CN116112320A - Method and device for constructing edge computing intelligent gateway based on object model - Google Patents
Method and device for constructing edge computing intelligent gateway based on object model Download PDFInfo
- Publication number
- CN116112320A CN116112320A CN202310383041.2A CN202310383041A CN116112320A CN 116112320 A CN116112320 A CN 116112320A CN 202310383041 A CN202310383041 A CN 202310383041A CN 116112320 A CN116112320 A CN 116112320A
- Authority
- CN
- China
- Prior art keywords
- object model
- query
- user
- model
- keyword
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/66—Arrangements for connecting between networks having differing types of switching systems, e.g. gateways
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a method and a device for constructing an intelligent gateway for edge calculation based on an object model, which can realize object model query based on specific keywords by establishing an object model warehouse and a keyword list, and further realize the efficiency of querying an available object model through the gateway by a single keyword optimizing query method and a model-based multi-keyword query method; when a user uses the service, the required function parameters of the object model are sent to the gateway, and the gateway calls the behavior of the corresponding object model according to the used service and the input function parameters and returns the result to the user; the gateway is enabled to provide the user with the ability to transparentize edge computing services.
Description
Technical Field
The invention relates to the technical field of combination of the Internet of things, artificial intelligence and computer science and technology, in particular to an edge computing intelligent gateway construction method and device based on an object model.
Background
The internet of things (Internet of Things, ioT for short) refers to collecting any object or process needing to be monitored, connected and interacted in real time through various information collecting and processing devices such as radio frequency identification, global positioning, infrared sensors, laser scanners and the like, collecting various needed information such as sound, light, heat, electricity, mechanics, chemistry, biology, positions and the like, accessing through various possible networks, realizing ubiquitous connection of objects and people, and realizing intelligent sensing, identification and management of objects and processes. The internet of things is an information carrier based on the internet, a traditional telecommunication network and the like, and enables all common physical objects which can be independently addressed to form an interconnection network.
The edge computing refers to computing on equipment deployed near an object end or a field end, and the edge computing equipment is terminal equipment for carrying acquisition and computing tasks at the entity end of an object and is an important infrastructure of the Internet of things. The gateway is an interface and portal for providing services to the outside of the Internet of things, and users of the Internet of things interact with edge computing equipment facilities through the gateway. The gateway of the Internet of things provides services for users, and manages and connects edge computing equipment internally, so that the gateway of the Internet of things plays a role of a hub of application and functions of the Internet of things.
The users of the internet of things pay more attention to functions rather than details of bottom equipment, and because the types and the quantity of equipment and facilities in the application of the internet of things are huge, the gateway in the prior art is commonly used for processing the data in huge face by feeding back the processes of receiving services, controlling the calculation of edge equipment and the like to the users according to the different types and quantity. The use difficulty of the internet of things in the prior art is not low, and the compatibility and flexibility of the internet of things are not enough.
Disclosure of Invention
The invention provides an edge computing intelligent gateway construction method and device based on an object model, which are used for overcoming at least one technical problem in the prior art.
In a first aspect, the present invention provides a method for constructing an edge computing intelligent gateway based on an object model, including:
acquiring functional data of each entity device in the Internet of things;
abstract an object model describing the entity equipment according to the functional data of each entity equipment;
the object model represents the name and function set of the entity equipment, and the function set comprises various working modes of the entity equipment, functions in the various working modes and function parameters;
receiving a user query request, and feeding back a query result to a user according to the query request;
receiving object model parameters which are defined and transferred by a user according to the query result and call the service;
and controlling the corresponding entity equipment to execute according to the object model parameters, and feeding back an execution result to the user.
Optionally, before receiving the user query request and feeding back the object model queue to the user according to the query request, the object model-based edge computing intelligent gateway construction method further includes:
adding each object model into an object model warehouse according to a unique name;
establishing an index corresponding to each object model and at least one keyword;
establishing a keyword list according to keywords corresponding to the object model;
and storing the keywords corresponding to each object model into an object model warehouse in the form of character arrays.
Optionally, after storing the keywords corresponding to each object model in the object model warehouse in the form of character arrays, the method for constructing the edge computing intelligent gateway based on the object model further comprises:
when a new entity device is added into the Internet of things, establishing an object model of the new entity device;
assigning at least one keyword to the object model of the new entity device;
when keywords appointed by the object model of the new entity equipment are stored in a keyword list, adding the object model of the new entity equipment into an object model queue corresponding to the keywords;
when the keywords specified by the object model of the new entity device are not stored in the keyword list, creating the keywords in the keyword list;
creating an empty model queue corresponding to the keywords newly added into the keyword list;
adding the object model of the new entity device into the empty object model queue.
Optionally, after storing the keyword corresponding to each object model in the form of character array in the object model warehouse, all object models in the object model warehouse are loaded to enter a controlled state.
