Point table matching method and system of Internet of Things platform, electronic equipment and storage medium

Abstract

The invention provides a point table matching method and system for an Internet of Things platform, electronic equipment and a storage medium, and the method comprises the steps: carrying out the word meaning conversion of entries in a terminal equipment point table and a virtual equipment point table through a word meaning technology, obtaining the word meaning vectors of the terminal equipment point table and the virtual equipment point table, and carrying out the word meaning conversion of the entries in the terminal equipment point table and the virtual equipment point table through the similarity; matching the items with the highest similarity from different point tables; realizing matching between the terminal equipment point table and the virtual equipment point table; the low efficiency, the consumption of a large amount of manpower and material resources and errors easily caused by human factors caused by manual matching are avoided, the matching efficiency and accuracy are improved, the operation and maintenance cost is reduced, and the stability and reliability of the Internet of Things platform are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of Internet of Things, and more specifically, particularly relates to a point table matching method and system, electronic equipment, and storage medium of an Internet of Things platform. Background Art

[0002] With the rapid development of IoT technology, IoT systems are becoming increasingly large and complex, with new devices and new point tables constantly being added to the system. However, when the system encounters new devices or new point tables, how to complete point table matching has become an urgent problem to be solved.

[0003] Currently, the method commonly used in the industry relies on manual operations, including tedious point table retrieval, classification, and subsequent multi-person parallel binding process.

[0004] However, the manual matching process is not only inefficient and consumes a lot of manpower and material resources, but is also prone to errors due to human factors, affecting the stability and reliability of the IoT system. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a point list matching method and system, electronic device, and storage medium for an Internet of Things platform, which are used to match the terminal device point list and the virtual device point list through semantic technology, improve matching efficiency and accuracy, reduce operation and maintenance costs, and improve the stability and reliability of the Internet of Things platform.

[0006] The first aspect of the present application discloses a point table matching method of an Internet of Things platform, comprising:

[0007] Get the terminal device point list connected to the IoT platform;

[0008] Preprocessing the terminal device point table to determine the hierarchical structure and grouping information of the terminal device point table;

[0009] For the virtual device point table and the terminal device point table established by the Internet of Things platform, each entry is converted into a word meaning according to their respective hierarchical structures and grouping information to obtain a word meaning vector of each entry in the virtual device point table and a word meaning vector of each entry in the terminal device point table; wherein the hierarchical structure of the virtual device point table is related to the hierarchical structure of the terminal device point table; each level includes at least one entry; and entries at the same level are divided into at least one group;

[0010] According to each word sense vector in the virtual device point table and each word sense vector in the terminal device point table, the entries in the virtual device point table are matched with the entries in the terminal device point table with the highest similarity.

[0011] Optionally, matching the entries of the virtual device point table with the entries of the terminal device point table with the highest similarity according to the word sense vectors in the virtual device point table and the word sense vectors in the terminal device point table, comprises:

[0012] According to the word sense vectors of the entries in the first point table, according to the hierarchical structure and grouping information thereof, a search algorithm is used to determine in the second point table the word sense vector of the second point table that has the highest similarity to the current word sense vector of the first point table; the first point table is one of the terminal device point table and the virtual device point table, and the second point table is the other of the terminal device point table and the virtual device point table;

[0013] Match the corresponding entry of the current word sense vector of the first point table with the corresponding entry of the word sense vector of the second point table with the highest similarity.

[0014] Optionally, the step of determining, according to the word sense vectors of the entries in the first point table, the word sense vector of the second point table having the highest similarity to the current word sense vector of the first point table by using a search algorithm in the second point table according to the hierarchical structure and grouping information thereof, comprises:

[0015] Determine candidate entries of the second point table using a search algorithm according to the entries of the first point table; the candidate entries of the second point table are all entries in the second point table that are at the same level and in the same group as the current entry in the first point table;

[0016] The word sense vector of the entry in the first point table and the word sense vector of the candidate entry in the second point table are calculated similarly to obtain two word sense vectors with the highest similarity.

[0017] Optionally, after matching the entries of the virtual device point table with the entries of the terminal device point table with the highest similarity according to the word sense vectors in the virtual device point table and the word sense vectors in the terminal device point table, the method further includes:

[0018] Proofreading the matching result; the matching result is the corresponding relationship after matching the entries of the virtual device point table with the entries of the terminal device point table.

