CN109991846A - Device control method, control device and storage medium - Google Patents

Abstract

The invention discloses a kind of apparatus control method, control equipment and storage mediums, wherein the described method includes: getting the identity information of target object；Obtain the initial environment data of the target object local environment；Wherein, the initial environment data are at least used to characterize at least one state of target object local environment；The environmental data of identity information, local environment based on the target object, it determines for the adjustment information of at least one of the local environment of target object terminal device, the ambient condition after being adjusted is changed to the initial environment state of the target object local environment.

Description

Device control method, control device and storage medium

technical field

The present invention relates to information processing technology in the field of communications, and in particular, to a device control method, a control device and a storage medium.

Background technique

With the rapid development of science and technology, hardware devices in life are becoming more and more intelligent, and realizing intelligent interaction between devices has become the focus of research. Now the most common way of intelligent interaction between devices is based on fixed rules (if-then), such as the control method of the vehicle intelligent interactive device and the rules mentioned in the system: after the access control is unlocked, the vehicle intelligent interactive device can be used wake. These rules are the same for every user and are not individually designed.

The existing device intelligent interaction is divided into two types, one is the intelligent interaction between humans and devices, and the other is the interaction between devices based on fixed rules. Among them, the interaction between the human and the device requires the participation of the human, and the human sends control commands such as voice or action to the device. Although this method simplifies the process of people's control of the equipment to a certain extent, it still requires the participation of people and cannot realize the interaction between the equipment. The intelligent interaction of devices based on fixed rules means that people design the operating rules between devices in advance, and certain devices will only start to work when a certain rule is met. However, because different users have different behavioral habits or personalized experiences of things, this rule-based device interaction has no personalized settings for users and cannot meet the personalized requirements of each user. And the interaction between devices is not encapsulated. When a new device joins or leaves, it will affect the use of the entire system.

SUMMARY OF THE INVENTION

The main purpose of the present invention is to propose a device control method, a control device and a storage medium, aiming to solve the above problems existing in the prior art.

In order to achieve the above object, the present invention provides a device control method, the method includes:

Obtain the identity information of the target object;

obtaining initial environment data of the environment where the target object is located; wherein the initial environment data is at least used to represent at least one state of the environment where the target object is located;

Based on the identity information of the target object and the environment data of the environment where the target object is located, adjustment information for at least one terminal device in the environment where the target object is located is determined, and the initial environment of the environment where the target object is located is determined. The state is changed to obtain the adjusted environment state.

The present invention provides a control device, characterized in that the control device includes:

an information obtaining unit, configured to obtain the identity information of the target object; obtain initial environment data of the environment where the target object is located; wherein, the initial environment data is at least used to represent at least one state of the environment where the target object is located;

an information processing unit, configured to determine adjustment information for at least one terminal device in the environment where the target object is located based on the identity information of the target object and the environment data of the environment where the target object is located, and for the target object The initial environmental state of the environment is changed to obtain the adjusted environmental state.

The present invention provides a control device, characterized in that the control device includes:

a communication interface for acquiring identity information of the target object; acquiring initial environment data of the environment where the target object is located; wherein the initial environment data is at least used to represent at least one state of the environment where the target object is located;

The processor is configured to determine, based on the identity information of the target object and the environment data of the environment where the target object is located, adjustment information for at least one terminal device in the environment where the target object is located, The initial environment state of the environment is changed to obtain the adjusted environment state.

The present invention provides a control device comprising: a processor and a memory for storing a computer program that can run on the processor,

Wherein, when the processor is configured to execute the computer program, the steps of the foregoing method are executed.

The present invention provides a storage medium on which a computer program is stored, wherein the computer program implements the steps of the aforementioned method when executed by a processor.

The device control method, control device and storage medium provided by the present invention determine how to adjust at least one terminal device through environmental parameters of the target user and the environment where the target user is located, so that the environment where the target user is located changes. As a result, different control schemes are provided for different users. In this way, the control of the terminal device can be made more intelligent and more in line with the needs of individual users.

Description of drawings

FIG. 1 is a schematic flowchart 1 of a device control method according to an embodiment of the present invention;

2 is a schematic diagram of model construction according to an embodiment of the present invention;

3 is a schematic flowchart 2 of a device control method according to an embodiment of the present invention;

FIG. 4 is a schematic diagram 1 of the composition structure of a control device according to an embodiment of the present invention;

FIG. 5 is a functional schematic diagram of an information processing unit according to an embodiment of the present invention;

FIG. 6 is a schematic diagram 2 of a composition structure of a control device according to an embodiment of the present invention.

Detailed ways

The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

Embodiment 1.

An embodiment of the present invention provides a device control method, as shown in FIG. 1 , including:

Step 101: Obtain the identity information of the target object;

Step 102: Obtain initial environment data of the environment where the target object is located; wherein, the initial environment data is at least used to represent at least one state of the environment where the target object is located;

Step 103: Based on the identity information of the target object and the environment data of the environment where the target object is located, determine adjustment information for at least one terminal device in the environment where the target object is located, and determine the adjustment information for the environment where the target object is located. The initial environment state is changed to obtain the adjusted environment state.

It should be further noted that, before performing the foregoing step 101, this embodiment also provides a processing method for establishing an operation model for the target object, specifically:

Acquire historical operation data of the target object; wherein the historical operation data includes state adjustment information of the target object and at least one terminal device within a preset time period, and the target object adjusts the at least one terminal device The historical environment parameters corresponding to the environment where the terminal device is located;

Based on the state adjustment information of at least one terminal device in the historical operation data and the historical environment parameter, an operation model corresponding to the target object is determined.

Wherein, the target object can be the user, the user can be any person who can enter the corresponding environment, and of course can also be any person who can manage the environment in which he is located, for example, in the house of user A, only reserved The operation model corresponding to user A may also retain user A and his family user B, plus the operation model corresponding to his friend user C. It can be set by the user.

In addition, the terminal device may be a smart device capable of receiving control information, such as smart home, smart lights, smart curtains, smart switches, smart water heaters, smart rice cookers, smart range hoods, smart stoves, and the like. It should be understood that there may be more smart terminal devices, and this embodiment can be set for all smart devices.

