A data query method, device, equipment and medium based on Internet of Things cards

Abstract

The present invention provides a method, device, equipment and medium for querying data based on an Internet of Things card, including: obtaining and analyzing the activity of the Internet of Things card of a customer account within a period to form an ordered list of highly active cards; dynamically predicting the change trend of the number of times each target customer account calls the interface for querying Internet of Things card data according to the triple exponential smoothing prediction algorithm, and predicting the number of times of accessing this interface; according to the prediction result, preloading the data of the most active cards managed under the customer account with the same number of access times into the cache. The present invention predicts the next period based on the data of the customer's historical call interface. After predicting the number of times of the query interface, it preloads the data of the Internet of Things cards with high activity and the same number of call times into the cache, and sets a validity period of one period, which can reduce the resource overhead of the CMP platform to a certain extent and provide the query efficiency of Internet of Things card data more efficiently.

Description

Technical Field

[0001] The present invention relates to the technical field of the Internet of Things, and particularly relates to a method, device, equipment and medium for querying information based on an Internet of Things card. Background Art

[0002] The Internet of Things connection management platform is mainly used to monitor, analyze, configure and manage the network connection status of Internet of Things devices, aiming to help users efficiently manage the connection status of a large number of Internet of Things devices at the network level, ensure the secure transmission of data between devices, and respond to device changes and network conditions in real time. Customers need to query the real-time information of the activated Internet of Things cards through the query interface provided by the CMP to complete autonomous monitoring and autonomous management. The CMP has to bear the interface access of a large number of customers within limited service resources and provide accurate and real-time query results, which poses a huge service pressure on the platform. For such a scenario, the CMP needs to continuously optimize the efficiency of the query interface to meet the customers' needs for querying Internet of Things cards within limited resources. For such a scenario, the CMP needs to continuously optimize the efficiency of the query interface so as to meet the customers' needs for querying Internet of Things cards within limited resources. Summary of the Invention

[0003] To solve the above problems, the present invention aims to propose a method, device, equipment and medium for querying information based on an Internet of Things card. By predicting the next cycle based on the data of the customer's historical call interface, after predicting the number of times of the query interface, the information of the highly active Internet of Things cards with the same number of calls is loaded into the cache in advance, and a validity period of one cycle is set, which can reduce the resource overhead of the CMP platform to a certain extent and provide a more efficient query efficiency for the information of the Internet of Things cards.

[0004] To achieve the above object, the technical solution of the present invention is realized as follows:

[0005] A method for querying information based on an Internet of Things card, the method comprising:

[0006] Obtaining the activity of the Internet of Things cards of a customer account within one cycle, analyzing and calculating to form an ordered list of highly active cards;

[0007] According to the triple exponential smoothing prediction algorithm, dynamically predicting the change trend of the number of times of each target customer account calling the interface for querying the information of the Internet of Things card, and predicting the number of times of accessing this interface;

[0008] According to the prediction result, preloading the information of the most active cards managed under this customer account with the same number of access times into the cache.

[0009] Further, the IoT card stores profile information associated with the activity level. The profile information includes call records of voice, SMS, and data usage of the IoT card, records of changes in the IoT card's life cycle, operation records of the IoT card's independent network disconnection and reconnection, records of changes in the card package, records of changes in the card function products, and location records of the card.

[0010] Further, weight settings are applied to the profile information. Each time a record appears, the activity level of the card will increase.

[0011] Further, the activity level calculation formula is as follows:

[0012]

[0013] Among them, totalTime is the time difference between the defined earliest cycle start time and the current statistical time point, timeInterval is the time difference between the time of the current behavior record and the current statistical time point, M represents the activity weight defined for this record, i represents the serial number of each activity record within the defined cycle, n represents the total number of records within the defined last T cycles. When (h - 1) ≥ T, the value is taken as T, representing that records before the defined time period will no longer be used for activity level calculation; then the records within the statistical period are used to calculate the operation activity level, and then summed up;

[0014] It can be seen from the formula that the farther the behavior occurrence time is from the current statistical time point, the lower the impact on the operation activity level;

[0015]