[0019] Optionally, if the matching relationship of at least one entry is modified during the process of checking the matching results, the entries whose matching relationship has not been modified are re-matched.

[0020] Optionally, after matching the entries of the virtual device point table with the entries of the terminal device point table with the highest similarity according to the word sense vectors in the virtual device point table and the word sense vectors in the terminal device point table, the method further includes:

[0021] Save the matching results.

[0022] Optionally, before performing semantic transformation on each entry in the virtual device point table and the terminal device point table established for the Internet of Things platform according to their respective hierarchical structures and grouping information to obtain the semantic vector of each entry in the virtual device point table and the semantic vector of each entry in the terminal device point table, the method further includes:

[0023] A virtual device and a point table thereof are established in the Internet of Things; the hierarchical structure and grouping information of the virtual device point table are related to the hierarchical structure and grouping information of the terminal virtual device point table.

[0024] The second aspect of the present application discloses a point table matching system for an Internet of Things platform, comprising:

[0025] The acquisition module is used to obtain the terminal device point list connected to the Internet of Things platform;

[0026] A preprocessing module, used to preprocess the terminal device point table to determine the hierarchical structure and grouping information of the terminal device point table;

[0027] A semantic transformation module is used to transform each entry of the virtual device point table and the terminal device point table established by the Internet of Things platform into a semantic transformation according to their respective hierarchical structures and grouping information, so as to obtain a semantic vector of each entry in the virtual device point table and a semantic vector of each entry in the terminal device point table; wherein the hierarchical structure of the virtual device point table is related to the hierarchical structure of the terminal device point table; each level includes at least one entry; and entries of the same level are divided into at least one group;

[0028] The matching module is used to match the entries of the virtual device point table with the entries of the terminal device point table with the highest similarity according to the word meaning vectors in the virtual device point table and the word meaning vectors in the terminal device point table.

[0029] The third aspect of the present application discloses an electronic device, comprising:

[0030] one or more processors;

[0031] a storage device having one or more programs stored thereon;

[0032] When one or more programs are executed by one or more processors, the one or more processors implement the point table matching method of the Internet of Things platform as described in any one of the first aspects of the present application.

[0033] A fourth aspect of the present application discloses a storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the point table matching method of the Internet of Things platform as described in any one of the first aspects of the present application is implemented.

[0034] It can be seen from the above technical scheme that the present invention provides a point table matching method for an Internet of Things platform, including: through the semantic technology, the entries in the terminal device point table and the virtual device point table are semantically converted to obtain the semantic vectors of the terminal device point table and the virtual device point table respectively, and using the similarity, the entries from different point tables with the highest similarity are matched; the matching of the terminal device point table and the virtual device point table is achieved; the inefficiency caused by manual matching is avoided, a large amount of manpower and material resources are consumed, and errors are easily caused by human factors, thereby improving the matching efficiency and accuracy, reducing the operation and maintenance costs, and improving the stability and reliability of the Internet of Things platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 It is a flow chart of a point table matching method of an Internet of Things platform provided by an embodiment of the present invention;

[0037] Figure 2 It is a schematic diagram of a point table matching system of an Internet of Things platform provided by an embodiment of the present invention;

[0038] Figure 3 It is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] In the present application, the term "comprise", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or equipment. In the absence of more restrictions, the elements defined by the sentence "comprise one ..." do not exclude the existence of other identical elements in the process, method, article or equipment including the elements. In addition, the terms "first", "second", "third", "fourth", etc. (if present) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable in appropriate circumstances, so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here, for example.

[0041] The data interaction between the terminal device and the platform relies on the point table, which defines all the data points that the terminal device can report or control. The existing technology uses manual point table matching methods, which are often time-consuming and error-prone, especially in large-scale IoT systems, where thousands of devices need to be quickly and accurately connected to the platform, which becomes an efficiency bottleneck. In the construction and implementation of traditional IoT systems, the point table matching between devices and gateways is inefficient.