The state adjustment information of the terminal device may be the adjustment performed by the target object for a certain type or several types of intelligent terminals in a corresponding environment.

For example, user A goes home at 7 o'clock in the evening and is ready to work overtime, then at this time, the lights in the study can be adjusted to the target brightness, and user A maintains this operating habit for a certain preset period of time (for example, 1 within a month, or within a week), then you can record based on the operations performed by the user within this certain preset time period and their corresponding environmental parameters, and then determine the operation model of the target object for the smart device based on these contents. . This is an operation model for an intelligent terminal.

For another example, user A enters the living room at 5 pm in winter. At this time, user A will open the curtains and turn on the lights in the home to ensure that the light in the living room meets certain requirements. Then, at this time, based on the current time, Environmental parameters such as temperature and humidity, as well as the status of smart curtains and smart lights, are used to establish operation models.

It should also be understood that the aforementioned operation model can be used to describe the state adjustment information of one or more terminal devices and the corresponding historical environment parameters.

The historical environment parameters may include: sensing parameters detected by at least one sensing device in the environment where the target object is located;

On top of this, detection data information of at least one state detection unit may also be included. The state detection unit may be a detection unit for certain specific data, such as time, humidity, temperature, and the like.

It should be pointed out that this embodiment can be applied to many scenarios, such as a smart home scenario, a smart conference room scenario, etc. The following will take a smart home scenario as an example to analyze the specific implementation process of this embodiment.

Firstly, for the construction of ontology operation model, the construction of ontology knowledge model mainly includes two steps of abstraction of concept level and association of attribute relationship. Figure 2 is the smart home ontology knowledge model designed based on these two steps.

(1) Concept level abstraction

First, abstract the smart devices, sensors, events, environmental information and service requirements involved in the field of smart home at the conceptual level, and abstract them into specific concepts, which can also be called classes. For example, temperature sensors and smart light sensing devices are abstracted upward as the concept of "sensors", and devices such as smart lights and smart air conditioners are abstracted into the concept of "smart devices".

(2) Attribute relationship association

The method further includes: determining an association relationship between at least one terminal device and the at least one sensing parameter and/or at least one detection data information.

Specifically, it is to associate attribute relationships between concepts and concepts and between concepts and attribute values. Attribute relationships include object attributes and data attributes. The association between abstract concepts (classes) is called object attributes, and the attribute values possessed by concepts (classes) are called data attributes. For example, there is a certain object attribute relationship between "smart light sensing device" and "sensor", that is, "smart light sensing device" is a subclass of "sensor" (is-a relationship); "environmental data" and "smart light sensing device" There is a measured object attribute relationship (measuredBy) between devices", and smart lights can be associated with the "light intensity" in the measured "environment data". The smart light has a data attribute value of "off" or "on", and the data attribute of the light intensity is the current light intensity value.

Then design inference rules:

Based on the two steps of concept level abstraction and attribute relationship association, an initial smart home ontology model has been established, including concepts and well-defined association relationships. In addition, it is also necessary to design inference rules for model inference to guide the interoperability and intelligent decision-making between devices.

Examples of inference rules:

[rule1:(?a rdf:type fa:Room)(?a fa:hasState?b)(?b rdf:type fa:LightState)(?b fa:hasValue 'weakLight')(?a fa:hasEvent?c )(?c rdf:type fa:LightEvent)(?d fa:controlledBy?c)(?d rdf:type fa:SmartLight)(?d fa:hasValue'0')—>(?c fa:hasValue'open ')];

The meaning of the inference rule rule1 is: if (a's type is Room) and (a has a state b) and (b's type is a light state) and (b has a value of "light weak") and (a has a control event c )and (the type of c is a light event) and (d is controlled by c) and (the type of d is a smart light) and (the current value of d is "0", "0" represents the off state) —> (c current value is "open");

To put it simply, when the light in a specific room is weak and the room is turned off, then we should reason that the lights in this room should be turned on to increase the indoor light intensity.

[rule2:(?a rdf:type fa:MeetingRoom)(?a fa:hasEvent?c)(?c rdf:type fa:LightEvent)(?c fa:hasValue'open')(?d fa:controlledBy?c )(?d rdf:type fa:SmartLight)(?d fa:hasService?e)(?e fa:hasServiceType 'set')(?e fa:hasServiceEndPoint?f)strConcat(?f,'/1',? g)—>(?e fa:hasServiceURL?g)];

Rule2 The meaning of this rule is: when the value of the control event of the light is "on", the service that controls the light will send a control command to turn on the light to turn on the lights in the room.

Part of the list of rules in this embodiment is as follows:

[rule3:(?a rdf:type fa:MeetingRoom)(?a fa:hasState?b)(?b rdf:type fa:LightState)(?b fa:hasValue 'weakLight')(?a fa:hasEvent?c )(?c rdf:type fa:LightEvent)(?d fa:controlledBy?c)(?d rdf:type fa:SmartLight)(?d fa:hasValue '1')->(?c fa:hasValue'undo ')];

[rule4:(?a rdf:type fa:MeetingRoom)(?a fa:hasState?b)(?b rdf:type fa:LightState)(?b fa:hasValue 'hardLight')(?a fa:hasEvent?c )(?c rdf:type fa:LightEvent)(?d fa:controlledBy?c)(?d rdf:type fa:SmartLight)(?d fa:hasValue '0')->(?c fa:hasValue'undo ')];

[rule5:(?a rdf:type fa:MeetingRoom)(?a fa:hasState?b)(?b rdf:type fa:LightState)(?b fa:hasValue 'hardLight')(?a fa:hasEvent?c )(?c rdf:type fa:LightEvent)(?d fa:controlledBy?c)(?d rdf:type fa:SmartLight)(?d fa:hasValue '1')->(?c fa:hasValue'off ')];

[rule6:(?a rdf:type fa:MeetingRoom)(?a fa:hasState?b)(?b rdf:type fa:LightState)(?b fa:hasValue 'suitable')(?a fa:hasEvent?c )(?c rdf:type fa:LightEvent)->(?c fa:hasValue 'undo')].

It should be understood that the foregoing rules are only examples, and in fact, rules can be established for various devices and their corresponding various environmental parameters.

