CN114979242A - Method and device for dynamically subscribing data, electronic equipment and storage medium - Google Patents
Method and device for dynamically subscribing data, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114979242A CN114979242A CN202210563164.XA CN202210563164A CN114979242A CN 114979242 A CN114979242 A CN 114979242A CN 202210563164 A CN202210563164 A CN 202210563164A CN 114979242 A CN114979242 A CN 114979242A
- Authority
- CN
- China
- Prior art keywords
- target
- subscription
- time period
- dynamic
- regression model
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000000977 initiatory effect Effects 0.000 claims abstract description 46
- 238000012549 training Methods 0.000 claims description 31
- 238000004891 communication Methods 0.000 claims description 18
- 238000012512 characterization method Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012417 linear regression Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 description 6
- 238000000611 regression analysis Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- 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
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/14—Session management
- H04L67/141—Setup of application sessions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/14—Session management
- H04L67/143—Termination or inactivation of sessions, e.g. event-controlled end of session
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure provides a method, a device, an electronic device and a storage medium for dynamically subscribing data, which relate to the technical field of computers, and the specific scheme is as follows: determining a target time period for initiating dynamic subscription to target equipment; wherein, the target time period is a designated time period in a time range belonging to the designated time granularity; predicting the target subscription times of the collector for initiating the dynamic subscription to the target equipment in the target time period by utilizing a pre-trained regression model; wherein the regression model is used to characterize: the corresponding relation between each designated time period under the designated time granularity and the number of subscriptions of the dynamic subscriptions initiated by the collector to the target device; and after entering the target time period, initiating the dynamic subscription to the target equipment based on the target subscription times to obtain the data content required by the dynamic subscription. The intelligent level of the dynamic subscription data can be improved through the scheme.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for dynamically subscribing to data, an electronic device, and a storage medium.
Background
Telemetering is a remote technique for collecting data from physical or virtual devices at high speed.
The telemetering can be realized by adopting a dynamic subscription mode. The dynamic subscription means that the device serves as a server, the collector serves as a client to actively initiate connection to the device, and the device performs data acquisition and uploading. Moreover, the collector can automatically cancel the dynamic subscription after disconnecting, and does not support the configuration recovery related to the dynamic subscription.
In order to implement multiple dynamic subscriptions, in the related art, a user manually configures multiple dynamic subscriptions, so that after configuration of each dynamic subscription is completed, the collector responds to the dynamic subscription, that is, the collector actively initiates connection to the device, thereby collecting data. Therefore, the dynamic subscription for the data is not intelligent enough due to the large workload of manual configuration.
Disclosure of Invention
The present disclosure provides a method, an apparatus, an electronic device and a storage medium for dynamically subscribing to data, so as to improve the intelligence level of dynamically subscribing to data. The specific technical scheme is as follows:
according to a first aspect of the present disclosure, a method for dynamically subscribing to data is provided, which is applied to a collector, and the method includes:
determining a target time period for initiating dynamic subscription to target equipment; the target time period is a specified time period in a time range of specified time granularity;
predicting the target subscription times of the collector for initiating the dynamic subscription to the target equipment in the target time period by utilizing a pre-trained regression model; wherein the regression model is used to characterize: the corresponding relation between each designated time period under the designated time granularity and the number of subscriptions of the dynamic subscriptions initiated by the collector to the target device;
and after entering the target time period, initiating the dynamic subscription to the target equipment based on the target subscription times to obtain the data content required by the dynamic subscription.
Optionally, the sample data utilized by the regression model when training includes:
the appointed time periods in the historical time range, and the number of times of subscription of the dynamic subscription initiated by the collector to the target equipment in each appointed time period in the historical time range; the historical time range belongs to the specified time granularity.
Optionally, the training mode of the regression model includes:
acquiring the sample data;
constructing each two-dimensional feature based on the sample data, wherein feature elements in the two-dimensional features comprise characterization data corresponding to a specified time period in the historical time range, and the number of times of subscription of the dynamic subscription initiated by the collector to the target device in the specified time period;
and training model parameters in the regression model to be trained by using each two-dimensional characteristic data to obtain the trained regression model.
Optionally, the determining manner of the regression model to be trained includes:
if all the subscription times in the sample data are in a linear trend according to the time sequence, determining a linear regression model as a regression model to be trained;
and if each subscription frequency in the sample data presents a nonlinear trend according to the time sequence, determining the nonlinear regression model as the regression model to be trained.
Optionally, predicting, by using a regression model trained in advance, a target subscription number of the collector initiating the dynamic subscription to the target device in the target time period, where the predicting includes:
determining model input data corresponding to the target time period;
and inputting the model input data into the pre-trained regression model to obtain the target subscription times of the collector initiating the dynamic subscription to the target equipment in the target time period.
Optionally, after entering the target time period, initiating the dynamic subscription to the target device based on the number of target subscriptions to obtain data content required by the dynamic subscription, including:
generating a subscription plan by using the generated target subscription times in the target time period; wherein the subscription plan comprises the target number of subscriptions and a time interval of adjacent dynamic subscriptions;
and according to the subscription plan, after entering the target time period, initiating the dynamic subscription to the target equipment to obtain the data content required by the dynamic subscription.
Optionally, the number of the target time periods is multiple;
the subscription plan specifically includes: a target number of subscriptions per target time period and a time interval between adjacent dynamic subscriptions per target time period.
According to a second aspect of the present disclosure, there is provided an apparatus for dynamically subscribing to data, the apparatus comprising:
the determining module is used for determining a target time period for initiating dynamic subscription to the target equipment; wherein, the target time period is a designated time period in a time range belonging to the designated time granularity;
the prediction module is used for predicting the target subscription times of the collector for initiating the dynamic subscription to the target equipment in the target time period by using a pre-trained regression model; wherein the regression model is used to characterize: the corresponding relation between each designated time period under the designated time granularity and the number of subscriptions of the dynamic subscriptions initiated by the collector to the target device;
and the subscription module is used for initiating the dynamic subscription to the target equipment based on the target subscription times after entering the target time period to obtain the data content required by the dynamic subscription.