[0016] i represents the serial number of each activity record within the defined cycle, n T will represent the total number of records within the defined last T cycles, N h represents the number of records within the hth cycle. The sigmoid function is used for normalization. C is an integer constant greater than 1, used to represent the influence coefficient of stability on the activity level. The closer the number of behavior occurrences within the statistical period is to the average occurrence number, and the less the change, the higher the stability;

[0017] Card activity level = ∑(operation behavior activity level * behavior stability)

[0018]

[0019] Further, the change trend of the number of times each target customer account calls and queries the IoT card profile interface is dynamically predicted according to the triple exponential smoothing prediction algorithm. Predicting the number of times of accessing this interface means:

[0020] First, the behavior of the user querying the data interface is predictable in the time dimension. The triple exponential smoothing algorithm is used to predict the time series containing both trends and seasonality, and predict the value of x in the next time period T. t+T As follows:

[0021] x t+T = A T + B T T + C T T 2

[0022]

[0023]

[0024]

[0025] Among them, the triple exponential smoothing calculation formula is:

[0026]

[0027] In the exponential smoothing method, all previous observations have an impact on the current smoothed value. However, if there are outliers in the historical data, it will directly affect the prediction accuracy. Therefore, it is necessary to clean the abnormal data before prediction.

[0028] If the operation within a certain period is the most abnormal or the least abnormal, it will be regarded as abnormal data. The measurement index is:

[0029]

[0030] When meeting the above conditions, the data is abnormal data.

[0031] Method for correcting outliers: After removing the outliers, perform cubic spline interpolation on the data in this period. Cubic spline interpolation modeling:

[0032] Let f(x) be a continuously differentiable function on the interval [a, b]. Given a set of base points on the interval [a, b], when the number of load data after removing the outlier points is (n + 1):

[0033] a = x0 < x1 < x2 < … < x n = b;

[0034] Let the function S(x) satisfy the conditions:

[0035] S(x) has the expression on each sub - interval [x i-1 , x i : S i (x) = a i x 3 + bi x 2 +c i x + d i ;

[0036] S(x) has second-order continuous derivative on the interval [a, b];

[0037] Solve for S in each sub-interval according to the following known conditions i (x):

[0038] S(x i ) = f(x i )

[0039] S(x i - 0) = S(x i + 0)

[0040] S′(x i - 0) = S′(x i + 0)

[0041] S″(x i - 0) = S″(x i + 0)

[0042] S″(x0) = f″(x0) = 0

[0043] S″(x n ) = f″(x n ) = 0; (i = 0, 1, …, n)

[0044] S i (x) After obtaining, the corresponding t at the time of the outlier can be substituted into the corresponding S i (x), (x i-1 < t < x i+1 ) to obtain the replacement point of the outlier.

[0045] Furthermore, it also includes the preheating of the card data cache, specifically referring to: after removing the outliers, predicting the historical data of the query interface called by the existing user accounts, dynamically predicting the change in the number of times each account calls the query card data, and predicting the number of queries n in the next cycle; by default, within one cycle, the interface call for querying the data of one card by one account is 1 time, and customers will not query the data of the Internet of Things cards with low activity; select the list of cards with high activity through activity calculation, query the data of the top n Internet of Things cards in terms of activity, and then add them to the cache, and the timeout duration is one cycle.

[0046] Furthermore, the preheating of the card data cache includes the following specific steps:

[0047] CMP first sets activity impact weights for the five types of behaviors under the IoT card: SMS, voice, and traffic history, life cycle change history, autonomous network disconnection and reconnection history, package change order history, and functional product change history, and sets the card activity filtering threshold. Then, the number of cycles and cycle time for historical record collection are specified;

[0048] Then, at the end of a CMP cycle, a scheduled task trigger triggers the task of predictively loading the card data cache;

[0049] Use multi-threading and concurrent means to calculate the activity of five types of behaviors, including SMS, voice, and traffic history, life cycle change history, autonomous network disconnection and network restoration history, package change order history, and functional product change history, under the IoT cards managed by key customers using the activity calculation method in this patent. After each thread completes the calculation, merge and filter the calculation results of each card to form a high-activity card list of IoT cards managed by the key customer.

