CN115102852A

CN115102852A - Internet of things service opening method and device, electronic equipment and computer medium

Info

Publication number: CN115102852A
Application number: CN202210684790.4A
Authority: CN
Inventors: 张迎
Original assignee: China United Network Communications Group Co Ltd
Current assignee: China United Network Communications Group Co Ltd
Priority date: 2022-06-17
Filing date: 2022-06-17
Publication date: 2022-09-23
Anticipated expiration: 2042-06-17
Also published as: CN115102852B

Abstract

The application provides a method and a device for opening Internet of things service, electronic equipment and a computer medium, wherein the method comprises the following steps: identifying the Internet of things service opening request based on a pre-built convolutional neural network model to obtain a service type identification result; generating an Internet of things service opening instruction based on the service type identification result; evaluating the correctness of the service opening instruction of the Internet of things to obtain a value of the correctness; and responding to the condition that the correctness value is higher than a preset threshold value, and opening the corresponding Internet of things service based on the Internet of things service opening instruction. According to the method and the device, the service opening efficiency and accuracy of the Internet of things can be effectively improved, the labor cost is reduced, a high-efficiency, convenient and high-accuracy service opening scheme of the Internet of things is provided for the user, and the user experience is improved.

Description

Internet of things service opening method and device, electronic equipment and computer medium

Technical Field

The application relates to the technical field of internet of things, in particular to a method and device for opening internet of things service, electronic equipment and computer media.

Background

With the continuous development of the fifth Generation Communication Technology (5th Generation Mobile Communication Technology, abbreviated as 5G), the services and applications of the internet of things are gradually increased, and the opening mode of the services of the internet of things becomes a problem concerned by researchers.

At the present stage, the service of the internet of things is mainly distributed through a system and is realized by using a human eye identification and manual manufacturing mode, the cost of manpower and material resources is increased, meanwhile, the human eye identification and manual manufacturing are adopted, the consumed time is longer, errors are easy to generate, and the opening and the use of the service of the internet of things by a user are further influenced.

Therefore, it is highly desirable to provide an efficient, convenient and highly accurate service provisioning scheme for the internet of things for users.

Disclosure of Invention

In view of the above problems, the application provides a method and device for provisioning a service of the internet of things, an electronic device, and a computer medium, so as to solve the problems that the current method for provisioning a service of the internet of things is low in efficiency, high in cost, easy to generate errors, and the like.

In order to achieve the above purpose, the present application provides the following technical solutions:

according to one aspect of the application, a method for opening a service of the internet of things is provided, which includes:

identifying the Internet of things service opening request based on a pre-built convolutional neural network model to obtain a service type identification result;

generating an Internet of things service opening instruction based on the service type identification result;

evaluating the correctness of the service opening instruction of the Internet of things to obtain a value of the correctness;

and responding to the condition that the correctness value is higher than a preset threshold value, and opening the corresponding Internet of things service based on the Internet of things service opening instruction.

In one embodiment, the identifying a service fulfillment request of the internet of things based on a pre-built convolutional neural network model to obtain a service type identification result includes:

extracting keywords of the Internet of things service opening request; converting the keywords into real number vectors;

and inputting the real number vector into a pre-built convolutional neural network model for deep learning to obtain a service type identification result.

In one embodiment, the method for identifying the service provisioning request of the internet of things based on the pre-built convolutional neural network model includes the following steps:

extracting keywords of service fulfillment requests of the Internet of things respectively;

converting the keywords into real number vectors to obtain a real number vector set, and preprocessing the real number vector set;

and inputting the preprocessed real number vector set into a pre-built convolutional neural network model for deep learning to obtain a service type identification result.

In one embodiment, the pre-built convolutional neural network model is a convolutional neural network model fused with a plurality of residual modules, and comprises a pooling layer and an anti-overfitting Dropout layer connected with the pooling layer, wherein the pooling layer comprises a first layer of maximum pooling and a second layer of global average pooling.