[0042] Based on this, an embodiment of the present application provides a point table matching method for an Internet of Things platform, which is used to solve the problem that the manual matching process in the prior art is not only inefficient and consumes a lot of manpower and material resources, but is also prone to errors due to human factors, affecting the stability and reliability of the Internet of Things system.

[0043] See also Figure 1 ,The point table matching method of the Internet of Things platform includes:

[0044] S101. Obtain a list of terminal devices connected to the Internet of Things platform.

[0045] The terminal device point table is directly obtained. For example, the device manufacturer usually provides a point table document of the device, including information such as an identifier, data type, and unit of each data point.

[0046] Therefore, when the terminal device is connected to the Internet of Things platform, the terminal device point list can be directly obtained.

[0047] The terminal device point table may include: address, item name, data meaning, unit; of course, it may also include other information, which will not be repeated here one by one, depending on the actual situation, and all are within the scope of protection of this application.

[0048] The address is a unique identifier for each data point in the terminal device. In a communication protocol, such as Modbus, each data point has a specific address, and the control system uses this address to read or write data.

[0049] The Entry Name is a descriptive name for the data point that provides an easily understandable reference for the operator or programmer. For example, a temperature sensor data point might be named "Temperature_Sensor_1".

[0050] Data meaning describes the physical quantity or logical state that a data point represents. For example, a data point may represent temperature, pressure, flow, switch state, etc. Understanding the meaning of data is critical to correctly interpreting and using the data.

[0051] Units specifies the unit of measurement of the data point, such as Celsius (℃), Pascals (Pa), liters per second (L / s), etc.

[0052] S102: Preprocess the terminal device point table to determine the hierarchical structure and grouping information of the terminal device point table.

[0053] There are many ways of preprocessing, such as missing value processing, outlier detection and processing, data standardization / normalization and data cleaning, etc. Of course, it can also include other processing methods, such as feature processing data type conversion, etc., which will not be listed here one by one. It depends on the actual situation and is within the scope of protection of this application.

[0054] The terminal device point table may include multiple levels, each level including at least one group.

[0055] The hierarchical structure can refer to the address level of the terminal equipment in the communication; the grouping information refers to different business groups under the same address level. For example, for fixed telephone numbers, there is no need to add +86 in China and 0371 in the city. This is the communication address level; in addition, there are emergency numbers such as 110, 120 and personal numbers in different business groups; that is, emergency numbers and personal numbers can be divided into different groups, and emergency numbers and personal numbers are at the same level.

[0056] That is to say, in the IoT architecture, hierarchical grouping is an important device organization and management strategy, which plays an important role at both the physical and logical levels. From a physical perspective, due to the limited connection capabilities of communication terminals such as edge gateways, hierarchical grouping becomes an effective means to expand the scale of equipment. At the logical level, taking the central air-conditioning system as an example, we can see the embodiment of hierarchical grouping in the device control logic: the shutdown of the outdoor unit will synchronously affect all indoor units, while the shutdown of a single indoor unit will not affect the operation of other indoor units. This hierarchical control logic ensures the flexibility and independence of the system.

[0057] In addition, the application of logical grouping is also reflected in the control of air conditioning systems in different areas. For example, the air conditioning in the office area and the computer room can operate independently without interfering with each other. It is worth noting that the logical hierarchical grouping often matches the physical structure. This matching relationship simplifies the management and optimization of the IoT system.

[0058] S103, for the virtual device point table and the terminal device point table established by the Internet of Things platform, each entry is converted into a word meaning according to their respective hierarchical structures and grouping information to obtain a word meaning vector for each entry in the virtual device point table and a word meaning vector for each entry in the terminal device point table.

[0059] The hierarchical structure of the virtual device point table is related to the hierarchical structure of the terminal device point table; each level includes at least one entry; and entries at the same level are divided into at least one group.

[0060] The virtual device point table is automatically generated when the virtual device is established, and the virtual device point table does not need to be preprocessed.

[0061] The purpose of point table matching is to match the terminal device point table with the virtual device point table. The virtual device point table is based on experience accumulation. All device information that users are concerned about is similar, and the data that IoT terminals can upload is limited by sensor technology. Generally speaking, the terminal device point table will provide slightly more data than the virtual device needs.