[0050] In another task thread, the interface call records of the key customer's card information query in the past specified period are obtained, and after removing abnormal data, the number of calls by the customer in the next period is predicted using the cubic exponential smoothing algorithm;

[0051] When the predicted call count and activity calculation tasks are completed, the data of the n IoT cards with the highest activity are queried in the corresponding data table of the database through the card access number, and the query results are loaded into the redis cache. The key in redis is the card access number, and the value is the card data structured data. The validity period of this cache is a specified period. The main query results of the IoT card's main product instance, functional product instance, package instance, and ICCID instance information are loaded into redis;

[0052] This completes the cache prediction process of predicting a key customer's card information query in the next cycle.

[0053] In order to achieve the above object, the present invention also provides a data query device based on an Internet of Things card, comprising:

[0054] Activity calculation module: used to obtain the activity of IoT cards of customer accounts in a period and perform analysis and calculation to form an ordered list of highly active cards;

[0055] Prediction module: used to dynamically predict the changing trend of the number of times each target customer account calls the interface for querying IoT card information based on the cubic exponential smoothing prediction algorithm, and predict the number of times the interface is accessed;

[0056] Loading module: used to pre-load the profiles of the most active cards managed under the customer account with the same number of access times as the prediction result into the cache.

[0057] To achieve the above object, the present invention also provides a computer device, which includes a memory and a processor. A computer program is stored on the memory, and when the processor executes the computer program, the method for querying the profile based on the Internet of Things card as described above is implemented.

[0058] To achieve the above object, the present invention also provides a storage medium, which stores a computer program. The computer program includes program instructions, and when the program instructions are executed by the processor, the method for querying the profile based on the Internet of Things card as described above can be implemented.

[0059] Beneficial effects: The present invention predicts the next cycle based on the data of the customer's historical call interface. After predicting the number of times of the query interface, the profiles of the Internet of Things cards with high activity and the same number of call times are pre-loaded into the cache in advance, and a validity period of one cycle is set. In this way, the resource overhead of the CMP platform can be reduced to a certain extent, and the query efficiency of the Internet of Things card profiles can be provided more efficiently. Description of the Drawings

[0060] The drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0061] Figure 1 It is a flowchart of the method for querying the profile based on the Internet of Things card according to the embodiment of the present invention;

[0062] Figure 2 It is a specific step flowchart of the preheating of the card profile cache of the method for querying the profile based on the Internet of Things card according to the embodiment of the present invention;

[0063] Figure 3 It is a schematic diagram of a customer querying the profile of an Internet of Things card of the method for querying the profile based on the Internet of Things card according to the embodiment of the present invention;

[0064] Figure 4 It is a schematic structural diagram of the device for querying the profile based on the Internet of Things card according to the embodiment of the present invention. Detailed Embodiments

[0065] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0066] Glossary

[0067] CMP: Connection Management Platform

[0068] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0069] Problems existing in some current Internet of Things connection management platforms: Since customers have a large demand for querying a large amount of Internet of Things card data carried by the CMP puzzle, the CMP needs to carry a large number of high-frequency and high-concurrency requests for querying card data. Since the underlying database resources of the CMP and the backend service resources provided by the service are limited, for such high-frequency and high-concurrency query requests for Internet of Things card data, it is necessary to improve the success rate and execution efficiency, and also ensure that resources are not occupied in large quantities. Therefore, it is necessary to pre-load the data of Internet of Things cards into the cache to handle the query access of the interface. However, the cache is also a kind of resource, and it is not possible to load all the Internet of Things card data. Therefore, after predicting the customer query behavior, it is necessary to cache and load the data of Internet of Things cards with high activity, so as to improve the query speed and reduce resource consumption.

[0070] Embodiment 1

[0071] Based on the above defects and design ideas of the prior art, see Figure 1 : A method for querying Internet of Things card data based on this embodiment, the method includes:

[0072] Obtain the activity of the Internet of Things cards of the customer account within a period and perform analysis and calculation to form an ordered list of high-activity cards;

[0073] According to the triple exponential smoothing prediction algorithm, dynamically predict the change trend of the number of times each target customer account calls the Internet of Things card data query interface, and predict the number of times of accessing this interface;

[0074] According to the prediction result, pre-load the data of the most active cards managed by this customer account with the same number of access times into the cache.