Optionally, receiving a user query request, and feeding back a query result to the user according to the query request includes:
inquiring all object models with corresponding relations in an object model warehouse according to the inquiring conditions;
the belonging model is fed back to the user as a query result;
receiving inquiry evaluation of a user on the belonging model;
establishing a query list for recording each query record;
wherein each query record comprises query conditions, query results and query evaluations.
Optionally, receiving a user query request, and feeding back a query result to the user according to the query request includes:
determining a query condition in the query request;
when the query condition is a keyword, querying all records in a query list according to the query condition in a controlled state, and determining target query records conforming to the query condition;
counting query evaluation of all object models in a target query record;
summing up the query evaluations of the same object model, and determining N first object models with the query evaluations ordered at the front;
inquiring a second object model which is not the first object model in the keyword list according to the input keywords;
attaching the second object model to the first object model according to the sequence in the keyword table to be used as a query result;
and feeding back the query result to the user.
Optionally, receiving a user query request, and feeding back a query result to the user according to the query request includes:
determining a query condition in the query request;
when the query conditions are a plurality of keywords, establishing an expected model for simulating the user query conditions and the user expected results;
performing iterative training on the expected model by comparing the actual value of the sample with the expected value to reduce the output loss, so as to obtain a trained expected model;
inputting a plurality of keywords input by a user into a trained expected model to obtain object models corresponding to a plurality of dimensions;
taking an object model with the output value of the dimension larger than the threshold value as a target object model;
and feeding the target object model back to the user as a query result.
Optionally, receiving object model parameters defined by the user according to the query result and transmitted by using the service includes:
receiving a target object model selected by a user according to a query result and defining actions of the target object model;
generating service according to the selected object model and the object model action;
and calling a service to obtain the functional parameters of the selected object model.
Optionally, after the query result is fed back to the user, the method for constructing the edge computing intelligent gateway based on the object model further comprises:
and receiving the evaluation of the user on each object model in the query result, and generating a current query record.
In a second aspect, the present invention provides an edge computing intelligent gateway construction device based on an object model, including:
the acquisition module is configured to acquire functional data of each entity device in the Internet of things;
the abstract module is configured to abstract an object model describing the entity equipment according to the functional data of each entity equipment;
the object model represents the name and function set of the entity equipment, and the function set comprises various working modes of the entity equipment, functions in the various working modes and function parameters;
the receiving model is configured to receive a user query request and feed back a query result to a user according to the query request;
the calling module is configured to receive object model parameters which are defined according to the query result and are transmitted by the user through the calling service;
and the execution module is configured to control the corresponding entity equipment to execute according to the object model parameters and feed back an execution result to the user.
The innovation points of the embodiment of the invention include:
1. the invention provides a method and a device for constructing an intelligent gateway for edge calculation based on an object model, wherein when a user uses a service, the gateway transmits the functional parameters of the object model to be transmitted to the gateway, and the gateway calls the behavior of a corresponding object model according to the used service and the transmitted functional parameters and returns the result to the user; the gateway is enabled to provide the user with the ability to transparentize edge computing services.
2. According to the invention, by establishing the object model warehouse and the keyword list, object model inquiry based on specific keywords can be realized, and the efficiency of inquiring the available object model by a user through a gateway is improved.
3. According to the invention, the single keyword optimization query method and the model-based multi-keyword query method are realized, so that the efficiency of querying the object model by the user is further improved, the user can more quickly find the object model required by the user, and the working efficiency is improved. Is one of the innovative points of the embodiments of the present invention.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic process diagram of an edge computing intelligent gateway construction method based on an object model;
FIG. 2 is a schematic flow diagram of a warehouse of a build model in accordance with the present invention;
FIG. 3 is a schematic flow chart of creating keywords and object models for a new entity device in the present invention;
FIG. 4 is a flow chart of providing query results to a user according to the present invention;
FIG. 5 is a flowchart of providing a query result to a user when the user inputs a keyword in the present invention;
FIG. 6 is a flowchart of providing a query result to a user when the user inputs a plurality of keywords in the present invention;
fig. 7 is a schematic structural diagram of an edge computing intelligent gateway construction device based on an object model according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without any inventive effort, are intended to be within the scope of the invention.
It should be noted that the terms "comprising" and "having" and any variations thereof in the embodiments of the present invention and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, article, or device that comprises a list of steps or elements is not limited to the list of steps or elements but may, in the alternative, include other steps or elements not expressly listed or inherent to such process, method, article, or device.
Example 1
The embodiment of the invention discloses an edge computing intelligent gateway construction method and device based on an object model. The following will describe in detail.