Finally, learn the personalized preferences of the user (target object) and choose the inference rules to trigger:

(1) Learning user personalized preferences

Different people have different personalized preferences and behavioral habits, such as some people are more sensitive to light, and some people are not sensitive to light. Therefore, we need to use machine learning (Machine Learning) algorithm to learn the user's personalized preferences, and perform semantic extraction on the user's personalized preferences. For example, it is learned through the machine learning algorithm that Xiaoming's "suitable" light intensity is (150-260), the light intensity is lower than 150 as "weak light", and higher than 260 as "light intensity"; User A's "suitable" light intensity The intensity is (200~300), the light intensity is lower than 200 as "light weak", and the light intensity higher than 300 is "light intensity". Finally, the semantic extraction of Xiaoming and user A's personalized feelings of light is carried out, and concepts such as "light intensity", "light weakness" and "suitability" are extracted.

(2) Select the triggering inference rule

The inference rules that need to be triggered are selected by semantic extraction of the user's personalized speech preferences. For example, when the light value in a room is 180, when Xiaoming enters this room, the machine learning method is used to learn that the current light value is "suitable" for Xiaoming, and rule6 is triggered; when user A enters this room, the current light value is learned. The light value is "weak" for user A, and rule1 or rule3 is triggered according to the current ON state of the indoor smart light.

Perform service execution and device control again.

In this embodiment, the service concept is added to the ontology knowledge model. The service encapsulates the operation process of the device, and can access and control the device in a unified manner, making the interoperation between the devices more convenient and intelligent. Services are generally divided into two types, one is perception service and the other is control service. The perception service is mainly to control the data acquisition equipment such as sensors to collect the current environmental data, and provide the basis for learning and selection for the user's personalized learning and rule selection stage. The control service mainly controls the device to change the current environmental state according to the decision of the ontology knowledge model and inference rules, so that the environmental state meets the individual requirements of the user and makes them feel comfortable.

How to use the rules can be explained as follows:

The determining, based on the identity information of the target object and the environment data of the environment where the target object is located, determines adjustment information for at least one terminal device in the environment where the target object is located, including:

Based on the identity information of the target object, the environment data, and the operation model corresponding to the target object, adjustment information for at least one terminal device in the environment where the target object is located is determined.

That is, after the operation model of the target object is determined, it can be determined how to adjust the terminal device in the environment where the target user is located according to the current environment data of the target user.

Further, the obtaining initial environment data of the environment where the target object is located includes:

Obtain at least one sensing parameter and/or at least one detection data information through at least one sensing device and/or at least one state detection unit in the environment where the target object is located;

Based on the at least one sensing parameter and/or the at least one detection data information, an initial environment parameter of the environment where the target object is located is determined.

This embodiment proposes a device intelligent interaction system based on personalized learning. The system is based on an ontology knowledge model, has rich semantic information, and uses a machine learning algorithm to learn the user's personalized preferences, and learn about the user's personalized preferences. Conceptual abstraction is carried out, and inference rules are selected according to the abstract preference concept, so that different devices can be interoperated according to the individual preferences of different users. At the same time, this embodiment realizes the mutual interaction between the devices based on the ontology. Through the interaction process between the devices, the environmental state and the current working state of the devices can be comprehensively considered to make more accurate and intelligent control decisions for the devices. In addition, we also added the service concept to the ontology knowledge model, encapsulated the execution and control interaction of the device, and encapsulated it as a perception service and control service. Through the service encapsulation, the device can be accessed and controlled uniformly. There is no need to consider differences in interfaces between devices, and when a device joins or leaves, it will not affect the use of the system, making the interoperability between devices more convenient and intelligent.

The specific execution process of the device intelligent interaction system based on personalized learning is shown in Figure 3. An example of the basic implementation process is as follows:

(1) Query the services associated with all smart devices and sensors in the room. The smart device service obtains the current working status of the smart device. At the same time, the sensor service triggers the sensor to monitor the environment and collect environmental data. For example, the service associated with the smart light obtains the current status of the smart light. Working status, and return; the light-sensing service associated with the smart light-sensing device triggers the smart light-sensing device to detect the light intensity in the room, collect the current light intensity data, and return it as the value of the service;

(2) Use the service return value to update the environment data instance in the model. For example, the smart light service returns the working status of the current light as "off", the light sensor service returns the light value in the current room as 180, and then updates the data attribute value of the smart light in the ontology model to "off", and the data of the light sensor sensor The property value is the current light value of 180.

(3) Based on the historical environmental data and user information, the machine learning algorithm is used to learn the user's personalized preference, and the concept of the user's personalized preference is abstracted. The current environmental state is determined according to the currently collected environmental data. For example, the current light limit is 180, and for user User A, the current environment state is "low light". Among them, the user information actually refers to the historical behavior of the user, such as under what conditions did he turn off the lights, under what conditions he turned on the lights; under what temperature conditions he turned on the air conditioner, and under what temperature he turned off the air conditioner . The acquisition of these user information is first recorded by devices such as smart lights, air conditioners, light sensors, and air conditioners after confirming the user's identity through identity authentication technology.

(4) Based on the designed rules and the updated ontology, the Jena inference engine is used for model inference and rule selection. The updated ontology refers to updating some attribute values in the ontology knowledge model in FIG. 2 according to the current environment state.

For example, for user A, the current environment state is "low light", and the current working state of the smart light can be obtained from the updated body as "off", and then the current environment state and the current working state of the device are combined to make rules Choose and make intelligent control decisions.

(5) Control the device to change the current environment state according to the decision of the ontology knowledge model and inference rules, so that the environment state meets the individual requirements of the user and makes them feel comfortable.

At the same time, through the acquisition of environmental data, equipment working status, model update and service control, the mutual interaction between equipment is realized, and the environmental status and the current status of the equipment are comprehensively considered, which makes our solution more intelligent.

An example of the interaction between devices during the light adjustment process is as follows:

When user A enters the room, the service associated with the smart light sensing device triggers the light sensing sensor to collect the light intensity value in the room, such as 180, and the service associated with the smart curtain obtains the current working status of the smart curtain, such as the closed state. The Ontology is updated through the return value of the light intensity and the status of the smart light by the service, so that the Ontology stores the current environmental data and device status. According to the personal preference classification model of user A learned by the machine learning algorithm, the light intensity value of 180 is darker for user A at this time, and the model reasoning, rule selection and Make the decision to open the curtains.