[0075] In this embodiment, the data of the next period is predicted through the data of the customer's historical call interface. After predicting the number of times of the query interface, the data of the Internet of Things cards with high activity and the same number of call times are pre-loaded into the cache, and a validity period of one period is set. In this way, the resource overhead of the CMP platform can be reduced to a certain extent, and the query efficiency of the Internet of Things card data can be provided more efficiently.

[0076] In a specific example, the IoT card stores profile information associated with the activity level. The profile information includes call records of voice, SMS, and data usage of the IoT card, records of changes in the IoT card's life cycle, operation records of the IoT card's autonomous network disconnection and reconnection, records of card package changes, records of changes in card function products, and location records of the card.

[0077] In a specific example, weight settings are applied to the profile information. Each time a record appears, the activity level of the card increases.

[0078] It should be noted that the activity level of the card is calculated based on the activity-related records defined within a certain number of specified cycles; the activity level of the card is affected by two factors. On the one hand, it is affected by the weight of the current operation behavior, and on the other hand, it is affected by the stability of this behavior of the card during this period; the farther the occurrence time point of the operation behavior is from the current statistical time point, the lower the impact on the activity level. Records before the defined number of cycles have no impact on the calculation of the card's activity level and are therefore not within the calculation scope; the more stable the behavior occurs within the statistical cycle, the better its activity level.

[0079] In a specific example, the activity level calculation formula is as follows:

[0080]

[0081] Where totalTime is the time difference between the start time of the earliest defined cycle and the current statistical time point, timeInterval is the time difference between the time of the current behavior record and the current statistical time point, M represents the activity weight defined for this record, i represents the sequence number of each activity record within the defined cycle, n represents the total number of records within the defined most recent T cycles. When (h - 1) ≥ T, the value is T, representing that records before the defined time cycle are no longer used for activity level calculation; then the records within the statistical cycle are used to calculate the operation activity level and then summed up;

[0082] It can be seen from the formula that the farther the behavior occurrence time is from the current statistical time point, the lower the impact on the operation activity level;

[0083]

[0084] i represents the sequence number of each activity record within the defined cycle, n T represents the total number of records within the defined most recent T cycles, N h represents the number of records within the hth cycle. The sigmoid function is used for normalization. C is an integer constant greater than 1, used to represent the influence coefficient of stability on the activity level. The closer the number of behavior occurrences within the statistical cycle is to the average occurrence number and the less the change, the higher the stability;

[0085] Card activity = ∑(operation behavior activity * behavior stability)

[0086]

[0087] It should be noted that the closer the behavior occurs to the current statistical time point, the greater the impact on the card activity, and the more times the impact will be greater; in addition, the historical habit of the card behavior should also be considered. The closer it is to the normal average value, the more normal the behavior occurs, which also means that this behavior is stable and has a higher impact on the card activity;

[0088] After calculating the activity and removing those with activity lower than the set threshold, the cards under key customers are sorted from high to low according to activity for the cache prediction loading of card data in the next cycle.

[0089] In a specific example, the dynamic prediction of the change trend of the number of times each target customer account calls the Internet of Things card data interface according to the triple exponential smoothing prediction algorithm. Predicting the number of times of accessing this interface means:

[0090] First, the behavior of the user querying the data interface is predictable in the time dimension. The triple exponential smoothing algorithm predicts the time series containing both trends and seasonality, and predicts x in the next time period T t+T As follows:

[0091] x t+T = A T + B T T + C T T 2

[0092]

[0093]

[0094]

[0095] Among them, the triple exponential smoothing calculation formula is:

[0096]

[0097] In the exponential smoothing method, all previous observations have an impact on the current smoothed value. However, if there are outliers in the historical data, it will directly affect the prediction accuracy; so it is necessary to clean the abnormal data before prediction;

[0098] If the operation is the most abnormal or the least abnormal within a certain period of time, it will be regarded as abnormal data. The measurement index is:

[0099]

[0100] When the above conditions are met, the data is abnormal data;

[0101] Method for correcting abnormal values: After removing the abnormal values, perform cubic spline interpolation on the data for this period, and establish a cubic spline interpolation model:

[0102] Let f(x) be a continuously differentiable function on the interval [a, b]. Given a set of base points on the interval [a, b], when the number of load data after removing the abnormal points is (n + 1):

[0103] a = x0 < x1 < x2 < … < x n = b;