The object model is an abstract entity with certain functions and describes a data model of the functions from the function point of view in the application of the internet of things, wherein the entity equipment and facilities (such as sensors, vehicle-mounted devices, buildings, factories and the like, namely 'objects') in the internet of things are summarized.
The gateway of the Internet of things has the capability of providing transparent service to the outside, is beneficial to more conveniently managing and utilizing equipment facilities of the Internet of things, reduces the use difficulty of the Internet of things, and improves the compatibility and flexibility of the Internet of things.
The invention provides an edge computing intelligent gateway construction method based on an object model, and referring to fig. 1, fig. 1 is a process schematic diagram of the edge computing intelligent gateway construction method based on the object model. The invention provides an edge computing intelligent gateway construction method based on an object model, which comprises the following steps:
s11, acquiring functional data of each entity device in the Internet of things;
s12, abstracting an object model for describing the entity equipment according to the functional data of each entity equipment;
the object model is a model for abstracting entity equipment and facilities in the Internet of things and describing functions of the entity equipment and the facilities. The object model represents the name of the entity device and a function set, and the function set comprises various working modes of the entity device, functions in the various working modes and function parameters.
The object model is an abstract entity with certain functions and describes a data model of the functions from the function point of view in the application of the internet of things, wherein the entity equipment and facilities (such as sensors, vehicle-mounted devices, buildings, factories and the like, namely 'objects') in the internet of things are summarized. Because the types and the quantity of equipment and facilities in the application of the Internet of things are very huge, and the users of the Internet of things pay more attention to functions rather than the details of bottom equipment, the Internet of things gateway is enabled to have the capability of providing external transparent services by an object model which abstracts an entity into logic, the facilities of the equipment of the Internet of things can be managed and utilized more conveniently, the use difficulty of the Internet of things is reduced, and the compatibility and the flexibility of the Internet of things are improved.
For example, the following object model can be created for an air conditioning system:
name of object model: air conditioner
Function set = {
The power supply is { power on, power off })
Temperature setting {18-30 }
The operation mode is { cooling, heating and dehumidifying }
Wind-swaying from left to right { open, close })
Wind swaying up and down { open, close })
Thermometer { measured ambient temperature }
}
It can be seen that after the entity equipment such as an air conditioner is abstracted into an object model, the entity equipment becomes a set of a series of functions, and each function may correspond to a terminal of the internet of things, such as a control switch, a rotating motor, a temperature collector and the like. Each of the functions may be implemented through one of the interfaces of the gateway. Through the gateway interface operation these functions, the service of the internet of things can be used by the user of the internet of things under the premise of not knowing the details of the bottom layer of the terminal.
S13, receiving a user query request, and feeding back a query result to the user according to the query request;
noteworthy are: after the name is used, the user can also query the belonging model with the corresponding relation with the keyword according to a certain designated keyword. The user designates keywords and transmits the keywords to the gateway, the gateway queries in a keyword list according to the keywords, finds a corresponding object model queue, and returns all object models in the queue as results.
S14, receiving object model parameters which are defined according to the query result and transferred by the user through the service;
the behavior of the object model is the execution of the object model function. For example, in the air-conditioning model, controlling the power supply of the air conditioner to be on, controlling the air-conditioning to be turned on left and right, reading the temperature count value, setting the operation mode to be refrigeration, and the like are each performed on different functions, and are each called one-time behavior. Invoking behavior of an object model requires specifying the object model, the function of the object model, and specific parameters of the object model function.
The method comprises the steps that a user can receive a target object model and a target object model action which are defined and selected according to a query result; generating service according to the selected object model and the object model action; and calling a service to obtain the functional parameters of the selected object model.
Wherein a function of the object model may correspond to a state of the physical device (in the example, "thermometer"), an action (in the example, "power") or a process (in the example "run mode"). Each function of the object model corresponds to one or more parameters (in the example "on, off").
The service is a further extension of the object model, and is a generic term for the behavior of the object model and the object model. The service is defined by the user and uploaded to the gateway. The gateway responds to the user's request by serving and returns the result desired by the user. The object model is the language in which the gateway communicates with the user, and the service is the tool by which the gateway performs the user request.
When the user uses the service, the required function parameters of the object model are sent to the gateway, and the gateway calls the behavior of the corresponding object model according to the used service and the input function parameters and returns the result to the user.
For example: one service, namely, turning on air-conditioning hot air, turning on curtains and electric lights every morning, wherein an object model required to be transmitted when a user uses the service comprises the following functional parameters:
{ air conditioner { Power supply { Power on }, operating mode { heating }, temperature setting {25 ° } }
{ shutter: { state: { pull-out } } })
{ Lamp: { Power-on } } } }
The gateway will perform the corresponding functions of the object model with the data entered by the user according to the definition of the service.
S15, controlling corresponding entity equipment to execute according to the object model parameters, and feeding back an execution result to a user.