The curtain control service will control the opening of the smart curtains. During the opening of the curtains, the light sensor senses the changes of the indoor light intensity in real time, and updates the data values to the ontology data model. With the opening of the smart curtain, the indoor light continues to increase. When the light value measured by the sensor reaches the comfortable condition of user A, the decision to control the device is made again through the rule selection and the updated ontology. Control the curtains to stop and continue to open through the control service of the smart curtains.

This process realizes the mutual interaction between the light sensor and the smart curtain, controls the opening degree of the smart curtain, and makes the indoor light more comfortable. Instead of simply sending a command to open the curtains, the curtains are fully opened, and the light may be stronger when the curtains are fully opened, which does not fail to meet the user's preference.

This application proposes a device intelligent interaction system based on personalized learning. By constructing an ontology knowledge model, conceptual layer abstraction and relational association of devices, events, environments, etc. are carried out; to guide the interoperability and intelligent decision-making between devices; since different users have different personalized preferences, it is necessary to use machine learning algorithms to learn the user's personalized preferences, and conceptually abstract the user's personalized preferences to achieve reasoning The selection of rules can realize a personalized device interaction system; at the same time, through the acquisition of environmental data, device working status, model update, rule reasoning and service control, the intelligent interaction between devices is realized, and the environment is comprehensively considered. state and the current state of the device, making our solution smarter. In addition, this embodiment also encapsulates the execution and control interaction of the device, and encapsulates it into a perception service and a control service. Through the encapsulation service, the device can be accessed and controlled uniformly, without considering the interface between the devices. Difference, when a device joins or leaves, it will not affect the use of the system, making the interoperability between devices more convenient and intelligent.

It can be seen that by adopting the above solution, it is possible to determine how to adjust at least one terminal device according to the environment parameters of the target user and the environment where the target user is located, so that the environment where the target user is located changes. As a result, different control schemes are provided for different users. In this way, the control of the terminal device can be made more intelligent and more in line with the needs of individual users.

Embodiment two,

An embodiment of the present invention provides a control device, as shown in FIG. 4 , including:

an information acquisition unit 41, configured to acquire the identity information of the target object; acquire initial environment data of the environment where the target object is located; wherein, the initial environment data is at least used to represent at least one state of the environment where the target object is located;

The information processing unit 42 is configured to, based on the identity information of the target object and the environment data of the environment where the target object is located, determine adjustment information for at least one terminal device in the environment where the target object is located, The initial environment state of the environment where the object is located is changed to obtain the adjusted environment state.

It should be further noted that the information acquisition unit 41 acquires historical operation data of the target object; wherein the historical operation data includes the state adjustment information of the target object and at least one terminal device within a preset duration, and The historical environment parameter corresponding to the environment where the terminal device is located when the target object adjusts the at least one terminal device;

The information processing unit 42 is configured to determine an operation model corresponding to the target object based on the state adjustment information of at least one terminal device in the historical operation data and the historical environment parameter.

Wherein, the target object can be the user, the user can be any person who can enter the corresponding environment, and of course can also be any person who can manage the environment in which he is located, for example, in the house of user A, only reserved The operation model corresponding to user A may also retain user A and his family user B, plus the operation model corresponding to his friend user C. It can be set by the user.

In addition, the terminal device may be a smart device capable of receiving control information, such as smart home, smart lights, smart curtains, smart switches, smart water heaters, smart rice cookers, smart range hoods, smart stoves, and the like. It should be understood that there may be more smart terminal devices, and this embodiment can be set for all smart devices.

The state adjustment information of the terminal device may be the adjustment performed by the target object for a certain type or several types of intelligent terminals in a corresponding environment.

For example, user A goes home at 7 o'clock in the evening and is ready to work overtime, then at this time, the lights in the study can be adjusted to the target brightness, and user A maintains this operating habit for a certain preset period of time (for example, 1 within a month, or within a week), then you can record based on the operations performed by the user within this certain preset time period and their corresponding environmental parameters, and then determine the operation model of the target object for the smart device based on these contents. . This is an operation model for an intelligent terminal.

For another example, user A enters the living room at 5 pm in winter. At this time, user A will open the curtains and turn on the lights in the home to ensure that the light in the living room meets certain requirements. Then, at this time, based on the current time, Environmental parameters such as temperature and humidity, as well as the status of smart curtains and smart lights, are used to establish operation models.

It should also be understood that the aforementioned operation model can be used to describe the state adjustment information of one or more terminal devices and the corresponding historical environment parameters.

The historical environment parameters may include: sensing parameters detected by at least one sensing device in the environment where the target object is located;

On top of this, detection data information of at least one state detection unit may also be included. The state detection unit may be a detection unit for certain specific data, such as time, humidity, temperature, and the like.

It should be pointed out that this embodiment can be applied to many scenarios, such as a smart home scenario, a smart conference room scenario, etc. The following will take a smart home scenario as an example to analyze the specific implementation process of this embodiment.

Firstly, for the construction of ontology operation model, the construction of ontology knowledge model mainly includes two steps of abstraction of concept level and association of attribute relationship. Figure 2 is the smart home ontology knowledge model designed based on these two steps.

(1) Concept level abstraction

First, abstract the smart devices, sensors, events, environmental information and service requirements involved in the field of smart home at the conceptual level, and abstract them into specific concepts, which can also be called classes. For example, temperature sensors and smart light sensing devices are abstracted upward as the concept of "sensors", and devices such as smart lights and smart air conditioners are abstracted into the concept of "smart devices".

(2) Attribute relationship association

The method further includes: determining an association relationship between at least one terminal device and the at least one sensing parameter and/or at least one detection data information.