Optionally, the sample data utilized by the regression model when training includes:
the appointed time periods in the historical time range, and the number of times of subscription of the dynamic subscription initiated by the collector to the target equipment in each appointed time period in the historical time range; the historical time range belongs to the specified time granularity.
Optionally, the training mode of the regression model includes:
acquiring the sample data;
constructing each two-dimensional feature based on the sample data, wherein feature elements in the two-dimensional features comprise characterization data corresponding to a specified time period in the historical time range, and the number of times of subscription of the dynamic subscription initiated by the collector to the target device in the specified time period;
and training model parameters in the regression model to be trained by utilizing each two-dimensional characteristic data to obtain the trained regression model.
Optionally, the determining manner of the regression model to be trained includes:
if all the subscription times in the sample data are in a linear trend according to the time sequence, determining a linear regression model as a regression model to be trained;
and if the subscription times in the sample data are in a nonlinear trend according to the time sequence, determining a nonlinear regression model as the regression model to be trained.
Optionally, the prediction module is specifically configured to:
determining model input data corresponding to the target time period;
and inputting the model input data into the pre-trained regression model to obtain the target subscription times of the collector initiating the dynamic subscription to the target equipment in the target time period.
Optionally, the subscription module is specifically configured to:
generating a subscription plan by using the generated target subscription times in the target time period; wherein the subscription plan comprises the target number of subscriptions and a time interval of adjacent dynamic subscriptions;
and according to the subscription plan, after entering the target time period, initiating the dynamic subscription to the target equipment to obtain the data content required by the dynamic subscription.
Optionally, the number of the target time periods is multiple;
the subscription plan specifically includes: a target number of subscriptions per target time period and a time interval between adjacent dynamic subscriptions per target time period.
According to a third aspect of the present disclosure, there is provided an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;
a memory for storing a computer program;
and the processor is used for realizing any method for dynamically subscribing the data when executing the program stored on the memory.
According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, having stored therein a computer program which, when executed by a processor, implements any method of dynamically subscribing to data.
The present disclosure also provides a computer program product containing instructions which, when run on a computer, cause the computer to perform any of the above described methods of dynamically subscribing to data.
The method for dynamically subscribing data provided by the embodiment of the disclosure can determine a target time period in which dynamic subscription is to be initiated to a target device, predict the target subscription times of the collector initiating dynamic subscription to the target device in the target time period by using a pre-trained regression model, and initiate dynamic subscription to the target device by using the predicted target subscription times after entering the target time period, thereby obtaining data content required by the dynamic subscription. Therefore, according to the scheme, the target subscription times in the target time period are reasonably predicted through the pre-trained regression model, and the dynamic subscription is initiated based on the target subscription times, instead of requiring manual configuration of the user for each dynamic subscription. Therefore, the intelligent level of the dynamic subscription data can be improved through the scheme.
Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the present disclosure or the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other embodiments can be obtained by those skilled in the art according to the drawings.
Fig. 1 is a schematic structural diagram of a system for dynamically subscribing to data according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a method for dynamically subscribing to data according to an embodiment of the present disclosure;
fig. 3 is another flowchart of a method for dynamically subscribing to data according to an embodiment of the present disclosure;
FIG. 4 is a functional diagram of a regression model fitted with sample data according to an embodiment of the present disclosure;
fig. 5 is a schematic diagram of an apparatus for dynamically subscribing to data according to an embodiment of the present disclosure;
fig. 6 is a schematic view of an electronic device according to an embodiment of the disclosure.
Detailed Description
The technical solutions in the present disclosure will be described clearly and completely with reference to the accompanying drawings in the present disclosure, and it is to be understood that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. All other embodiments derived from the present application by a person of ordinary skill in the art based on the embodiments in the present disclosure are within the scope of protection of the present disclosure.
At present, when Telemetry dynamic subscription is carried out, the connection between a collector and equipment is disconnected, the equipment can automatically cancel subscription, does not sample and push data, does not support configuration recovery, and can only wait for manual reconfiguration, so that the collector can send a connection request again. Not only is the level of intelligence and automation inadequate, but also re-manual configuration in the case of possible subscription acquisition requirements not only increases the workload but also leads to a lag in the sampling effort.
In order to improve the intelligence level of dynamic subscription for data, the disclosure provides a method, a device, an electronic device and a storage medium for dynamically subscribing data.
The method for dynamically subscribing data provided by the disclosure can be applied to a collector, and the collector can initiate connection to physical equipment or virtual equipment so as to collect data. It is understood that the present disclosure does not limit the specific form of the collector, such as: the collector can be in a terminal form or a server form.
In particular, an executive body of a method for dynamically subscribing to data provided by the present disclosure may be a device for dynamically subscribing to data. The device for dynamically subscribing to data may be functional software running on the collector, for example: and the functional software is used for dynamically subscribing data, and at the moment, the device for dynamically subscribing data can initiate dynamic subscription to the physical equipment or the virtual equipment so as to collect data.
It should be noted that, the method for dynamically subscribing to data provided by the present disclosure may be applied to any scenario with a requirement for dynamically subscribing to data, for example: the method includes the steps of collecting a scene of information such as interface traffic, a Central Processing Unit (CPU) or memory data from a physical device or a virtual device, where the physical device may include but is not limited to a router, a switch, and the like, and the virtual device may include but is not limited to various virtual machines and the like. In addition, it is understood that the collector in the embodiment of the present disclosure is a device in a system for implementing dynamic subscription data, and the system for implementing dynamic subscription data may further include a target device of the collected data, that is, the above-mentioned physical device or virtual device.