[0104] Let the function S(x) satisfy the conditions:

[0105] S(x) has an expression on each sub-interval [x i-1 , x i : S i (x) = a i x 3 + b i x 2 + c i x + d i ;

[0106] S(x) has a second-order continuous derivative on the interval [a, b];

[0107] Solve for S i (x) for each sub-interval according to the following known conditions:

[0108] S(x i ) = f(x i )

[0109] S(x i -0) = S(x i +0)

[0110] S′(x i -0) = S′(x i +0)

[0111] S″(x i -0) = S″(x i +0)

[0112] S″(x0) = f″(x0) = 0

[0113] S″(x n ) = f″(x n ) = 0; (i = 0, 1, …, n)

[0114] S i(After finding (x), substitute the corresponding t at the time of the outlier into the corresponding S i (x),(x i-1 <t < x i+1 ) Obtain the replacement points for the outliers.

[0115] It should be noted that the current CMP platform stores data of hundreds of millions of IoT cards, including the life cycle status of the cards, card opening time, activation time, card opening location, ordered functional products, ordered packages, information of the traffic pools they belong to, etc. CMP provides query interfaces for various card data. Customers on CMP can make large-scale calls through HTTP / HTTPS; however, CMP has to bear the interface access of a large number of customers within limited service resources and provide accurate and real-time query results, resulting in relatively high platform service pressure. Therefore, by using the triple exponential smoothing prediction algorithm to dynamically predict the changing trend of the number of times each target customer account calls the query interface for IoT card data, accurately predict the number of times of this interface access, and load the data of highly active IoT cards with the same number of calls into the cache in advance according to the prediction results, and set a cycle validity period. This can reduce the resource overhead of the CMP platform to a certain extent and provide more efficient query efficiency for IoT card data.

[0116] In a specific example, it also includes the preheating of the card data cache, specifically referring to: after removing outliers, predicting the historical data of the existing user accounts calling the query interface, dynamically predicting the change in the number of times each account calls to query card data, and predicting the number of queries n in the next cycle; by default, within one cycle, the interface call for querying the data of one card by one account is 1 time, and customers will not query the data of IoT cards with low activity; select a list of highly active cards through activity calculation, query the data of the top n IoT cards in terms of activity, and then add them to the cache, with the timeout duration being one cycle.

[0117] In this embodiment, through the preheating of the card data cache, the cache loading of the predicted data for customers to query card data in the next cycle is completed; the query access of the customer account to card data within one cycle will fall into the data cache of highly active cards, which greatly speeds up the query speed of the interface and reduces the consumption of database resources.

[0118] In a specific example, refer to Figure 2 : The preheating of the card data cache includes the following specific steps:

[0119] CMP first sets activity impact weights for the five types of behaviors under the IoT card: SMS, voice, and traffic history, life cycle change history, autonomous network disconnection and reconnection history, package change order history, and functional product change history, and sets the card activity filtering threshold. Then, the number of cycles and cycle time for historical record collection are specified;

[0120] Then, at the end of a CMP cycle, a scheduled task trigger triggers the task of predictively loading the card data cache;

[0121] Use multi-threading and concurrent means to calculate the activity of five types of behaviors, including SMS, voice, and traffic history, life cycle change history, autonomous network disconnection and network restoration history, package change order history, and functional product change history, under the IoT cards managed by key customers using the activity calculation method in this patent. After each thread completes the calculation, merge and filter the calculation results of each card to form a high-activity card list of IoT cards managed by the key customer.

[0122] In another task thread, the interface call records of the key customer's card information query in the past specified period are obtained, and after removing abnormal data, the number of calls by the customer in the next period is predicted using the cubic exponential smoothing algorithm;

[0123] When the predicted call count and activity calculation tasks are completed, the data of the n IoT cards with the highest activity are queried in the corresponding data table of the database through the card access number, and the query results are loaded into the redis cache. The key in redis is the card access number, and the value is the card data structured data. The validity period of this cache is a specified period. The main query results of the IoT card's main product instance, functional product instance, package instance, and ICCID instance information are loaded into redis;

[0124] This completes the cache prediction process of predicting a key customer's card information query in the next cycle.