In one embodiment, the evaluating the correctness of the service provisioning instruction of the internet of things includes:

performing vocabulary decomposition on the Internet of things service opening instruction to obtain a decomposition result;

acquiring the dangerous word exchange rate of the words in the decomposition result; and the number of the first and second groups,

and evaluating the correctness of the Internet of things service opening instruction based on the dangerous word exchange rate.

In an embodiment, the evaluating the correctness of the service provisioning instruction of the internet of things further includes:

acquiring the correct vocabulary rate and the correct parameter format rate of the vocabulary in the decomposition result;

the assessing the correctness of the service opening instruction of the internet of things based on the dangerous word exchange rate comprises the following steps: and evaluating the correctness of the service fulfillment instruction of the Internet of things based on the dangerous word exchange rate, the correct word exchange rate and the parameter format correct rate.

In one embodiment, the obtaining the dangerous vocabulary rate of the vocabulary in the decomposition result includes:

comparing the vocabulary in the decomposition result with the vocabulary types defined in the preset dangerous vocabulary library to obtain a comparison result; and calculating the dangerous word exchange rate of the words in the decomposition result based on the comparison result.

In one embodiment, the preset dangerous vocabulary library comprises a low-risk vocabulary sub-library, a medium-risk vocabulary sub-library and a high-risk vocabulary word library, wherein the low-risk vocabulary sub-library defines the type of the query command; the medium-risk vocabulary sub-library defines parameter range types of different vocabularies; the high-risk vocabulary sub-library defines different parameters corresponding to different service types of the Internet of things;

calculating the dangerous word exchange rate of the words in the decomposition result based on the comparison result, and obtaining the dangerous word exchange rate according to the following formula:

Y＝a*V1+b*V2+c*V3/(a+b+c)

in the formula, Y represents the exchange rate of dangerous words, a represents the number of low-risk words in the comparison result, b represents the number of low-risk words in the comparison result, c represents the number of high-risk words in the comparison result, V1, V2 and V3 respectively represent preset percentages, and V1 < V2 < V3.

In an embodiment, the correctness of the service provisioning instruction of the internet of things is evaluated based on the dangerous vocabulary rate, the correct vocabulary rate and the parameter format correct rate, and is obtained according to the following formula:

accuracy＝(A1+A2+A3)/(A1+A2+A3+B1+B2+B3)

in the formula, accuracy represents the value of the correctness of the internet of things service opening instruction, a1 represents the vocabulary correct rate, B1 represents the vocabulary error rate, a2 represents the parameter format correct rate, B2 represents the parameter format error rate, A3 represents the non-dangerous vocabulary exchange rate, and B3 represents the dangerous vocabulary exchange rate.

According to another aspect of the present application, there is provided an internet of things service provisioning apparatus, including:

the recognition module is configured to recognize the Internet of things service fulfillment request based on a pre-built convolutional neural network model to obtain a service type recognition result;

the instruction generation module is used for generating an Internet of things service opening instruction based on the service type identification result;

the evaluation module is used for evaluating the correctness of the service opening instruction of the Internet of things to obtain a value of the correctness;

and the opening module is set to respond that the value of the correctness is higher than a preset threshold value, and open the corresponding Internet of things service based on the Internet of things service opening instruction.

According to yet another aspect of the present application, there is provided an electronic device including: a memory and a processor;

the memory stores computer-executable instructions;

the processor executes the computer execution instruction stored in the memory, so that the electronic equipment executes the Internet of things service opening method.

According to another aspect of the present application, a computer-readable storage medium is provided, where computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, the computer-executable instructions are used to implement the service provisioning method for the internet of things.

According to the method, the device, the electronic equipment and the computer medium for opening the service of the internet of things, automatic identification of various services of the internet of things is achieved through the convolutional neural network, the service type identification result is obtained, the service opening instruction of the internet of things is generated according to the service type identification result, the correctness of the instruction is evaluated, when the evaluation threshold value is reached, opening of the service of the internet of things is achieved based on the instruction, the service opening efficiency and the accuracy of the service of the internet of things can be effectively improved, the labor cost is reduced, an efficient, convenient and high-accuracy service opening scheme of the internet of things is provided for a user, and the user experience is improved.

