Internet of Things fault early warning method, device and readable storage medium

Abstract

The present invention provides an early warning method, device and readable storage medium for Internet of Things faults, and relates to the technical field of Internet of Things, wherein the above-mentioned early warning method for Internet of Things faults includes: obtaining user data of each user in the Internet of Things; determining the user portrait corresponding to each user based on the user data, wherein the user portrait includes multiple tag types and weight values ​​of the multiple tag types; and performing fault early warning for each user in the Internet of Things according to the user portrait corresponding to each user. Since the present application can detect abnormal situations in the Internet of Things user data in advance based on the user portrait in the model, and perform early warning analysis on the abnormal situations, and push the early warning situation to the Internet of Things management personnel, the effect of early fault warning and timely follow-up processing can be achieved, and at the same time, the complaint rate of Internet of Things users can be effectively reduced, and customer satisfaction can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to an Internet of Things fault early warning method, device and readable storage medium. Background Art

[0002] With the development of IoT technology, IoT has been widely used in all walks of life, and the number of IoT customers has also increased. When using IoT cards, IoT customers often encounter various problems such as IoT card failure, terminal failure, base station failure, etc., which lead to the inability to use them normally, which easily leads to customer complaints. Since there is no corresponding early warning mechanism for IoT failures, they are not discovered and solved until they occur, resulting in a high user complaint rate and low customer satisfaction. Summary of the invention

[0003] The embodiments of the present invention provide an early warning method and device for Internet of Things faults, so as to solve the problem that there is no corresponding early warning mechanism for existing Internet of Things faults, and the faults are not discovered and solved until they occur, thus resulting in a high user complaint rate and low customer satisfaction.

[0004] In order to solve the above-mentioned technical problems, the present invention is achieved as follows:

[0005] The embodiment of the present invention provides an early warning method for Internet of Things failures, including:

[0006] Obtain user data of each user in the Internet of Things;

[0007] Based on the user data, determining a user portrait corresponding to each user, wherein the user portrait includes multiple tag types and weight values ​​of the multiple tag types;

[0008] According to the user portrait corresponding to each user, a fault warning is provided to each user in the Internet of Things.

[0009] The embodiment of the present invention further provides an early warning device for Internet of Things failures, including:

[0010] An acquisition module, used to acquire user data of each user in the Internet of Things;

[0011] A determination module, configured to determine a user portrait corresponding to each user based on the user data, wherein the user portrait includes a plurality of tag types and weight values ​​of the plurality of tag types;

[0012] The early warning module is used to provide fault early warning to each user in the Internet of Things according to the user portrait corresponding to each user.

[0013] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned Internet of Things failure early warning method are implemented.

[0014] In an embodiment of the present invention, the user data of each user in the Internet of Things is obtained; based on the user data, the user portrait corresponding to each user is determined, wherein the user portrait includes multiple tag types and weight values ​​of the multiple tag types; and according to the user portrait corresponding to each user, a fault warning is performed for each user in the Internet of Things. Since the present application can detect abnormal situations in the user data of the Internet of Things in advance based on the user portrait in the model, and perform early warning analysis on the abnormal situations, and push the early warning situation to the Internet of Things management personnel, the effect of early fault warning and timely follow-up processing can be achieved, and at the same time, the complaint rate of Internet of Things users can be effectively reduced, and customer satisfaction can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 One of the flow charts of the early warning method for Internet of Things failure provided by an embodiment of the present invention;

[0016] Figure 2 A schematic diagram of the effect of a user portrait provided by an embodiment of the present invention;

[0017] Figure 3 A second flowchart of the early warning method for Internet of Things failure provided by an embodiment of the present invention;

[0018] Figure 4 Flow chart 3 of the early warning method for Internet of Things failure provided by an embodiment of the present invention;

[0019] Figure 5 A schematic diagram of the structure of an early warning device for Internet of Things failures provided by an embodiment of the present invention;

[0020] Figure 6 A schematic diagram of the structure of a determination module provided in an embodiment of the present invention;

[0021] Figure 7 A schematic diagram of the structure of an early warning module provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail in conjunction with the accompanying drawings and specific embodiments. In the following description, specific details such as specific configurations and components are provided only to help fully understand the embodiments of the present invention. Therefore, it should be clear to those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. In addition, for clarity and brevity, the description of known functions and structures is omitted.