Specifically, it is to associate attribute relationships between concepts and concepts and between concepts and attribute values. Attribute relationships include object attributes and data attributes. The association between abstract concepts (classes) is called object attributes, and the attribute values possessed by concepts (classes) are called data attributes. For example, there is a certain object attribute relationship between "smart light sensing device" and "sensor", that is, "smart light sensing device" is a subclass of "sensor" (is-a relationship); "environmental data" and "smart light sensing device" There is a measured object attribute relationship (measuredBy) between devices", and smart lights can be associated with the "light intensity" in the measured "environment data". The smart light has a data attribute value of "off" or "on", and the data attribute of the light intensity is the current light intensity value.

Then design inference rules:

Based on the two steps of concept level abstraction and attribute relationship association, an initial smart home ontology model has been established, including concepts and well-defined association relationships. In addition, it is also necessary to design inference rules for model inference to guide the interoperability and intelligent decision-making between devices.

Examples of inference rules:

[rule1:(?a rdf:type fa:Room)(?a fa:hasState?b)(?b rdf:type fa:LightState)(?b fa:hasValue 'weakLight')(?a fa:hasEvent?c )(?c rdf:type fa:LightEvent)(?d fa:controlledBy?c)(?d rdf:type fa:SmartLight)(?d fa:hasValue'0')—>(?c fa:hasValue'open ')];

The meaning of the inference rule rule1 is: if (a's type is Room) and (a has a state b) and (b's type is a light state) and (b has a value of "light weak") and (a has a control event c )and (the type of c is a light event) and (d is controlled by c) and (the type of d is a smart light) and (the current value of d is "0", "0" represents the off state) —> (c current value is "open");

To put it simply, when the light in a specific room is weak and the room is turned off, then we should reason that the lights in this room should be turned on to increase the indoor light intensity.

[rule2:(?a rdf:type fa:MeetingRoom)(?a fa:hasEvent?c)(?c rdf:type fa:LightEvent)(?c fa:hasValue'open')(?d fa:controlledBy?c )(?d rdf:type fa:SmartLight)(?d fa:hasService?e)(?e fa:hasServiceType 'set')(?e fa:hasServiceEndPoint?f)strConcat(?f,'/1',? g)—>(?e fa:hasServiceURL?g)];

Rule2 The meaning of this rule is: when the value of the control event of the light is "on", the service that controls the light will send a control command to turn on the light to turn on the lights in the room.

Part of the list of rules in this embodiment is as follows:

[rule3:(?a rdf:type fa:MeetingRoom)(?a fa:hasState?b)(?b rdf:type fa:LightState)(?b fa:hasValue 'weakLight')(?a fa:hasEvent?c )(?c rdf:type fa:LightEvent)(?d fa:controlledBy?c)(?d rdf:type fa:SmartLight)(?d fa:hasValue '1')->(?c fa:hasValue'undo ')];

[rule4:(?a rdf:type fa:MeetingRoom)(?a fa:hasState?b)(?b rdf:type fa:LightState)(?b fa:hasValue 'hardLight')(?a fa:hasEvent?c )(?c rdf:type fa:LightEvent)(?d fa:controlledBy?c)(?d rdf:type fa:SmartLight)(?d fa:hasValue '0')->(?c fa:hasValue'undo ')];

[rule5:(?a rdf:type fa:MeetingRoom)(?a fa:hasState?b)(?b rdf:type fa:LightState)(?b fa:hasValue 'hardLight')(?a fa:hasEvent?c )(?c rdf:type fa:LightEvent)(?d fa:controlledBy?c)(?d rdf:type fa:SmartLight)(?d fa:hasValue '1')->(?c fa:hasValue'off ')];

[rule6:(?a rdf:type fa:MeetingRoom)(?a fa:hasState?b)(?b rdf:type fa:LightState)(?b fa:hasValue 'suitable')(?a fa:hasEvent?c )(?c rdf:type fa:LightEvent)->(?c fa:hasValue 'undo')].

It should be understood that the foregoing rules are only examples, and in fact, rules can be established for various devices and their corresponding various environmental parameters.

Finally, learn the personalized preferences of the user (target object) and choose the inference rules to trigger:

(1) Learning user personalized preferences

Different people have different personalized preferences and behavioral habits, such as some people are more sensitive to light, and some people are not sensitive to light. Therefore, we need to use machine learning (Machine Learning) algorithm to learn the user's personalized preferences, and perform semantic extraction on the user's personalized preferences. For example, it is learned through the machine learning algorithm that Xiaoming's "suitable" light intensity is (150-260), the light intensity is lower than 150 as "weak light", and higher than 260 as "light intensity"; User A's "suitable" light intensity The intensity is (200~300), the light intensity is lower than 200 as "light weak", and the light intensity higher than 300 is "light intensity". Finally, the semantic extraction of Xiaoming and user A's personalized feelings of light is carried out, and concepts such as "light intensity", "light weakness" and "suitability" are extracted.

(2) Select the triggering inference rule

The inference rules that need to be triggered are selected by semantic extraction of the user's personalized speech preferences. For example, when the light value in a room is 180, when Xiaoming enters this room, the machine learning method is used to learn that the current light value is "suitable" for Xiaoming, and rule6 is triggered; when user A enters this room, the current light value is learned. The light value is "low light" for user A, and rule1 or rule3 is triggered according to the current ON state of the indoor smart light.

Perform service execution and device control again.

In this embodiment, the service concept is added to the ontology knowledge model. The service encapsulates the operation process of the device, and can access and control the device in a unified manner, making the interoperation between the devices more convenient and intelligent. Services are generally divided into two types, one is perception service and the other is control service. The perception service is mainly to control the data acquisition equipment such as sensors to collect the current environmental data, and provide the basis for learning and selection for the user's personalized learning and rule selection stage. The control service mainly controls the device to change the current environmental state according to the decision of the ontology knowledge model and inference rules, so that the environmental state meets the individual requirements of the user and makes them feel comfortable.

How to use the rules can be explained as follows:

The information processing unit 42 is configured to determine at least one terminal device in the environment where the target object is located based on the identity information of the target object, the environment data, and the operation model corresponding to the target object adjustment information.

That is, after the operation model of the target object is determined, it can be determined how to adjust the terminal device in the environment where the target user is located according to the current environment data of the target user.

