WO2024001196A1

WO2024001196A1 - Household appliance control method and apparatus, storage medium, and electronic apparatus

Info

Publication number: WO2024001196A1
Application number: PCT/CN2023/075053
Authority: WO
Inventors: 邓邱伟; 申钊; 张旭; 翟建光
Original assignee: 青岛海尔科技有限公司; 青岛海尔智能家电科技有限公司; 海尔智家股份有限公司
Priority date: 2022-06-29
Filing date: 2023-02-08
Publication date: 2024-01-04
Also published as: CN115268282A

Abstract

A household appliance control method and apparatus, a storage medium, and an electronic apparatus, which relate to the technical field of smart homes. The household appliance control method comprises: acquiring N device operation logs (S202); generating a heterogeneous graph on the basis of the N device operation logs (S204), wherein the heterogeneous graph comprises a plurality of operation jump nodes amongst M household appliances and a connection relationship amongst the plurality of operation jump nodes; determining in the heterogeneous graph jump probability distribution between a target operation jump node and other operation jump nodes so as to determine a jump node associated with the target operation jump node (S206); and, according to the jump node associated with the target operation jump node, determining a target operation instruction of a target household appliance (S208).

Description

Control method, device, storage medium and electronic device for home appliances

This disclosure claims priority to the Chinese patent application filed with the China Patent Office on June 29, 2022, with application number 202210751813.9 and the invention title "Control method, device, storage medium and electronic device for home appliances", the entire content of which is incorporated by reference. incorporated in this disclosure.

Technical field

The present disclosure relates to the field of equipment, and specifically, to a control method, device, storage medium and electronic device for home appliances.

Background technique

Scenario generation is a difficult point, involving permutations and combinations of multiple network devices and multiple functions. The possible order of magnitude is hundreds of millions. However, not all permutations and combinations are meaningful, and it is basically impossible to achieve it by manual screening. Manually predefined scenarios are relatively monotonous, and it is difficult to take into account the personalized needs of users. At present, the control of home appliances is still based on "single point intelligence", that is, focusing on the intelligence of a single network device. Generate control instructions based on isomorphic graphs, ignoring the attributes of nodes and edges in the graph. It cannot accurately generate control instructions for interconnection between home appliances.

Contents of the invention

Embodiments of the present disclosure provide a method, device, storage medium, and electronic device for controlling home appliances, so as to at least solve the problem in the related art that control instructions for interconnection between home appliances cannot be accurately generated.

According to an embodiment of the present disclosure, a method for controlling home appliances is provided, including: obtaining N device operation logs, wherein each of the above device operation logs includes multiple operation jump instructions executed on M home appliances. , the above-mentioned operation jump instruction is used to represent jumping from the first operation control of the above-mentioned home appliance to other operation control, the above-mentioned M and the above-mentioned N are both natural numbers greater than or equal to 1; generate heterogeneous based on N above-mentioned device operation logs Figure, wherein the above-mentioned heterogeneous graph includes multiple operation jump nodes between the M above-mentioned home appliances and connection relationships between the multiple above-mentioned operation jump nodes; it is determined in the above-mentioned heterogeneous graph Determine the jump probability distribution between the target operation jump node and other above-mentioned operation jump nodes to determine the jump node associated with the above-mentioned target operation jump node; determine according to the jump node associated with the above-mentioned target operation jump node Target operating instructions for the target home appliance.

According to an embodiment of the present disclosure, a control device for home appliances is provided, including: a first acquisition module configured to acquire N device operation logs, wherein each of the above device operation logs includes information on M home appliances. Multiple operation jump instructions are executed. The above-mentioned operation jump instructions are used to indicate jumping from the first operation control of the above-mentioned home appliance to other operation controls. The above-mentioned M and the above-mentioned N are both natural numbers greater than or equal to 1; the first The generation module is configured to generate a heterogeneous graph based on the N above-mentioned device operation logs, wherein the above-mentioned heterogeneous graph includes a plurality of operation jump nodes between the M above-mentioned home appliances and a plurality of the above-mentioned operation jump nodes. The connection relationship; the first determination module is configured to determine the jump probability distribution between the target operation jump node and other above-mentioned operation jump nodes in the above-mentioned heterogeneous graph to determine the jump probability distribution associated with the above-mentioned target operation jump node. Jump node; the second determination module is configured to determine the target operation instruction of the target home appliance device according to the jump node associated with the above-mentioned target operation jump node.

According to yet another embodiment of the present disclosure, a computer-readable storage medium is also provided. A computer program is stored in the computer-readable storage medium, wherein the computer program is configured to execute any of the above methods when running. Steps in Examples.

According to yet another embodiment of the present disclosure, an electronic device is also provided, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to perform any of the above. Steps in method embodiments.

Through the present disclosure, N device operation logs are obtained, wherein each device operation log includes a plurality of operation jump instructions executed on M home appliances, and the operation jump instructions are used to represent the first operation on the home appliances. Control jumps to other operation controls. Both M and N are natural numbers greater than or equal to 1; a heterogeneous graph is generated based on N device operation logs. The heterogeneous graph includes multiple operation jumps between M home appliances. The connection relationship between a node and multiple operation jump nodes; determine the jump probability distribution between the target operation jump node and other operation jump nodes in the heterogeneous graph to determine the jump associated with the target operation jump node Jump node; determine the target operation instruction of the target home appliance according to the jump node associated with the target operation jump node. Therefore, it can solve the problem that the related technology cannot accurately generate the control of the interconnection between home appliances. A question of instructions.