Drawings

Fig. 1 is a schematic diagram of a possible application scenario provided in an embodiment of the present application;

fig. 2 is a schematic flow chart of a service provisioning method for the internet of things according to an embodiment of the present application;

FIG. 3 is a diagram illustrating one possible example of step S201 in FIG. 2;

FIG. 4 is a diagram illustrating one possible example of step S204 in FIG. 2;

fig. 5 is a schematic flow chart of another method for provisioning services of the internet of things according to the embodiment of the present application;

fig. 6 is a second schematic flow chart of another method for provisioning services of the internet of things according to the embodiment of the present application;

FIG. 7 is a diagram illustrating exemplary words and parameters in an adjustment instruction according to an embodiment of the present application;

fig. 8 is a third schematic flow chart of another method for provisioning services of the internet of things according to the embodiment of the present application;

fig. 9 is a schematic structural diagram of an internet of things service provisioning device according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

At the present stage, the service of the internet of things has different services for different types of users, the service types are various, and the service opening of the user of the internet of things needs to be manually made with a script and then operated on a corresponding network element. Because the influence caused by misoperation of the core network is great, the error rate of manually making scripts is high, the high error rate can influence the support experience of the access province, and the service use of the user is seriously influenced.

In view of the above technical problems, an embodiment of the present application provides an automatic identification and provisioning scheme for services of the internet of things, which utilizes a convolutional neural network to realize automatic identification of various services of the internet of things, then automatically makes scripts for the identified services to generate an opening instruction for services of the internet of things, and evaluates correctness of the instruction, thereby implementing the opening of the services of the internet of things. According to the embodiment of the application, the service type is automatically identified through the convolutional neural network fusion residual error module, so that the accuracy of service classification is improved; the colleagues integrate various indexes, evaluate the correctness of the instruction, improve the accuracy of the instruction issuing, reduce the error rate of manual manufacturing, improve the support experience of the access province and effectively improve the service use experience of the Internet of things of the user.

In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be described in more detail below with reference to the accompanying drawings in the embodiments of the present application. In the drawings, the same or similar reference numerals denote the same or similar components or components having the same or similar functions throughout. The described embodiments are only some of the embodiments of the present application, and not all of them. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.

Fig. 1 is a schematic diagram of a possible scenario provided in an embodiment of the present application, as shown in fig. 1, including a terminal device 110 and a server 120, where the terminal device 110 and the server 120 are connected to each other through a wired or wireless network. In some embodiments, the terminal 110 is configured to build a convolutional neural network model for identifying an internet of things service fulfillment request, provide the pre-built convolutional neural network model to the server 120, and the server 120 is configured to identify the internet of things service fulfillment request based on the convolutional neural network model provided by the terminal 110, generate an internet of things service fulfillment instruction, and provision a corresponding internet of things service. Optionally, in the process of building the convolutional neural network model, the server 120 undertakes secondary calculation work, and the terminal 110 undertakes primary calculation work; alternatively, the server 120 undertakes primary computational tasks and the terminal 110 undertakes secondary computational tasks; alternatively, the server 120 or the terminal 110 can be capable of undertaking the computing work individually.

The terminal device 110 may include, but is not limited to, a computer, a smart phone, a tablet computer, an e-book reader, a motion Picture experts group audio layer III (MP 3 for short) player, a motion Picture experts group audio layer 4 (MP 4 for short) player, a portable computer, a vehicle-mounted computer, a wearable device, a desktop computer, a set-top box, a smart television, and the like.

The server 120 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, a cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.

Optionally, the number of the terminals 110 or the servers 120 may be more or less, which is not limited in the embodiment of the present application. In some embodiments, the terminal 110 and the server 120 may also serve as nodes in a blockchain system, and synchronize the resistivity model reconstructed network obtained through training to other nodes in the blockchain, so as to implement wide application of the resistivity model reconstructed network.