Further, the information processing unit 42 is configured to acquire at least one sensing parameter, and/or, through at least one sensing device and/or at least one state detection unit in the environment where the target object is located. at least one detection data information;

Based on the at least one sensing parameter and/or the at least one detection data information, an initial environment parameter of the environment where the target object is located is determined.

This embodiment proposes a device intelligent interaction system based on personalized learning. The system is based on an ontology knowledge model, has rich semantic information, and uses a machine learning algorithm to learn the user's personalized preferences, and learn about the user's personalized preferences. Conceptual abstraction is carried out, and inference rules are selected according to the abstract preference concept, so that different devices can be interoperated according to the individual preferences of different users. At the same time, this embodiment realizes the mutual interaction between the devices based on the ontology. Through the interaction process between the devices, the environmental state and the current working state of the devices can be comprehensively considered to make more accurate and intelligent control decisions for the devices. In addition, we also added the service concept to the ontology knowledge model, encapsulated the execution and control interaction of the device, and encapsulated it as a perception service and control service. Through the service encapsulation, the device can be accessed and controlled uniformly. There is no need to consider differences in interfaces between devices, and when a device joins or leaves, it will not affect the use of the system, making the interoperability between devices more convenient and intelligent.

Combined with the structural description of the aforementioned device, this embodiment also proposes a device intelligent interaction system based on personalized learning, through the process of constructing an ontology knowledge model, learning user personal preferences, reasoning rules, and controlling services. The intelligent interaction between them makes the environment state conform to the user's personalized preference and makes the user's living state more comfortable. As shown in FIG. 5 , the four modules in the figure can be respectively performed by the information processing unit in this embodiment to perform functions corresponding to the implements. Specifically, among them:

By building an ontology knowledge model, abstract and relational relation at the conceptual level of equipment, events, environments, etc.;

Inference rule equipment, based on the ontology knowledge model, design inference rules for model inference to guide the interoperability and intelligent decision-making between devices;

Learning the user's personalized number, because different users have different personalized preferences, it is necessary to use machine learning algorithms to learn the user's personalized preferences, abstract the concept of the user's personalized preferences, and realize the selection of inference rules, so as to achieve Personalized device interaction system; at the same time, service execution and device control realize intelligent interaction between devices through the acquisition of environmental data, device working status, model update, rule reasoning, and service control, taking into account the environmental status. as well as the current state of the device, making our solution smarter. In addition, this embodiment also encapsulates the execution and control interaction of the device, and encapsulates it into a perception service and a control service. Through the encapsulation service, the device can be accessed and controlled uniformly, without considering the interface between the devices. Difference, when a device joins or leaves, it will not affect the use of the system, making the interoperability between devices more convenient and intelligent.

It can be seen that by adopting the above solution, it is possible to determine how to adjust at least one terminal device according to the environment parameters of the target user and the environment where the target user is located, so that the environment where the target user is located changes. As a result, different control schemes are provided for different users. In this way, the control of the terminal device can be made more intelligent and more in line with the needs of individual users.

Embodiment three,

An embodiment of the present invention provides a control device, as shown in FIG. 6 , including:

The communication interface 61 is used to obtain the identity information of the target object; obtain initial environment data of the environment where the target object is located; wherein, the initial environment data is used to represent at least one state of the environment where the target object is located;

The processor 62 is configured to determine, based on the identity information of the target object and the environment data of the environment where the target object is located, adjustment information for at least one terminal device in the environment where the target object is located. The initial environmental state of the environment is changed to obtain the adjusted environmental state.

It should be further noted that the communication interface 61 obtains the historical operation data of the target object; wherein, the historical operation data includes the state adjustment information of the target object and at least one terminal device within a preset time period, and all the historical environment parameters corresponding to the environment where the terminal device is located when the target object adjusts the at least one terminal device;

The processor 62 determines an operation model corresponding to the target object based on the state adjustment information of at least one terminal device in the historical operation data and the historical environment parameter.

Wherein, the target object can be the user, the user can be any person who can enter the corresponding environment, and of course can also be any person who can manage the environment in which he is located, for example, in the house of user A, only reserved The operation model corresponding to user A may also retain user A and his family user B, plus the operation model corresponding to his friend user C. It can be set by the user.

In addition, the terminal device may be a smart device capable of receiving control information, such as smart home, smart lights, smart curtains, smart switches, smart water heaters, smart rice cookers, smart range hoods, smart stoves, and the like. It should be understood that there may be more smart terminal devices, and this embodiment can be set for all smart devices.

The state adjustment information of the terminal device may be the adjustment performed by the target object for a certain type or several types of intelligent terminals in a corresponding environment.

For example, user A goes home at 7 o'clock in the evening and is ready to work overtime, then at this time, the lights in the study can be adjusted to the target brightness, and user A maintains this operating habit for a certain preset period of time (for example, 1 within a month, or within a week), then you can record based on the operations performed by the user within this certain preset time period and their corresponding environmental parameters, and then determine the operation model of the target object for the smart device based on these contents. . This is an operation model for an intelligent terminal.

For another example, user A enters the living room at 5 pm in winter. At this time, user A will open the curtains and turn on the lights in the home to ensure that the light in the living room meets certain requirements. Then, at this time, based on the current time, Environmental parameters such as temperature and humidity, as well as the status of smart curtains and smart lights, are used to establish operation models.

It should also be understood that the aforementioned operation model can be used to describe the state adjustment information of one or more terminal devices and the corresponding historical environment parameters.

The historical environment parameters may include: sensing parameters detected by at least one sensing device in the environment where the target object is located;

On top of this, detection data information of at least one state detection unit may also be included. The state detection unit may be a detection unit for certain specific data, such as time, humidity, temperature, and the like.

It should be pointed out that this embodiment can be applied to many scenarios, such as a smart home scenario, a smart conference room scenario, etc. The following will take a smart home scenario as an example to analyze the specific implementation process of this embodiment.

Firstly, for the construction of ontology operation model, the construction of ontology knowledge model mainly includes two steps of abstraction of concept level and association of attribute relationship. Figure 2 is the smart home ontology knowledge model designed based on these two steps.

(1) Concept level abstraction

First, abstract the smart devices, sensors, events, environmental information and service requirements involved in the field of smart home at the conceptual level, and abstract them into specific concepts, which can also be called classes. For example, temperature sensors and smart light sensing devices are abstracted upward as the concept of "sensors", and devices such as smart lights and smart air conditioners are abstracted into the concept of "smart devices".