Description of drawings

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

In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those of ordinary skill in the art, It is said that other drawings can be obtained based on these drawings without exerting creative labor.

Figure 1 is a schematic diagram of the hardware environment of a method for controlling home appliances according to an embodiment of the present disclosure;

Figure 2 is a control method of a home appliance according to an embodiment of the present disclosure;

Figure 3 is a schematic diagram of nodes and edges according to an embodiment of the present disclosure;

Figure 4 is a schematic diagram of a probability distribution according to an embodiment of the present disclosure;

Figure 5 is a structural block diagram of a control device for home appliances according to an embodiment of the present disclosure;

FIG. 6 is a structural block diagram of an electronic device according to an embodiment of the present disclosure.

Detailed ways

In order to enable those skilled in the art to better understand the present disclosure, the following will clearly and completely describe the technical solutions in the present disclosure embodiments in conjunction with the accompanying drawings. Obviously, the described embodiments are only These are part of the embodiments of this disclosure, not all of them. Based on the embodiments in this disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts should fall within the scope of protection of this disclosure.

It should be noted that the terms "first", "second", etc. in the description and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances so that the embodiments of the disclosure described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "include" and "have "have" and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus that consists of a series of steps or units need not be limited to those steps or units expressly listed, but may Includes other steps or units that are not expressly listed or that are inherent to these processes, methods, products, or devices.

According to an aspect of an embodiment of the present disclosure, a method for controlling a home appliance is provided. The control method of this home appliance device is widely used in whole-house intelligent digital control application scenarios such as smart home, smart home, smart home equipment ecology, and smart residence (Intelligence House) ecology. Optionally, in this embodiment, the above method for controlling home appliances can be applied to a hardware environment composed of a terminal device 102 and a server 104 as shown in FIG. 1 . As shown in Figure 1, the server 104 is connected to the terminal device 102 through the network and can be used to provide services (such as application services, etc.) for the terminal or the client installed on the terminal. The database can be set on the server or independently of the server. To provide data storage services for the server 104, cloud computing and/or edge computing services may be configured on the server or independently of the server, and are configured to provide data computing services for the server 104.

The above-mentioned network may include but is not limited to at least one of the following: wired network, wireless network. The above-mentioned wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, and local area network. The above-mentioned wireless network may include at least one of the following: WIFI (Wireless Fidelity, Wireless Fidelity), Bluetooth. The terminal device 102 may be, but is not limited to, a PC, a mobile phone, a tablet, a smart air conditioner, a smart hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing equipment, a smart dishwasher, or a smart projection device. , smart TV, smart clothes drying rack, smart curtains, smart audio and video, smart sockets, smart audio, smart speakers, 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 steamers, smart microwave ovens, smart kitchen appliances, smart purifiers, smart water dispensers, smart door locks, etc.

This embodiment provides a control method for home appliances. Figure 2 is a control method for home appliances according to an embodiment of the present disclosure. As shown in Figure 2, the process includes the following steps:

Step S202: Obtain N device operation logs, where each device operation log includes multiple operation jump instructions executed on M home appliances. The operation jump instructions are used to indicate a jump from the first operation control on the home appliances. Moving to other operational controls, M and N are both natural numbers greater than or equal to 1;

Step S204, generate a heterogeneous graph based on N device operation logs, where the heterogeneous graph includes multiple operation jump nodes and connection relationships between multiple operation jump nodes between M home appliances;

Step S206, determine the jump probability distribution between the target operation jump node and other operation jump nodes in the heterogeneous graph to determine the jump node associated with the target operation jump node;

Step S208: Determine the target operation instruction of the target home appliance according to the jump node associated with the target operation jump node.

Optionally, the values of N and M can be flexibly set based on the actual reference scene or composition requirements. For example, more than 5 million device operation logs are obtained, and each device operation log represents an operation of a home appliance in a family. transfer. For example, take a household as a unit and record the control operations from turning on the air conditioner to turning off the air conditioner. In addition, a device operation log includes contextual features such as time, location, weather, and some family portrait features from the from operation to the to operation.

The execution subject of the above steps may be a terminal, a server, a specific processor provided in the terminal or server, or a processor or processing device provided relatively independently from the terminal or server, but is not limited thereto.

Through the above steps, N device operation logs are obtained, wherein each device operation log includes multiple operation jump instructions executed on M home appliance devices, and the operation jump instructions are used to represent the first operation on the home appliance device. Control jumps to other operation controls. Both M and N are natural numbers greater than or equal to 1; a heterogeneous graph is generated based on N device operation logs. The heterogeneous graph includes multiple operation jumps between M home appliances. The connection relationship between a node and multiple operation jump nodes; determine the jump probability distribution between the target operation jump node and other operation jump nodes in the heterogeneous graph to determine the jump associated with the target operation jump node Jump node; determine the target operation instruction of the target home appliance according to the jump node associated with the target operation jump node. Since in the above method, a heterogeneous graph of operation logs is constructed, the attributes of the edges between multiple operation jump nodes and the attributes of multiple operation jump nodes can be obtained. By integrating the attributes of edges and nodes and the jump probability distribution between the target operation jump node and other operation jump nodes, control instructions for home appliances can be generated more closely to the actual situation. While ensuring the search speed, it also improves the accuracy and diversity of search control instructions. Therefore, the problem in related technologies that the control instructions for interconnection between home appliances cannot be accurately generated can be solved.