The invention provides an edge computing intelligent gateway construction method based on an object model, which establishes an interactive interface between an edge computing gateway and a user thereof by adopting the object model; and an intelligent query method is designed for the query of the interactive key point object model, and a variety of object model query schemes are provided through the key word interface and the expected model, so that a user can quickly query the object model to be used from the gateway, and the response capability of the gateway to the user query is improved.
Example two
As shown in fig. 2, as an alternative embodiment of the present invention, before receiving a user query request and feeding back an object model queue to a user according to the query request, the object model-based edge computing intelligent gateway construction method further includes:
s21, adding each object model into an object model warehouse according to a unique name;
s22, establishing indexes of each object model and at least one keyword;
s23, establishing a keyword list according to keywords corresponding to the object model;
s24, storing the keywords corresponding to each object model into an object model warehouse in the form of character arrays.
Noteworthy are: the user needs to know the object model provided by the gateway in advance by using the service provided by the gateway, so the gateway is required to provide an interface for inquiring the object model. In the invention, an edge computing gateway establishes an object model warehouse to store all object models which can be used by users, and each object model has a unique name; the user may use the object model by its name. In addition, object models are also indexed in the warehouse in the form of keywords, each object model corresponding to one or more keywords; the keywords are stored in the object model warehouse in the form of character arrays, each character array consisting of one or more characters; when a user queries according to the keywords, the belonging model establishing the corresponding relation with the keywords can be searched. When an object model is built, the name of the object model needs to be specified, and at least one keyword is specified; adding the newly established object model into an object model warehouse, and adding the corresponding keywords into a keyword list of the object model warehouse.
According to the invention, after the keywords corresponding to each object model are stored in the object model warehouse in the form of character arrays, all object models in the object model warehouse are loaded to enter a controlled state.
By establishing a substance model warehouse and a keyword list, substance model inquiry based on specific keywords can be realized, and convenience is brought to users to inquire and use the substance model.
When the belonging model associated with the edge computing gateway is added, the edge computing gateway is set to a "controlled" state. In the controlled state, the object model repository of the gateway does not allow changes, only allows user queries.
Example III
As shown in fig. 3, as an alternative embodiment of the present invention, after storing the keywords corresponding to each object model in the form of character arrays in the object model repository, the method for constructing the edge computing intelligent gateway based on the object model further includes:
s31, when a new entity device is added into the Internet of things, establishing an object model of the new entity device;
s32, designating at least one keyword for the object model of the new entity equipment;
s33, when the keywords appointed by the object model of the new entity equipment are stored in a keyword list, adding the object model of the new entity equipment into an object model queue corresponding to the keywords;
s34, when the keywords specified by the object model of the new entity device are not stored in the keyword list, creating the keywords in the keyword list;
s35, creating an empty model queue corresponding to the keywords newly added into the keyword list;
s36, adding the object model of the new entity device into the empty object model queue.
Noteworthy are: if the newly added keyword exists in the keyword list, the object model corresponding to the newly added keyword is directly attached to the tail end of the object model queue corresponding to the keyword. If the newly added keyword does not exist in the keyword list, the keyword list is newly built, an empty object model queue corresponding to the keyword is created, and a new object model is added to the tail end of the empty queue. Of course, the keyword is added to describe the entity device, and when a new entity device is added to the internet of things, the keyword needs to be specified for the entity device.
Example IV
As shown in fig. 4, as an alternative embodiment of the present invention, receiving a query request from a user, and feeding back a query result to the user according to the query request includes:
s41, inquiring all object models with corresponding relations in an object model warehouse according to inquiry conditions;
s42, feeding the belonging model back to the user as a query result;
s43, receiving inquiry evaluation of a user on the object model;
s44, establishing a query list for recording each query record;
wherein each query record comprises query conditions, query results and query evaluations.
When the gateway enters the controlled state, a query record table is established at one end of the gateway, and all query records and evaluation on query results from the current entering the controlled state are recorded.
The look-up table contains a limited number of records, each record comprising three parts: query conditions, query results, query evaluations. The query condition is a keyword input during query, the query result refers to the first N object models returned after query according to the query condition, and the query evaluation refers to the evaluation of the user on the object models returned according to the query condition, wherein the value is 1 or-1. N is a positive integer, and n=10 is preferable; user satisfaction is indicated when the query rating is 1, and dissatisfaction is indicated when the rating is-1.
User evaluation satisfaction is essentially the satisfaction of the ranking of the query returns, because the list of object models returned to the user is ordered in order, the higher the user's satisfaction if the object model that the user really needs to use is ranked ahead. Each record of the lookup table reflects whether the top N results of the query can satisfy the user.