The method for dynamically subscribing the data provided by the present disclosure may include the following steps:
determining a target time period for initiating dynamic subscription to target equipment; wherein, the target time period is a designated time period in a time range belonging to the designated time granularity;
predicting the target subscription times of the collector for initiating the dynamic subscription to the target equipment in the target time period by utilizing a pre-trained regression model; wherein the regression model is used to characterize: the corresponding relation between each designated time period under the designated time granularity and the number of subscriptions of the dynamic subscriptions initiated by the collector to the target device;
and after entering the target time period, initiating the dynamic subscription to the target equipment based on the target subscription times to obtain the data content required by the dynamic subscription.
The method for dynamically subscribing data provided by the embodiment of the disclosure can determine a target time period in which dynamic subscription is to be initiated to a target device, predict the target subscription times of the collector initiating dynamic subscription to the target device in the target time period by using a pre-trained regression model, and initiate dynamic subscription to the target device by using the predicted target subscription times after entering the target time period, thereby obtaining data content required by the dynamic subscription. Therefore, according to the scheme, the target subscription times in the target time period are reasonably predicted through the pre-trained regression model, and the dynamic subscription is initiated based on the target subscription times, instead of requiring manual configuration of the user for each dynamic subscription. Therefore, the intelligent level of the dynamic subscription data can be improved through the scheme.
For ease of understanding the scheme, the following first introduces the working principle from the perspective of a system for implementing dynamic subscription data. As shown in fig. 1, the system for implementing dynamic subscription data may include: a collector on the collection side and a device on the device side. Wherein, the device at the device side initiates a target device of dynamic subscription for the collector, for example: router a, Router B … … Router N. During dynamic subscription, the collector can actively initiate connection to the equipment side so as to collect data generated by the required equipment side, wherein the data can be interface flow data, CPU (central processing unit), memory data and the like; after the acquired data are obtained, the data can be analyzed by the collector or other equipment communicated with the collector, so that the network and/or the equipment can be optimized in time, and the network effect of the system for dynamically subscribing the data is improved.
In the scheme provided by the embodiment of the disclosure, when the sliding window Δ T comes, the collector can collect and count historical dynamic subscription data, obtain the dynamic subscription frequency of the current sliding window through regression analysis, and initiate dynamic subscription to the device on the device side to obtain data content required by the dynamic subscription. It should be noted that the sliding window Δ T is the target time period, one sliding window may be a designated time period, and each sliding window constitutes a time range of a designated time granularity, that is, each designated time period constitutes a period T of the dynamic subscription; the regression analysis is to predict the times of the collector initiating dynamic subscription to the target equipment in the target time period by utilizing a pre-trained regression model; collecting statistics, namely collecting and counting sample data required by the regression model during training: and collecting and counting each designated time period in the historical time range, and the times of initiating dynamic subscription to the target equipment by the collector in each designated time period in the historical time range.
When the collector initiates dynamic subscription of collected data, the target device may report data content required by the dynamic subscription to the collector according to the requirement of the collector. In addition, the collector may generate a connection with a target device on the device side through a specified Network command, so as to obtain data content required by dynamic subscription, where the specified Network command may be a connection establishment command of a TCP protocol or a connection establishment command of a UDP protocol, and the like.
It should be noted that the above description of the interaction relationship between the devices in the system for implementing dynamic subscription data is only an example, and should not be construed as a limitation to the present disclosure.
As shown in fig. 2, a method for dynamically subscribing to data provided by the present disclosure may include the following steps:
s201: determining a target time period for initiating dynamic subscription to target equipment;
wherein, the target time period is a designated time period in a time range belonging to the designated time granularity;
the method for dynamically subscribing data provided by the disclosure predicts the dynamic subscription times in a specified time period and automatically initiates subscription, so that in order to complete dynamic subscription of data, a target time period to initiate dynamic subscription to target equipment needs to be determined first, so as to execute subsequent steps of dynamically subscribing data, and realize dynamic subscription of data.
In addition, the method for dynamically subscribing to data provided by the present disclosure may dynamically subscribe to data for one or more target time periods, and therefore, it is reasonable that the number of the target time periods is not limited, that is, one target time period may be determined, or a plurality of time periods may also be determined.
It should be noted that the specified time granularity may be set according to actual requirements, for example: the specified time granularity may be days, weeks, months, etc.; after the designated time granularity is determined, the time range of the designated time granularity can be divided according to the preset time length, so that a plurality of designated time periods are obtained, and the target time period is a designated time period. For example: taking days as the designated time granularity, wherein the duration range of the designated time granularity is one day, and if hours are taken as the preset duration, the one day can be divided into 24 designated time periods; then the target time period is one hour of a certain day; or, taking a week as the specified time granularity, the time range of the specified time granularity is one week, and taking a day as the predetermined time length, at this time, one week may be divided into 7 specified time periods, and then, the target time period is one day of a certain week.
It is understood that, in a specific application, the user may give the target time period for which the dynamic subscription is to be initiated to the target device through the human-computer interaction interface, but is not limited thereto.
S202: predicting the target subscription times of the collector initiating dynamic subscription to the target equipment in the target time period by utilizing a pre-trained regression model;
wherein the regression model is used to characterize: the corresponding relation between each designated time period under the designated time granularity and the number of subscriptions of the dynamic subscriptions initiated by the collector to the target device;
after the target time period in which the dynamic subscription is to be initiated to the target device is determined, the target subscription times in which the collector initiates the dynamic subscription to the target device can be predicted by using a pre-trained regression model, so that the subsequent step of dynamically subscribing data is performed to obtain the data content required by the dynamic subscription.
Optionally, in an implementation, the regression model is a model trained by using sample data; the sample data comprises each designated time period in a historical time range, and the number of times of subscription of the dynamic subscription initiated by the collector to the target equipment in each designated time period in the historical time range; the historical time range belongs to the specified time granularity.
