes. The storage parameters represented by the candidate knowledge nodes and the target knowledge nodes are determined as the storage parameters included in the food storage information. The request intent features are intent features obtained by performing intent recognition on the food storage query request.

2. The method according to claim 1, characterized in that, Find at least one pair of knowledge nodes in the first group of knowledge nodes and the second group of knowledge nodes, including: Search for at least one pair of knowledge nodes corresponding to the request intent feature in the first group of knowledge nodes and the second group of knowledge nodes, wherein the request intent feature is the intent feature obtained by performing intent recognition on the food storage query request.

3. The method according to claim 2, characterized in that, The step of searching for at least one pair of knowledge nodes corresponding to the request intent feature in the first group of knowledge nodes and the second group of knowledge nodes includes: When the request intent feature is used to indicate the storage temperature included in the storage parameters requested for querying, at least one pair of knowledge nodes corresponding to the storage temperature is searched in the first group of knowledge nodes and the second group of knowledge nodes; and / or When the request intent feature is used to indicate the storage humidity included in the storage parameters requested for querying, at least one pair of knowledge nodes corresponding to the storage humidity is searched in the first group of knowledge nodes and the second group of knowledge nodes; and / or When the request intent feature is used to indicate the storage region included in the storage parameters of the requested query, at least one pair of knowledge nodes corresponding to the storage region is searched in the first group of knowledge nodes and the second group of knowledge nodes; and / or When the request intent feature is used to indicate the number of storage days included in the storage parameters requested for querying, at least one pair of knowledge nodes corresponding to the number of storage days is searched in the first group of knowledge nodes and the second group of knowledge nodes.

4. The method according to claim 3, characterized in that, The step of searching for at least one pair of knowledge nodes corresponding to the storage temperature in the first group of knowledge nodes and the second group of knowledge nodes includes: In the first set of knowledge nodes, a first knowledge node corresponding to the storage temperature is searched, and in the second set of knowledge nodes, a set of knowledge nodes corresponding to the storage temperature is searched. The first knowledge node is used to represent the recommended storage temperature of the target food, and each knowledge node in the set of knowledge nodes is used to represent the working temperature of the storage area in the target refrigerator. In the set of knowledge nodes, a second knowledge node is searched, wherein the working temperature represented by the second knowledge node corresponds to the recommended storage temperature, and the first knowledge node and the second knowledge node are a pair of knowledge nodes found.

5. The method according to claim 1, characterized in that, The step of searching for target knowledge nodes that are associated with candidate knowledge nodes in the target knowledge graph includes: When the request intent feature indicates the storage parameters to be queried, including storage temperature, storage area, and storage days, and the partial intent feature indicates the storage temperature and the storage days, the target knowledge node that is associated with the candidate knowledge node is searched in the target knowledge graph. The candidate knowledge node is the knowledge node representing the target operating temperature and the knowledge node representing the target storage days in the second group of knowledge nodes. The target knowledge node is used to represent the target storage area in the target refrigerator.

6. The method according to claim 1, characterized in that, The step of searching for target knowledge nodes that are associated with candidate knowledge nodes in the target knowledge graph includes: When the request intent feature indicates the storage temperature, storage humidity, and storage area included in the requested query storage parameters, and the partial intent feature indicates the storage temperature and the storage humidity, the target knowledge node that is associated with the candidate knowledge node is searched in the target knowledge graph. The candidate knowledge node is the knowledge node representing the target operating temperature in the second group of knowledge nodes and the knowledge node representing the target operating humidity in the second group of knowledge nodes. The target knowledge node is used to represent the target storage area in the target refrigerator.

7. A device for determining food storage information, characterized in that, include: The first acquisition module is used to acquire a food storage query request, wherein the food storage query request is used to request the storage parameters of storing target food on the target refrigerator; The second acquisition module is used to acquire a set of food features of the target food and a set of refrigerator status features of the target refrigerator in response to the food storage query request; wherein the set of refrigerator status features includes the current storage status of the target refrigerator. The query module is used to query a first set of knowledge nodes associated with the set of food features in a preset target knowledge graph, and to query a second set of knowledge nodes associated with the set of refrigerator status features in the target knowledge graph. The search module is used to search for at least one pair of knowledge nodes in the first group of knowledge nodes and the second group of knowledge nodes, wherein the two knowledge nodes in each pair of knowledge nodes are related and belong to the first group of knowledge nodes and the second group of knowledge nodes respectively. A generation module is configured to, upon finding the at least one pair of knowledge nodes, generate food storage information based on the knowledge nodes belonging to the second group of knowledge nodes in each of the at least one pair of knowledge nodes, wherein the food storage information includes storage parameters in one or more dimensions of storing the target food on the target refrigerator; The generation module is further configured to: If at least one pair of knowledge nodes corresponding to each intent feature in the request intent feature is found in the first group of knowledge nodes and the second group of knowledge nodes, the storage parameters represented by some or all of the knowledge nodes in the second group of knowledge nodes in each pair of knowledge nodes are determined as the storage parameters included in the food storage information, wherein the request intent feature is the intent feature obtained by performing intent recognition on the food storage query request. If at least one pair of knowledge nodes corresponding to a portion of the intent features in the request intent features is found in the first group of knowledge nodes and the second group of knowledge nodes, target knowledge nodes that are associated with the candidate knowledge nodes are searched in the target knowledge graph. The candidate knowledge nodes are some or all of the knowledge nodes in the second group of knowledge nodes in each of the at least one pair of knowledge nodes. The storage parameters represented by the candidate knowledge nodes and the target knowledge nodes are determined as the storage parameters included in the food storage information. The request intent features are intent features obtained by performing intent recognition on the food storage query request.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method of any one of claims 1 to 6.

9. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method of any one of claims 1 to 6 through the computer program.

Images