Example five
As shown in fig. 5, as an alternative embodiment of the present invention, receiving a query request from a user, and feeding back a query result to the user according to the query request includes:
s51, determining query conditions in the query request;
s52, when the query condition is a keyword, querying all records in the query list according to the query condition in a controlled state, and determining target query records conforming to the query condition;
s53, counting query evaluation of the object models in the target query records;
s54, summing query evaluations of the same object model, and determining N first object models with the query evaluations ranked at the front;
s55, inquiring a second object model which is not the first object model in the keyword list according to the input keywords;
s56, attaching the second object model to the first object model according to the sequence in the keyword table to serve as a query result;
s57, feeding back the query result to the user.
S58, receiving the evaluation of the user on each object model in the query result, and generating the query record.
When a keyword is input by a user, the gateway performs the following steps:
and A.1, finding records with all query conditions being the keywords in a query record table.
A2, taking the first N object models of each record query result according to all the records found in the A.1; the number of the query results is less than N, and the actual number is taken.
And A.3, counting the corresponding query evaluation value of each object model in the query record table according to the object models found out in the A.2, and summing the evaluation values; if the evaluation of an object model in a query record is satisfactory, its evaluation value is increased by 1, otherwise, by 1.
And A.4, finding out the object models with the highest evaluation values according to the evaluation values calculated in the step A.3, and sorting the object models according to the evaluation values from high to low; if N cannot be found, the largest possible number is taken.
And A.5, inquiring all object models which are not included in the returned results of the A.4 in a keyword list according to the N object models and the input keywords obtained by the calculation of the A.4, and sequentially attaching the inquiring results of the object models to the inquiring results of the A.4 according to the sequence in the keyword list.
And A.6, returning the object model result of the A.5 to the user in sequence.
And A.7, the user evaluates the returned result and returns the evaluation result to the gateway.
And A.8, the gateway adds the keywords of the query, the result of A.6 and the user evaluation as one record into a query record table.
Through the steps, according to the feedback optimization of the user on the keyword query, the object model with higher user attention is ranked in front of the query result according to the result of the keyword query object model, so that the user can conveniently and quickly pass through the keyword positioning object model.
Example six
As shown in fig. 6, as an alternative embodiment of the present invention, receiving a query request from a user, and feeding back a query result to the user according to the query request includes:
s61, determining query conditions in the query request;
s62, when the query conditions are a plurality of keywords, building a desired model for simulating the user query conditions and the user desired results;
noteworthy are: and establishing a desired model M for processing the situation that the query keyword input by the user is greater than 1.
Expected model
The definition is as follows:
in the above formula, x is the set of all keywords of the gateway, u is the element number of the keyword set,
represents the u-th keyword->
A keyword representing a distance p near the u-th keyword,/->
Five keywords representing that the distance range around the u-th keyword is-2 to 2, u is the center, +.>
Is an array according to the intermediate result of formula (1), if the total number of keywords is K, then the array +.>
The size of (2) is K; q is in the range of 0 to 3, (-)>
Four values +.>
、/>
、/>
、/>
Corresponds to the maximum value of +.>
Four values in the vicinity are mapped to one value +.>
，/>
The intermediate calculation result is an array, and the size is K/4; />
Representation of
And->
Weights in between; />
Three linear offsets. />
Is a nonlinear function defined as: />
The formulas (1) and (2) are used for modeling the input keyword groups and the output object models and simulating the relationship between the user query conditions and the user expected results.
The input x is the set of all keywords of the gateway,
for the u-th keyword, if +.>
The keyword is contained in the keyword group input by the user, otherwise +.>
。
The output y is a set of gateway belonging models, neither x nor y change when the gateway is in a controlled state,
representing the z-th thereofKeywords.
Training the expected model M, and collecting a plurality of groups of training samples, wherein each group of training samples comprises an input and an output, the input is a query keyword input by a user, and the output is a final object model selected by the user; inputting a certain dimension
When 1, the user input is indicated to contain the keyword, otherwise 0; outputting a certain dimension +.>
When 1, it means that the user selects the object model from the query results, and otherwise 0.
Training the model M according to the training sample, and calculating corresponding output according to the sample input x and formulas (1) and (2)
And comparing with the true value y of the training sample:
wherein, the liquid crystal display device comprises a liquid crystal display device,
、/>
vectors respectively->
、/>
Is a component of (a). />
To control the coefficients, the robustness of the model to noise is improved. Preferably, take->
。
After the adoption ofThe extremum of the function (3) is found by the forward propagation method (GoodFe, ian; bengio, yoshia; courville, aaron (2016), "6.5 Back-Propagation and Other Differentiation Algorithms". Deep learning. MIT Press. Pp. -220. ISBN 9780262035613.), and the parameters can be found
Is used to complete modeling of M.