[0062] After identifying the hierarchical structure and grouping information of the terminal device point table, the hierarchical structure and grouping information of the virtual device point table can be obtained; then the corresponding entries can be semantically converted according to the hierarchical structure and grouping information. Specifically, the semantic conversion can be performed on each entry in the same level and group according to the hierarchical structure and grouping information. After completing the conversion of the level and group, the entries of other levels or groups can be converted. Of course, it is not ruled out that the entries of each level and group are converted together without being divided.

[0063] The semantic transformation is to convert text data into word sense vectors that can capture its intrinsic semantic information.

[0064] Specifically, the open source model "bge-m3" can be used to achieve semantic conversion. Of course, other models can also be used, such as M3E series models, OpenAI Text Embedding series models, Text2vec series models, etc. Take the open source model "bge-m3" as an example: the usage method is to clone its source code library and use pip to install the FlagEmbedding content provided by the source code. After installation and introduction, first obtain the model, such as the code: Model = BGEM3FlagModel ('BAAI / bge-m3', use_fp16 = True); then use the model to encode the meaning of the virtual device and terminal device point table entry names; such as the code: Embecddings_virtual device = Model.encode (virtual device point table entry name) ['dense_vecs']; and, Embecddings_terminal device = Model.encode (terminal device point table entry name) ['dense_vecs'].

[0065] The built-in string "BAAI / bge-m3" is used to explicitly specify the required model, ensuring the consistency and accuracy of the model call. The Model.encode function plays a vital role in our search and matching process. In the first search and match, we encoded all device names one by one and used the Model.encode function to convert them into precise word meaning vector values. This step not only provides a numerical representation for the device name, but also lays the foundation for subsequent semantic analysis and matching.

[0066] Then, in the second search and match, we repeated this process for all the entry names in the selected point table, and used the Model.encode function again to generate the corresponding word sense vector values. These vector values ​​capture the deep semantic information of the entry, allowing us to perform more refined search and matching operations. In this way, we ensure that the semantic matching of device names and point table entry names is both accurate and efficient, providing strong support for data management and analysis of the Internet of Things platform. For the virtual device point table, word sense vectors can be generated for each entry, which can accurately express the data characteristics of the virtual device. Similarly, for the terminal device point table, corresponding word sense vectors are also generated to ensure that the data attributes of the terminal device can be accurately reflected. This application mainly describes the semantic conversion of entries.

[0067] It should be noted that semantic conversion is to send data into the conversion model and directly obtain the converted vector; the input data is the names of each item in the point table that has been grouped in the early stage, and the retrieved data is the converted vector of each item name.

[0068] Through this conversion process, two sets of word meaning vectors are obtained: one set represents the data of the virtual device point table, and the other set represents the data of the terminal device point table. These vectors provide a solid foundation for further data analysis, matching and decision-making.

[0069] In other words, we are committed to achieving a deep understanding and effective management of the virtual device point table and the terminal device data point table. The text data of each entry is converted into word meaning vectors. These vectors not only capture the deep semantics of the data, but also provide strong support for data integration, matching and intelligent analysis. Finally, two sets of accurate word meaning vectors are obtained, one set represents the data features of the virtual device, and the other set represents the data attributes of the terminal device. This lays a solid foundation for the intelligent decision-making and automated operation of the IoT platform. For example, the similarity between the entries in the virtual device point table and the entries in the terminal device point table is calculated through these two sets of data features, and then the two entries with the greatest similarity belonging to different point tables are matched.

[0070] Optionally, before executing step S103, the method further includes: establishing virtual devices and their point tables in the Internet of Things; the hierarchical structure of the virtual device point table and its grouping information are related to the hierarchical structure of the terminal virtual device point table and its grouping information.

[0071] Specifically, according to the on-site conditions, equipment types and quantities, corresponding types and quantities of virtual devices are established in the IoT platform. Virtual devices are provided by the IoT platform and include information such as global unique codes, equipment categories, equipment models, equipment common point table entries, and point table entry metadata.

[0072] According to the hierarchical structure and grouping information of the terminal device point table, the hierarchical structure and grouping of the virtual device point table in the Internet of Things platform can be adjusted, and the hierarchical structure relationship of the virtual gateway can also be adjusted.