In an exemplary embodiment, N device operation logs are obtained, including:

S1, obtain each device operation log and obtain N device operation logs. To obtain each device operation log, perform the following operations:

Obtain operating instructions for controlling home appliances in a preset area and obtain multiple operating instructions;

At least one of the following information is determined as a device operation log: multiple operation instructions, time information corresponding to the multiple operation instructions, location information corresponding to the multiple operation instructions, and environment information corresponding to the multiple operation instructions.

Optionally, the preset area can be a local area network. For example, with a family as a unit, operations such as "turn on the air conditioner - turn off the air conditioner" that occur in a family are obtained, and each operation issued in the "turn on the air conditioner - turn off the air conditioner" is recorded. The time of the command, the location of the air conditioner, and weather information (for example, sunny or rainy day), etc. By obtaining each device operation log on a household basis, heterogeneous graphs can be accurately generated based on the contextual features of the device operation logs.

In an exemplary embodiment, a heterogeneous graph is generated based on N device operation logs, including:

S1, perform deduplication processing on N device operation logs to obtain K device operation logs, where K is a natural number less than or equal to M;

S2, determine the operation category of each device operation log in the K device operation logs;

S3, determine the operation jump node corresponding to each operation jump instruction in the K device operation logs, and obtain multiple operation jump nodes;

S4, determine the connection relationship between multiple operation jump nodes and obtain multiple connection edges;

S5 generates a heterogeneous graph based on operation categories, multiple operation jump nodes, and multiple connecting edges.

Optionally, the value of K can be flexibly set based on actual reference scenarios or composition requirements. For example, removing duplicate logs from 5 million device operation logs results in 3 million device operation logs.

Optionally, the deduplicated device operation logs can be set in a collection. To record the log information corresponding to the device operation log in the collection (for example, the type of log, the time and location of acquisition, etc.).

In an exemplary embodiment, after generating the heterogeneous graph based on N device operation logs, the method also includes include:

S1, determine the operation category corresponding to each operation jump node;

S2, based on the operation category corresponding to each operation jump node, uses the heterogeneous graph to respond to the operation instructions acting on the home appliance.

Optionally, the operation categories corresponding to different operation jump nodes may be the same or different. For example, the operation category of the instruction to turn on the air conditioner is "turn on". Adjusting the temperature of the refrigerator to 4 degrees falls under the "temperature adjustment" category. Select the operation jump node corresponding to the user's operation instruction from the heterogeneous graph. For example, the operation jump node corresponding to the air conditioner can be <turn on the air conditioner, lower the air conditioner temperature, and increase the air conditioner wind speed>.

In an exemplary embodiment, determining the jump probability distribution between the target operation jump node and other operation jump nodes in the heterogeneous graph to determine the jump node associated with the target operation jump node includes:

S1, receives the operation instruction acting on the target home appliance, where the operation instruction includes the target operation jump node;

S2, determine the environmental information in the preset area corresponding to the operation instruction, and the characteristic information that triggers the operation instruction, where the target home appliance is set in the preset area;

S3, use the heterogeneous graph to determine the jump probability distribution between the target operation jump node and the adjacent operation jump nodes, where the adjacent operation jump nodes are included in other operation jump nodes;

S4: Determine the jump node associated with the target operation jump node based on the jump probability distribution, environmental information and feature information.

Optionally, the operation instructions may be in the form of voice or touch screen. For example, the user issues an instruction to "turn on the water heater" and searches for the operation jump nodes adjacent to "turn on the water heater" in the heterogeneous graph, such as "adjust the air conditioner temperature to 28 degrees", "turn on the ventilation equipment", etc. And calculate the jump probability between "Adjust the air conditioner temperature to 28 degrees" and "Turn on the ventilation equipment". When the probability of jump between "Adjust the air conditioner temperature to 28 degrees" and "Turn on the ventilation equipment" is greater than 70%, determine whether "Adjust the air conditioner temperature to 28 degrees" and "Turn on the ventilation equipment" are the same as "Turn on the water heater" The associated jump node controls the opening of the air conditioner and ventilation equipment according to the control instructions corresponding to the associated jump node.

In an exemplary embodiment, using a heterogeneous graph to determine the jump probability distribution between a target operation jump node and adjacent operation jump nodes includes:

S1, determine multiple operation jump nodes associated with the target operation jump node;

S2, determine the connection relationships between multiple associated operation jump nodes and the target operation jump node in the heterogeneous graph, and determine multiple connection relationships;

S3, determine the sum of weights of multiple connection relationships;

S4, the sum of normalized weights to determine the jump probability distribution.

Optionally, multiple connection relationships may be connections between operation jump nodes in the heterogeneous graph. Constitutes the edges of a heterogeneous graph. For example, the transition from operation i to operation j is an edge, and the edge is a directed graph. If there are multiple transfer operations between node i and node j, then there will be multiple edges, and there will be homogeneous edges among the multiple edges. You can aggregate them according to the edge attributes, and aggregate the edges with the same attributes together.

Optionally, in this embodiment, without considering user or family characteristic information and contextual characteristics, all edge weights belonging to node i to node j can be added together and then normalized to determine the probability distribution.