The scene schematic diagram of the present application is briefly described above, and the service provisioning method for the internet of things provided in the embodiment of the present application is described in detail below by taking the server 120 applied in fig. 1 as an example.

Referring to fig. 2, fig. 2 is a schematic flow chart of a service provisioning method for the internet of things according to an embodiment of the present application, where the method includes steps S201 to S204.

Step S201, identifying the Internet of things service opening request based on the pre-built convolutional neural network model to obtain a service type identification result.

In this embodiment, the internet of things Service provisioning request, that is, the internet of things Service provisioning application initiated by the User may be one or more, may be a real-time request, and may also be a historical application work order, where the internet of things Service includes black and white list making, MEC (Multi-access Edge Computing, Edge cloud) and SMF (Service Management Function) docking, or UPF (User Port Function) provisioning, and the like. In practical application, for an internet of things service provisioning application initiated by a user, the internet of things service type is mainly identified manually, and a script is made manually to provision a corresponding internet of things service for the user, so that the method is low in efficiency and high in cost, and is accompanied with a high error rate.

The pre-built convolutional neural network model may be built and trained by the terminal 110 and transmitted to the server 120, and in some embodiments, the server 120 may also build and train the convolutional neural network model in advance and put into use.

In this embodiment, the convolutional neural network model may include two or more layers, and finally the pooling operation of the first layer adopts maximum pooling, the pooling operation of the second layer adopts global average pooling, and a better learning effect is achieved by using the maximum pooling and the average pooling.

In a more specific embodiment, in order to improve learning efficiency, the identifying a service provisioning request of the internet of things based on a pre-built convolutional neural network model to obtain a service type identification result (step S201), including the following steps:

The method is characterized in that N states are coded by using an N-bit state register, each state has an independent register bit, and only One bit is valid at any time.

In another embodiment, when there are a plurality of internet-of-things service provisioning requests, the learning efficiency is further improved by preprocessing the real number vector set, and the internet-of-things service provisioning request is identified based on the pre-constructed convolutional neural network model to obtain a service type identification result (step S201), including the following steps:

In the embodiment, all the Internet of things user application work orders are collected, the Internet of things user service application work order names are integrated into one data set, then the data set is sent into the convolutional neural network model for classification, the characteristics of each work order type are extracted, the model can independently learn according to the keywords and the characteristics which are unique to each service work order, and finally automatic identification and classification of the Internet of things service work orders are achieved. And moreover, the keyword is converted into a real number vector by the Internet of things user service application work order data set in a thermal coding mode, and the collected data set can be input into a convolutional neural network model after data preprocessing because the convolutional neural network can only identify binary data. That is, the data is preprocessed, i.e., the real vector is converted into a binary vector.

In some embodiments, in order to further improve the accuracy of model classification, a service type feature library may be established, as shown in fig. 3, an internet of things service type identification model is a convolutional neural network model, an identification result module is used to store a service type identification result, a service provisioning system corresponds to a provisioning module 94 in the later-described apparatus embodiment, interaction is performed with the service type feature library based on the convolutional neural network model, the convolutional neural network model identifies the internet of things service type based on features extracted from the network and features in the service type feature library, and obtains a service type identification result, and the service provisioning of the internet of things service is completed in subsequent steps.

And S202, generating an Internet of things service opening instruction based on the service type identification result.

In the embodiment, the identified service type can be automatically made through python to generate the service opening instruction of the internet of things, in a specific implementation mode, a Django-based foreground and background interoperation platform can be built in a 5G internet of things guarantee system, file data exported from a network manager is extracted based on the corresponding service of the internet of things in the service type identification result, and necessary parameters are input according to customer requirements in combination with a front-end page to achieve automatic making of the instruction. That is to say, the service provisioning instruction of the internet of things includes the service type of the internet of things and the parameters of the service of the internet of things.