(2) Attribute relationship association

The method further includes: determining an association relationship between at least one terminal device and the at least one sensing parameter and/or at least one detection data information.

Specifically, it is to associate attribute relationships between concepts and concepts and between concepts and attribute values. Attribute relationships include object attributes and data attributes. The association between abstract concepts (classes) is called object attributes, and the attribute values possessed by concepts (classes) are called data attributes. For example, there is a certain object attribute relationship between "smart light sensing device" and "sensor", that is, "smart light sensing device" is a subclass of "sensor" (is-a relationship); "environmental data" and "smart light sensing device" There is a measured object attribute relationship (measuredBy) between devices", and smart lights can be associated with the "light intensity" in the measured "environment data". The smart light has a data attribute value of "off" or "on", and the data attribute of the light intensity is the current light intensity value.

Then design inference rules:

Based on the two steps of concept level abstraction and attribute relationship association, an initial smart home ontology model has been established, including concepts and well-defined association relationships. In addition, it is also necessary to design inference rules for model inference to guide the interoperability and intelligent decision-making between devices.

Examples of inference rules:

[rule1:(?a rdf:type fa:Room)(?a fa:hasState?b)(?b rdf:type fa:LightState)(?b fa:hasValue 'weakLight')(?a fa:hasEvent?c )(?c rdf:type fa:LightEvent)(?d fa:controlledBy?c)(?d rdf:type fa:SmartLight)(?d fa:hasValue'0')—>(?c fa:hasValue'open ')];

The meaning of the inference rule rule1 is: if (a's type is Room) and (a has a state b) and (b's type is a light state) and (b has a value of "light weak") and (a has a control event c )and (the type of c is a light event) and (d is controlled by c) and (the type of d is a smart light) and (the current value of d is "0", "0" represents the off state) —> (c current value is "open");

To put it simply, when the light in a specific room is weak and the room is turned off, then we should reason that the lights in this room should be turned on to increase the indoor light intensity.

[rule2:(?a rdf:type fa:MeetingRoom)(?a fa:hasEvent?c)(?c rdf:typefa:LightEvent)(?c fa:hasValue 'open')(?d fa:controlledBy?c) (?d rdf:typefa:SmartLight)(?d fa:hasService?e)(?e fa:hasServiceType 'set')(?efa:hasServiceEndPoint?f)strConcat(?f,'/1',?g) — >(?e fa:hasServiceURL?g)];

Rule2 The meaning of this rule is: when the value of the control event of the light is "on", the service that controls the light will send a control command to turn on the light to turn on the lights in the room.

Part of the list of rules in this embodiment is as follows:

[rule3:(?a rdf:type fa:MeetingRoom)(?a fa:hasState?b)(?b rdf:type fa:LightState)(?b fa:hasValue 'weakLight')(?a fa:hasEvent?c )(?c rdf:type fa:LightEvent)(?d fa:controlledBy?c)(?d rdf:type fa:SmartLight)(?d fa:hasValue '1')->(?c fa:hasValue'undo ')];

[rule4:(?a rdf:type fa:MeetingRoom)(?a fa:hasState?b)(?b rdf:type fa:LightState)(?b fa:hasValue 'hardLight')(?a fa:hasEvent?c )(?c rdf:type fa:LightEvent)(?d fa:controlledBy?c)(?d rdf:type fa:SmartLight)(?d fa:hasValue '0')->(?c fa:hasValue'undo ')];

[rule5:(?a rdf:type fa:MeetingRoom)(?a fa:hasState?b)(?b rdf:type fa:LightState)(?b fa:hasValue 'hardLight')(?a fa:hasEvent?c )(?c rdf:type fa:LightEvent)(?d fa:controlledBy?c)(?d rdf:type fa:SmartLight)(?d fa:hasValue '1')->(?c fa:hasValue'off ')];

[rule6:(?a rdf:type fa:MeetingRoom)(?a fa:hasState?b)(?b rdf:type fa:LightState)(?b fa:hasValue 'suitable')(?a fa:hasEvent?c )(?c rdf:type fa:LightEvent)->(?c fa:hasValue 'undo')].

It should be understood that the foregoing rules are only examples, and in fact, rules can be established for various devices and their corresponding various environmental parameters.

Finally, learn the personalized preferences of the user (target object) and choose the inference rules to trigger:

(1) Learning user personalized preferences

Different people have different personalized preferences and behavioral habits, such as some people are more sensitive to light, and some people are not sensitive to light. Therefore, we need to use machine learning (Machine Learning) algorithm to learn the user's personalized preferences, and perform semantic extraction on the user's personalized preferences. For example, it is learned through the machine learning algorithm that Xiaoming's "suitable" light intensity is (150-260), the light intensity is lower than 150 as "weak light", and higher than 260 as "light intensity"; User A's "suitable" light intensity The intensity is (200~300), the light intensity is lower than 200 as "light weak", and the light intensity higher than 300 is "light intensity". Finally, the semantic extraction of Xiaoming and user A's personalized feelings of light is carried out, and concepts such as "light intensity", "light weakness" and "suitability" are extracted.

(2) Select the triggering inference rule

The inference rules that need to be triggered are selected by semantic extraction of the user's personalized speech preferences. For example, when the light value in a room is 180, when Xiaoming enters this room, the machine learning method is used to learn that the current light value is "suitable" for Xiaoming, and rule6 is triggered; when user A enters this room, the current light value is learned. The light value is "low light" for user A, and rule1 or rule3 is triggered according to the current ON state of the indoor smart light.

Perform service execution and device control again.

In this embodiment, the service concept is added to the ontology knowledge model. The service encapsulates the operation process of the device, and can access and control the device in a unified manner, making the interoperation between the devices more convenient and intelligent. Services are generally divided into two types, one is perception service and the other is control service. The perception service is mainly to control the data acquisition equipment such as sensors to collect the current environmental data, and provide the basis for learning and selection for the user's personalized learning and rule selection stage. The control service mainly controls the device to change the current environmental state according to the decision of the ontology knowledge model and inference rules, so that the environmental state meets the individual requirements of the user and makes them feel comfortable.