[0073] Generally, the terminal device point table data has been divided according to the hierarchical structure and group information. Therefore, the virtual devices in the IoT platform are grouped according to this hierarchical structure and group information. Therefore, at the communication level and business group levels, the virtual devices and terminal devices should be naturally matched. For devices under the communication level and business group, the virtual device name may not completely correspond to the name of the terminal device. Therefore, the respective device names are first converted into word meaning vectors and then searched and matched to match them, that is, the word meaning vectors of the device names corresponding to each level and group are converted according to the level and group, and then the device names in different point tables are matched; after the device name is matched, for the entry corresponding to the device name in the point table, the entries of each group of virtual devices and terminal devices are also first converted into word meaning vectors and then searched and matched to match them.

[0074] According to the on-site situation, a corresponding number and type of virtual gateways are established in the IoT platform. Common IoT protocol communication gateways are pre-installed inside the IoT. The virtual gateway is responsible for converting different terminal devices into a unified communication method to interact with the platform virtual devices after accessing them with their respective communication protocols.

[0075] It should be noted that the point table of the terminal device is generally transmitted to the IoT platform through three steps, namely the device itself, the edge gateway and the virtual gateway; that is, it is sent from the virtual gateway to the IoT platform. In theory, point table matching can be performed at any node, but it is more convenient and maintainable to perform point table matching between the virtual gateway and the IoT platform.

[0076] S104. According to each word meaning vector in the virtual device point table and each word meaning vector in the terminal device point table, match the entry in the virtual device point table with the entry in the terminal device point table that has the highest similarity.

[0077] The above description has obtained the word sense vector groups of the two point tables, each of which represents the data features of an entry.

[0078] First, the data point tables generated by virtual devices and terminal devices are deeply analyzed and converted into word meaning vectors that can express rich semantic information. Then, the similarity of word meaning vectors belonging to different point tables is determined to identify the most semantically similar entries and match the two entries belonging to different point tables. This matching process not only ensures the accurate correspondence of data, but also improves the data processing capability and efficiency of the entire system.

[0079] Optionally, the similarity is the cosine distance between two word sense vectors; the highest similarity is when the cosine distance between the two word sense vectors is the smallest.

[0080] That is to say, the cosine distance can be determined for the word meaning vectors of two entries belonging to different point tables. For a certain entry in a point table, the entry in another point table with the smallest cosine distance can be determined, and the two entries can be matched. The purpose of matching is to find the communication protocol and communication address of the corresponding terminal device for each entry of the virtual device; the method is to match the entry name of the terminal device point table that is closest to the word meaning vector of the entry in the virtual device point table.

[0081] In this embodiment, the entries in the terminal device point table and the virtual device point table are converted into semantics through the semantic technology to obtain the semantic vectors of the terminal device point table and the virtual device point table respectively, and the entries from different point tables with the highest similarity are matched by using the similarity; the matching of the terminal device point table and the virtual device point table is achieved; the inefficiency caused by manual matching is avoided, a large amount of manpower and material resources are consumed, and errors are easily caused by human factors, thereby improving the matching efficiency and accuracy, reducing the operation and maintenance costs, and improving the stability and reliability of the Internet of Things platform.

[0082] It should be noted that the use of the "object model conversion script" existing locally or in the cloud to complete the rapid matching of the software and hardware point tables has the disadvantage that the automatic matching of the software and hardware point tables cannot be performed when encountering new devices or new point tables; the point table feature data is stored locally and in the cloud to quickly match the point table, but the disadvantage is that the point table may not be quickly matched when encountering new devices or new point tables.

[0083] In this embodiment, automatic matching is performed using a search algorithm after understanding the meaning of words, which greatly reduces the time for manual configuration and search. When encountering a new terminal device and a new terminal device point table, the terminal device point table and the virtual device point table can be quickly matched; even in the face of complex and changeable device types, a high matching accuracy rate can be maintained; in addition, the point table matching method provided in this application is used to bind the point tables, and its speed is estimated to be an order of magnitude faster than manual binding, reducing the need for manual intervention, avoiding matching failures due to human errors, reducing the deployment time of the Internet of Things system, and reducing operation and maintenance costs.