It is understood that the regression model is a model for predicting the number of target subscriptions for which the collector initiates dynamic subscriptions to the target device for the target time period, and therefore, for accurately predicting the number of target subscriptions, the number of subscriptions for which the collector initiates dynamic subscriptions to the target device for each specified time period in the historical time range and for each specified time period in the historical time range may be utilized, and the historical time range belongs to the specified time granularity. That is, the regression model is trained by using the corresponding relationship between each specified time period and the historical subscription times in the historical period. By means of a training mode of the regression model by the sample data, the target subscription times in the target time period can be accurately predicted, and the efficiency of dynamically subscribing data is improved.
In addition, in an implementation manner, a manner of predicting, by using a regression model trained in advance, a target subscription number for a collector to initiate a dynamic subscription to a target device in a target time period may include:
determining model input data corresponding to the target time period;
and inputting the model input data into the pre-trained regression model to obtain the target subscription times of the collector initiating the dynamic subscription to the target equipment in the target time period.
In order to complete the prediction of the target subscription times, firstly, model input data corresponding to the target time period needs to be determined, wherein the model input data are characterization data of the target time period, and the determination mode is the same as that of the characterization data utilized in the model training. For example, the determining manner of the characterization data of the target time period may include: and using the position information of the target time period in a plurality of specified time periods included in the specified time granularity as the characterization data of the target time period. For example: taking the above-described division of a day into 24 designated time periods as an example, for a target time period: 7:00-8:00, the characterization data of the target time period can be position information of the target time period in 24 designated time periods: 8. the above determination of the characterization data of the target time period is only an example, and should not be construed as limiting the disclosure, for example: different designated time periods may correspond to different number information, and at this time, the number information may be used as the characterization data of the target time period.
After the model input data corresponding to the target time period is determined, the model input data can be input into a pre-trained regression model, so that the target subscription times of dynamic subscription to the target equipment are obtained by the collector in the target time period.
S203: after entering the target time period, initiating dynamic subscription to the target equipment based on the target subscription times to obtain data content required by the dynamic subscription;
after the target subscription times for the target time period are obtained and the target time period is entered, the dynamic subscription can be initiated to the target equipment based on the target subscription times, so that the data content required by the dynamic subscription is obtained, and the dynamic subscription data is realized.
It should be noted that there are various ways to initiate dynamic subscription to the target device, which are not limited herein. In some embodiments, after entering the target time period, initiating the dynamic subscription to the target device based on the target subscription number, and obtaining the data content required by the dynamic subscription may include:
generating a subscription plan by using the generated target subscription times in the target time period; wherein the subscription plan comprises the target number of subscriptions and a time interval of adjacent dynamic subscriptions;
and according to the subscription plan, after entering the target time period, initiating the dynamic subscription to the target equipment to obtain the data content required by the dynamic subscription.
If the number of the target time periods is multiple; the subscription plan specifically includes: a target number of subscriptions per target time period and a time interval between adjacent dynamic subscriptions per target time period.
It should be noted that, the time interval of the adjacent dynamic subscriptions may be evenly distributed or randomly distributed, which is not limited herein, and when the time interval is evenly distributed, the determination manner of the time interval may be: and determining the time interval of the adjacent dynamic subscriptions according to the ratio of the target time period to the target subscription times. The subscription plan may be generated only according to the number of subscriptions, and the time interval between adjacent dynamic subscriptions is not limited, for example: it is reasonable to initiate the next dynamic subscription to the target device immediately after one dynamic subscription is completed.
In some embodiments, for a target time period, after entering the target time period, initiating a dynamic subscription to the target device according to the generated subscription plan for the target time period includes: setting the initial subscription number to be 0, and starting dynamic subscription to the target equipment once by the collector within the target time period, wherein the subscription number is +1 until the subscription number is equal to the target subscription number, so as to obtain data content required by the dynamic subscription; and the time interval between the adjacent dynamic subscriptions is the time interval set by the subscription plan.
It should be noted that, the manner of initiating the dynamic subscription to the target device is only used as an example, and should not be construed as a limitation to the present disclosure.
The method for dynamically subscribing data provided by the embodiment of the disclosure can determine a target time period in which dynamic subscription is to be initiated to a target device, predict the target subscription times of the collector initiating dynamic subscription to the target device in the target time period by using a pre-trained regression model, and initiate dynamic subscription to the target device by using the predicted target subscription times after entering the target time period, thereby obtaining data content required by the dynamic subscription. Therefore, according to the scheme, the target subscription times in the target time period are reasonably predicted through the pre-trained regression model, and the dynamic subscription is initiated based on the target subscription times, instead of requiring manual configuration of the user for each dynamic subscription. Therefore, the intelligent level of the dynamic subscription data can be improved through the scheme.
In addition, the method for dynamically subscribing the data provided by the invention combines the regression thought in statistics, and provides a method for dynamically subscribing and acquiring the data by using regression analysis. The collector performs statistics and regression analysis on the number of dynamic subscriptions in each specified time period in the historical time range, fits a regression model with good correlation, and predicts the target subscription number in the target time period according to the fitted regression model, so that a reasonable dynamic subscription period plan can be generated automatically, the workload of artificial configuration is reduced, and the intelligent level is improved.
Optionally, in another embodiment of the present disclosure, a training mode of the regression model includes:
acquiring the sample data;
constructing each two-dimensional feature based on the sample data, wherein feature elements in the two-dimensional features comprise characterization data corresponding to a specified time period in the historical time range, and the number of times of subscription of the dynamic subscription initiated by the collector to the target device in the specified time period;
and training model parameters in the regression model to be trained by using each two-dimensional characteristic data to obtain the trained regression model.