How to use the rules can be explained as follows:

The processor determines, based on the identity information of the target object, the environment data, and an operation model corresponding to the target object, adjustment information for at least one terminal device in the environment where the target object is located.

That is, after the operation model of the target object is determined, it can be determined how to adjust the terminal device in the environment where the target user is located according to the current environment data of the target user.

Further, the processor obtains at least one sensing parameter and/or at least one detection unit through at least one sensing device and/or at least one state detection unit in the environment where the target object is located Data information;

Based on the at least one sensing parameter and/or the at least one detection data information, an initial environment parameter of the environment where the target object is located is determined.

It can be seen that by adopting the above solution, it is possible to determine how to adjust at least one terminal device according to the environment parameters of the target user and the environment where the target user is located, so that the environment where the target user is located changes. As a result, different control schemes are provided for different users. In this way, the control of the terminal device can be made more intelligent and more in line with the needs of individual users.

Further, the present application also provides a control device, comprising: a processor and a memory for storing a computer program that can be run on the processor,

Wherein, when the processor is configured to run the computer program, the steps of the method of one embodiment are executed. And the processor can execute each step of the method provided in the first embodiment, which is not repeated here.

The present application also provides a storage medium on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the method described in Embodiment 1 are implemented.

It should be noted that, herein, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements, It also includes other elements not expressly listed or inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

The above-mentioned serial numbers of the embodiments of the present invention are only for description, and do not represent the advantages or disadvantages of the embodiments.

From the description of the above embodiments, those skilled in the art can clearly understand that the method of the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is better implementation. Based on this understanding, the technical solutions of the present invention can be embodied in the form of software products in essence or the parts that make contributions to the prior art, and the computer software products are stored in a storage medium (such as ROM/RAM, magnetic disk, CD-ROM), including several instructions to make a terminal device (which may be a mobile phone, a computer, an apparatus, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of the present invention.

The above are only preferred embodiments of the present invention, and are not intended to limit the scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the description and drawings of the present invention, or directly or indirectly applied in other related technical fields , are similarly included in the scope of patent protection of the present invention.

Claims (13)

1. A device control method, wherein the method comprises: Obtain the identity information of the target object; obtaining initial environment data of the environment where the target object is located; wherein the initial environment data is at least used to represent at least one state of the environment where the target object is located; Based on the identity information of the target object and the environment data of the environment where the target object is located, adjustment information for at least one terminal device in the environment where the target object is located is determined, and the initial environment of the environment where the target object is located is determined. The state is changed to obtain the adjusted environment state. 2. The method according to claim 1, wherein the method further comprises: Acquire historical operation data of the target object; wherein the historical operation data includes state adjustment information of the target object and at least one terminal device within a preset time period, and the target object adjusts the at least one terminal device The historical environment parameters corresponding to the environment where the terminal device is located; Based on the state adjustment information of at least one terminal device in the historical operation data and the historical environment parameter, an operation model corresponding to the target object is determined. 3. The method according to claim 2, wherein the method further comprises: An association relationship between at least one terminal device and the at least one sensing parameter and/or at least one detection data information is determined. 4 . The method according to claim 2 , wherein the at least one of the environment where the target object is located is determined based on the identity information of the target object and the environment data of the environment where the target object is located. 5 . Adjustment information of terminal equipment, including: Based on the identity information of the target object, the environment data, and the operation model corresponding to the target object, adjustment information for at least one terminal device in the environment where the target object is located is determined. 5. The method according to any one of claims 1-4, wherein the acquiring initial environment data of the environment where the target object is located comprises: Obtain at least one sensing parameter and/or at least one detection data information through at least one sensing device and/or at least one state detection unit in the environment where the target object is located; Based on the at least one sensing parameter and/or the at least one detection data information, an initial environment parameter of the environment where the target object is located is determined. 6. A control device, characterized in that the control device comprises: an information obtaining unit, configured to obtain the identity information of the target object; obtain initial environment data of the environment where the target object is located; wherein, the initial environment data is at least used to represent at least one state of the environment where the target object is located; an information processing unit, configured to determine adjustment information for at least one terminal device in the environment where the target object is located based on the identity information of the target object and the environment data of the environment where the target object is located, and for the target object The initial environmental state of the environment is changed to obtain the adjusted environmental state. 7. A control device, characterized in that the control device comprises: a communication interface for acquiring identity information of the target object; acquiring initial environment data of the environment where the target object is located; wherein the initial environment data is at least used to represent at least one state of the environment where the target object is located; The processor is configured to determine, based on the identity information of the target object and the environment data of the environment where the target object is located, adjustment information for at least one terminal device in the environment where the target object is located, The initial environment state of the environment is changed to obtain the adjusted environment state. 8 . The control device according to claim 7 , wherein the communication interface is used to obtain historical operation data of the target object; wherein the historical operation data includes the target object within a preset duration. 9 . with state adjustment information of at least one terminal device, and historical environment parameters corresponding to the environment where the terminal device is located when the target object adjusts the at least one terminal device; The processor is configured to determine an operation model corresponding to the target object based on the state adjustment information of at least one terminal device in the historical operation data and the historical environment parameter. 9 . The control device according to claim 8 , wherein the processor is configured to determine at least one terminal device, and the at least one sensing parameter and/or at least one detection data information. 10 . relationship between. 10 . The control device according to claim 8 , wherein the processor is configured to determine, based on the identity information of the target object, the environment data, and an operation model corresponding to the target object, Describe the adjustment information of at least one terminal device in the environment where the target object is located. 11. The control device according to any one of claims 7-10, wherein the processor is configured to pass at least one sensing device and/or at least one sensing device in the environment where the target object is located a state detection unit, which acquires at least one sensing parameter and/or at least one detection data information; Based on the at least one sensing parameter and/or the at least one detection data information, an initial environment parameter of the environment where the target object is located is determined. 12. A control device comprising: a processor and a memory for storing a computer program executable on the processor, Wherein, the processor is configured to execute the steps of the method of any one of claims 1-5 when running the computer program. 13. A storage medium on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the method of any one of claims 1-5.