S63, performing iterative training on the expected model by comparing the actual value of the sample with the expected value to reduce the output loss, so as to obtain a trained expected model;
s64, inputting a plurality of keywords input by a user into a trained expected model to obtain object models corresponding to a plurality of dimensions;
s65, taking the object model with the output value of the dimension larger than the threshold value as a target object model;
and S66, feeding the target object model back to the user as a query result.
When the user inputs more than one non-duplicate keyword, the gateway performs the following steps:
and B.1, inputting the keyword group input by the user into the model M.
B.2 parameters obtained from training
And (2) are substituted into the values of (1) and (2), and the corresponding outputs are obtained.
B.3 dimension with output value greater than 0.5
And returning the corresponding object model to the user as a result.
According to the method, an interactive interface between the edge computing gateway and a user is established by adopting the object model, the user calls the service of the gateway by inputting the object model and parameters thereof, and the gateway executes the function of the corresponding object model according to the input of the user, so that the capability of the edge computing gateway for providing transparent service for the user is realized, and the user can utilize the function of the Internet of things without paying attention to the implementation details of the bottom edge computing terminal.
The gateway establishes a physical model warehouse and a keyword list to record the use condition of a user on the physical model, and realizes physical model inquiry based on specific keywords on the basis of inquiring the physical model basically through names, thereby being convenient for the user to inquire and use the physical model.
As shown in fig. 7, the edge computing intelligent gateway construction device based on the object model provided by the invention includes:
an obtaining module 71 configured to obtain functional data of each entity device in the internet of things;
an abstraction module 72 configured to abstract to a physical model describing the physical device according to the functional data of the respective physical device;
the object model represents the name and function set of the entity equipment, and the function set comprises various working modes of the entity equipment, functions in the various working modes and function parameters;
a receiving model 73 configured to receive a user query request and to feed back a query result to a user according to the query request;
a calling module 74 configured to receive user definition and call service-incoming object model parameters according to the query result;
the execution module 75 is configured to control the corresponding entity device to execute according to the object model parameters, and feedback the execution result to the user.
The following records the query efficiency (number of times of traversal) according to the name query object model, according to the keyword query object model and according to the keyword intelligent query (step 3) object model according to the actual usage feedback (see table 1), when the gateway returns the candidate result of the object model, the number of times of traversal search of the object model required by the user is found according to the sequence, for example, the required object model is located at the 3 rd, 5 th and 7 th positions in the returned result, and the corresponding number of times of traversal is 3, 5 and 7. The results of table 1 show that intelligent querying in a controlled state can effectively accelerate the querying efficiency. Because the object model and the key words thereof do not need to be frequently changed in most application scenes, the intelligent query method based on the controlled state can effectively improve the working efficiency of a user for utilizing the gateway.
TABLE 1
Those of ordinary skill in the art will appreciate that: the drawing is a schematic diagram of one embodiment and the modules or flows in the drawing are not necessarily required to practice the invention.
Those of ordinary skill in the art will appreciate that: the modules in the apparatus of the embodiments may be distributed in the apparatus of the embodiments according to the description of the embodiments, or may be located in one or more apparatuses different from the present embodiments with corresponding changes. The modules of the above embodiments may be combined into one module, or may be further split into a plurality of sub-modules.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The method for constructing the edge computing intelligent gateway based on the object model is characterized by comprising the following steps of:
acquiring functional data of each entity device in the Internet of things;
abstract an object model describing the entity equipment according to the functional data of each entity equipment;
the object model represents the name of the entity equipment and a function set, wherein the function set comprises various working modes of the entity equipment, functions in the various working modes and function parameters;
receiving a user query request, and feeding back a query result to a user according to the query request;
receiving object model parameters which are defined and transferred by a user according to the query result and are transferred into the service;
and controlling the corresponding entity equipment to execute according to the object model parameters, and feeding back an execution result to the user.
2. The method of claim 1, wherein before receiving a user query and feeding back a queue of object models to a user according to the query, the method further comprises:
adding each object model into an object model warehouse according to a unique name;
establishing an index corresponding to each object model and at least one keyword;
establishing a keyword list according to keywords corresponding to the object model;
and storing the keywords corresponding to each object model into an object model warehouse in the form of character arrays.
3. The object model-based edge computing intelligent gateway construction method according to claim 2, wherein after storing the keyword corresponding to each object model in the object model repository in the form of a character array, the object model-based edge computing intelligent gateway construction method further comprises:
when a new entity device is added into the Internet of things, establishing an object model of the new entity device;
assigning at least one keyword to the object model of the new entity device;
when keywords appointed by the object model of the new entity equipment are stored in a keyword list, adding the object model of the new entity equipment into an object model queue corresponding to the keywords;
when the keywords specified by the object model of the new entity device are not stored in the keyword list, creating the keywords in the keyword list;
creating an empty model queue corresponding to the keywords newly added into the keyword list;
adding the object model of the new entity device into the empty object model queue.