It should be noted that, when training the regression model, sample data needs to be obtained first, so as to implement training of the regression model. The sample data may be data formed based on manually configured dynamic subscriptions at various specified time periods within the historical time range. That is, historical manually configured dynamic subscriptions are associated with each specified time period within the historical time range. After sample data is obtained, considering that the sample data contains characterization data corresponding to a specified time period within a historical time range and the subscription times of the dynamic subscription initiated by the collector to the target device in the specified time period, each two-dimensional feature can be constructed based on the sample data, and a regression model is trained according to each two-dimensional feature data to obtain a trained regression model. The characterization data corresponding to a specified time period in the historical time range may be: position information or number information of the specified time zone in the history time range. To facilitate understanding of the respective two-dimensional feature data, the following is presented in conjunction with the contents of table 1:
TABLE 1
| Nth sliding window DeltaT | Number of subscriptions N | Two |
| 1 | 6 | (1，6) |
| 2 | 10 | (2,10) |
| 3 | 5 | (3,5) |
| 4 | 9 | (4,9) |
| 5 | 8 | (5,8) |
| 6 | 12 | (6,12) |
| 7 | 15 | (7,15) |
| 8 | 2 | (8,2) |
| 9 | 20 | (9,20) |
| 10 | 17 | (10,17) |
| 11 | 26 | (11,26) |
| 12 | 4 | (12,4) |
| 13 | 19 | (13,19) |
| 14 | 13 | (14,13) |
| 15 | 20 | (15,20) |
| 16 | 15 | (16,15) |
| 17 | 11 | (17,11) |
| 18 | 18 | (18,18) |
| 19 | 15 | (19,15) |
| 20 | 10 | (20,10) |
| 21 | 6 | (21,6) |
| 22 | 7 | (22,7) |
| 23 | 12 | (23,12) |
| 24 | 26 | (24,26) |
In this case, the historical time range is one day, the time range included in each sliding window Δ T is 1 hour, each of the specified time periods is a 24-hour time period, that is, one day is divided into 24 sliding windows, where n may be the characterization data corresponding to one specified time period in the historical time range. In table 1, two-dimensional features (N Δ T, N) are formed for the correspondence between each sliding window and the number of subscriptions, where N Δ T represents the nth sliding window Δ T, and the regression model may be trained using the formed two-dimensional features. And (3) a process of training the model parameters in the regression model to be trained by using each two-dimensional feature data, which is not limited by the disclosure.
By means of constructing each two-dimensional feature by using sample data, the regression model can be accurately trained according to the sample data, so that the regression model is fitted, and the efficiency of dynamically subscribing data is improved.
Optionally, in another embodiment of the present disclosure, the determining method of the regression model to be trained includes:
if all the subscription times in the sample data are in a linear trend according to the time sequence, determining a linear regression model as a regression model to be trained;
and if the subscription times in the sample data are in a nonlinear trend according to the time sequence, determining a nonlinear regression model as the regression model to be trained.
Since there are many regression models, it is necessary to select an appropriate regression model for training according to actual situations. In addition, different regression models can be selected for training in consideration of the distribution mode of the subscription times corresponding to each specified time period obtained in the sample data. When the respective subscription times are in a linear trend in time sequence, the linear regression model may be determined as the regression model to be trained, for example: ridge regression models, Lasso regression models, etc. When the number of subscriptions in each time sequence is in a non-linear trend, the non-linear regression model may be determined as the regression model to be trained, for example: logistic regression models, polynomial regression models, and the like.
Illustratively, in one implementation, the ridge regression model is a biased estimation regression model dedicated to collinear data analysis, which is essentially an improved least squares estimation method, and by abandoning the unbiased property of the least squares method, the regression coefficients obtained at the expense of partial information loss and accuracy are more practical and reliable. The Lasso regression model is a relatively refined model obtained by constructing a penalty function, retains the advantage of subset shrinkage, and is a biased estimation model for processing complex collinearity data. The logistic regression model is a model for predicting the number of dynamic subscriptions trained by continuous arguments or classified arguments. The polynomial regression model is obtained by training a plurality of coefficients of a polynomial expansion using a plurality of data points, the coefficients being determined by least squares fitting. By determining different regression models in the above manner, the regression model to be trained which is more in line with the reality can be determined, and the training precision of the regression model is improved, so that the efficiency of dynamically subscribing data is improved.
Aiming at different trends of each subscription frequency in the sample data, presented according to a time sequence, different regression models can be selected for training, so that the trained regression models can be fit to the sample data with different trends, the applicability is strong, and the accuracy of the obtained regression models in predicting the dynamic subscription frequency can be improved.
For ease of understanding, the following presents a schematic content of a method for dynamically subscribing to data provided by the present disclosure with reference to fig. 3.
First, a time range T is counted 1 ～T 2 The number of subscriptions of each sliding window in (1), that is, the number of subscriptions for which the collector initiates dynamic subscriptions to the target device at each specified time period within the historical time range; extracting two-dimensional features (N delta T, N), wherein N is the number of a sliding window delta T, and N is the subscription frequency within the time range of the sliding window delta T; then, selecting a proper regression model, namely the regression model to be trained is determined; obtaining a fitted regression model by fitting the correlation coefficient, namely training model parameters in the regression model to be trained by using each two-dimensional characteristic data to obtain a trained regression model; after the fitted regression model is obtained, the subscription number N corresponding to the next sliding window Δ T can be predicted, that is, the target subscription number of the dynamic subscription initiated by the collector to the target device in the target time period is predicted.
When the next sliding window delta T comes, the predicted subscription times can be utilized, and the collector initiates dynamic subscription to the target equipment, namely after the target time period is entered, the dynamic subscription is initiated to the target equipment based on the target subscription times, and the data content required by the dynamic subscription is obtained.
According to the method for dynamically subscribing the data, the collector can carry out statistics and regression analysis on the dynamic subscription times of each designated time period in the historical time range, and fits a regression model with good correlation, so that the target subscription times of the target time period are predicted, the manual configuration workload can be reduced, and the intelligent level of dynamic subscription is improved.