[0023] like Figure 1 As shown, Figure 1 One of the flowcharts of the early warning method for Internet of Things failure provided by the embodiment of the present invention includes:

[0024] Step S100, obtaining user data of each user in the Internet of Things.

[0025] The above user data includes but is not limited to the name of the enterprise to which the IoT card belongs, the Mobile Subscriber International ISDN / PSTN number (MSISDN), the Integrated Circuit Card Identity (ICCID), the International Mobile Subscriber Identification Number (IMSI), the cumulative Internet usage this month, the cumulative SMS usage this month, the package type, the power on / off status, the online / offline status, the power on status of the terminal, the area information, the base station information, etc., which are not specifically limited here. The method of obtaining user data can be directly obtained from various IoT platforms (such as BOSS system, etc.), various IoT service gateways, network elements, or obtained from a database established based on the IoT, which are not specifically limited here.

[0026] Step S200: determining a user portrait corresponding to each user based on the user data, wherein the user portrait includes a plurality of tag types and weight values ​​of the plurality of tag types.

[0027] Since the user data of each user in the Internet of Things contains multiple tag types, the user data of the user can be divided according to the different tag types, and then the weight value corresponding to the tag type can be calculated based on the data in each tag type after division. For other users in the Internet of Things, the above method can be used to obtain the tag type and the weight value corresponding to each tag type. The tag types in this application include but are not limited to user tag types, business tag types, group tag types, base station tag types, and regional tag types. Assuming that in this embodiment, user tags, base station tags, and regional tags are used as tag types, the schematic diagram of the user portrait effect generated based on user tags, base station tags, and regional tags is as follows: Figure 2 As shown. Figure 2 In the data, each user tag contains attribute data such as the online status of the IoT card corresponding to the user, the offline status of the terminal, etc., each base station tag contains the business interaction data of all users in each base station, and each area tag contains the business interaction data of all base stations in each area.

[0028] The above-mentioned user tag types may include data such as the online status of the IoT card, the power-on status of the terminal corresponding to the IoT card, etc.; the above-mentioned business tag types may include IoT business interaction information, such as interaction duration, cumulative Internet usage, cumulative SMS usage, etc.; the above-mentioned group tag types may include the name of the customer group, the IoT card activation batch in the customer group, the IoT business interaction information of the same batch, the IoT card packages of each batch of activation, etc.; the above-mentioned base station tag type includes information about the base station to which the IoT card belongs, such as the working status of the base station, the interaction information of each IoT card within the base station range, etc.; the above-mentioned area tag type includes location information of the area to which the IoT card belongs, the working conditions of all base stations within different areas, etc.

[0029] Since the data corresponding to the tag types of different users are different, the weight values ​​calculated from the data corresponding to the tag types of each user are also different. They are used as the features of the user portraits of each user to obtain the user portraits of each user. The user portrait here is a collection of the tag types of a certain user and the weight values ​​corresponding to all tag types. For example, for example, the user data of user A is analyzed and the weight value corresponding to the user tag type of user A is 1, the weight value corresponding to the business tag type is 0.5, the weight value corresponding to the group tag type is 0.2, the weight value corresponding to the base station tag type is 0.8, and the weight value corresponding to the regional tag type is 0.6. For user B, the weight value corresponding to the user tag type of user B is 0, the weight value corresponding to the business tag type is 0.5, the weight value corresponding to the group tag type is 0.6, the weight value corresponding to the base station tag type is 0.2, and the weight value corresponding to the regional tag type is 0.7. Then the user portraits of user A and user B are obtained.