4. A method of constructing an edge computing intelligent gateway based on object models according to claim 3, wherein after storing the keyword corresponding to each object model in the form of character array in the object model repository, all object models in the object model repository are loaded to enter a controlled state.
5. The method for constructing an edge computing intelligent gateway based on an object model according to claim 1, wherein receiving a user query request and feeding back a query result to a user according to the query request comprises:
inquiring all object models with corresponding relations in the object model warehouse according to the inquiring conditions;
the belonging model is fed back to the user as a query result;
receiving inquiry evaluation of a user on the belonging model;
establishing a query list for recording each query record;
wherein each query record comprises query conditions, query results and query evaluations.
6. The method for constructing an edge computing intelligent gateway based on an object model according to claim 3, wherein the steps of receiving a user query request and feeding back a query result to a user according to the query request include:
determining a query condition in the query request;
when the query condition is a keyword, querying all records in a query list according to the query condition in a controlled state, and determining target query records conforming to the query condition;
counting query evaluation of all object models in a target query record;
summing up the query evaluations of the same object model, and determining N first object models with the query evaluations ordered at the front;
inquiring a second object model which is not the first object model in the keyword list according to the input keywords;
attaching the second object model to the first object model according to the sequence in the keyword table to be used as a query result;
and feeding back the query result to the user.
7. The method for constructing an edge computing intelligent gateway based on an object model according to claim 2, wherein the steps of receiving a user query request and feeding back a query result to a user according to the query request include:
determining a query condition in the query request;
when the query conditions are a plurality of keywords, building a desired model for simulating the user query conditions and the user desired results;
performing iterative training on the expected model by comparing the actual value of the sample with the expected value to reduce the output loss, so as to obtain a trained expected model;
inputting a plurality of keywords input by a user into a trained expected model to obtain object models corresponding to a plurality of dimensions;
taking an object model with the output value of the dimension larger than the threshold value as a target object model;
and feeding the target object model back to the user as a query result.
8. The method for constructing an edge computing intelligent gateway based on an object model according to claim 6 or 7, wherein the receiving object model parameters defined by the user according to the query result and using the service includes:
receiving a target object model selected by a user according to a query result and defining actions of the target object model;
generating a service according to the selected object model and the object model action;
and calling the service to obtain the functional parameters of the selected object model.
9. The object model-based edge computing intelligent gateway construction method according to claim 6 or 7, wherein after feeding back the query result to the user, the object model-based edge computing intelligent gateway construction method further comprises:
and receiving the evaluation of the user on each object model in the query result, and generating a current query record.
10. An edge computing intelligent gateway construction device based on an object model, which is characterized by comprising:
the acquisition module is configured to acquire functional data of each entity device in the Internet of things;
the abstract module is configured to abstract an object model describing the entity equipment according to the functional data of each entity equipment;
the object model represents the name of the entity equipment and a function set, wherein the function set comprises various working modes of the entity equipment, functions in the various working modes and function parameters;
the receiving model is configured to receive a user query request and feed back a query result to a user according to the query request;
the calling module is configured to receive object model parameters which are defined and called by a user according to the query result and are transmitted by the service;
and the execution module is configured to control the corresponding entity equipment to execute according to the object model parameters and feed back an execution result to the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310383041.2A CN116112320B (en) | 2023-04-12 | 2023-04-12 | Method and device for constructing edge computing intelligent gateway based on object model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310383041.2A CN116112320B (en) | 2023-04-12 | 2023-04-12 | Method and device for constructing edge computing intelligent gateway based on object model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116112320A true CN116112320A (en) | 2023-05-12 |
| CN116112320B CN116112320B (en) | 2023-08-01 |
Family
ID=86260061
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310383041.2A Active CN116112320B (en) | 2023-04-12 | 2023-04-12 | Method and device for constructing edge computing intelligent gateway based on object model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116112320B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116405393A (en) * | 2023-06-09 | 2023-07-07 | 广东致盛技术有限公司 | Edge intelligent gateway optimization method and device for data twinning |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104424310A (en) * | 2013-09-06 | 2015-03-18 | 中国海洋大学 | Ontology-based smart home semantic query method and ontology-based smart home semantic query device |