For convenience of understanding, taking a polynomial regression model as an example, a training process and a training result of the regression model are described:
taking a polynomial regression model as an example, training sample data of the polynomial regression model as data in table 1; the polynomial regression model may be:
N＝a 0 +a 1 t+a 2 t 2 +…+a m t m ，t＝nΔT
when the polynomial regression model is trained, the constructed two-dimensional features (N Δ T, N) can be used as input until model fitting is performed, that is, model parameters in the regression model to be trained are trained by using each two-dimensional feature data to obtain the trained regression model.
Training the polynomial regression model through the sample data in fig. 4, and obtaining the trained regression model may be:
N＝12.18-4.593t+1.108t 2 -0.07709t 3 +0.001646t 4
as shown in fig. 4, each point in the graph is the constructed two-dimensional feature (N Δ T, N), the abscissa is the nth sliding window Δ T, and the ordinate is the subscription count N of each sliding window; the curve in the graph is the trained fourth-order polynomial regression model.
After the trained fourth-order polynomial regression model is obtained, the collector can predict the subscription times of the sliding window delta T in the time range of the next period according to the fourth-order polynomial regression model. For example: when the target time period T is 13, the target subscription number N is 17(N is an integer), and the target subscription number of each target time period within the time range of the specified time granularity can be predicted, that is, the subscription number corresponding to each of 24 sliding windows within the period range of one day can be predicted.
According to the predicted target subscription times, a subscription plan can be generated, and for the 13 th sliding window, according to the generated subscription plan, the collector can actively initiate 17 dynamic subscriptions to the target device in the 13 th sliding window Δ T in one day.
The method for dynamically subscribing data provided by the embodiment of the disclosure can determine a target time period in which dynamic subscription is to be initiated to a target device, predict the target subscription times of the collector initiating dynamic subscription to the target device in the target time period by using a pre-trained regression model, and initiate dynamic subscription to the target device by using the predicted target subscription times after entering the target time period, thereby obtaining data content required by the dynamic subscription. Therefore, according to the scheme, the target subscription times in the target time period are reasonably predicted through the pre-trained regression model, and the dynamic subscription is initiated based on the target subscription times, instead of requiring manual configuration of the user for each dynamic subscription. Therefore, the intelligent level of the dynamic subscription data can be improved through the scheme.
Based on the above method for dynamically subscribing to data, an embodiment of the present disclosure further provides a device for dynamically subscribing to data, as shown in fig. 5, the device includes:
a determining module 510, configured to determine a target time period in which a dynamic subscription is to be initiated to a target device; wherein, the target time period is a designated time period in a time range belonging to the designated time granularity;
a predicting module 520, configured to predict, by using a pre-trained regression model, a target subscription number for the acquirer to initiate the dynamic subscription to the target device in the target time period; wherein the regression model is used to characterize: the corresponding relation between each designated time period under the designated time granularity and the number of subscriptions of the dynamic subscriptions initiated by the collector to the target device;
a subscription module 530, configured to initiate the dynamic subscription to the target device based on the number of target subscriptions after entering the target time period, so as to obtain data content required by the dynamic subscription.
The method for dynamically subscribing data provided by the embodiment of the disclosure can determine a target time period in which dynamic subscription is to be initiated to a target device, predict the target subscription times of the collector initiating dynamic subscription to the target device in the target time period by using a pre-trained regression model, and initiate dynamic subscription to the target device by using the predicted target subscription times after entering the target time period, thereby obtaining data content required by the dynamic subscription. Therefore, according to the scheme, the target subscription times in the target time period are reasonably predicted through the pre-trained regression model, and the dynamic subscription is initiated based on the target subscription times, instead of requiring manual configuration of the user for each dynamic subscription. Therefore, the intelligent level of the dynamic subscription data can be improved through the scheme.
Optionally, the sample data utilized by the regression model when training includes: the appointed time periods in the historical time range, and the number of times of subscription of the dynamic subscription initiated by the collector to the target equipment in each appointed time period in the historical time range; the historical time range belongs to the specified time granularity.
Optionally, the training mode of the regression model includes:
acquiring the sample data;
constructing each two-dimensional feature based on the sample data, wherein feature elements in the two-dimensional features comprise characterization data corresponding to a specified time period in the historical time range, and the number of times of subscription of the dynamic subscription initiated by the collector to the target device in the specified time period;
and training model parameters in the regression model to be trained by using each two-dimensional characteristic data to obtain the trained regression model.
Optionally, the determining manner of the regression model to be trained includes:
if all the subscription times in the sample data are in a linear trend according to the time sequence, determining a linear regression model as a regression model to be trained;
and if each subscription frequency in the sample data presents a nonlinear trend according to the time sequence, determining the nonlinear regression model as the regression model to be trained.
Optionally, the prediction module is specifically configured to:
determining model input data corresponding to the target time period;
and inputting the model input data into the pre-trained regression model to obtain the target subscription times of the collector initiating the dynamic subscription to the target equipment in the target time period.
Optionally, the subscription module is specifically configured to:
generating a subscription plan by using the generated target subscription times in the target time period; wherein the subscription plan comprises the target number of subscriptions and a time interval of adjacent dynamic subscriptions;
and according to the subscription plan, after entering the target time period, initiating the dynamic subscription to the target equipment to obtain the data content required by the dynamic subscription.
Optionally, the number of the target time periods is multiple;
the subscription plan specifically includes: a target number of subscriptions per target time period and a time interval between adjacent dynamic subscriptions per target time period.
