CN115766533A

CN115766533A - Intelligent gateway localization test method and device

Info

Publication number: CN115766533A
Application number: CN202211321695.4A
Authority: CN
Inventors: 周克林; 余南华; 陈玲莉; 刘振祥
Original assignee: Guangzhou Sitai Information Technology Co ltd
Current assignee: Guangzhou Sitai Information Technology Co ltd
Priority date: 2022-10-26
Filing date: 2022-10-26
Publication date: 2023-03-07

Abstract

The invention is suitable for the technical field of gateway testing, and particularly relates to an intelligent gateway localization testing method and device, wherein the method comprises the following steps: calculating the localization test time, and judging whether detection is needed; sending a test request, receiving data to be checked and collected, and receiving data to be processed; calling a corresponding acquisition end simulation model, and processing data to be processed to obtain check acquisition data; and comparing the difference between the data to be detected and the data to be checked to obtain difference data, and importing the difference data into the trained neural network model to obtain a detection result. According to the invention, time measurement is carried out, tested data acquisition ends are selected one by one during testing, the difference between data is determined by means of sending test data and simulating data processing, and then whether a fault exists or not is judged by using a preset model according to the data difference, so that the type and the reason of the fault are determined.

Description

Intelligent gateway localization test method and device

Technical Field

The invention belongs to the technical field of gateway testing, and particularly relates to an intelligent gateway localization testing method and device.

Background

In an actual production environment, the intelligent gateway uses the container as a standard basic operating environment. The connection and hardware selection of the intelligent gateway device face the problems of various gateway types, different application scenes, incompatible communication protocols, diversified connection modes, complex management and control, fluctuation in connectivity and compatibility and the like.

The access capability and index of the intelligent gateway do not have a unified standard and a complete evaluation system, the intelligent gateway is subjected to delivery test by the technical level of each manufacturer, and after the intelligent gateway is put into operation, if the intelligent gateway needs to be operated and maintained, the intelligent gateway needs to be connected with relevant manufacturers to arrive at the site by using a special customized tool for testing, so that the intelligent gateway is long in period, inconvenient to use, large in workload and high in cost.

In the existing intelligent gateways, fault detection is required by external means, local autonomous test is difficult to realize, and therefore fault conditions are difficult to master in time.

Disclosure of Invention

The embodiment of the invention aims to provide a local testing method for an intelligent gateway, and aims to solve the problems that fault detection needs to be carried out through external means in the existing intelligent gateway, local autonomous testing is difficult to realize, and the fault condition is difficult to master in time.

The embodiment of the invention is realized in such a way that an intelligent gateway localization test method comprises the following steps:

calculating the localization test time, and judging whether detection is needed;

sending test requests to at least two test acquisition ends, receiving data to be inspected from the tested acquisition ends, and receiving data to be processed from the test acquisition ends;

calling a corresponding acquisition end simulation model according to the type of the to-be-tested acquisition end, and processing the to-be-processed data by using the acquisition end simulation model to obtain check acquisition data;

and comparing the difference between the data to be detected and the data to be checked to obtain difference data, and importing the difference data into the trained neural network model to obtain a detection result, wherein the detection result comprises a fault type and a fault cause.

Preferably, the step of sending the test request to at least two test acquisition terminals, receiving the data to be inspected and acquired from the tested acquisition terminals, and receiving the data to be processed from the test acquisition terminals specifically includes:

numbering each acquisition end according to a preset acquisition end list, randomly selecting at least three acquisition ends, dividing one acquisition end into tested acquisition ends, and taking other acquisition ends as tested acquisition ends;

sending test requests to two groups of test acquisition ends, and sending data to be processed to the tested acquisition ends after the test acquisition ends receive the test requests;

and receiving data to be processed from a test acquisition end, wherein the test acquisition end sends the data to be processed to the intelligent gateway after receiving the test request, and the data to be processed sent by different test acquisition ends are different.

Preferably, the step of calling a corresponding acquisition end simulation model according to the type of the to-be-tested acquisition end, and processing the to-be-processed data by using the acquisition end simulation model to obtain the check acquisition data specifically includes:

identifying the equipment type of the tested acquisition terminal, and inquiring a model database according to the equipment type;

calling a collecting end simulation model matched with the tested collecting end;

and importing the data to be processed into the acquisition end simulation model, and outputting the verification acquisition data.

Preferably, the step of comparing the difference between the data to be checked and the data checked to obtain difference data, and importing the difference data into the trained neural network model to obtain a detection result specifically includes:

aligning the data to be checked and the data to be checked;

comparing according to the data arrangement sequence, determining the difference of the data of each part, and generating difference data, wherein the difference data comprises the data with the difference and the position of the data;

and constructing a neural network model, training by using a preset training set and a preset test set, importing the difference data into the neural network model, and outputting a detection result.

Preferably, when the localized test time exceeds a preset value or a preset monitoring event occurs, the detection is determined.

Preferably, the localized test time is recalculated after a test is completed.

Another objective of an embodiment of the present invention is to provide an intelligent gateway localization testing apparatus, where the apparatus includes:

the test judgment module is used for calculating the localized test time and judging whether detection is needed or not;

the data transmission module is used for sending test requests to at least two test acquisition ends, receiving the data to be inspected and acquired from the tested acquisition ends and receiving the data to be processed from the test acquisition ends;

the data processing simulation module is used for calling a corresponding acquisition end simulation model according to the type of the tested acquisition end, and processing the data to be processed by using the acquisition end simulation model to obtain check acquisition data;

and the fault identification module is used for comparing the difference between the to-be-detected acquired data and the verified acquired data to obtain difference data, and importing the difference data into the trained neural network model to obtain a detection result, wherein the detection result comprises a fault type and a fault cause.

Preferably, the data transmission module includes:

the acquisition terminal classifying unit is used for numbering each acquisition terminal according to a preset acquisition terminal list, randomly selecting at least three acquisition terminals, dividing one acquisition terminal into tested acquisition terminals, and taking other acquisition terminals as tested acquisition terminals;

the device comprises a request sending unit, a test acquisition end and a data processing unit, wherein the request sending unit is used for sending test requests to two groups of test acquisition ends, and the test acquisition ends send data to be processed to tested acquisition ends after receiving the test requests;

the data receiving unit is used for receiving the data to be processed from the test acquisition end, the test acquisition end sends the data to be processed to the intelligent gateway after receiving the test request, and the data to be processed sent by different test acquisition ends are different.

Preferably, the data processing simulation module includes:

the model query unit is used for identifying the equipment type of the tested acquisition terminal and querying the model database according to the equipment type;

the model calling unit is used for calling a collection end simulation model matched with the collection end to be tested;

and the simulation processing unit is used for importing the data to be processed into the acquisition end simulation model and outputting the verification acquisition data.

Preferably, the fault identification module includes:

the data alignment module is used for aligning the data to be checked and collected and the data to be checked and collected;

the difference comparison module is used for comparing according to the data arrangement sequence, determining the difference of the data of each part and generating difference data, wherein the difference data comprises the data with the difference and the position of the data;

and the fault detection unit is used for constructing a neural network model, training by using a preset training set and a test set, importing the difference data into the neural network model and outputting a detection result.

According to the intelligent gateway localization test method provided by the embodiment of the invention, through time measurement, localization detection is carried out when a preset event occurs or reaches a preset period, tested data acquisition ends are selected one by one during testing, the difference between data is determined through the modes of sending test data and simulating data processing, and then whether a fault exists is judged according to the data difference by using a preset model, so that the type and the reason of the fault are determined.

Drawings

Fig. 1 is a flowchart of a localized testing method for an intelligent gateway according to an embodiment of the present invention;

fig. 2 is a flowchart of steps of sending a test request to at least two test acquisition terminals, receiving data to be tested from the tested acquisition terminals, and receiving data to be processed from the test acquisition terminals according to an embodiment of the present invention;

fig. 3 is a flowchart of a step of calling a corresponding acquisition end simulation model according to the type of an acquisition end to be tested, and processing data to be processed by using the acquisition end simulation model to obtain check acquisition data according to the embodiment of the present invention;

fig. 4 is a flowchart of steps of comparing differences between the data to be detected and the data to be checked to obtain difference data, and importing the difference data into a trained neural network model to obtain a detection result according to the embodiment of the present invention;

fig. 5 is an architecture diagram of an intelligent gateway localization test apparatus according to an embodiment of the present invention;

fig. 6 is an architecture diagram of a data transmission module according to an embodiment of the present invention;

fig. 7 is an architecture diagram of a data processing simulation module according to an embodiment of the present invention;

fig. 8 is an architecture diagram of a fault identification module according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.

It will be understood that, as used herein, the terms "first," "second," and the like may be used herein to describe various elements, but these elements are not limited by these terms unless otherwise specified. These terms are only used to distinguish one element from another. For example, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script, without departing from the scope of the present application.

The access capability and the index of the intelligent gateway do not have a unified standard and a complete evaluation system, the intelligent gateway is still subjected to delivery test by depending on the technical level of each manufacturer, and after the intelligent gateway is put into operation, if the intelligent gateway needs to be operated and maintained, relevant manufacturers need to be contacted to arrive at the site by using a special customized tool for testing, so that the period is long, the use is inconvenient, the workload is large, and the cost is high. In the existing intelligent gateways, fault detection is required by external means, local autonomous test is difficult to realize, and therefore the fault condition is difficult to master in time.

According to the invention, through time measurement, local detection is carried out when a preset event occurs or a preset period is reached, tested data acquisition ends are selected one by one during testing, the difference between data is determined through the modes of sending test data and simulating data processing, and then whether a fault exists is judged according to the data difference by using a preset model, so that the type and the reason of the fault are determined.

As shown in fig. 1, a flowchart of an intelligent gateway localization testing method provided in an embodiment of the present invention is shown, where the method includes:

and S100, calculating the localization test time and judging whether detection is needed.

In this step, the localized test time is calculated, and a time period is set, for example, one month is used as one time period, when the localized test time reaches the one time period, the localized test is started, each acquisition end is detected, and similarly, the acquisition ends can also be monitored for events, whether the detection is performed or not is judged based on the specific event, and the acquisition ends establish network connection and can transmit data with each other.

S200, sending test requests to at least two test acquisition ends, receiving the data to be inspected and acquired from the tested acquisition ends, and receiving the data to be processed from the test acquisition ends.

In this step, the test acquisition ends send test requests to at least two test acquisition ends, specifically, the test acquisition ends can be three or more, each more test acquisition end has a group of test data, the detection accuracy can be improved, the tested acquisition ends are randomly selected from all the acquisition ends, all the acquisition ends need to be tested in the process, each acquisition end is sequentially selected to serve as the tested acquisition end, the test acquisition ends are randomly selected from other acquisition ends in the tested acquisition ends, the test acquisition ends send the data to be processed to the tested acquisition ends and the intelligent gateway at the same time, and the data to be processed is synchronously processed through the tested acquisition ends and the intelligent gateway.

S300, calling a corresponding acquisition end simulation model according to the type of the tested acquisition end, and processing the data to be processed by using the acquisition end simulation model to obtain verification acquisition data.

In this step, a corresponding acquisition end simulation model is called according to the type of the acquisition end to be tested, a model database is constructed, a plurality of acquisition end simulation models are arranged in the model database, and the acquisition end simulation models are used for processing data in the same data processing mode as the acquisition end, so that when the acquisition end has no fault, the data processed by the acquisition end and the data processed by the acquisition end simulation models should be the same, namely, the check acquisition data and the data to be checked acquisition should be the same, and if the check acquisition data and the data to be checked acquisition are different, the possibility that the acquisition end to be tested has the fault is indicated, and the fault type of the acquisition end to be tested needs to be further determined.

S400, comparing the difference between the data to be detected and the data to be checked to obtain difference data, and importing the difference data into the trained neural network model to obtain a detection result, wherein the detection result comprises a fault type and a fault cause.

In the step, the difference between the data to be detected and the data to be checked is compared, since the data to be processed sent to the detected acquisition end and the intelligent gateway are the same, if the detected acquisition end is not abnormal, the difference does not exist, the difference between the data to be detected and the data to be checked is determined by comparison, and the difference data is obtained, at the moment, the neural network model is used for processing, the type of the fault and the cause of the fault are determined according to the difference data, when the neural network model is trained, a known fault case is taken as a basis, if the fault A causes local loss of the data B, the data difference corresponding to each fault is determined according to the local loss, and then the type of the fault can be determined according to the data difference.

As shown in fig. 2, as a preferred embodiment of the present invention, the step of sending a test request to at least two test acquisition terminals, receiving the data to be tested and acquired from the tested acquisition terminals, and receiving the data to be processed from the test acquisition terminals specifically includes:

s201, numbering each acquisition end according to a preset acquisition end list, randomly selecting at least three acquisition ends, dividing one acquisition end into tested acquisition ends, and taking other acquisition ends as tested acquisition ends.

In this step, according to the collection end list of predetermineeing, numbering is carried out for each collection end, and every collection end all needs to detect, through setting up the serial number, can be when testing, confirm the test order according to the serial number, and collection end of random selection earlier is regarded as the collection end that is tested, will be tested the number that collection end corresponds afterwards and reject, and two sets of collection ends of random selection again can as the collection end that tests.

S202, sending test requests to the two groups of test acquisition ends, and sending data to be processed to the tested acquisition ends after the test acquisition ends receive the test requests.

In the step, test requests are sent to the two groups of test acquisition ends, when testing is carried out, the intelligent gateway sends the test requests to the test acquisition ends according to the numbers of the tested acquisition ends and the test acquisition ends, the test requests comprise addresses of the tested acquisition ends, the test acquisition ends send data to be processed to the addresses at the moment, and meanwhile the same data to be processed are sent to the intelligent gateway.

S203, receiving the data to be processed from the test acquisition end, sending the data to be processed to the intelligent gateway after the test acquisition end receives the test request, wherein the data to be processed sent by different test acquisition ends are different.

In this step, the data to be processed from the test acquisition end is received, and after the data to be processed is received by the tested acquisition end, the data to be processed is processed to obtain the data to be inspected and acquired.

As shown in fig. 3, as a preferred embodiment of the present invention, the step of calling a corresponding acquisition end simulation model according to the type of an acquisition end to be tested, and processing data to be processed by using the acquisition end simulation model to obtain calibration acquisition data specifically includes:

s301, identifying the equipment type of the tested acquisition terminal, and inquiring a model database according to the equipment type.

And S302, calling a collecting end simulation model matched with the tested collecting end.

In this step, the type of the device of the tested collection end is identified, the data collected by different collection ends are different, so the data processing modes are also different, collection end simulation models corresponding to all the collection ends are preset in the intelligent gateway, the collection end simulation models and the corresponding collection ends have the same data processing mode, and the corresponding collection end simulation models can be obtained by inquiring and calling according to the type of the collection ends.

And S303, importing the data to be processed into the acquisition end simulation model, and outputting the verification acquisition data.

In this step, the data to be processed is imported into the acquisition end simulation model, and the acquisition end simulation model performs simulation operation to process the data to be processed, so as to output check acquisition data.

As shown in fig. 4, as a preferred embodiment of the present invention, the step of comparing the difference between the data collected for standby examination and the data collected for verification to obtain difference data, and importing the difference data into the trained neural network model to obtain a detection result specifically includes:

s401, aligning the data to be checked and the data to be checked.

S402, comparing according to the data arrangement sequence, determining the difference of the data of each part, and generating difference data, wherein the difference data comprises the data with the difference and the position of the data.

In this step, in order to ensure the accuracy of the data comparison, the two are aligned, so that during the comparison, the bytes are compared one by one, the same byte is represented as 0, the different byte is represented as 1, so as to obtain difference data, and the abnormal position can be determined according to the distribution of 0 and 1 in the difference data.

And S403, constructing a neural network model, training by using a preset training set and a test set, importing the difference data into the neural network model, and outputting a detection result.

In the step, a neural network model is constructed, a preset training set is led into the neural network model, the neural network model is trained, and after the training is finished, difference data is led into the neural network model, so that a result is output by using the neural network model, a detection result is obtained, and in the detection result, the fault type and the fault cause are determined.

As shown in fig. 5, an intelligent gateway localization testing apparatus provided in an embodiment of the present invention includes:

the test determining module 100 is configured to calculate a localized test time and determine whether detection is required.

In the present apparatus, the test determination module 100 calculates the localized test time, and sets a time period, for example, a month is used as a time period, when the localized test time reaches the time period, the localized test is started, and each acquisition end is detected, and similarly, event monitoring may be performed on the acquisition ends, and whether detection is performed is determined based on a specific event that occurs, and network connection is established between the acquisition ends, so that data can be transmitted between them.

The data transmission module 200 is configured to send a test request to at least two test acquisition ends, receive data to be inspected from the tested acquisition ends, and receive data to be processed from the test acquisition ends.

In this device, data transmission module 200 sends the test request to two at least test collection ends, and is specific, the test collection end can be three or more, every more test collection end, just a set of test data has been more, can promote the degree of accuracy that detects, the end is gathered from all collection ends by the test random selection, this in-process needs to test all collection ends, then select each collection end in proper order, regard it as the end is gathered by the test, the end is gathered from being in other collection ends of being tested collection end and carry out the random selection, the end is gathered by the test and send the data to be processed for end and intelligent gateway simultaneously, carry out synchronous processing to this data to be processed through the end that is gathered by the test and intelligent gateway.

And the data processing simulation module 300 is configured to invoke a corresponding acquisition end simulation model according to the type of the tested acquisition end, and process the data to be processed by using the acquisition end simulation model to obtain the verification acquisition data.

In the device, a data processing simulation module 300 calls a corresponding acquisition end simulation model according to the type of an acquisition end to be tested, and constructs a model database, a plurality of acquisition end simulation models are arranged in the model database, and the acquisition end simulation models are used for processing data in the same data processing mode as the acquisition end, so that when the acquisition end has no fault, the data processed by the acquisition end and the data processed by the acquisition end simulation models are the same, namely, the check acquisition data and the standby acquisition data are the same, and if the check acquisition data and the standby acquisition data are different, the possibility that the acquisition end to be tested has the fault is indicated, and the fault type of the acquisition end to be tested needs to be further determined.

And the fault identification module 400 is configured to compare the difference between the to-be-checked acquired data and the checked acquired data to obtain difference data, and import the difference data into the trained neural network model to obtain a detection result, where the detection result includes a fault type and a fault cause.

In the device, the fault identification module 400 compares the difference between the data to be detected and the data to be checked, since the data to be processed sent to the detected acquisition end and the intelligent gateway are the same, if the detected acquisition end is not abnormal, the difference does not exist, the difference between the data to be detected and the data to be checked is determined by comparing the data to be detected and the data to be checked, the difference data is obtained, at the moment, the neural network model is used for processing, the type of the fault and the cause of the fault are determined according to the difference data, when the neural network model is trained, if a fault case is known, the data B is locally lost, the data difference corresponding to each fault is determined according to the data difference, and then the type of the fault can be determined according to the data difference.

As shown in fig. 6, as a preferred embodiment of the present invention, the data transmission module 200 includes:

and the acquisition end classification unit 201 is used for numbering each acquisition end according to a preset acquisition end list, randomly selecting at least three acquisition ends, dividing one acquisition end into tested acquisition ends, and taking other acquisition ends as test acquisition ends.

In this module, the collecting end classifying unit 201 numbers each collecting end according to a preset collecting end list, each collecting end needs to be detected, and by setting a number, when a test is performed, a test sequence is determined according to the number, a collecting end is randomly selected as a tested collecting end, then the number corresponding to the tested collecting end is eliminated, and two sets of collecting ends are randomly selected again and can be used as the tested collecting end.

The request sending unit 202 is configured to send test requests to the two groups of test acquisition ends, and the test acquisition ends send to-be-processed data to the tested acquisition ends after receiving the test requests.

In this module, the request sending unit 202 sends test requests to the two sets of test acquisition ends, and when testing, the intelligent gateway sends the test requests to the test acquisition ends according to the numbers of the tested acquisition ends and the test acquisition ends, where the test requests include the addresses of the tested acquisition ends, and at this time, the test acquisition ends send the data to be processed to the addresses, and at the same time, send the same data to be processed to the intelligent gateway.

The data receiving unit 203 is configured to receive data to be processed from the test acquisition end, where the test acquisition end sends the data to be processed to the intelligent gateway after receiving the test request, and the data to be processed sent by different test acquisition ends are different.

In this module, the data receiving unit 203 receives data to be processed from the test acquisition end, and after the data to be processed is received by the test acquisition end, the data to be processed is processed to obtain data to be inspected and acquired.

As shown in fig. 7, as a preferred embodiment of the present invention, the data processing simulation module 300 includes:

and the model query unit 301 is configured to identify the device type of the tested acquisition end, and query the model database according to the device type.

And the model calling unit 302 is used for calling a collection end simulation model matched with the collection end to be tested.

In the module, the type of the equipment of the tested acquisition end is identified, the data acquired by different acquisition ends are different, so the data processing modes are different, acquisition end simulation models corresponding to all the acquisition ends are preset in the intelligent gateway, the acquisition end simulation models and the corresponding acquisition ends have the same data processing mode, and the corresponding acquisition end simulation models can be obtained by inquiring and calling according to the type of the acquisition ends.

And the simulation processing unit 303 is configured to import the data to be processed into the acquisition end simulation model, and output the verification acquired data.

In the module, data to be processed is imported into the acquisition end simulation model, the acquisition end simulation model carries out simulation operation, the data to be processed is processed, and therefore verification acquisition data are output.

As shown in fig. 8, as a preferred embodiment of the present invention, the fault identifying module 400 includes:

and the data alignment module 401 is configured to perform alignment processing on the to-be-inspected acquired data and the verification acquired data.

A difference comparison module 402, configured to perform comparison according to the data arrangement order, determine the difference between the data of each part, and generate difference data, where the difference data includes data with a difference and a position of the data.

In this module, in order to ensure the accuracy of data comparison, the data alignment module 401 aligns the two data, and then compares the two data one by one during comparison, where the same byte is represented as 0 and the different byte is represented as 1, so as to obtain difference data, and the abnormal position can be determined according to the distribution of 0 and 1 in the difference data.

And the fault detection unit 403 is configured to construct a neural network model, train with a preset training set and a test set, import difference data into the neural network model, and output a detection result.

In this module, the fault detection unit 403 constructs a neural network model, introduces a preset training set into the neural network model, trains the neural network model, and introduces difference data into the neural network model after the training is completed, so as to output a result by using the neural network model, i.e., obtain a detection result in which the fault type and the cause of the fault are determined.

It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in various embodiments may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.

The above description is intended to be illustrative of the preferred embodiment of the present invention and should not be taken as limiting the invention, but rather, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.

Claims

1. An intelligent gateway localization test method, characterized in that the method comprises:

2. The intelligent gateway localization test method according to claim 1, wherein the steps of sending test requests to at least two test acquisition terminals, receiving the standby inspection acquisition data from the tested acquisition terminals, and receiving the to-be-processed data from the test acquisition terminals specifically include:

numbering each acquisition end according to a preset acquisition end list, randomly selecting at least three acquisition ends, dividing one acquisition end into tested acquisition ends, and taking other acquisition ends as testing acquisition ends;

and receiving the data to be processed from the test acquisition end, sending the data to be processed to the intelligent gateway after the test acquisition end receives the test request, wherein the data to be processed sent by different test acquisition ends are different.

3. The intelligent gateway localization test method according to claim 1, wherein the step of calling a corresponding acquisition end simulation model according to the type of the acquisition end to be tested, and processing the data to be processed by using the acquisition end simulation model to obtain the verification acquisition data specifically comprises:

calling an acquisition end simulation model matched with the acquisition end to be tested;

4. The intelligent gateway localization test method according to claim 1, wherein the step of comparing the difference between the backup acquisition data and the check acquisition data to obtain difference data, and importing the difference data into the trained neural network model to obtain a detection result specifically comprises:

aligning the data to be checked and collected;

and constructing a neural network model, training by using a preset training set and a test set, importing the difference data into the neural network model, and outputting a detection result.

5. The intelligent gateway localization test method according to claim 1, wherein the localization test time is determined to be detected when exceeding a preset value or when a preset listening event occurs.

6. The intelligent gateway localized testing method of claim 1, wherein the localized testing time is recalculated after a detection is completed.

7. An intelligent gateway localization test apparatus, the apparatus comprising:

the test judging module is used for calculating the localization test time and judging whether the detection is needed or not;

and the fault identification module is used for comparing the difference between the data to be detected and the data checked to obtain difference data, and importing the difference data into the trained neural network model to obtain a detection result, wherein the detection result comprises a fault type and a fault cause.

8. The intelligent gateway localization testing device according to claim 7, wherein the data transmission module comprises:

the acquisition terminal classifying unit is used for numbering each acquisition terminal according to a preset acquisition terminal list, randomly selecting at least three acquisition terminals, dividing one acquisition terminal into tested acquisition terminals, and taking the other acquisition terminals as test acquisition terminals;

the device comprises a request sending unit, a test acquisition end and a data processing unit, wherein the request sending unit is used for sending test requests to two groups of test acquisition ends, and the test acquisition ends send data to be processed to the tested acquisition ends after receiving the test requests;

and the data receiving unit is used for receiving the data to be processed from the test acquisition end, the test acquisition end sends the data to be processed to the intelligent gateway after receiving the test request, and the data to be processed sent by different test acquisition ends are different.

9. The intelligent gateway localization testing device of claim 7, wherein the data processing simulation module comprises:

the model query unit is used for identifying the equipment type of the tested acquisition end and querying the model database according to the equipment type;

10. The intelligent gateway localization test apparatus according to claim 7, wherein the fault identification module comprises:

the data alignment module is used for aligning the data to be checked and collected and the data checked and collected;

and the fault detection unit is used for constructing a neural network model, training by using a preset training set and a preset test set, importing the difference data into the neural network model and outputting a detection result.