| CN109040200A (en) * | 2018-07-13 | 2018-12-18 | 深圳绿米联创科技有限公司 | The cut-in method and device of internet of things equipment |
| CN110020228A (en) * | 2019-04-08 | 2019-07-16 | 浙江大学城市学院 | A kind of relevance evaluation method for Internet of Things Item Information searching order |
| CN110851593A (en) * | 2019-09-23 | 2020-02-28 | 天津大学 | Complex value word vector construction method based on position and semantics |
| CN110941698A (en) * | 2019-11-18 | 2020-03-31 | 陕西师范大学 | Service discovery method based on convolutional neural network under BERT |
| CN111552462A (en) * | 2019-12-31 | 2020-08-18 | 远景智能国际私人投资有限公司 | Equipment model construction method and device of Internet of things equipment and storage medium |
| CN113422693A (en) * | 2021-05-28 | 2021-09-21 | 武汉云图智能科技有限公司 | Model construction method and recognition method of Internet of things equipment and computer equipment |
| CN115576806A (en) * | 2022-09-28 | 2023-01-06 | 裕太微电子股份有限公司 | Test case generation and result comparison analysis method based on command line interface |
-
2023
- 2023-04-12 CN CN202310383041.2A patent/CN116112320B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104424310A (en) * | 2013-09-06 | 2015-03-18 | 中国海洋大学 | Ontology-based smart home semantic query method and ontology-based smart home semantic query device |
| CN109040200A (en) * | 2018-07-13 | 2018-12-18 | 深圳绿米联创科技有限公司 | The cut-in method and device of internet of things equipment |
| CN110020228A (en) * | 2019-04-08 | 2019-07-16 | 浙江大学城市学院 | A kind of relevance evaluation method for Internet of Things Item Information searching order |
| CN110851593A (en) * | 2019-09-23 | 2020-02-28 | 天津大学 | Complex value word vector construction method based on position and semantics |
| CN110941698A (en) * | 2019-11-18 | 2020-03-31 | 陕西师范大学 | Service discovery method based on convolutional neural network under BERT |
| CN111552462A (en) * | 2019-12-31 | 2020-08-18 | 远景智能国际私人投资有限公司 | Equipment model construction method and device of Internet of things equipment and storage medium |
| WO2021137767A1 (en) * | 2019-12-31 | 2021-07-08 | Envision Digital International Pte. Ltd. | Method and apparatus for constructing device model of iot device, and storage medium |
| CN113422693A (en) * | 2021-05-28 | 2021-09-21 | 武汉云图智能科技有限公司 | Model construction method and recognition method of Internet of things equipment and computer equipment |
| CN115576806A (en) * | 2022-09-28 | 2023-01-06 | 裕太微电子股份有限公司 | Test case generation and result comparison analysis method based on command line interface |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116405393A (en) * | 2023-06-09 | 2023-07-07 | 广东致盛技术有限公司 | Edge intelligent gateway optimization method and device for data twinning |
| CN116405393B (en) * | 2023-06-09 | 2023-09-22 | 广东致盛技术有限公司 | Edge intelligent gateway optimization method and device for data twinning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116112320B (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Perera et al. | Context-aware sensor search, selection and ranking model for internet of things middleware | |
| CN116112320B (en) | Method and device for constructing edge computing intelligent gateway based on object model | |
| Amato et al. | SNOPS: a smart environment for cultural heritage applications | |
| CN102243647B (en) | Higher-order knowledge is extracted from structural data | |
| CN110197258A (en) | Neural network searching method, image processing method and device, equipment and medium | |
| CN106991576A (en) | A kind of heating power of geographic area shows method and apparatus | |
| CN105912633A (en) | Sparse sample-oriented focus type Web information extraction system and method | |
| CN110020175B (en) | Search processing method, processing equipment and system | |
| CN110188210A (en) | One kind is based on figure regularization and the independent cross-module state data retrieval method of mode and system | |
| WO2021038435A1 (en) | Database tuning using a federated machine learning system of a centerless network | |
| CN108197225A (en) | Sorting technique, device, storage medium and the electronic equipment of image | |
| CN111562541A (en) | Software platform for realizing electric energy meter detection data management by applying CART algorithm | |
| CN106991097A (en) | A kind of processing method and processing device of identification data | |
| CN112925994B (en) | Group recommendation method, system and equipment based on local and global information fusion | |
| CN114330668A (en) | Model processing method and device, electronic equipment and computer storage medium | |
| KR101273646B1 (en) | Method and system for indexing and searching in multi-modality data | |
| CN108241709A (en) | A kind of data integrating method, device and system | |
| CN109766353A (en) | A kind of system and working method based on big data multidimensional property dynamic generation label | |
| CN108182228A (en) | User social contact method, device and the computing device realized using augmented reality | |
| CN110377805A (en) | A kind of sensor resource recommended method for matching sort algorithm based on speediness embranchment | |
| JP4780668B2 (en) | Traffic analysis model construction method, apparatus, construction program, and storage medium thereof | |
| Zheng et al. | An efficient preference-based sensor selection method in Internet of Things | |
| CN109815474A (en) | A kind of word order column vector determines method, apparatus, server and storage medium | |
| CN103455625B (en) | A kind of quick target rearrangement method for video abstraction | |
| US20210240890A1 (en) | System and method for producing personalized and customized hardware component based on description thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |