WO2023191707A1

WO2023191707A1 - Method and apparatus for managing internet of things device, device, and storage medium

Info

Publication number: WO2023191707A1
Application number: PCT/SG2022/050252
Authority: WO
Inventors: Ming MU; Lang MING
Original assignee: Envision Digital International Pte. Ltd.; Shanghai Envision Digital Co., Ltd.
Priority date: 2022-03-31
Filing date: 2022-04-27
Publication date: 2023-10-05
Also published as: CN114866575A

Abstract

Disclosed are a method and apparatus for managing an Internet of things (IoT) device, a device, and a storage medium, which belong to the field of IoT technologies. The method includes: acquiring characteristic data of a target IoT device; acquiring n standard thing models from at least one standard thing model in a standard model library, wherein n is a positive integer; determining a target standard thing model from the n standard thing models based on the characteristic data; and managing the target IoT device based on the target standard thing model. In embodiments of the present disclosure, the thing model of the IoT device is automatically matched, which improves the efficiency of defining the thing model. In addition, in the embodiments of the present disclosure, since an IoT platform automatically matches the thing model of the IoT device, in the case of a larger number of accessed IoT devices, not only the labor cost is reduced, but also the accuracy of defining the thing model is improved.

Description

METHOD AND APPARATUS FOR MANAGING INTERNET OF THINGS DEVICE, DEVICE, AND STORAGE MEDIUM

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the field of Internet of things (loT) technologies, and m particular relate o a method and apparatus for managing an loT device, a device, and a storage medium.

BACKGROUND

[0002] A thing model, which may also be referred to as a thing specification language (TSL) model, is digital modeling for an entity in physical space.

[0003] Tire entity in the physical space may be various sensors, or a specific device (such as a wind turbine, a photovoltaic panel and an in-vehicle device), or may even be a building, a bridge, and the like. The entity may be abstracted on an loT platform by establishing a digital model of the entity in the physical space. In addition, based on the thing model, a communication channel between an entity and the cloud may be defined, and interaction data between the entity and the loT platform may also be parsed and encapsulated. In the related art, when the entity accesses the loT platform, the thing model of tire entity is defined manually.

[0004] However, when a large number of entities access to the loT platform, defining the thing models is a heavy and tedious work, which not only consumes considerable labor costs, but also goes wrong extremely.

SUMMARY

[0005] The embodiments of the present disclosure provide a method and apparatus for managing an Internet of things (loT) device, a device, and a storage medium, which may be capable of automatically matching a thing model of the loT device to improve the efficiency of defining the thing model. The technical solutions are as follows.

[0006] In an aspect, a method for managing an loT device is provided. The method includes:

[0007] acquiring characteristic data of a target loT device;

[0008] acquiring n standard thing models from at least one standard thing model in a standard model library, n being a positive integer;

[0009] determining a target standard thing model from the n standard thing models based on the characteristic data; and

[0010] managing the target loT device based on the target standard thing model. [0011] In another aspect, an apparatus for managing an loT device is provided. Tire apparatus includes:

[0012] a data acquiring module, configured to acquire characteristic data of a target loT device;

[0013] a thing model acquiring module, configured to acquire n standard thing models from at least one standard tiling model in a standard model library, n being a positive integer;

[0014] a tiling model determining module, configured to determine a target standard thing model from the n standard thing models based on the characteristic data; and

[0015] a device managing module, configured to manage the target loT device based on the target standard thing model.

[0016] In still another aspect, a computer device is provided. The computer device includes a processor and a memory. The memory stores a computer program that, when loaded and executed by the processor, causes the processor to implement the method for managing the loT device as described above.

[0017] In still another aspect, a computer-readable storage medium is provided. The computer- readable storage medium stores a computer program that, when executed by a processor, causes the processor to implement the method for managing an loT device as described above.

[0018] In still another aspect, a computer program product is provided. The computer program product, when executed by a processor, causes the processor to implement the method for managing an loT device as described above.

[0019] The technical solutions according to the embodiments of the present disclosure may bring the following beneficial effects.

[0020] The loT platform may determine the standard thing model matching with the loT device from the standard model library based on the characteristic data uploaded by the accessed loT device and manage the loT device based on the standard thing model, to automatically match the thing model of the loT device, thereby improving the efficiency of defining the thing model. In addition, in the embodiments of the present disclosure, since the loT platform automatically matches the thing model of the loT device, in the case of a large number of accessed loT devices, not only the labor cost is reduced, but also the accuracy of defining the thing model is improved.

BRIEF DESCRIPTION OF THE DRAWINGS

[0021] To describe the technical solutions in the embodiments of the present disclosure more clearly, the following briefly introduces accompanying drawings required for describing the embodiments. Apparently, the accompanying drawings in the following description show merely some embodiments of the present disclosure, and a person of ordinary skill in the art may derive other drawings from these accompanying drawings without creative efforts.

[0022] FIG. 1 is a schematic diagram of a system for managing an loT device according to an embodiment of the present disclosure;

[0023] FIG. 2 is a flowchart of a method for managing an loT device according to an embodiment of the present disclosure;

[0024] FIG. 3 is a schematic diagram of a method for managing an loT device according to an embodiment of the present disclosure;

[0025] FIG. 4 is a schematic diagram of matching a standard thing model according to an embodiment of the present disclosure;

[0026] FIG, 5 is a block diagram of an apparatus for managing an loT device according to an embodiment of the present disclosure;

[0027] FIG, 6 is a block diagram of an apparatus for managing an loT device according to another embodiment of the present disclosure; and

[0028] FIG. 7 is a structural block diagram of a computer device according to an embodiment of the present disclosure.

DETAILED DESCRIPTION

[0029] For clearer descriptions of the objectives, technical solutions, and advantages of the present disclosure, the embodiments of the present disclosure are described in detail hereinafter with reference to the accompanying drawings.

[0030] Firstly, descriptions are made to relevant terms involved in the embodiments of the present disclosure.

[0031] A thing model refers to digital modeling for an entity in a physical space. The thing model describes what the entity is, what the entity can do and which information the entity can provide from three dimensions, i.e., properties (including a static property and a dynamic property), services and events. By defining the three dimensions, a functional definition of the entity is completed, and the loT platform generates the thing model of the entity. Generally, the thing model is represented in a JSON format, and thus the thing model may also be referred to as a TSL model.

[0032] An loT device refers to an entity in tlie physical space, which may be various sensors, or a specific device (such as wind power equipment, a wind turbine, a photovoltaic device, a boxtype transformer, a combiner box, an optical communication device, and an in-vehicle device), or may even be a building, a bri dge, and the like in the embodiments of the present disclosure. [0033] An alert rule: refers to a comparison threshold and/or a comparison rule, and the like set for an indicator. When corresponding data is collected and/or acquired for the indicator (e.g., when data is collected and/or acquired for the indicator for once, for a set number of times, for a time length or the like), the alert rule is evaluated once, and the alert event is triggered in response to the alert rule passing the evaluation (that is, if the alert rule reaches the comparison threshold set in the alert rale and/or satisfies the comparison rule set in the alert rule, or the like).

[0034] A vector space model (VSM) refers to an algebraic model that represents a text file as an identifier (e.g., an index) vector. The VSM can express a semantic similarity with a spatial sim ilarity, and the VSM is applicable to information filtering, information retrieval, indexing and related sorting.

[0035] Jaccard index may also be referred to as a Jaccard similarity coefficient, and is intended to compare the similarity and difference among limited sample sets. The Jaccard index is equal to a ratio of an intersection of sample sets to a union of sample sets. Tire larger the Jaccard index is, the higher the sample similarity is.

[0036] Referring to FIG. 1, FIG.l is a schematic diagram of a system for managing an loT device according to an embodiment of the present disclosure. As shown in FIG. 1, the system for managing an loT device includes an loT device 10 and an loT platform 20.

[0037] The loT device 10 may access the loT platform 20, and the loT platform 20 may manage the loT device 10. The content, managed by the loT platform 20, of the loT device 10 is not limited in the embodiments of the present disclosure. In some embodiments, the content, managed by the loT platform 20, of the loT device 10 includes, but is not limited to, at least one of: storage of data uploaded by the loT device 10, parsing of data uploaded by the loT device 10, indexing of data uploaded by the loT device 10, and triggering of an alert event for the loT device 10.

[0038] It is to be understood that, the loT device 10 is a generalized device, which generally not only includes an entity device with communication functions, but also includes all entities in the physical space that may be managed by the loT platform 20. For the specific implementations of the loT device 10, reference may be made to the above embodiment, which is not repeated herein.

[0039] In embodiment of the present disclosure, one or more computer devices 22 are distributed on the loT platform 20 (FIG. 1 is shown by taking a plurality of computer devices 22 being distributed on the loT platform 20), and the computer devices 22 have data analysis and storage capabilities. Optionally, the computer device 22 may be implemented as a terminal such as a personal computer and a mobile phone, or may be implemented as a server. When the computer device 22 is implemented as a server, the computer device 22 may be implemented as one server, a server cluster composed of a plurality of servers, or a cloud computing center.

[0040] In some embodiments, after accessing the loT platform 20, the loT device 10 may upload data to the loT platform 20. The loT platform 20 may determine the thing model of the loT device 10 based on the data uploaded by the loT device 10 and manage the loT device 10 based on the thing model of the loT device 10. Optionally, the loT platform 20 may also determine an alert rule corresponding to the loT device 10 based on the thing model of the loT device 10, and trigger an alert event for the loT device 10 based on the alert rule.

[0041] Referring to FIG. 2, FIG. 2 is a flowchart of a method for managing an loT device according to an embodiment of the present disclosure. The method is applicable to the loT platform 20 described above, and may include the following steps (step 210 to step 240).

[0042] In step 210, characteristic data of a target ToT device is acquired.

[0043] The target loT device refers to an entity in the physical space that may be managed through the loT platform, and the specific implementation of the target loT device is not limited in the embodiments of the present disclosure. Optionally, the target loT device may be implemented as a sensor, a specific device (such as a wind turbine and a photovoltaic panel), or a building, a bridge, and the like.

[0044] In embodiments of the present disclosure, the characteristic data of the target loT device is configured to indicate characteristics of the target loT device, such as what the target loT device is, what the target loT device can do, and which information the target loT device can provide. Optionally, the characteristic data of the target loT device includes property data and state data. The property data is configured to indicate the static property of the target loT device. For example, in the case that the target loT device is implemented as a wind turbine, the property data includes a model, longitude, latitude, and the like of the of the wind turbine. The state data is configured to indicate the running state of the target loT device. For example, in the case that the target loT device is implemented as a wind turbine, the state data includes active power of a power generator of the wind turbine, cabin temperature, and the like.

[0045] In step 220, n standard thing models are acquired from at least one standard thing model in a standard model library, wherein n is a positive integer.

[0046] The standard model library' includes at least one standard thing model. The standard model library may be stored in the loT platform or other platforms, which is not limited m the embodiments of the present disclosure. The standard thing model refers to a standard thing model preset for the loT device. [0047] The classification of the standard thing models in the standard model library is not limited in the embodiments of the present disclosure. In some embodiments, the standard thing model in the standard model library corresponds to the device type and/or device model of the loT device. That is, one type and/or model of the loT devices correspond to one standard thing model. For example, the wind turbine corresponds to one standard thing model, and the wind turbines of different models may correspond to the same standard thing model, or may correspond to different standard thing models. For another example, the standard tiling models m the standard model library correspond to the field and the like of the loT device. That is, the loT devices in one field correspond to one or more standard thing models. For example, the wind field corresponds to one or more standard thing models. The loT devices of different types and/or models in the wind field may correspond to the same standard thing model, or may correspond to different standard thing models.

[0048] The loT platform may acquire n standard thing models from at least one standard thing model in the standard model library, where n is a positive integer. Optionally, the n standard thing models acquired by the loT platform may be all or part of die standard thing models in the standard model library.

[0049] By taking an example in which the standard model library includes standard thing models of loT devices in at least one field, in some embodiments, the above step 220 includes: determining a target field to which the target loT device belongs based on the characteristic data of the target loT device; and acquiring the standard thing models of loT devices in the target field from at least one standard thing model in the standard model library. The at least one field corresponding to the standard model library’ includes the target field, and the standard thing models of loT devices in the target field include n standard thing models.

[0050] For example, assuming that the standard model library includes standard thing models of loT devices in the wind field, light field and buildings and the like, and the target loT device is a wind turbine, based on this, the loT platform determines that the wind turbine belongs to the wind field based on characteristic data of the wind turbine. Therefore, the loT platform can acquire standard thing models, i.e., n standard thing models, of loT devices in the wind field from the standard model library.

[0051] hr step 230, a target standard thing model is determined from the n standard tiling models based on the characteristic data.

[0052] After acquiring the characteristic data of the target loT device and n standard thing models, the loT platform may determine the target standard thing model from the n standard thing models. The target standard thing model is a standard thing model corresponding to the target loT device. [0053] The way of determining the target standard thing model by the loT platform is not limited in the embodiments of the present disclosure. In some embodiments, the loT platform may randomly select a standard thing model from the n standard thing models as the target standard thing model. In some other embodiments, the n standard thing models correspond to different device types respectively, and tire loT platform determines the standard thing model corresponding to the device type of the target loT device from the n standard tiring models as the target standard thing model. In still some other embodiments, the loT platform selects a standard thing model from the n standard thing models as the standard thing model of the target loT device based on a recommendation algorithm. Optionally, the process of determining the target standard thing model from the n standard thing models may be performed by a recommendation engine on the loT platform. For other descriptions of determining the target standard thing model by the loT platform, reference is made to the following method embodiments, and details are not repeated here.

[0054] In step 240, the target ToT device is managed based on the target standard thing model.

[0055] After matching the target loT device with the corresponding target standard thing model, the loT platform may manage the target loT device based on the target standard thing model. For example, based on the target standard tiling model, the loT platform may define a communication channel between the target loT device and the loT platform, and parse and encapsulate interaction data between the target loT device and the loT platform.

[0056] In the embodiments of the present disclosure, the loT platform may further trigger an alert event for the target loT device. Based on this, in some embodiments, after the above step 230, a target alert rule associated with the target standard thing model is acquired; and the target loT device is managed based on the target alert rule. Optionally, managing the target loT device by the loT platform based on the target alert rule includes: evaluating, by the loT platform, the characteristic data uploaded by the target ToT device based on the target alert rule; and triggering an alert event for the target ToT device in the case that the characteristic data passes the evaluation.

[0057] For example, it’s assumed that the target loT device is implemented as a wind turbine, the characteristic data uploaded by the target loT device includes cabin temperature of the wind turbine, and the target alert rule includes a temperature threshold set for the cabin temperature of the wind turbine. Thus, in the case that the cabin temperature in the characteristic data uploaded by the wind turbine is greater than the temperature threshold set by the target alert rule, the loT platform triggers the alert event for the wind turbine to remind relevant personnel to handle the abnormality in time. [0058] The way of acquiring the target alert rule associated with the target standard thing model by the loT platform is not limited in the embodiments of the present disclosure. In some embodiments, after determining the target standard thing model, the loT platform sets the target alert rule in real time based on the target standard thing model and/or the target loT device. In some other embodiments, the loT platform presets tlie associated alert rules for the standard thing models in the standard model library respectively. That is, the loT platform stores at least one group of association relationships, the association relationship refers to an association relationship between the standard thing model and the alert rule, and the at least one group of association relationships includes an association relationship between the target standard thing model and the target alert rule. Based on this, the loT platform acquires at least one group of association relationships; and acquires the target alert rule associated with the target standard thing model from at least one alert rale based on the at least one grop of association relationships. [0059] For example, as shown in FIG. 3, the loT platform includes a standard model library' and an alert rale library. The standard model library includes standard thing models of loT devices in at least one field (such as tlie wind field, light field, and buildings), and the alert rule library includes at least one alert rule. There is an association relationship between the standard thing model in the standard model library and the alert rule in the alert rule library. Optionally, one standard thing model may correspond to one or more alert rules, which is not limited in the embodiments of the present disclosure. After accessing the loT platform, the target loT device may upload characteristic data to the loT platform. The recommendation engine on the loT platform may determine the target standard thing model based on the characteristic data uploaded by the target loT device (e.g., characteri stic data uploaded in a period of time) and the standard thing model in the standard model library'. The target standard thing model is the standard thing model corresponding to the target loT device. Then, the loT platform may manage the target ToT device based on the target standard thing model and the target alert rale associated with the target standard thing model.

[0060] In summary, according to the technical solutions provided in tlie embodiments of the present disclosure, the loT platform determines the standard tiling model matching with tlie loT device from the standard model library based on the characteristic data uploaded by the accessed loT device and manage the loT device based on tlie standard thing model, to automatically match the thing model of tlie loT device, which improves the efficiency of defining the thing model. In the embodiments of the present disclosure, since the loT platform automatically matches the thing model of the loT device, in the case of a large number of accessed loT devices, not only the labor cost is reduced, but the accuracy of defining the thing model is improved. In addition, in the embodiments of the present disclosure, the loT platform may also preset the associated alert rule for the standard thing model to rapidly acquire the associated alert rale after determining the standard thing model matching with the loT device, which improves the efficiency and accuracy of defining the alert rale.

[0061] The process of determining the target standard thing model is described below.

[0062] hr some embodiments, the above step 230 includes the following several steps (step 232 to step 238).

[0063] In step 232, a first characteristic vector is constructed based on the characteristic data.

[0064] The loT platform may construct the first characteristic vector based on the characteristic data uploaded by the loT device. Characteristics of one dimension in the characteristic data may correspond to characteristic components of one or more dimensions in the first characteristic vector. Optionally, the first characteristic vector is a vector space model, that is, the characteristic components in the first characteristic vector may be in a numeral format, a text format, or the like.

[0065] In step 234, for any one of the n standard thing models, a second characteristic vector is constructed based on the standard tiling model to acquire n second characteristic vectors.

[0066] For any one of the selected n standard thing models, the loT platform constructs the second characteristic vector based on the standard thing model, such that the loT platform may acquire n second characteristic vectors. The n second characteristic vectors are in one-to-one correspondence with the n standard thing models. Optionally, the second characteristic vector is also a vector space model, that is, characteristic components in the second characteristic vector may be in a numeral format, a text format, or the like.

[0067] In step 236, n vector similarities are acquired by determining a similarity between the first characteristic vector and each of the n second characteristic vectors.

[0068] After constructing the first characteristic vector and n second characteristic vectors respectively, the loT platform determines the similarity between the first characteristic vector and each of n second characteristic vectors to acquire n vector similarities. The n vector similarities are in one-to-one correspondence with the n second characteristic vectors, that is, the n vector similarities are in one-to-one correspondence with the n standard thing models.

[0069] By taking an example in which the first characteristic vector and the second characteristic vector both include m (m is a positive integer) characteristic components, optionally, the above step 236 includes: for an i^,h second characteristic vector of the n second characteristic vectors, acquiring m component similarities by determining the similarities between m characteristic components of the first characteristic vector and m characteristic components of the i^m second characteristic vector, where i is a positive integer less than or equal to n; and determining an i^tR vector similarity in the n vector similarities based on the m component similarities. Here, the m component similarities are in one-to-one correspondence with the m characteristic components. Optionally, the component similarity between the characteristic components may be acquired by a similarity calculation method, such as the Jaccard similarity coefficient calculation method.

[0070] Hie way of acquiring the vector similarity based on the component similarity is not limited in the embodiments of the present disclosure. By taking the i^,h vector similarity as an example, optionally, the loT platform acquires the i^th vector similarity by directly adding the above m component similarities together; or the loT platform acquires the i^tn vector similarity by performing weighted summation on the above m component similarities, that is, the loT platform acquires weighted values corresponding to m characteristic components respectively; and acquires the i^:|i vector similarity by performing weighted summation on the m component similarities based on the weighted values corresponding to the m characteristic components respectively. The weighted value corresponding to the characteristic component may be set manually based on business understanding, or may be acquired by training through machine learning, or the like, which is not limited in the embodiments of the present disclosure.

[0071] For example, it is assumed that the first characteristic vector constructed by the loT platform based on the characteristic data of the target loT device is Vi, the i^th second characteristic vector constructed by the loT platform based on the i^Ui standard thing model is V₂, and Vi and V₂ are

respectively.

[0072] Then, the similarity (the i^th similarity) between the first characteristic vector and the i® second characteristic vector may be:

[0073] Alternatively, the similarity (the i^tR similarity') between the first characteristic vector and the i® second characteristic vector may be:

[0074] Here,

refers to a cosine similarity between the first characteristic vector Vi and the i® second characteristic vector V₂; sim(p_t,q_t') refers to a cosine similarity between a t® characteristic component in the first characteristic vector V 1 and a t® characteristic component in the i® second characteristic vector V2: and W_t refers to a weighted value corresponding to the t® characteristic component. [0075] In step 238, the standard thing model corresponding to the vector similarity satisfying a target condition in the n vector similarities is determined as the target standard thing model.

[0076] After determining the n vector similarities, the loT platform may take the standard thing model corresponding to the vector similarity satisfying the target condition in the n vector similarities as the target standard thing model matching with the target loT device. The target condition includes but is not limited to any of the followings: a value of the vector similarity is the biggest, or the value of the vector similarity is greater than or equal to a similarity threshold.

[0077] For example, as shown in FIG. 4, the recommendation engine on tire loT platform constructs the first characteristic vector based on the characteristic data uploaded by the target loT device, and constructs n second characteristic vectors based on n standard thing models. Then, the recommendation engine on the loT platform acquires n vector similarities by calculating the vector similarity between the first characteristic vector and each of the n second characteristic vectors respectively. Finally, the recommendation engine on the loT platform determines the standard thing model corresponding to the vector similarity with the biggest value in the n vector similarities as the target standard thing model matching with the target loT device. [0078] In summary, according to the technical solutions provided in the embodiments of the present disclosure, the loT platform constructs the characteristic vectors based on the characteristic data uploaded by the loT device and the standard thing model, and matches the standard thing model for the loT device based on the vector similarity between the characteristic vectors, thereby providing a way of automatically matching the thing model of the loT device.

[0079] The following descriptions are apparatus embodiments of the present disclosure, w’hich may be applied to perform the method embodiments of the present disclosure. For details not provided in the apparatus embodiments of the present disclosure, reference may be made to the method embodiments of the present disclosure,

[0080] Referring to FIG. 5, FIG. 5 is a block diagram of an apparatus for managing an loT device according to an embodiment of the present disclosure. Hie apparatus 500 has the function of implementing the above method embodiments, and the function may be implemented byhardware or may be implemented by corresponding software executed by hardware. The apparatus 500 may be a computer device on tire loT platform described above, or may be configured in the computer device. The apparatus 500 may include a data acquiring module 510, a thing model acquiring module 520, a thing model determining module 530 and a device managing module 540.

[0081] The data acquiring module 510 is configured to acquire characteristic data of a target loT device. [0082] The thing model acquiring module 520 is configured to acquire n standard thing models from at least one standard thing model in a standard model library. Here, n is a positive integer.

[0083] The thing model determining module 530 is configured to determine a target standard thing model from the n standard thing models based on the characteristic data.

[0084] The device managing module 540 is configured to manage the target loT device based on the target standard thing model.

[0085] In some embodiments, the at least one standard tiling model includes standard thing models of loT devices in at least one field. The thing model acquiring module 520 is configured to: determine a target field to which the target loT device belongs based on the characteristic data, wherein the at least one field includes the target field; and acquire standard thing models of loT devices in the target field from the at least one standard thing model, wherein the standard thing models of loT devices in the target field include n standard thing models,

[0086] In some embodiments, as shown in FIG. 6, the thing model determining module 530 includes: a first vector constructing unit 532 configured to construct a first characteristic vector based on the characteristic data; a second vector constructing unit 534 configured to, for any one of the n standard thing models, construct a second characteristic vector based on the standard thing model to acquire n second characteristic vectors; a similarity determining unit 536 configured to acquire n vector similarities by determining the similarity between the first characteristic vector and each of tire n second characteristic vectors respectively; and a tiling model determining unit 538 configured to determine the standard thing model corresponding to the vector similarity satisfying a target condition in the n vector similarities as the target standard thing model.

[0087] In some embodiments, the first characteristic vector and the second characteristic vector both include m characteristic components, wherein m is a positive integer. As shown in FIG. 6, the similarity determining unit 536 is configured to: for an 1^th second characteristic vector in the n second characteristic vectors, determine similarities between m characteristic components of the first characteristic vector and m characteristic components of the i^th second characteristic vector to acquire m component similarities, wherein i is a positive integer less than or equal to n; and determine an i^th vector similarity in the n vector similarities based on the m component similarities.

[0088] hr some embodiments, as shown in FIG. 6, the similarity determining unit 536 is further configured to: acquire weighted values corresponding to the m characteristic components respectively; and acquire the i^th vector similarity by performing weighted summation on the m component similarities based on the weighted values corresponding to the m characteristic components respectively. [0089] In some embodiments, as shown in FIG. 6, the apparatus 500 further includes a rale acquiring module 550 configured to acquire a target alert rule associated with the target standard thing model; and the device numaging module 540 is further configured to manage the target loT device based on the target alert rule.

[0090] In some embodiments, as shown in FIG. 6, the rule acquiring module 550 is configured to: acquire at least one group of association relationships which includes an association relationship between tlie target standard thing model and the target alert rule; and acquire the target alert rule associated with the target standard thing model from at least one alert rule based on the at least one group of association relationships.

[0091] In summary, according to the technical solutions provided in the embodiments of the present disclosure, the loT platform may determine the standard thing model matching with the loT device from the standard model library based on the characteristic data uploaded by the accessed loT device and manage the loT device based on the standard thing model, to automatically match the thing model of the loT device, thereby improving the efficiency? of defining the thing model. In addition, in the embodiments of the present disclosure, since the loT platform automatically matches the thing model of the loT device, in the case of a large number of accessed loT devices, not only the labor cost is reduced, but also the accuracy of defining the thing model is improved.

[0092] It is to be noted that the apparatus according to the embodiments of the present disclosure, when implementing its functions, only takes division of all functional modules described above as an example. In practice, the above functions may- be allocated to be completed by different functional modules according to requirements. That is, the internal structure of the apparatus is divided into different functional modules to complete all or part of the functions described above. In addition, the above apparatus embodiments have the same concept as the method embodiments. For the specific implementation process of the above apparatus embodiments, reference may be made to the method embodiments, and details are not repeated herein.

[0093] Referring to FIG. 7, FIG. 7 is a structural block diagram of a computer device according to an embodiment of the present disclosure . The computer device is applicable to implement the method for managing the loT device according to the above embodiments.

[0094] The computer device 700 includes a processing unit 701 (such as a central processing unit (CPU), a graphics processing unit (GPU) and a field programmable gate array? (FPGA)), a system memory 704 including a random-access memory' (RAM) 702 and a read-only memory (ROM) 703, and a system bus 705 connecting the system memory 704 and the central processing unit 701. The computer device 700 further includes an input/output system (I/O system) 706 assisting in transmission of information among different components in the computer device, and a mass storage device 707 for storing an operating system 713, an application 714 and other program modules 715.

[0095] The I/O system 706 includes a display 708 for displaying information and an input device 709, such as a mouse and a keyboard, for inputting information by a user. The display 708 and the input device 709 are connected to the central processing unit 701 through an input/output controller 710 connected to the system bus 705. The I/O system 706 may further include the input/output controller 710 for receiving and processing input from a plurality of other devices, such as the keyboard, the mouse, or an electronic stylus. Similarly, the input/output controller 710 further provides output to a display screen, a printer or other types of output devices.

[0096] The mass storage device 707 is connected to the central processing unit 701 through a mass storage controller (not shown) connected to the system bus 705. The mass storage device 707 and the associated computer-readable medium provide non-volatile storage for the computer device 700. That is, the mass storage device 707 may include a computer-readable medium (not shown) such as a hard disk or a compact disc read-only memory (CD-ROM) drive.

[0097] Without loss of generality, the computer-readable medium may include a computer storage medium and a communication medium. The computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of in formation such as a computer-readable instruction, a data structure, a program module or other data. The computer storage medium includes an RAM, an ROM, an erasable programmable read-only memory' (EPROM), an electrically’ erasable programmable read-only' memory' (EEPROM), a flash memory' or other solid-state storage technologies, a CD- ROM, a digital video disc (DVD) or other optical storage, a cassete, a magnetic tape, a disk storage or other magnetic storage devices. Certainly, it is known by persons skilled in the art that the computer storage medium is not limited to above. The system memory 704 and the mass storage device 707 described above may be collectively referred to as the memory.

[0098] According to the embodiments of the present disclosure, the computer device 700 may also be connected to a remote computer through a network, such as the Internet. That is, the computer device 700 may be connected to the network 712 through a network interface unit 711 connected to the system bus 705, or may be connected to other types of networks or remote computer systems (not shown) through the network interface unit 711. [0099] Tire memory⁷ further includes a computer program. The computer program is stored in the memory⁷ and configured to be executed by one or more processors, to implement the above method for managing the loT device.

[00100] An embodiment of the present disclosure further provides a computer-readable storage medium storing a computer program thereon. The computer program, when executed by a processor, causes the processor to implement the above method for managing the loT device.

[00101] An example embodiment of the present disclosure further provides a computer program product. The computer program product, when executed by a processor, causes the processor to implement the above method for managing the loT device.

[00102] It is to be understood that the term "a plurality of mentioned herein refers to two or more. The term "and/or" describes an association relationship between associated objects and indicates that there may be three relationships. For example, A and/or B may be expressed as: A exists alone, A and B exist concurrently, and B exists alone. The character "/" generally indicates an "or" relationship between the associated objects.

[00103] Idle descriptions above are merely example embodiments of the present disclosure, and are not intended to limit the present disclosure. Within the spirit and principles of the present disclosure, any modifications, equivalent substitutions, improvements, and tlie like are within the protection scope of the present disclosure.

Claims

CLAIMS What is claimed is:

1. A method for managing an Internet of things (loT) device, comprising: acquiring characteristic data of a target loT device; acquiring n standard thing models from at least one standard thing model in a standard model library, wherein n is a positive integer; determining a target standard thing model from the n standard thing models based on the characteristic data; and managing the target loT device based on the target standard thing model.

2. The method according to claim 1, wherein the at least one standard thing model comprises standard thing models of loT devices in at least one field; and acquiring the n standard thing models from the at least one standard thing model in the standard model library comprises: determining a target field to which the target loT device belongs based on the characteristic data, the at least one field comprising the target field; and acquiring standard thing models of loT devices in the target field from the at least one standard thing model, the standard thing models of the loT devices in the target field comprising the n standard thing models.

3. The method according to claim 1, wherein determining the target standard thing model from the n standard thing models based on the characteristic data comprises: constructing a first characteristic vector based on the characteristic data; for any one of the n standard thing models, constructing a second characteristic vector based on the standard thing model to acquire n second characteristic vectors; acquiring n vector similarities by determining a similarity between the first characteristic vector and each of the n second characteristic vectors respectively; and determining the standard thing model corresponding to the vector similarity satisfying a target condition in the n vector similarities as the target standard thing model.

4. The method according to claim 3, wherein the first characteristic vector and the second characteristic vector both comprise m characteristic components, m being a positive integer; and acquiring the n vector similarities by determining the similarity between the first characteristic vector and each of the n second characteristic vectors respectively comprises: for an i^th second characteristic vector in the n second characteristic vectors, acquiring m component similarities by determining similarities between m characteristic components of the first characteristic vector and m characteristic components of the i^th second characteristic vector, i being a positive integer less than or equal to n; and determining an i^th vector similarity in the n vector similarities based on the m component similarities.

5. The method according to claim 4, wherein determining the i^th vector similarity in the n vector similarities based on the m component similarities comprises: acquiring weighted values corresponding to the m characteristic components respectively; and acquiring the i^th vector similarity by performing weighted summation on the m component similarities based on the weighted values corresponding to the m characteristic components respectively.

6. The method according to claim 1, wherein after determining the target standard thing model from the n standard thing models based on the characteristic data, the method further comprises: acquiring a target alert rule associated with the target standard thing model; and managing the target loT device based on the target alert rule.

7. The method according to claim 6, wherein acquiring the target alert rule associated with the target standard thing model comprises: acquiring at least one group of association relationships, the at least one group of association relationships comprising an association relationship between the target standard thing model and the target alert rule; and acquiring the target alert rule associated with the target standard thing model from at least one alert rule based on the at least one group of association relationships.

8. An apparatus for managing an Internet of things (loT) device, comprising: a data acquiring module, configured to acquire characteristic data of a target loT device; a thing model acquiring module, configured to acquire n standard thing models from at least one standard thing model in a standard model library, n being a positive integer; a thing model determining module, configured to determine a target standard thing model from the n standard thing models based on the characteristic data; and a device managing module, configured to manage the target loT device based on the target standard thing model.

9. A computer device, comprising a processor and a memory, wherein the memory stores a computer program that, when loaded and executed by the processor, causes the processor to implement the method for managing the loT device as defined in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to implement the method for managing the loT device as defined in any one of claims 1 to 7.