S2, determine multiple connecting edges between the target operation jump node and the associated multiple operation jump nodes as sample data;

S3, use the sample data to establish a network model to use the network model to output a jump probability distribution.

Optionally, each connecting edge in the heterogeneous graph can be used as a sample. For example, in a heterogeneous graph, node i to node j can produce T samples. After obtaining the training samples, xgboost or LSTM time series modeling can be used to learn the probability from node i to any of its adjacent nodes.

In an exemplary embodiment, after determining the target operation instruction of the target home appliance according to the jump node associated with the target operation jump node, the method further includes:

S1. Modify the target operation instruction according to the device information of the target home appliance.

Optionally, the revised rules include but are not limited to: the sub-function of the home appliance must be turned on after the home appliance itself is turned on; the time difference between turning on and off the same home appliance must be greater than the established threshold; the output operation instructions do not include pause operations. instruction.

The present disclosure is described below with reference to specific embodiments:

This embodiment takes the control of home appliances as an example. In this embodiment, the operation (action) of the home appliances is a specific operation on the network device function, such as "turn on the air conditioner", "increase the wind speed of the air conditioner". ”, “TV pause”, the network controller function is used to express control instructions for home appliances. In this embodiment, the network appliance function can generate usage scenarios for home appliances. For example, when taking a bath, a bathing scene is recommended to the user (the scene is the linked operation of several network appliances. The bathing scene here can be <turn on the water heater, set Set the temperature to 39°C, turn on the bathroom heater, and turn on the ventilation fan>).

Scene is set to represent an operation sequence (that is, associated operation instructions), for example, <turn on the air conditioner, lower the air conditioner temperature, increase the air conditioner fan speed>.

This embodiment uses multiple operation logs to generate a heterogeneous graph, where the heterogeneous graph G=(V, E), V is used to represent a set of nodes, V={v ₁ , v ₂ ,..., _vi , ...}, 1≤i≤|V|, E is used to represent the set of edges E={e ₁ , e ₂ ,..., e _j ,...}, 1≤j≤|E|. If there is a mapping Φ: V→O and a mapping Ψ: E→R, O and R are used to represent the type set of nodes and edges respectively. If |O|+|R|＞2, the graph G is a heterogeneous graph. In this embodiment, action is used to represent nodes in the heterogeneous graph, and the transfer relationship between actions is the edge of the heterogeneous graph.

The main implementation process of this embodiment includes:

Step 1, collect and clean the historical operation logs of all users;

Step2, build a heterogeneous graph based on the operation log;

Step 3. Based on the heterogeneous graph, use the beamsearch strategy to search and produce several scenarios (operating instructions associated with home appliances);

Step 4: Modify the output scenario according to the established rules.

In this embodiment, collecting and cleaning the historical operation logs of all users specifically includes: obtaining more than 5 million records, each record is an operation transfer of a family, for example, from turning on the air conditioner to turning off the air conditioner, here the family is taken as a unit. In addition, a record will include contextual features such as time, location, weather, and some family portrait features from the from operation to the to operation.

In this embodiment, building a heterogeneous graph specifically includes:

1) Define nodes (corresponding to the operation jump nodes in the above): Based on the full data obtained in Step 1, the action set can be obtained by deduplicating all actions, which constitutes all the nodes v _i ∈ V of the heterogeneous graph, and defines each The category _{c i} _to which node vi belongs, c _i ∈C, for example, "turn on the air conditioner" belongs to the "cooling" category, and "turn on the oven" belongs to the "cooking" category.

2) Define the edge (corresponding to the connecting edge above): the transfer from operation i to operation j is an edge, represented by e _ij (here is a directed graph). If there are multiple transfer operations between node i and node j, then there will be multiple edges, and there will be homogeneous edges among the multiple edges. You can aggregate them according to the edge attributes, and aggregate the edges with the same attributes together.

The schematic diagram of nodes and edges is shown in Figure 3. Optionally, use represents the set of edges from i to j, where, is the t-th edge from node i to j, using a vector To represent the attributes of the t-th edge of E _ij , use a scalar to represent the weight of the t-th edge of E _ij . The actual meaning of the weight is the number of times operation i is transferred to operation j within the statistical range.

3) Define the heterogeneous graph: After obtaining all nodes and edges, the heterogeneous graph G=(V, E) can be constructed;

4) Define metapath: metapath is a human-designed walking rule, which is set to constrain the type of node selected when walking, M=[m ₁ , m ₂ ,..., m _m ], m comes from the node type set C. For example, if M = [Cooling, Refrigeration, Light], the first two positions in the output scene operation sequence must be nodes of the "Cooling" class, and the third must be a node of the "Light" class. This is similar to the idea of metapath2vec, but metapath is not required to be symmetrical.

In this embodiment, based on the heterogeneous graph, the beamsearch strategy (beamsearch strategy is used to select better results) is used to search, and several scenarios are generated; searching based on beamsearch is a kind of Trade-off between search complexity and search speed. If there is no beam constraint on the search, the complexity will increase exponentially every time it is expanded to one level, which is equivalent to a full arrangement. If depth is the depth, n is the number of nodes, k is the search bandwidth, the complexity is O(n ^depth ), using beamseach to constrain the search bandwidth can reduce the complexity to O(depth·k·n). If a greedy strategy is used to search, it is equivalent to beam=1, that is, the search only produces one sequence.