It can be understood that the service provisioning request of the internet of things carries parameters corresponding to the customer requirements, and the parameters may be operation parameters corresponding to provisioning of the service of the internet of things.

And S203, evaluating the correctness of the Internet of things service opening instruction to obtain a value of the correctness.

In some embodiments, the correctness of the instruction may be evaluated by analyzing and evaluating the vocabulary in the service provisioning instruction of the internet of things, and a corresponding evaluation value is obtained, and the specific process of which is described in detail in the embodiments described later.

And S204, responding to the condition that the correctness value is higher than a preset threshold value, opening the corresponding service of the Internet of things based on the service opening instruction of the Internet of things, and otherwise, ending the process and opening the service of the Internet of things according to the prior art.

In this embodiment, the service of the internet of things is opened by using an internet of things service opening instruction automatically generated by the system, in one example, to further ensure the opening of the service of the internet of things, the service of the internet of things opening instruction is sent to a network manager for operation and execution, as shown in fig. 4, the service of the internet of things is taken as an example for adding a physical network element slice ADD PNFNS, and in fig. 4, the service of the internet of things opening instruction carries various parameters and index information, so that the service of the internet of things can be quickly opened.

It should be noted that the preset value can be adaptively set by those skilled in the art in combination with the actual application.

In the related art, when the service of the internet of things is opened, the correctness of the service opening instruction of the internet of things or the script of the service of the internet of things is generally not evaluated, so that the service opening error rate of the service of the internet of things is high.

Referring to fig. 5, fig. 5 is a schematic flow chart of another method for provisioning an internet of things service provided in the embodiment of the present application, where on the basis of the previous embodiment, the present embodiment further illustrates a process for evaluating the correctness of an instruction for provisioning an internet of things service, where the evaluating the correctness of the instruction for provisioning an internet of things service (step S203) includes steps S501 to S503.

And S501, performing vocabulary decomposition on the Internet of things service opening instruction to obtain a decomposition result.

In the embodiment, the internet of things service opening instruction carries the type of the internet of things service to be opened and the corresponding parameters thereof, the instruction is subjected to vocabulary decomposition, all vocabularies carried in the instruction are analyzed, the correctness of the instruction is further obtained, and the correctness evaluation result of the instruction can be effectively improved.

And step S502, acquiring the dangerous word exchange rate of the vocabulary in the decomposition result.

In this embodiment, the accuracy of the instruction is evaluated by obtaining the dangerous vocabulary rate of decomposing the vocabulary, and according to the dangerous vocabulary rate, wherein the dangerous vocabulary, i.e., the vocabulary which may affect the network, may be divided into low-risk vocabulary, medium-risk vocabulary and high-risk vocabulary according to the degree of the impact on the network, and wherein the higher the dangerous vocabulary rate is, the lower the accuracy is.

In one embodiment, the method includes the steps of constructing a preset dangerous vocabulary library, and comparing the vocabulary in the decomposition result with the vocabulary types defined in the preset dangerous vocabulary library to obtain a dangerous vocabulary rate, so as to improve the recognition effect of the dangerous vocabulary rate, specifically, the method includes the following steps:

Further, the preset dangerous vocabulary library comprises a low-risk vocabulary sub-library, a medium-risk vocabulary sub-library and a high-risk vocabulary word library, wherein the low-risk vocabulary sub-library defines the type of the query command; the medium-risk vocabulary sub-library defines parameter range types of different vocabularies; and the high-risk vocabulary sub-library defines different parameters corresponding to different service types of the Internet of things.

Illustratively, the present embodiment constructs the important parameter set by: constructing a low-risk vocabulary library: classifying query commands such as LST and DSP into low-risk vocabularies; constructing an intermediate-risk vocabulary library: setting a certain range for corresponding parameters, and defining the out-of-range as a medium-risk instruction; constructing a high-risk vocabulary library: different parameters are specified as different types, for example, the type of APN (Access Point Name) is specified as xxxxx.jnm2mapn, xxxxx.jnoot; in addition, in order to facilitate the opening of the internet of things service, parameters (parameters carried by the instruction) uploaded by the user and parameters (such as the maximum value of the index value) in an operation log on the equipment can be collected, and a json set related to the relevant parameters for opening the service is constructed (for example, the maximum value of the index: 15).

Y＝a*V1+b*V2+c*V3/(a+b+c)

Illustratively, the word risk rate ═ low risk × + 20% + medium risk × + high risk × + 50%/(low risk + medium risk + high risk), the corresponding word rate of non-risk i.e. 1-low risk × + 20% + medium risk × + 30% + high risk/(low risk + medium risk + high risk).

Step S503, evaluating the correctness of the Internet of things service opening instruction based on the dangerous word exchange rate.

In an implementation manner, a risk threshold may be set, and the risk exchange rate is compared with the risk threshold, so that when the risk exchange rate is smaller than the threshold, the preset threshold for correctness evaluation may be considered to be reached.

In an embodiment, when the service type of the internet of things is evaluated, besides considering the word risk, problems such as word errors and parameter format errors may also occur, which may result in the efficiency of opening the service of the internet of things, as shown in fig. 6, the evaluating the correctness of the service opening instruction of the internet of things (step S203) further includes step S504.

And step S504, obtaining the correct vocabulary rate and the correct parameter format rate of the vocabulary in the decomposition result.

Acquiring the correct word exchange rate of the vocabulary, and judging whether the vocabulary is correct, such as whether the spelling is correct; obtaining the accuracy of the parameter format, it can be understood that the service of the internet of things is opened with a general parameter format, and if the parameter format carried in the instruction is different from the general parameter format, the parameter format is considered to be incorrect.

The evaluating the correctness of the internet of things service provisioning instruction based on the dangerous word exchange rate (step S403), specifically: step S503a, evaluating the correctness of the internet of things service provisioning instruction based on the dangerous vocabulary rate, the correct vocabulary rate and the parameter format correct rate.

Compared with the method for evaluating the vocabulary correctness only through the dangerous vocabulary rate, the method for evaluating the vocabulary correctness of the mobile terminal increases the correct vocabulary rate and the parameter format correctness rate, and can effectively improve the accuracy of the evaluation result.

accuracy＝(A1+A2+A3)/(A1+A2+A3+B1+B2+B3)

in the formula, accuracy represents the value of the correctness of the internet of things service opening instruction, a1 represents the vocabulary correct rate, B1 represents the vocabulary error rate, a2 represents the parameter format correct rate, B2 represents the parameter format error rate, A3 represents the non-dangerous vocabulary exchange rate, and B3 represents the dangerous vocabulary exchange rate. For easy understanding, please refer to table 1 below, where a1+ B1 is 1, a2+ B2 is 1, and A3+ B3 is 1.

Table 1:

in an example, if accuracy is greater than or equal to 99% (preset threshold), the internet of things service is opened based on the internet of things service, and when accuracy is less than 99%, the flow is ended, and the wrong vocabulary, the parameters which do not conform to the format and the like in the internet of things service opening instruction can be adjusted, wherein the process of adjusting the vocabulary and the parameters in the instruction can be as shown in fig. 7, and then the internet of things service opening instruction is generated again; in another example, when accurve is less than 99%, the command of accurve is greater than or equal to 95% and accurve is less than or equal to 98% can be automatically searched and checked, the command is updated, and if accurve is less than or equal to 94%, the vocabulary, the parameters and the like in the service opening command of the internet of things are adjusted, and the service opening command of the internet of things is regenerated.

In order to facilitate understanding of the embodiment of the present application, referring to fig. 8, fig. 8 provides a second flowchart of the embodiment of the present application, and it should be noted that black and white list creation, MEC and SMF docking, and UPF opening between the neural network model and the instruction creation are three different internet of things service types in the drawing.

Based on the same technical concept, an embodiment of the present application further provides a service provisioning apparatus for internet of things, as shown in fig. 9, the apparatus includes:

the identification module 91 is configured to identify the service fulfillment request of the internet of things based on a pre-built convolutional neural network model to obtain a service type identification result;

the instruction generating module 92 is configured to generate an internet of things service opening instruction based on the service type identification result;

the evaluation module 93 is configured to evaluate the correctness of the service provisioning instruction of the internet of things to obtain a value of correctness;

and the provisioning module 94 is configured to provision the corresponding internet of things service based on the internet of things service provisioning instruction in response to the value of the correctness being higher than a preset threshold value.

In one embodiment, the identification module 91 includes:

the first extraction unit is used for extracting keywords of the Internet of things service opening request; and a first conversion unit arranged to convert the keyword into a real number vector;

and the first learning unit is used for inputting the real number vector into a pre-built convolutional neural network model for deep learning to obtain a service type identification result.

In an embodiment, the service provisioning request of the internet of things is multiple, and the identifying module 91 includes:

the second extraction unit is used for respectively extracting keywords of the service fulfillment requests of the Internet of things;

the second conversion unit is used for converting the keywords into real vectors to obtain a real vector set and preprocessing the real vector set;

and the second learning unit is used for inputting the preprocessed real number vector set into a pre-built convolutional neural network model for deep learning to obtain a service type identification result.

In one embodiment, the evaluation module 93 includes:

the decomposition unit is used for decomposing vocabularies of the Internet of things service opening instruction to obtain a decomposition result;

a first obtaining unit configured to obtain a dangerous vocabulary rate of the vocabulary in the decomposition result; and the number of the first and second groups,

and the evaluation unit is used for evaluating the correctness of the Internet of things service opening instruction based on the dangerous word exchange rate.

In one embodiment, the evaluation module 93 further includes:

the second acquisition unit is used for acquiring the correct vocabulary rate and the parameter format correct rate of the vocabulary in the decomposition result;

the evaluation unit is specifically configured to evaluate the correctness of the service fulfillment instruction of the internet of things based on the dangerous word exchange rate, the correct word exchange rate and the parameter format correct rate.

In one embodiment, the first obtaining unit is specifically configured to compare the vocabulary in the decomposition result with the vocabulary types defined in the preset dangerous vocabulary library to obtain a comparison result; and calculating the dangerous word exchange rate of the words in the decomposition result based on the comparison result.

In one embodiment, the preset dangerous vocabulary library comprises a low-risk vocabulary sub library, a medium-risk vocabulary sub library and a high-risk vocabulary word library, wherein the low-risk vocabulary sub library defines the type of the query command; the medium-risk vocabulary sub-library defines parameter range types of different vocabularies; the high-risk vocabulary sub-library defines different parameters corresponding to different service types of the Internet of things;

calculating the dangerous vocabulary rate of the vocabulary in the decomposition result based on the comparison result, and obtaining the dangerous vocabulary rate according to the following formula:

Y＝a*V1+b*V2+c*V3/(a+b+c)

accuracy＝(A1+A2+A3)/(A1+A2+A3+B1+B2+B3)

in the formula, accuracy represents the value of the correctness of the internet of things service opening instruction, a1 represents the vocabulary correct rate, B1 represents the vocabulary error rate, a2 represents the parameter format correct rate, B2 represents the parameter format error rate, A3 represents the non-dangerous word exchange rate, and B3 represents the dangerous word exchange rate.

Based on the same technical concept, embodiments of the present application correspondingly further provide an electronic device, as shown in fig. 10, the electronic device includes: a memory 101 and a processor 102;

the memory 101 stores computer-executable instructions;

the processor 102 executes the computer execution instructions stored in the memory 101, so that the electronic device executes the internet of things service provisioning method.

Based on the same technical concept, the embodiment of the application correspondingly provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the method for opening the service of the internet of things is realized.

It will be understood by those of ordinary skill in the art that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media).

The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer.

In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.

In the description of the embodiments of the present application, the term "and/or" merely represents an association relationship describing an associated object, and means that three relationships may exist, for example, a and/or B may represent: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" means any combination of any one or more of a variety of at least two, including, for example, A, B, and may mean any one or more elements selected from the group consisting of A, B and C. Further, the term "plurality" means two or more unless specifically stated otherwise.

In the description of the embodiments of the present application, the terms "first," "second," "third," "fourth," and the like (if any) are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may be modified, or some or all of the technical features may be equivalently replaced; and these modifications or substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for opening a service of the Internet of things is characterized by comprising the following steps:

2. The method according to claim 1, wherein the identifying of the service provisioning request of the internet of things based on the pre-built convolutional neural network model to obtain a service type identification result comprises:

3. The method according to claim 1, wherein the Internet of things service provisioning requests are multiple, the Internet of things service provisioning requests are identified based on a pre-built convolutional neural network model, and a service type identification result is obtained, and the method comprises the following steps:

converting the keywords into real vectors to obtain a real vector set, and preprocessing the real vector set;

4. The method according to any one of claims 1 to 3, wherein the pre-built convolutional neural network model is a convolutional neural network model fused with a plurality of residual modules, and comprises a pooling layer and an anti-overfitting Dropout layer connected with the pooling layer, wherein the pooling layer comprises a first layer of maximal pooling and a second layer of global average pooling.

5. The method according to claim 1, wherein the evaluating the correctness of the internet of things service provisioning instruction comprises:

6. The method of claim 5, wherein the evaluating the correctness of the IOT service provisioning instruction further comprises:

acquiring the correct vocabulary rate and the parameter format correct rate of the vocabulary in the decomposition result;

the assessing the correctness of the internet of things service opening instruction based on the dangerous word exchange rate comprises the following steps: and evaluating the correctness of the service fulfillment instruction of the Internet of things based on the dangerous word exchange rate, the correct word exchange rate and the parameter format correct rate.

7. The method of claim 5, wherein obtaining the dangerous vocabulary rate of the vocabulary in the decomposition result comprises:

comparing the vocabulary in the decomposition result with the vocabulary types defined in the preset dangerous vocabulary library to obtain a comparison result; and calculating the dangerous vocabulary rate of the vocabulary in the decomposition result based on the comparison result.

8. The method of claim 7, wherein the preset dangerous vocabulary libraries comprise a low-risk vocabulary sub-library, a medium-risk vocabulary sub-library and a high-risk vocabulary word library, wherein the low-risk vocabulary sub-library defines query command types; the medium-risk vocabulary sub-library defines parameter range types of different vocabularies; different parameters of the high-risk vocabulary sub-library are defined to correspond to different service types of the Internet of things;

Y＝a*V1+b*V2+c*V3/(a+b+c)

in the formula, Y represents the exchange rate of dangerous words, a represents the number of low-risk words in the comparison result, b represents the number of low-risk words in the comparison result, c represents the number of high-risk words in the comparison result, V1, V2 and V3 respectively represent preset percentages, and V1 is more than V2 and is more than V3.

9. The method according to claim 6, wherein the correctness of the service provisioning instruction of the internet of things is evaluated based on the dangerous vocabulary rate, the correct vocabulary rate and the parameter format correct rate, and is obtained according to the following formula:

accuracy＝(A1+A2+A3)/(A1+A2+A3+B1+B2+B3)

10. The utility model provides a device is opened to thing networking service which characterized in that includes:

the evaluation module is configured to evaluate the correctness of the service opening instruction of the internet of things to obtain a value of the correctness;

11. An electronic device, comprising: a memory and a processor;

the memory stores computer-executable instructions;

the processor executes the computer-executable instructions stored in the memory to cause the electronic device to perform the method for provisioning internet of things service as claimed in any one of claims 1 to 9.

12. A computer-readable storage medium, wherein computer-executable instructions are stored in the computer-readable storage medium, and when executed by a processor, the computer-executable instructions are configured to implement the service provisioning method for internet of things according to any one of claims 1 to 9.