[0030] Step S300: providing fault warning to each user in the Internet of Things according to the user portrait corresponding to each user.

[0031] According to the weight values ​​corresponding to each label type in the user portrait, based on the algorithm of the pre-set fault weight value, the fault weight value of each user is determined, and the current risk level of fault of each user is predicted according to the fault weight value. When the risk level reaches a certain threshold, the user is given a fault warning.

[0032] The above-mentioned fault warning method can be to push the abnormal user directly to the Internet of Things management personnel, or to push the user portrait information of the abnormal user to the Internet of Things management personnel, so that the Internet of Things management personnel can check the abnormal data of the abnormal user and determine the cause of the fault.

[0033] In an embodiment of the present invention, the user data of each user in the Internet of Things is obtained; based on the user data, the user portrait corresponding to each user is determined, wherein the user portrait includes multiple tag types and weight values ​​of the multiple tag types; and according to the user portrait corresponding to each user, a fault warning is performed for each user in the Internet of Things. Since the present application can predict abnormal situations in the user data of the Internet of Things in advance based on the user portrait in the model, and perform early warning analysis on the abnormal situations, the early warning situation is pushed to the management personnel of the Internet of Things, so as to achieve the effect of early fault warning and timely follow-up processing, and at the same time, it can also effectively reduce the complaint rate of users of the Internet of Things and improve customer satisfaction.

[0034] Alternatively, if Figure 3 As shown, Figure 3 The second flowchart of the early warning method for Internet of Things failure provided by the embodiment of the present invention is based on the above Figure 1 In the embodiment shown, the above step S200, based on the user data, determines the user portrait corresponding to each user, including:

[0035] Step S210, for each user in the Internet of Things, obtaining the target data of the user, where the target data of the user is data corresponding to a preset key field in the user data of the user;

[0036] Step S220, dividing the target data into a plurality of tag types according to the preset key field, wherein the tag type includes at least one of a user tag type, a service tag type, a group tag type, a base station tag type, and a regional tag type;

[0037] Step S230, obtaining a weight value corresponding to the tag type;

[0038] Step S240: determining a user portrait of the user based on the tag type and the weight value corresponding to the tag type.

[0039] When acquiring user data, the corresponding data content can be acquired based on the preset key fields, and the target data thus obtained is the data corresponding to the preset key fields. Since the mapping relationship between each key field and the tag type is preset in the model, the target data can be divided based on the preset key fields to obtain the data required for each tag category.

[0040] In this embodiment, the tag type includes at least one of the user tag type, service tag type, group tag type, base station tag type and area tag type. The above-mentioned user tag type may include data such as the online status of the IoT card, the power-on status of the terminal corresponding to the IoT card, etc.; the above-mentioned service tag type may include IoT service interaction information, such as interaction duration, cumulative Internet usage, cumulative SMS usage, etc.; the above-mentioned group tag type may include data such as the name of the customer group, the IoT card activation batch in the customer group, the IoT service interaction information of the same batch, the IoT card packages of each batch of activation, etc.; the above-mentioned base station tag type includes information about the base station to which the IoT card belongs, such as the working status of the base station, the interaction information of each IoT card within the base station range, etc.; the above-mentioned area tag type includes location information of the area to which the IoT card belongs, working conditions of all base stations within different areas, etc.

[0041] When obtaining the weight value corresponding to the tag type, the weight value corresponding to the tag type can be determined according to the data in each tag type. Specifically, in this embodiment, the user tag type includes two parameters: the online state of the Internet of Things card (the online state corresponds to 1, and the offline state corresponds to 0) and the power-on state of the terminal corresponding to the Internet of Things card (the power-on state corresponds to 1, and the power-off state corresponds to 0), and the weight value corresponding to the user tag type is the product of the two parameters of the online state of the Internet of Things card and the power-on state of the terminal corresponding to the Internet of Things card. When the Internet of Things card of user A is in an offline state or a power-off state, the weight value corresponding to the user tag type of user A is 0. The weight value corresponding to the business tag type is whether there is business interaction within the preset time period of the Internet of Things card (interaction corresponds to 1, and no interaction corresponds to 0). The preset time period can be set according to the actual situation and is not specifically limited here. When user A has business interaction within the preset time period, the weight value corresponding to the business tag type of user A is 1; otherwise, the corresponding weight value is 0. The weight value corresponding to the group tag type is the ratio of the number of IoT cards with no business interaction in the same group to the total number of IoT cards in the same group. The same group here means the same batch of IoT cards opened in the same time period or the same batch of IoT cards divided based on business classification. If only 50% of the cards in the group to which user A belongs have business interaction, the group tag type of user A is 50%. The weight value corresponding to the base station tag type is the ratio of the number of IoT cards with business interaction under the same base station to the total number of IoT cards under the same base station. If only 50% of the cards in the base station to which user A belongs have business interaction, the base station tag type of user A is 50%. The weight value corresponding to the regional tag type is the ratio of the number of IoT cards with business interaction in the same area to the total number of IoT cards in the same area. If only 50% of the cards in the area to which user A belongs have business interaction, the regional tag type of user A is 50%. In this embodiment, data corresponding to each tag category is obtained from user data, and the weight value of each tag category is calculated according to the data corresponding to each tag category, thereby obtaining a user portrait of each user, so that the IoT usage status of each user can be clearly and intuitively seen, which is conducive to subsequent fault warning through user portraits.

[0042] like Figure 4 As shown, Figure 4 The third flowchart of the early warning method for Internet of Things failure provided by the embodiment of the present invention is based on the above Figure 1 In the embodiment shown, the above step S300, according to the user portrait corresponding to each user, performs a fault warning for each user in the Internet of Things, including:

[0043] Step S310, determining an algorithm for calculating a fault weight value of the user according to a weight value corresponding to a user tag type of the user;

[0044] Step S320, determining the fault weight value of the user based on the algorithm;

[0045] Step S330: When the fault weight value is higher than a first preset threshold, a fault warning is issued to the user.

[0046] When calculating the fault weight value of each user, the same algorithm or different algorithms may be used. For example, for each user, the fault weight value is determined based on the weight value corresponding to any one or more of the user tag type, service tag type, group tag type, base station tag type and area tag type.

[0047] Since there are many types of IoT failures, the tag type data that is mainly referenced for each type of failure is often different. For example, for failure types caused by the user himself, such as failure to pay on time, terminal power failure and shutdown, poor contact between the IoT card and the card slot, etc., the user tag type data will be mainly referenced for judgment. For a certain base station or regional network failure, the base station tag type and regional tag type data will be mainly referenced for judgment. Therefore, in another embodiment, when calculating the fault weight value, different algorithms can be determined based on the different weight values ​​corresponding to the user tag type, so as to facilitate targeted analysis of different types of failures.

[0048] It should be noted that the above fault weight value represents the risk level of the fault predicted by the model. Assuming that 1 represents the presence of a fault and 0 represents the absence of a fault, the fault weight value is a value in the range of [0, 1]. The above first preset threshold value can be set according to actual conditions and is not specifically limited here. Preferably, the first preset threshold value is 0.5.

[0049] In this embodiment, an algorithm is determined according to the weight value corresponding to the user tag type of the user, and then the fault weight value is calculated according to different algorithms, so that there are multiple ways to calculate the fault weight value, which is conducive to targeted analysis of different fault types.

[0050] Optionally, the above step S310, determining an algorithm for calculating the fault weight value of the user according to the weight value corresponding to the user tag type of the user, includes:

[0051] Step S311, when the weight value corresponding to the user tag type of the user is greater than or equal to the second preset threshold, determining that the algorithm for calculating the fault weight value of the user is a first algorithm, wherein the first algorithm is positively correlated with at least one of the weight value corresponding to the user tag type, the weight value corresponding to the service tag type, the weight value corresponding to the group tag type, the weight value corresponding to the base station tag type, and the weight value corresponding to the area tag type;

[0052] Step S312, when the weight value corresponding to the user tag type of the user is less than a second preset threshold, determine that the algorithm for calculating the fault weight value of the user is a second algorithm, wherein the second algorithm is positively correlated with at least one of the weight value corresponding to the service tag type, the weight value corresponding to the group tag type, the weight value corresponding to the base station tag type, and the weight value corresponding to the area tag type.

[0053] In this embodiment, the user tag type includes two parameters: the online state of the Internet of Things card (the online state corresponds to 1, and the offline state corresponds to 0) and the power-on state of the terminal corresponding to the Internet of Things card (the power-on state corresponds to 1, and the power-off state corresponds to 0), and the weight value corresponding to the user tag type is the product of the two parameters: the online state of the Internet of Things card and the power-on state of the terminal corresponding to the Internet of Things card. When the Internet of Things card of user A is in an offline state or the terminal is in a power-off state, the weight value corresponding to the user tag type of user A is 0; when the Internet of Things card of user A is in an online state and the terminal is in a power-on state, the weight value corresponding to the user tag type of user A is 1.

[0054] When the weight value corresponding to the user tag type of the user is greater than or equal to the second preset threshold, the algorithm for calculating the fault weight value of the user is determined to be the first algorithm; when the weight value corresponding to the user tag type of the user is less than the second preset threshold, the algorithm for calculating the fault weight value of the user is determined to be the second algorithm. The above-mentioned second preset threshold can be any value within the range of 0 to 1, such as 0.2, 0.3, 0.4, etc., and can be specifically set according to actual conditions during actual implementation, and this embodiment does not make specific limitations. Preferably, the above-mentioned second preset threshold is 1, that is, when the second preset threshold is 1, the first algorithm is used to calculate the fault weight value, and when the second preset threshold is 0, the second algorithm is used to calculate the fault weight value.

[0055] It should be noted that the first algorithm here may be positively correlated with any one or more of the weight values ​​corresponding to the above-mentioned service label type, the weight values ​​corresponding to the group label type, the weight values ​​corresponding to the base station label type, and the weight values ​​corresponding to the regional label type. The second algorithm here may be positively correlated with any one or more of the weight values ​​corresponding to the above-mentioned service label type, the weight values ​​corresponding to the group label type, the weight values ​​corresponding to the base station label type, and the weight values ​​corresponding to the regional label type, and this application does not make specific limitations.

[0056] In this embodiment, two different fault weight value algorithms are determined according to the size of the weight value corresponding to the user tag type, so that in the case of a fault caused by the user himself, other fault types can be further determined, avoiding the situation where the IoT card is offline or the terminal is shut down and the fault of other operators' network terminals can be further determined.

[0057] Optionally, the first algorithm is the product of a weight value corresponding to the user tag type, a weight value corresponding to the service tag type, a weight value corresponding to the group tag type, a weight value corresponding to the base station tag type, and a weight value corresponding to the area tag type;

[0058] The second algorithm is the product of the weight value corresponding to the service label type, the weight value corresponding to the group label type, the weight value corresponding to the base station label type, and the weight value corresponding to the area label type.

[0059] For example, assuming that the weight value corresponding to the user tag type of user A is 1, the weight value corresponding to the service tag type is 0.5, the weight value corresponding to the group tag type is 0.2, the weight value corresponding to the base station tag type is 0.8, and the weight value corresponding to the regional tag type is 0.6. Since the weight value corresponding to the user tag type of user A is greater than or equal to the second preset threshold, the fault weight value of user A = the weight value corresponding to the user tag type * the weight value corresponding to the service tag type * the weight value corresponding to the group tag type * the weight value corresponding to the base station tag type * the weight value corresponding to the regional tag type

[0060] =1*0.5*0.2*0.8*0.6=0.048. Assume that the weight value corresponding to the user tag type of user B is 0, the weight value corresponding to the service tag type is 0.5, the weight value corresponding to the group tag type is 0.6, the weight value corresponding to the base station tag type is 0.2, and the weight value corresponding to the regional tag type is 0.7. Since the weight value corresponding to the user tag type of user B is less than the second preset threshold, the fault weight value of user B = the weight value corresponding to the service tag type * the weight value corresponding to the group tag type * the weight value corresponding to the base station tag type * the weight corresponding to the regional tag type = 0.5*0.6*0.2*0.7=0.042.