When doing beamsearch search, each time you expand to one level, you need to refer to the probability distribution from the current node to its leading node, P(node _j |node _i ), Represents the domain of node i. It is also necessary to consider the user or family characteristics and contextual characteristics that trigger scene generation, which are represented by q. Both q and a _ij are n-order vectors, so the probability distribution to be learned is P(node _j |node _i , q).

In this embodiment, the probability distribution can be determined in the following two ways:

1) Use the generative model generative-mode1:

Based on the heterogeneous graph of Step 2, if user or family characteristics and context characteristics are not considered, the probability distribution is obtained by adding all the edge weights belonging to node i to node j and then normalizing them, that is function.

2) Use the discriminative model discriminative-mode1:

Each edge of the heterogeneous graph in Step 2 can be used as a sample. The action corresponding to node i and the attributes of the edge from i to j are used as independent variables x, and the action corresponding to node j is used as dependent variable y. More formally: In a heterogeneous graph, node i to node j can produce T samples, each sample s ^(t) = {x ^(t) , y ^(t) }, y ^(t) = action _j , where t∈[1, T]. After obtaining the training samples, xgboost or LSTM time series modeling can be used to learn the probability P(node _j |node _i , p)=model(node _i , p) from node i to any of its adjacent nodes.

In practical applications, it is found that heterogeneous graphs are highly sparse, and the discriminant method is more practical.

In addition, when selecting the next node, not only the probability distribution from the current node to its adjacent nodes is considered, but also the node of the previous step is considered, for example, as shown in Figure 4:

t->v->z, the weight is 0 because vz has no path;

t->v->t, the weight is 0 because looking back is not allowed;

t->v->x3, the weight is w(t, v)+w(v, x ₃ );

t->v->x1, the weight is w(t, v)+w(v, x ₁ )+α·w(t, x ₁ ). Because t->x1 also has a path, the weight of this part is also considered Come in, controlled by a coefficient α, α>0, the larger the value, the more likely it is to wander locally.

When performing walking in this embodiment, the walking can be performed based on the defined metapath, and nodes that do not meet the metapath requirements will not be selected as the next node.

In this embodiment, the output scene is modified according to established rules. Specific revised rules include: the device sub-function must be turned on after the device itself is turned on; the time difference between turning on and off the same device must be greater than the established threshold; the output scene does not contain pause-type operations.

To sum up, in this embodiment, in the field of intelligent network device linkage, it is proposed to abstract the actual network device linkage problem into a heterogeneous graph for modeling, and define the attributes of each network device and each transfer operation. During reasoning, Combining user characteristics and contextual characteristics is more realistic; it can realize beamsearch's performance in scene generation and improve the accuracy and diversity of search results while ensuring search speed; based on machine learning methods, it considers user characteristics and Contextual features predict the user’s next actions. It is more realistic, making the output results more personalized, and improving the user experience; better algorithm performance, even for depth-first search, ensures that the results are controlled at the same time, making the engineering better and easier to use. .

This embodiment also provides an image processing device, which is used to implement the above embodiments and preferred implementations. What has been described will not be described again. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

Figure 5 is a structural block diagram of a control device for home appliances according to an embodiment of the present disclosure. As shown in Figure 5, the device includes:

The first acquisition module 52 is configured to acquire N device operation logs, wherein each device operation log includes multiple operation jump instructions executed on M home appliances, and the operation jump instructions are used to represent the operation jump instructions from the pair of M home appliances. The first operation control of the home appliance jumps to other operation controls, and M and N are both natural numbers greater than or equal to 1;

The first generation module 54 is configured to generate a heterogeneous graph based on N device operation logs, where the heterogeneous graph includes multiple operation jump nodes between M home appliances and multiple operation jump nodes between them. connection relationship;

The first determination module 56 is configured to determine the jump probability distribution between the target operation jump node and other operation jump nodes in the heterogeneous graph to determine the jump node associated with the target operation jump node;

The second determination module 58 is configured to determine the target operation instruction of the target home appliance according to the jump node associated with the target operation jump node.

In an exemplary embodiment, the above-mentioned first acquisition module includes:

The first acquisition unit is configured to acquire each of the above-mentioned device operation logs and obtain N above-mentioned device operation logs, wherein obtaining each of the above-mentioned device operation logs performs the following operations: acquiring the operation instructions for controlling the above-mentioned home appliances in the preset area , obtain multiple operation instructions; determine at least one of the following information as the above-mentioned device operation log: multiple above-mentioned operation instructions, time information corresponding to the multiple above-mentioned operation instructions, location information corresponding to multiple above-mentioned operation instructions, multiple above-mentioned operations The environment information corresponding to the instruction.

In an exemplary embodiment, the above-mentioned first generation module includes:

The first processing unit is configured to perform deduplication processing on N of the above-mentioned device operation logs to obtain K of the above-mentioned device operation logs, where the above-mentioned K is a natural number less than or equal to the above-mentioned M;

The first determination unit is configured to determine the operation category of each of the K above-mentioned device operation logs;

The second determination unit is configured to determine the operation jump node corresponding to each of the above-mentioned operation jump instructions in the K above-mentioned device operation logs, and obtain a plurality of the above-mentioned operation jump nodes;

The third determination unit is configured to determine the connection relationship between multiple above-mentioned operation jump nodes and obtain multiple connection edges;

The first generation unit is configured to be based on the above-mentioned operation category, a plurality of the above-mentioned operation jump nodes and the above The multiple connecting edges generate the above heterogeneous graph.

In an exemplary embodiment, the above device further includes:

The third determination module is configured to determine the operation category corresponding to each of the above operation jump nodes after generating a heterogeneous graph based on the N above-mentioned device operation logs;

The first response module is configured to use the above-mentioned heterogeneous graph to respond to the operation instructions acting on the above-mentioned home appliance based on the operation category corresponding to each of the above-mentioned operation jump nodes.

In an exemplary embodiment, the above-mentioned first determination module includes:

The first receiving unit is configured to receive an operation instruction acting on the above-mentioned target home appliance, wherein the above-mentioned operation instruction includes the above-mentioned target operation jump node;

The fourth determination unit is configured to determine the environmental information in the preset area corresponding to the above-mentioned operation instruction, and the characteristic information that triggers the above-mentioned operation instruction, wherein the above-mentioned target home appliance is arranged in the above-mentioned preset area;

The fifth determination unit is configured to determine the jump probability distribution between the above-mentioned target operation jump node and the above-mentioned adjacent operation jump node using the above-mentioned heterogeneous graph, wherein the adjacent above-mentioned operation jump node is included in other In the jump node of the above operation;

The sixth determination unit is configured to determine the jump node associated with the target operation jump node based on the jump probability distribution, the environment information and the characteristic information.

In an exemplary embodiment, the fifth determination unit mentioned above includes:

The first determining subunit is configured to determine multiple operation jump nodes associated with the above-mentioned target operation jump node;

The second determination subunit is configured to determine connection relationships between multiple associated operation jump nodes and the target operation jump node in the heterogeneous graph, and determine multiple connection relationships;

The third determination subunit is configured to determine the sum of weights of multiple above-mentioned connection relationships;

The first processing subunit is configured to normalize the sum of the above weights to determine the above jump probability distribution.

The fourth determination subunit is configured to determine multiple operation jump nodes associated with the above-mentioned target operation jump node;

The fifth determination subunit is configured to determine multiple connecting edges between the above-mentioned target operation jump node and multiple associated above-mentioned operation jump nodes as sample data;

The first establishment subunit is configured to establish a network model using the above-mentioned sample data, so as to use the above-mentioned network model to output the above-mentioned jump probability distribution.

In an exemplary embodiment, the above device further includes:

The first correction module is configured to modify the target operation instruction according to the device information of the target home appliance after determining the target operation instruction of the target home appliance according to the jump node associated with the target operation jump node.

It should be noted that each of the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but is not limited to this: the above modules are all located in the same processor; or the above modules can be implemented in any combination. The forms are located in different processors.

Embodiments of the present disclosure also provide a storage medium in which a computer program is stored, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.

In an exemplary embodiment, in this embodiment, the above-mentioned storage medium may be configured to store a computer program for performing the following steps:

S1, obtain N device operation logs, wherein each device operation log includes multiple operation jump instructions executed on M home appliances, and the operation jump instructions are used to represent the operation jump instructions from the M home appliances. The first operation control jumps to other operation controls, and the M and N are both natural numbers greater than or equal to 1;

S2. Generate a heterogeneous graph based on N device operation logs, wherein the heterogeneous graph includes multiple operation jump nodes between the M home appliance devices and between multiple operation jump nodes. connection relationship;

S3: Determine the relationship between the target operation jump node and other operation jump nodes in the heterogeneous graph. a jump probability distribution to determine a jump node associated with the target operation jump node;

S4: Determine the target operation instruction of the target home appliance according to the jump node associated with the target operation jump node.

In an exemplary embodiment, in this embodiment, the above-mentioned storage medium may include but is not limited to: U disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as Various media that can store computer programs such as RAM), removable hard drives, magnetic disks or optical disks.

Embodiments of the present disclosure also provide an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

In an exemplary embodiment, the above-mentioned electronic device may further include a transmission device and an input-output device, wherein the transmission device is connected to the above-mentioned processor, and the input-output device is connected to the above-mentioned processor.

In an exemplary embodiment, in this embodiment, the above-mentioned processor may be configured to perform the following steps through a computer program:

S3: Determine the jump probability distribution between the target operation jump node and other operation jump nodes in the heterogeneous graph to determine the jump node associated with the target operation jump node;

Optionally, those of ordinary skill in the art can understand that the structure shown in Figure 6 is only illustrative, and the electronic device can also be a smart phone (such as an Android phone, iOS phone, etc.), a tablet computer, a handheld computer, and a Mobile Internet Devices (MID), PAD and other terminal equipment. FIG. 6 does not limit the structure of the above-mentioned electronic device. For example, the electronic device may also include more or fewer components (such as network interfaces, etc.) than shown in FIG. 6 , or have a different configuration than that shown in FIG. 6 .

The memory 702 can be used to store software programs and modules, such as program instructions/modules corresponding to the communication connection methods and devices in the embodiments of the present disclosure. The processor 704 executes various software programs and modules by running the software programs and modules stored in the memory 702. Function application and data processing, that is, realizing the above communication connection method. Memory 702 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 702 may further include memory located remotely relative to the processor 704, and these remote memories may be connected to the terminal through a network. Examples of the above-mentioned networks include but are not limited to the Internet, intranets, local area networks, mobile communication networks and combinations thereof. As an example, as shown in FIG. 6 , the memory 702 may include, but is not limited to, the first acquisition module 52 , the first generation module 54 , the first determination module 56 , and the second determination module 58 in the communication connection device. In addition, it may also include but is not limited to other modular units in the above-mentioned communication connection device, which will not be described again in this example.