[0084] Optionally, according to each word sense vector in the virtual device point table and each word sense vector in the terminal device point table, matching the entry in the virtual device point table with the entry in the terminal device point table that has the highest similarity includes:

[0085] First, based on the word sense vectors of the entries in the first point table, according to the hierarchical structure and its grouping information, a search algorithm is used to determine in the second point table the word sense vector of the second point table that has the highest similarity to the current word sense vector of the first point table; the first point table is one of the terminal device point table and the virtual device point table, and the second point table is the other of the terminal device point table and the virtual device point table.

[0086] Secondly, the corresponding entry of the current word sense vector of the first point table is matched with the corresponding entry of the word sense vector of the second point table with the highest similarity.

[0087] Specifically, taking a certain entry as an example, it is named the first entry. According to the word sense vector of the first entry in the first point table, according to the hierarchical structure and grouping information, the target word sense vector with the highest similarity to the word sense vector of the first entry in the second point table is searched; the target word sense vector is the word sense vector of the second entry in the second point table, and the first entry in the first point table is matched with the second entry in the second point table; the same is true for other entries, which will not be described one by one here, and they are all within the scope of protection of this application.

[0088] The search algorithm may be a naive search algorithm; the naive search algorithm generally refers to a direct and simple approach to solving a problem without using complex optimization techniques. The following are several common naive search algorithms:

[0089] Linear search: In a sequence, each element is checked one by one until the target value is found or all elements are searched. Time complexity: O(n), where n is the length of the sequence.

[0090] Depth-first search: Starting from a vertex in the graph, search the branches of the graph as deeply as possible until you find the target or reach the end. Time complexity: O(V+E), where V is the number of vertices and E is the number of edges.

[0091] Breadth-first search: Starting from the starting point, traverse all vertices of the graph layer by layer until the target is found. Time complexity: O(V+E).

[0092] The advantages of a naive search algorithm are that it is simple to implement and easy to understand.

[0093] Optionally, according to the word sense vectors of the entries in the first point table, according to the hierarchical structure and grouping information thereof, a search algorithm is used to determine in the second point table the word sense vector of the second point table that has the highest similarity to the current word sense vector of the first point table, including:

[0094] First, according to the entries in the first point table, a search algorithm is used to determine candidate entries in the second point table; the candidate entries in the second point table are all entries in the second point table that are at the same level and in the same group as the current entry in the first point table.

[0095] Next, the word sense vectors of the entries in the first point table and the word sense vectors of the candidate entries in the second point table are similarly calculated to obtain the two word sense vectors with the highest similarity.

[0096] Specifically, taking a certain entry as an example, it is named as the first entry. According to the first entry in the first point table, according to the hierarchical structure and grouping information, the candidate entry in the second point table is searched. The candidate entry is in the same level and group as the first entry. It should be noted that since the hierarchical structure of the terminal device point table and the virtual device point table are the same and grouping is related, even if the first entry and the candidate entry come from different point tables, they still have the same level and grouping. Finally, the word meaning vector of the first entry is calculated for similarity with the word meaning vector of the candidate entry to obtain the two word meaning vectors with the highest similarity. It should be noted that the two word meaning vectors with the highest similarity come from different point tables, thereby achieving matching between the two point tables. The same is true for other entries, which will not be described one by one here, and they are all within the scope of protection of this application.

[0097] That is to say, since the time complexity of the search algorithm is high, the hierarchical grouping and device division method can be used before searching to reduce the search scope. For example, the established virtual device and its hierarchical grouping information are "OP1-lighting equipment-street lamp 086". The entries corresponding to the virtual device point table include but are not limited to 4 examples: "current current", "current voltage", "working time of the day", and "standby state". The entries corresponding to the terminal device point table include but are not limited to 6 examples: "current", "voltage", "working time of the day", "standby state", "fault indication", and "working time of the month". For all 10 entries involved, semantic conversion is performed, and each entry obtains a corresponding vector value. For the semantic vector values ​​of the 4 entries in the virtual device point table, the distance of the semantic vectors that have not been matched in the 6 entries in the terminal device point table is calculated in turn, and the entry of the nearest terminal device point table is selected to match the entry of the virtual device point table and recorded.