[0061] In this embodiment, the fault weight value is calculated by multiplying the weight values ​​corresponding to multiple label categories in the first algorithm and the second algorithm, so that the fault weight value is proportional to each corresponding label category in the algorithm, and the weight values ​​of multiple label categories can be comprehensively considered, thereby making the calculation result more accurate and closer to the actual situation.

[0062] Optionally, before the above step S320, based on the algorithm, obtaining the fault weight value of the user, the method further includes:

[0063] Step S340: When the weight value corresponding to the user tag type of the user is less than a second preset threshold, a fault self-check prompt is sent to the user.

[0064] Since it can be determined that the fault is caused by the user's own reasons when the weight value corresponding to the user tag type is confirmed to be less than the second preset threshold, a fault self-check prompt can be sent to the corresponding user at this time. The fault self-check prompt here can be any form of prompt information such as voice, text, and pictures. When prompting, the specific cause of the fault can be further determined according to the data in the user tag type. For example, when the online status of the Internet of Things card (online status corresponds to 1, offline status corresponds to 0) is 0, prompts such as "Please check whether the Internet of Things card is in arrears" and "Please check whether the Internet of Things card has poor contact" are sent; when the power-on status of the terminal corresponding to the Internet of Things card (power-on status corresponds to 1, power-off status corresponds to 0) is 0, prompts such as "Please check whether the terminal has sufficient power" are sent.

[0065] In this embodiment, when the weight value corresponding to the user tag type is less than the second preset threshold, a fault self-check prompt is sent to the corresponding user, prompting the user to detect the fault in himself, which can effectively avoid the user from filing a complaint without knowing the cause of the fault, thereby reducing the user complaint rate.

[0066] like Figure 5 As shown, Figure 5 The schematic diagram of the structure of the early warning device for Internet of Things failure provided by an embodiment of the present invention is as follows. The early warning device 40 for Internet of Things failure includes:

[0067] The acquisition module 410 is used to acquire user data of each user in the Internet of Things;

[0068] A determination module 420, configured to determine a user portrait corresponding to each user based on the user data, wherein the user portrait includes a plurality of tag types and weight values ​​of the plurality of tag types;

[0069] The early warning module 430 is used to issue a fault early warning to each user in the Internet of Things according to the user portrait corresponding to each user.

[0070] Alternatively, if Figure 6 As shown, the determination module 420 includes:

[0071] A first acquisition unit 421 is used to acquire target data of each user in the Internet of Things, where the target data of the user is data corresponding to a preset key field in the user data of the user;

[0072] A division unit 422, configured to divide the target data into a plurality of tag types according to the preset key field, wherein the tag type includes at least one of a user tag type, a service tag type, a group tag type, a base station tag type, and an area tag type;

[0073] A second acquisition unit 423 is used to acquire a weight value corresponding to the tag type;

[0074] The first determining unit 424 is used to determine the user portrait of the user based on the tag type and the weight value corresponding to the tag type.

[0075] Alternatively, if Figure 7 As shown, the early warning module 430 includes:

[0076] A second determining unit 431 is used to determine an algorithm for calculating a fault weight value of the user according to a weight value corresponding to a user tag type of the user;

[0077] A third determining unit 432 is used to determine the fault weight value of the user based on the algorithm;

[0078] The early warning unit 433 is used to issue a fault early warning to the user when the fault weight value is higher than a first preset threshold.

[0079] Optionally, the second determining unit 431 includes:

[0080] A first determining subunit is configured to determine that, when the weight value corresponding to the user tag type of the user is greater than or equal to a second preset threshold, the algorithm for calculating the fault weight value of the user is a first algorithm, wherein the first algorithm is positively correlated with at least one of the weight value corresponding to the user tag type, the weight value corresponding to the service tag type, the weight value corresponding to the group tag type, the weight value corresponding to the base station tag type, and the weight value corresponding to the area tag type;

[0081] A second determination subunit is used to determine that the algorithm for calculating the fault weight value of the user is a second algorithm when the weight value corresponding to the user tag type of the user is less than a second preset threshold, wherein the second algorithm is positively correlated with at least one of the weight value corresponding to the service tag type, the weight value corresponding to the group tag type, the weight value corresponding to the base station tag type, and the weight value corresponding to the area tag type.

[0082] Optionally, the first algorithm is the product of a weight value corresponding to the user tag type, a weight value corresponding to the service tag type, a weight value corresponding to the group tag type, a weight value corresponding to the base station tag type, and a weight value corresponding to the area tag type;

[0083] The second algorithm is the product of the weight value corresponding to the service label type, the weight value corresponding to the group label type, the weight value corresponding to the base station label type, and the weight value corresponding to the area label type.

[0084] Optionally, the early warning module 430 includes:

[0085] A prompting unit is used to send a fault self-checking prompt to the user when the weight value corresponding to the user tag type of the user is less than a second preset threshold.

[0086] The early warning device 40 for Internet of Things failure in the embodiment of the present invention is a device corresponding to the early warning method for Internet of Things failure described above. All implementation methods in the above method are applicable to the embodiment of the device and can achieve the same technical effect, which will not be described one by one here.

[0087] The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned early warning method for Internet of Things failure are implemented. All implementation methods in the above-mentioned method are applicable to the embodiment of the computer-readable storage medium, and can also achieve the same technical effect, and are not described one by one here.

[0088] The above are preferred embodiments of the present invention. It should be noted that ordinary persons skilled in the art can make several improvements and modifications without departing from the principles of the present invention. These improvements and modifications are also within the protection scope of the present invention.

Claims

1. A method for early warning of Internet of Things failures, characterized in that: include: Obtain user data of each user in the Internet of Things; Based on the user data, determining a user portrait corresponding to each user, wherein the user portrait includes multiple tag types and weight values ​​of the multiple tag types; Providing fault warning to each user in the Internet of Things according to the user portrait corresponding to each user; The determining, based on the user data, a user portrait corresponding to each user includes: For each user in the Internet of Things, obtaining target data of the user, where the target data of the user is data corresponding to a preset key field in the user data of the user; According to the preset key field, the target data is divided into a plurality of tag types, wherein the tag type includes at least one of a user tag type, a service tag type, a cluster tag type, a base station tag type, and an area tag type; Obtain the weight value corresponding to the tag type; Based on the tag type and the weight value corresponding to the tag type, a user profile of the user is determined.

2. The method according to claim 1, characterized in that The providing fault warning to each user in the Internet of Things according to the user portrait corresponding to each user includes: Determining an algorithm for calculating a fault weight value of the user according to a weight value corresponding to a user tag type of the user; Based on the algorithm, determining a fault weight value of the user; When the fault weight value is higher than a first preset threshold, a fault warning is issued to the user.

3. The method according to claim 2, characterized in that The step of determining an algorithm for calculating a fault weight value of the user according to a weight value corresponding to a user tag type of the user includes: When the weight value corresponding to the user tag type of the user is greater than or equal to a second preset threshold, determining that the algorithm for calculating the fault weight value of the user is a first algorithm, wherein the first algorithm is positively correlated with at least one of the weight value corresponding to the user tag type, the weight value corresponding to the service tag type, the weight value corresponding to the cluster tag type, the weight value corresponding to the base station tag type, and the weight value corresponding to the area tag type; When the weight value corresponding to the user tag type of the user is less than a second preset threshold, it is determined that the algorithm for calculating the fault weight value of the user is a second algorithm, wherein the second algorithm is positively correlated with at least one of the weight value corresponding to the service tag type, the weight value corresponding to the cluster tag type, the weight value corresponding to the base station tag type, and the weight value corresponding to the area tag type.

4. The method according to claim 3, characterized in that The first algorithm is the product of the weight value corresponding to the user tag type, the weight value corresponding to the service tag type, the weight value corresponding to the cluster tag type, the weight value corresponding to the base station tag type, and the weight value corresponding to the area tag type; The second algorithm is the product of the weight value corresponding to the service label type, the weight value corresponding to the cluster label type, the weight value corresponding to the base station label type, and the weight value corresponding to the area label type.

5. The method according to claim 2, characterized in that: Before obtaining the fault weight value of the user based on the algorithm, the method includes: When the weight value corresponding to the user tag type of the user is less than a second preset threshold, a fault self-check prompt is sent to the user.

6. An early warning device for Internet of Things failure, characterized in that: include: An acquisition module, used to acquire user data of each user in the Internet of Things; A determination module, configured to determine a user portrait corresponding to each user based on the user data, wherein the user portrait includes a plurality of tag types and weight values ​​of the plurality of tag types; An early warning module, used to provide fault early warning to each user in the Internet of Things according to the user portrait corresponding to each user; The determining module comprises: A first acquisition unit is used to acquire target data of each user in the Internet of Things, where the target data of the user is data corresponding to a preset key field in the user data of the user; A division unit, configured to divide the target data into a plurality of tag types according to the preset key field, wherein the tag type includes at least one of a user tag type, a service tag type, a group tag type, a base station tag type, and a regional tag type; A second acquisition unit, used to acquire a weight value corresponding to the tag type; The first determining unit is used to determine the user portrait of the user based on the tag type and the weight value corresponding to the tag type.

7. The device according to claim 6, characterized in that The early warning module comprises: A second determining unit, configured to determine an algorithm for calculating a fault weight value of the user according to a weight value corresponding to a user tag type of the user; A third determining unit, configured to determine a fault weight value of the user based on the algorithm; The early warning unit is used to issue a fault early warning to the user when the fault weight value is higher than a first preset threshold.

8. The device according to claim 7, characterized in that The second determining unit includes: A first determining subunit is configured to determine that, when the weight value corresponding to the user tag type of the user is greater than or equal to a second preset threshold, the algorithm for calculating the fault weight value of the user is a first algorithm, wherein the first algorithm is positively correlated with at least one of the weight value corresponding to the user tag type, the weight value corresponding to the service tag type, the weight value corresponding to the group tag type, the weight value corresponding to the base station tag type, and the weight value corresponding to the area tag type; A second determination subunit is used to determine that the algorithm for calculating the fault weight value of the user is a second algorithm when the weight value corresponding to the user tag type of the user is less than a second preset threshold, wherein the second algorithm is positively correlated with at least one of the weight value corresponding to the service tag type, the weight value corresponding to the group tag type, the weight value corresponding to the base station tag type, and the weight value corresponding to the area tag type.

9. The device according to claim 8, characterized in that The first algorithm is the product of the weight value corresponding to the user tag type, the weight value corresponding to the service tag type, the weight value corresponding to the group tag type, the weight value corresponding to the base station tag type, and the weight value corresponding to the area tag type; The second algorithm is the product of the weight value corresponding to the service label type, the weight value corresponding to the group label type, the weight value corresponding to the base station label type, and the weight value corresponding to the area label type.

10. The device according to claim 7, characterized in that The early warning module comprises: A prompting unit is used to send a fault self-checking prompt to the user when the weight value corresponding to the user tag type of the user is less than a second preset threshold.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the early warning method for Internet of Things failures as described in any one of claims 1 to 5 are implemented.

Images