Optionally, the above-mentioned transmission device 706 is used to receive or send data via a network. Specific examples of the above-mentioned network may include wired networks and wireless networks. In one example, the transmission device 706 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers through network cables to communicate with the Internet or a local area network. In one example, the transmission device 1106 is a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet wirelessly.

In addition, the above-mentioned electronic device also includes: a display 708 configured to display the above-mentioned task knowledge graph; and a connection bus 710 configured to connect various module components in the above-mentioned electronic device.

In an exemplary embodiment, for specific examples in this embodiment, reference may be made to the examples described in the above-mentioned embodiments and optional implementations, and details will not be described again in this embodiment.

Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present disclosure can be implemented using general-purpose computing devices, and they can be concentrated on a single computing device, or distributed across a network composed of multiple computing devices. , in one exemplary embodiment, they may be implemented using a computing device executable Program code is implemented so that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in a different order than herein, or may be made separately. into individual integrated circuit modules, or multiple modules or steps among them are made into a single integrated circuit module. As such, the present disclosure is not limited to any specific combination of hardware and software.

For specific examples in this embodiment, reference may be made to the examples described in the above-mentioned embodiments and exemplary implementations, and details will not be described again in this embodiment.

The above are only preferred embodiments of the present disclosure. It should be pointed out that for those of ordinary skill in the art, several improvements and modifications can be made without departing from the principles of the present disclosure. These improvements and modifications can also be made. should be regarded as the scope of protection of this disclosure.

Claims

A control method for home appliances, including:

Obtain N device operation logs, wherein each device operation log includes a plurality of operation jump instructions executed on M home appliances, and the operation jump instructions are used to represent the first step from the first operation to the home appliances. The operation control jumps to other operation control, and the M and N are both natural numbers greater than or equal to 1;

A heterogeneous graph is generated based on N device operation logs, wherein the heterogeneous graph includes multiple operation jump nodes between M home appliance devices and connections between multiple operation jump nodes. relation;

Determine a jump probability distribution between a target operation jump node and other operation jump nodes in the heterogeneous graph to determine a jump node associated with the target operation jump node;

The target operation instruction of the target home appliance is determined according to the jump node associated with the target operation jump node.
The method according to claim 1, wherein obtaining N device operation logs includes:

Obtain each of the device operation logs and obtain N device operation logs. The following operations are performed to obtain each of the device operation logs:

Obtain operating instructions for controlling the home appliance in the preset area, and obtain multiple operating instructions;

Determine at least one of the following information as the device operation log: a plurality of operation instructions, time information corresponding to a plurality of operation instructions, location information corresponding to a plurality of operation instructions, location information corresponding to a plurality of operation instructions, environmental information.
The method according to claim 1, wherein generating a heterogeneous graph based on N device operation logs includes:

Perform deduplication processing on N equipment operation logs to obtain K equipment operation logs, where K is a natural number less than or equal to M;

Determine the operation category of each of the K device operation logs;

Determine the operation jump nodes corresponding to each of the operation jump instructions in the K device operation logs, and obtain a plurality of the operation jump nodes;

Determine the connection relationship between multiple operation jump nodes and obtain multiple connection edges;

The heterogeneous graph is generated based on the operation category, the plurality of operation jump nodes, and the plurality of connecting edges.
The method according to claim 3, wherein after generating the heterogeneous graph based on N device operation logs, the method further includes:

Determine the operation category corresponding to each operation jump node;

Based on the operation category corresponding to each operation jump node, the heterogeneous graph is used to respond to the operation instructions acting on the home appliance.
The method according to claim 1, wherein a jump probability distribution between a target operation jump node and other operation jump nodes is determined in the heterogeneous graph to determine the relationship between the target operation jump node and the target operation jump node. Associated jump nodes include:

Receive an operation instruction acting on the target home appliance, wherein the operation instruction includes the target operation jump node;

Determine the environmental information in the preset area corresponding to the operation instruction, and the characteristic information that triggers the operation instruction, wherein the target home appliance is set in the preset area;

The heterogeneous graph is used to determine the jump probability distribution between the target operation jump node and the adjacent operation jump nodes, wherein the adjacent operation jump nodes are included in other operation jump nodes. in transfer node;

Based on the jump probability distribution, the environment information and the characteristic information, a jump node associated with the target operation jump node is determined.
The method according to claim 5, wherein using the heterogeneous graph to determine the jump probability distribution between the target operation jump node and the adjacent operation jump nodes includes:

Determine a plurality of operation jump nodes associated with the target operation jump node;

Determine connection relationships between multiple associated operation jump nodes and the target operation jump node in the heterogeneous graph, and determine multiple connection relationships;

Determine the sum of the weights of multiple connection relationships;

The sum of weights is normalized to determine the jump probability distribution.
The method according to claim 5, wherein using the heterogeneous graph to determine the jump probability distribution between the target operation jump node and the adjacent operation jump nodes includes:

Determine a plurality of operation jump nodes associated with the target operation jump node;

Determine multiple connecting edges between the target operation jump node and multiple associated operation jump nodes as sample data;