[0098] Optionally, after matching the entries of the virtual device point table with the entries of the terminal device point table with the highest similarity according to the word sense vectors in the virtual device point table and the word sense vectors in the terminal device point table, the method further includes:

[0099] Proofreading the matching result; the matching result is the corresponding relationship between the entries in the virtual device point table and the entries in the terminal device point table after matching.

[0100] Manual verification or automatic verification can be used, which is not specifically limited here and depends on the actual situation. All are within the scope of protection of this application.

[0101] The proofreading process may include: proofreading the matching result includes carefully reviewing and verifying the correspondence between the entries in the virtual device point table and the entries in the terminal device point table.

[0102] Proofreading the matching results helps ensure the accuracy of the matching results and avoid data analysis deviations or equipment management errors caused by incorrect matching; it can also ensure the consistency of data between different equipment point tables, laying a solid foundation for subsequent data integration and analysis.

[0103] The names of the items in the virtual device point table and the terminal device point table are reasonable and do not need to be manually checked in most cases. Manual checking may be clicking a button to confirm all items or confirming some of the items.

[0104] Proofreading does not require modification of all entries, only the wrong entries need to be corrected. Re-automatic matching will not change the manually matched data, and matching will be performed in the entries that have not been manually matched.

[0105] Optionally, if the matching relationship of at least one entry is modified during the process of checking the matching results, the entries whose matching relationship has not been modified are re-matched.

[0106] It should be noted that, in the process of checking the matching results, if the matching relationship of at least one entry is modified, re-matching is not performed, and the entries whose matching relationship has not been modified are re-matched.

[0107] In most cases, after the semantic transformation of the entries in the two point tables, the same or similar entries will be converted into similar vectors for correct matching. However, in very rare cases, the semantic transformation cannot be automatically matched correctly based on the converted vectors.

[0108] There are two situations where automatic matching cannot be performed correctly. One is that only one or two matches are inappropriate, and the rest of the matches are affected by the one or two incorrect matches. The other is that the matches are completely chaotic. By using automatic matching and manual matching alternately, the first situation where the match cannot be performed correctly can be quickly fixed. That is, after manually correcting one or two incorrectly matched items, the rest can be matched correctly. By using the alternating matching method, even if the second situation is encountered, all items in the point table can be manually proofread.

[0109] That is to say, this application first semanticizes two point tables, which are the standardized point table (virtual terminal point table) of the Internet of Things platform and the device point table (terminal device point table) from various manufacturers. Then, a simple search algorithm is used to calculate the similarity and automatically sort the items in the semanticized point table to achieve matching of the two point tables and proofread the matching results. Proofreading and automatic matching can be performed alternately, that is, if proofreading is performed after the first automatic matching, the unproofreaded or unmodified items will be re-matched until all items are proofread or no proofreading is required.

[0110] Optionally, after checking the matching results, it also includes:

[0111] Save the matching results.

[0112] Save the matching results, which can be used for subsequent proofreading or calling when needed.

[0113] That is, after the entries of the virtual device point table and the terminal device point table are accurately matched, the matching results are saved, which not only ensures the consistency and integrity of the data, but also provides a solid foundation for further analysis and application of the data.

[0114] Specifically, the action of saving the matching result may be triggered when the matching result is proofread and not modified, or when the proofread matching result is not adopted, which is not specifically limited here.

[0115] Another embodiment of the present application provides a point table matching system for an Internet of Things platform.

[0116] See also Figure 2 ,The point table matching system of the IoT platform includes:

[0117] The acquisition module 101 is used to obtain a point list of terminal devices connected to the Internet of Things platform.

[0118] The preprocessing module 102 is used to preprocess the terminal device point table to determine the hierarchical structure and grouping information of the terminal device point table.

[0119] The semantic module 103 is used to perform semantic conversion on each entry in the virtual device point table and the terminal device point table established by the Internet of Things platform according to their respective hierarchical structures and grouping information, and obtain the semantic vector of each entry in the virtual device point table and the semantic vector of each entry in the terminal device point table.

[0120] The hierarchical structure of the virtual device point table is related to the hierarchical structure of the terminal device point table; each level includes at least one entry; and entries at the same level are divided into at least one group.