[0125] It should be noted that see Figure 3 : When the customer queries the IoT card data API managed by it in the next cycle, if the card cache is loaded in advance and it is determined that the card has a cache, the data cache corresponding to the card number will be structured and output and returned to the customer.

[0126] If it does not exist, the SQL query statement will be executed to retrieve the card information data from the database and return it to the customer in a structured manner.

[0127] The efficiency of querying through the cache is much higher than that of querying the database. Therefore, the efficiency of querying the managed card information by the customer in the next cycle will be greatly improved, with an approximate 20% increase in response speed.

[0128] In the specific implementation, based on the Internet of Things card information query solution of China Telecom's 5G Internet of Things connection management platform, the engine of this embodiment is added.

[0129] Embodiment 2

[0130] See Figure 4 : An information query device based on Internet of Things cards, including:

[0131] Activity calculation module: used to obtain and analyze the activity of the Internet of Things cards of the customer account within a cycle, and form an ordered list of highly active cards;

[0132] Prediction module: used to dynamically predict the change trend of the number of times each target customer account calls the Internet of Things card information query interface according to the triple exponential smoothing prediction algorithm, and predict the number of times of accessing this interface;

[0133] Loading module: used to load the information of the most active cards managed under this customer account with the same number of access times into the cache in advance according to the prediction result.

[0134] The advantages of the Internet of Things card-based information query device of this embodiment compared with the above-mentioned Internet of Things card-based information query method over the prior art are the same and will not be elaborated here.

[0135] Embodiment 3

[0136] A computer device, the computer device includes a memory and a processor, a computer program is stored on the memory, and when the processor executes the computer program, it implements the Internet of Things card-based information query method as described above.

[0137] It should be noted that the computer device can be a terminal or a server. Among them, the terminal can be an electronic device with communication functions such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device. The server can be an independent server or a server cluster composed of multiple servers.

[0138] Embodiment 4

[0139] A storage medium, the storage medium stores a computer program, the computer program includes program instructions, and when the program instructions are executed by the processor, they can implement the Internet of Things card-based information query method as described above.

[0140] It should be understood that in the embodiments of the present application, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, 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, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0141] The storage medium may be a U disk, a mobile hard disk, a read-only memory (ROM), a magnetic disk, an optical disk or other various computer-readable storage media that can store program codes.

[0142] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for querying information based on an Internet of Things card, characterized in that The method comprises: Obtain the activity of IoT cards of customer accounts in a period and perform analysis and calculation to form an ordered list of highly active cards; The cubic exponential smoothing prediction algorithm is used to dynamically predict the changing trend of the number of times each target customer account calls the interface for querying IoT card information, and the number of times the interface is accessed is predicted; Based on the prediction results, the data of the most active cards managed under the customer account with the same number of access times are loaded into the cache in advance; It also includes the preheating of the card data cache, which specifically means: after removing outliers, predict the historical data of existing user accounts calling the query interface, dynamically predict the changes in the number of times each account calls to query card data, and predict the number of queries n in the next cycle; by default, within a cycle, an account calls the interface for querying card data once, and customers will not query the data of IoT cards with low activity; after calculating the activity, select a list of highly active cards, query the data of the top n IoT cards in terms of activity, and then add them to the cache, with a timeout period of one cycle; The preheating of the card data cache includes the following specific steps: CMP first sets activity impact weights for five types of behaviors: SMS, voice, and traffic history, life cycle change history, autonomous network disconnection and reconnection history, package change order history, and functional product change history. It also sets the card activity filtering threshold. Then it specifies the number of cycles and cycle time for historical record collection. Then, at the end of a CMP cycle, a scheduled task trigger triggers the task of predictively loading the card data cache; Use multi-threading and concurrent means to calculate the activity of five types of behaviors under the IoT cards managed by key customers, including SMS, voice, and traffic history, life cycle change history, autonomous network disconnection and restoration history, package change order history, and functional product change history. Then, after each thread completes the calculation, merge the calculation results of each card and filter the data to form a high-activity card list of the IoT cards managed by the key customer; In another task thread, the interface call records of the key customer's card information query in the past specified period are obtained, and after removing abnormal data, the number of calls by the customer in the next period is predicted using the cubic exponential smoothing algorithm; When the predicted call count and activity calculation tasks are completed, the data of the n IoT cards with the highest activity are queried in the corresponding data table of the database through the card access number, and the query results are loaded into the redis cache. The key in redis is the card access number, and the value is the card data structured data. The validity period of this cache is a specified period. The main product instance, functional product instance, package instance, and ICCID instance information of the IoT card are queried and loaded into redis; This completes the cache prediction process of predicting a key customer's card information query in the next cycle.