The present disclosure also provides an electronic device, as shown in fig. 6, comprising a processor 601, a communication interface 602, a memory 603 and a communication bus 604, wherein the processor 601, the communication interface 602, and the memory 603 complete communication with each other through the communication bus 604,
a memory 603 for storing a computer program;
the processor 601 is configured to implement any method for dynamically subscribing to data when executing the program stored in the memory 603.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
In another embodiment provided by the present disclosure, a computer-readable storage medium is further provided, in which a computer program is stored, and the computer program, when executed by a processor, implements any of the above methods for dynamically subscribing to data.
In yet another embodiment provided by the present disclosure, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform any of the above-described embodiments of the method for dynamically subscribing to data.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause, in whole or in part, the processes or functions described in accordance with the present disclosure. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present disclosure, and is not intended to limit the scope of the present disclosure. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure are included in the scope of protection of the present disclosure.
Claims (16)
1. A method for dynamically subscribing data is applied to a collector, and the method comprises the following steps:
determining a target time period for initiating dynamic subscription to target equipment; the target time period is a specified time period in a time range of specified time granularity;
predicting the target subscription times of the collector for initiating the dynamic subscription to the target equipment in the target time period by utilizing a pre-trained regression model; wherein the regression model is used to characterize: the corresponding relation between each designated time period under the designated time granularity and the number of subscriptions of the dynamic subscriptions initiated by the collector to the target device;
and after entering the target time period, initiating the dynamic subscription to the target equipment based on the target subscription times to obtain the data content required by the dynamic subscription.
2. The method of claim 1, wherein the sample data utilized by the regression model when training comprises:
the appointed time periods in the historical time range, and the number of times of subscription of the dynamic subscription initiated by the collector to the target equipment in each appointed time period in the historical time range; the historical time range belongs to the specified time granularity.
3. The method of claim 2, wherein the regression model is trained by:
acquiring the sample data;
constructing each two-dimensional feature based on the sample data, wherein feature elements in the two-dimensional features comprise characterization data corresponding to a specified time period in the historical time range, and the number of times of subscription of the dynamic subscription initiated by the collector to the target device in the specified time period;
and training model parameters in the regression model to be trained by using each two-dimensional characteristic data to obtain the trained regression model.
4. The method of claim 3, wherein the regression model to be trained is determined in a manner comprising:
if all the subscription times in the sample data are in a linear trend according to the time sequence, determining a linear regression model as a regression model to be trained;
and if each subscription frequency in the sample data presents a nonlinear trend according to the time sequence, determining the nonlinear regression model as the regression model to be trained.
5. The method of any one of claims 1-4, wherein predicting, using a pre-trained regression model, a target number of subscriptions for which the collector initiates the dynamic subscription to the target device for the target time period comprises:
determining model input data corresponding to the target time period;
and inputting the model input data into the pre-trained regression model to obtain the target subscription times of the collector initiating the dynamic subscription to the target equipment in the target time period.
6. The method according to any one of claims 1 to 4, wherein initiating the dynamic subscription to the target device based on the target number of subscriptions after entering the target time period to obtain data content required by the dynamic subscription comprises:
generating a subscription plan by using the generated target subscription times in the target time period; wherein the subscription plan includes the target number of subscriptions and a time interval of adjacent dynamic subscriptions;
and according to the subscription plan, after entering the target time period, initiating the dynamic subscription to the target equipment to obtain the data content required by the dynamic subscription.
7. The method of claim 6, wherein the number of target time periods is plural;
the subscription plan specifically includes: a target number of subscriptions per target time period and a time interval between adjacent dynamic subscriptions per target time period.
8. An apparatus for dynamically subscribing to data, the apparatus comprising:
the determining module is used for determining a target time period for initiating dynamic subscription to the target equipment; wherein, the target time period is a designated time period in a time range belonging to the designated time granularity;
the prediction module is used for predicting the target subscription times of the collector for initiating the dynamic subscription to the target equipment in the target time period by using a pre-trained regression model; wherein the regression model is used to characterize: the corresponding relation between each designated time period under the designated time granularity and the number of subscriptions of the dynamic subscriptions initiated by the collector to the target device;
and the subscription module is used for initiating the dynamic subscription to the target equipment based on the target subscription times after entering the target time period to obtain the data content required by the dynamic subscription.
9. The apparatus of claim 8, wherein the sample data utilized by the regression model when training comprises:
the appointed time periods in the historical time range, and the number of times of subscription of the dynamic subscription initiated by the collector to the target equipment in each appointed time period in the historical time range; the historical time range belongs to the specified time granularity.
10. The apparatus of claim 9, wherein the regression model is trained by:
acquiring the sample data;
constructing each two-dimensional feature based on the sample data, wherein feature elements in the two-dimensional features comprise characterization data corresponding to a specified time period in the historical time range, and the number of times of subscription of the dynamic subscription initiated by the collector to the target device in the specified time period;
and training model parameters in the regression model to be trained by using each two-dimensional characteristic data to obtain the trained regression model.
11. The apparatus of claim 10, wherein the regression model to be trained is determined by:
if all the subscription times in the sample data are in a linear trend according to the time sequence, determining a linear regression model as a regression model to be trained;
and if each subscription frequency in the sample data presents a nonlinear trend according to the time sequence, determining the nonlinear regression model as the regression model to be trained.
12. The apparatus according to any of claims 8-11, wherein the prediction module is specifically configured to:
determining model input data corresponding to the target time period;
and inputting the model input data into the pre-trained regression model to obtain the target subscription times of the collector initiating the dynamic subscription to the target equipment in the target time period.
13. The apparatus according to any of claims 8-11, wherein the subscription module is specifically configured to:
generating a subscription plan by using the generated target subscription times in the target time period; wherein the subscription plan comprises the target number of subscriptions and a time interval of adjacent dynamic subscriptions;
and according to the subscription plan, after entering the target time period, initiating the dynamic subscription to the target equipment to obtain the data content required by the dynamic subscription.