A network model is established using the sample data to output the jump probability distribution using the network model.
The method according to claim 1, wherein after determining the target operation instruction of the target home appliance according to the jump node associated with the target operation jump node, the method further includes:

The target operation instruction is modified according to the device information of the target home appliance.
A control device for home appliances, which includes:

The first acquisition module is configured to acquire N device operation logs, wherein each of the device operation logs includes multiple operation jump instructions executed on M home appliances, and the operation jump instructions are used to represent the slave operation logs. The first operation control of the home appliance jumps to other operation controls, and the M and N are both natural numbers greater than or equal to 1;

The first generation module is configured to generate a heterogeneous graph based on N device operation logs, wherein the heterogeneous graph includes a plurality of operation jump nodes between the M home appliances and a plurality of the Operate the connection relationship between jump nodes;

The first determination module is configured to determine the jump probability distribution between the target operation jump node and other operation jump nodes in the heterogeneous graph to determine the jump associated with the target operation jump node. transfer node;

The second determination module is configured to determine the target operation instruction of the target home appliance according to the jump node associated with the target operation jump node.
The device according to claim 9, wherein the first acquisition module includes:

The first acquisition unit is configured to acquire each of the above-mentioned device operation logs and obtain N above-mentioned device operation logs, wherein obtaining each of the above-mentioned device operation logs performs the following operations: acquiring the operation instructions for controlling the above-mentioned home appliances in the preset area , obtain multiple operation instructions; determine at least one of the following information as the above-mentioned device operation log: multiple above-mentioned operation instructions, time information corresponding to the multiple above-mentioned operation instructions, location information corresponding to multiple above-mentioned operation instructions, multiple above-mentioned operations The environment information corresponding to the instruction.
The device according to claim 9, wherein the first generating module includes:

The first processing unit is configured to perform deduplication processing on N of the above-mentioned device operation logs to obtain K of the above-mentioned device operation logs, where the above-mentioned K is a natural number less than or equal to the above-mentioned M;

The first determination unit is configured to determine the operation category of each of the K above-mentioned device operation logs;

The second determination unit is configured to determine the operation jump node corresponding to each of the above-mentioned operation jump instructions in the K above-mentioned device operation logs, and obtain a plurality of the above-mentioned operation jump nodes;

The third determination unit is configured to determine the connection relationship between multiple above-mentioned operation jump nodes and obtain multiple connection edges; the first generation unit is configured to determine the connection relationship between the above-mentioned operation jump nodes and the above-mentioned operation jump nodes based on the above-mentioned operation category, and the above-mentioned operation jump nodes. Multiple connecting edges generate the above heterogeneous graph.
The device of claim 9, further comprising:

The third determination module is configured to determine the operation category corresponding to each of the above-mentioned operation jump nodes after generating a heterogeneous graph based on the N above-mentioned device operation logs; the first response module is configured to determine the operation category corresponding to each of the above-mentioned operation jump nodes. The corresponding operation category uses the above-mentioned heterogeneous graph to respond to the operation instructions acting on the above-mentioned household appliances.
The device according to claim 9, wherein the first determining module includes:

The first receiving unit is configured to receive operating instructions acting on the above-mentioned target home appliance, wherein, The above operation instructions include the above target operation jump node;

The fourth determination unit is configured to determine the environmental information in the preset area corresponding to the above-mentioned operation instruction, and the characteristic information that triggers the above-mentioned operation instruction, wherein the above-mentioned target home appliance is arranged in the above-mentioned preset area;

The fifth determination unit is configured to determine the jump probability distribution between the above-mentioned target operation jump node and the above-mentioned adjacent operation jump node using the above-mentioned heterogeneous graph, wherein the adjacent above-mentioned operation jump node is included in other Among the above-mentioned operation jump nodes, the sixth determination unit is configured to determine the jump node associated with the above-mentioned target operation jump node based on the above-mentioned jump probability distribution, the above-mentioned environment information and the above-mentioned characteristic information.
The device according to claim 13, wherein the fifth determining unit includes:

The first determining subunit is configured to determine multiple operation jump nodes associated with the above-mentioned target operation jump node;

The second determination subunit is configured to determine connection relationships between multiple associated operation jump nodes and the target operation jump node in the heterogeneous graph, and determine multiple connection relationships;

The third determination sub-unit is configured to determine the sum of weights of a plurality of the above-mentioned connection relationships; the first processing sub-unit is configured to normalize the sum of the above-mentioned weights to determine the above-mentioned jump probability distribution.
The device according to claim 13, wherein the fifth determining unit includes:

The fourth determination subunit is configured to determine multiple operation jump nodes associated with the above-mentioned target operation jump node;

The fifth determination subunit is configured to determine multiple connecting edges between the above-mentioned target operation jump node and multiple associated above-mentioned operation jump nodes as sample data;

The first establishment subunit is configured to establish a network model using the above-mentioned sample data, so as to use the above-mentioned network model to output the above-mentioned jump probability distribution.
The device of claim 9, further comprising:

The first correction module is configured to, after determining the target operation instruction of the target home appliance device according to the jump node associated with the target operation jump node, correct the above-mentioned device information according to the device information of the target home appliance device. Target operation instructions.
A computer-readable storage medium includes a stored program, wherein the method of any one of claims 1 to 8 is executed when the program is run.
An electronic device includes a memory and a processor, a computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 8 through the computer program.