2. The method for querying materials based on an IoT card according to claim 1, wherein The IoT card stores material information associated with the activity level. The material information includes call records of voice, SMS, and traffic of the IoT card, records of changes in the IoT card life cycle, operation records of the IoT card's independent network disconnection and reconnection, records of card package changes, records of changes in card function products, and positioning records of the card.

3. The method for querying materials based on an IoT card according to claim 2, wherein Weight settings are performed on the material information. Each time a record appears, the activity level of the card will increase.

4. The method for querying materials based on an IoT card according to claim 3, wherein The calculation formula for the activity level is as follows: Operating behavior activity = Among them, is the time difference between the defined earliest cycle start time and the current statistical time point, is the time difference between the time of the current behavior record and the current statistical time point, represents the activity weight defining this record, represents the serial number of each activity record within the defined cycle, will represent the total number of records in the defined last cycles. When at ( , the value is , indicating that records before the defined time cycle are no longer subject to activity calculation; then the records within the statistical cycle are operated on for activity calculation and then summed up; It can be seen from the formula that the farther the behavior occurrence time is from the current statistical time point, the lower the impact on the operation activity level; Behavior stability = Represents the serial number of each activity record within the defined period, Will represent the total number of records within the most recent defined cycles, Represents the number of records within the function for normalization, Is an integer constant greater than 1, used to represent the influence coefficient of stability on activity. The closer the number of occurrences of behavior is to the average number of occurrences within the statistical period, and the less the change, the higher the stability; Card activity = Card activity = .

5. The method for querying information based on an IoT card according to claim 1, wherein Based on the triple exponential smoothing prediction algorithm to dynamically predict the change trend of the number of times each target customer account calls the IoT card material query interface. Predicting the number of accesses to this interface means: First, the behavior of the user querying the data interface is predictable in the time dimension. The triple exponential smoothing algorithm is used to predict the time series containing both trends and seasonality, and predict the as follows: Among them, the triple exponential smoothing calculation formula is: In the exponential smoothing method, all previous observation values have an impact on the current smoothed value. However, if there are outliers in the historical data, it will directly affect the prediction accuracy; therefore, it is necessary to clean the abnormal data before prediction; If the operation abnormality is the largest or the smallest within a certain period of time, it will be regarded as abnormal data. The measurement index is: When meeting the above conditions, this data is abnormal data; Method for correcting outliers: After removing the outliers, perform cubic spline interpolation on the data of this period. Cubic spline interpolation modeling: Let be a continuously differentiable function on the interval , and a set of base points is given on the interval . When the number of load data after removing outliers is ( ): ； Let the function satisfy the conditions: Over each subinterval there is an expression: ; on the interval has a second-order continuous derivative; Solve for each sub-interval based on the following known conditions : ； After obtaining, the t corresponding to the outlier moment can be substituted into the corresponding , to obtain the substitution point of the outlier.

6. An apparatus using the method for querying materials based on an Internet of Things card according to any one of claims 1-5, characterized in that, Includes: Activity level calculation module: used to obtain the activity level of the IoT card of the customer account within a period and perform analysis and calculation to form an ordered list of high-activity cards; Prediction module: used to dynamically predict the change trend of the number of times each target customer account calls the IoT card material query interface based on the triple exponential smoothing prediction algorithm, and predict the number of accesses to this interface; Loading module: used to load the materials of the most active cards managed under this customer account with the same number of accesses in advance into the cache according to the prediction result.

7. A computer device, characterized in that, The computer device includes a memory and a processor. A computer program is stored on the memory. When the processor executes the computer program, it implements the IoT card-based material query method according to any one of claims 1-5.

8. A storage medium, characterized in that, The storage medium stores a computer program. The computer program includes program instructions. When the program instructions are executed by the processor, they can implement the IoT card-based material query method according to any one of claims 1-5.

Images