14. The apparatus of claim 13, wherein the number of target time periods is plural;
the subscription plan specifically includes: a target number of subscriptions per target time period and a time interval between adjacent dynamic subscriptions per target time period.
15. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1 to 7 when executing a program stored in the memory.
16. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210563164.XA CN114979242A (en) | 2022-05-18 | 2022-05-18 | Method and device for dynamically subscribing data, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210563164.XA CN114979242A (en) | 2022-05-18 | 2022-05-18 | Method and device for dynamically subscribing data, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114979242A true CN114979242A (en) | 2022-08-30 |
Family
ID=82984616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210563164.XA Pending CN114979242A (en) | 2022-05-18 | 2022-05-18 | Method and device for dynamically subscribing data, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114979242A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110247816A (en) * | 2019-05-13 | 2019-09-17 | 中国联合网络通信集团有限公司 | Index monitoring method and device |
| CN110427551A (en) * | 2019-07-01 | 2019-11-08 | 五八有限公司 | Information-pushing method, device, electronic equipment and computer-readable medium |
| CN110445671A (en) * | 2019-06-27 | 2019-11-12 | 浪潮思科网络科技有限公司 | A kind of network flow monitoring method based on SDN |
| WO2020000426A1 (en) * | 2018-06-29 | 2020-01-02 | 深圳中兴力维技术有限公司 | Method, system, storage medium for collecting information |
| CN111049698A (en) * | 2018-10-15 | 2020-04-21 | 华为技术有限公司 | Telemetering data acquisition method and device |
| CN112187525A (en) * | 2019-10-31 | 2021-01-05 | 华为技术有限公司 | Device management method, device, system, device and storage medium |
| WO2021089905A1 (en) * | 2019-11-04 | 2021-05-14 | Nokia Technologies Oy | Dynamically unsubscribing from a plmn/npn service |
| CN112884944A (en) * | 2021-04-28 | 2021-06-01 | 奥特酷智能科技(南京)有限公司 | Method and system for realizing rapid diagnosis of vehicle-mounted sensor based on Telemetry technology |
| CN113114480A (en) * | 2020-01-10 | 2021-07-13 | 华为技术有限公司 | Data reporting method and related equipment |
-
2022
- 2022-05-18 CN CN202210563164.XA patent/CN114979242A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020000426A1 (en) * | 2018-06-29 | 2020-01-02 | 深圳中兴力维技术有限公司 | Method, system, storage medium for collecting information |
| CN111049698A (en) * | 2018-10-15 | 2020-04-21 | 华为技术有限公司 | Telemetering data acquisition method and device |
| CN110247816A (en) * | 2019-05-13 | 2019-09-17 | 中国联合网络通信集团有限公司 | Index monitoring method and device |
| CN110445671A (en) * | 2019-06-27 | 2019-11-12 | 浪潮思科网络科技有限公司 | A kind of network flow monitoring method based on SDN |
| CN110427551A (en) * | 2019-07-01 | 2019-11-08 | 五八有限公司 | Information-pushing method, device, electronic equipment and computer-readable medium |
| CN112187525A (en) * | 2019-10-31 | 2021-01-05 | 华为技术有限公司 | Device management method, device, system, device and storage medium |
| WO2021089905A1 (en) * | 2019-11-04 | 2021-05-14 | Nokia Technologies Oy | Dynamically unsubscribing from a plmn/npn service |
| CN113114480A (en) * | 2020-01-10 | 2021-07-13 | 华为技术有限公司 | Data reporting method and related equipment |
| CN112884944A (en) * | 2021-04-28 | 2021-06-01 | 奥特酷智能科技(南京)有限公司 | Method and system for realizing rapid diagnosis of vehicle-mounted sensor based on Telemetry technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI733217B (en) | Push and display method, device and equipment of login method | |
| CN106294614B (en) | Method and apparatus for accessing business | |
| CN105824834B (en) | Search traffic cheating behavior identification method and device | |
| RU2394262C2 (en) | System for configuring devices and method of preventing abnormal situations on production plant | |
| CN107305611B (en) | Method and device for establishing model corresponding to malicious account and method and device for identifying malicious account | |
| CN109495770A (en) | A kind of direct broadcasting room recommended method, device, equipment and medium | |
| CN110491124B (en) | Vehicle flow prediction method, device, equipment and storage medium | |
| CN103646086A (en) | Junk file cleaning method and device | |
| WO2023016159A1 (en) | Method and system for predicting network traffic of smart city | |
| CN110019382B (en) | User intimacy index determination method and device, storage medium and electronic equipment | |
| CN114637911B (en) | Method for recommending next interest point of attention fusion perception network | |
| CN114205690A (en) | Flow prediction method, flow prediction device, model training method, model training device, electronic equipment and storage medium | |
| CN111835536A (en) | Flow prediction method and device | |
| CN114979242A (en) | Method and device for dynamically subscribing data, electronic equipment and storage medium | |
| CN110781743B (en) | Crowd gathering event processing method and device and electronic equipment | |
| WO2020034756A1 (en) | Method and apparatus for predicting target device, and electronic device and storage medium | |
| WO2023142349A1 (en) | Behavior sequence generation method and apparatus, storage medium and electronic device | |
| WO2023165051A1 (en) | Identity determination method, storage medium and electronic apparatus | |
| CN113837807B (en) | Heat prediction method, heat prediction device, electronic equipment and readable storage medium | |
| CN111429920B (en) | User distinguishing method, user behavior library determining method, device and equipment | |
| CN113380241A (en) | Semantic interaction adjusting method and device, voice equipment and storage medium | |
| CN110674330B (en) | Expression management method and device, electronic equipment and storage medium | |
| CN111161741B (en) | Personalized information identification method and device, electronic equipment and storage medium | |
| De Caro et al. | Continual adaptation of federated reservoirs in pervasive environments | |
| CN112115298B (en) | Video recommendation method and device, electronic equipment and storage medium |
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 |