[0121] The matching module 104 is used to match the entries in the virtual device point table with the entries in the terminal device point table with the highest similarity according to the word meaning vectors in the virtual device point table and the word meaning vectors in the terminal device point table.

[0122] For details of the specific working process and principle of each of the above modules, please refer to the point table matching method of the Internet of Things platform provided in the above embodiment, which will not be described one by one here. It depends on the actual situation and is within the protection scope of this application.

[0123] In this embodiment, the acquisition module 101 acquires the terminal device point table connected to the Internet of Things platform; the preprocessing module 102 preprocesses the terminal device point table to determine the hierarchical structure and grouping information of the terminal device point table; the semantic module 103 performs semantic conversion on the virtual device point table and the terminal device point table established by the Internet of Things platform according to their respective hierarchical structures and grouping information to obtain the semantic vector of each entry in the virtual device point table and the semantic vector of each entry in the terminal device point table; wherein the hierarchical structure of the virtual device point table is related to the hierarchical structure of the terminal device point table; each level includes at least one entry; the entries of the same level are divided into at least one group; the matching module 104 matches the entries of the virtual device point table with the entries of the terminal device point table with the entries with the highest similarity according to the semantic vectors in the virtual device point table and the semantic vectors in the terminal device point table; avoids the inefficiency caused by manual matching, consumes a lot of manpower and material resources, and is prone to errors due to human factors, improves matching efficiency and accuracy, reduces costs, and improves the stability and reliability of the Internet of Things platform.

[0124] Another embodiment of the present application provides a storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the point table matching method of the Internet of Things platform as described in any one of the above embodiments is implemented.

[0125] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0126] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0127] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0128] Another embodiment of the present invention provides an electronic device, such as Figure 3 As shown, including:

[0129] One or more processors 201.

[0130] The storage device 202 stores one or more programs.

[0131] When one or more programs are executed by one or more processors 201, the one or more processors 201 implement the point table matching method of the Internet of Things platform as described in any one of the above embodiments.

[0132] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart.

[0133] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

[0134] Although several specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Certain features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination.

[0135] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0136] The features recorded in the various embodiments in this specification can be replaced or combined with each other, and the same and similar parts between the various embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0137] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0138] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A point table matching method for an Internet of Things platform, characterized in that: include: Obtain a list of terminal devices connected to the IoT platform; Preprocessing the terminal device point table to determine the hierarchical structure and grouping information of the terminal device point table; For the virtual device point table and the terminal device point table established by the Internet of Things platform, each entry is converted into a word meaning according to their respective hierarchical structures and grouping information to obtain a word meaning vector of each entry in the virtual device point table and a word meaning vector of each entry in the terminal device point table; wherein the hierarchical structure of the virtual device point table is related to the hierarchical structure of the terminal device point table; each level includes at least one entry; and entries at the same level are divided into at least one group; According to each word sense vector in the virtual device point table and each word sense vector in the terminal device point table, the entries in the virtual device point table are matched with the entries in the terminal device point table with the highest similarity.

2. The point table matching method of the Internet of Things platform according to claim 1 is characterized in that: The matching of the entries of the virtual device point table with the entries of the terminal device point table with the highest similarity according to the word meaning vectors in the virtual device point table and the word meaning vectors in the terminal device point table includes: According to the word sense vectors of the entries in the first point table, according to the hierarchical structure and grouping information thereof, a search algorithm is used to determine in the second point table the word sense vector of the second point table that has the highest similarity to the current word sense vector of the first point table; the first point table is one of the terminal device point table and the virtual device point table, and the second point table is the other of the terminal device point table and the virtual device point table; Match the corresponding entry of the current word sense vector of the first point table with the corresponding entry of the word sense vector of the second point table with the highest similarity.

3. The point table matching method of the Internet of Things platform according to claim 2 is characterized in that: The method of determining, according to the word sense vectors of the entries in the first point table, a word sense vector of the second point table having the highest similarity to the current word sense vector of the first point table by using a search algorithm in the second point table according to the hierarchical structure and grouping information thereof, comprises: Determine candidate entries of the second point table using a search algorithm according to the entries of the first point table; the candidate entries of the second point table are all entries in the second point table that are at the same level and in the same group as the current entry in the first point table; The word sense vector of the entry in the first point table and the word sense vector of the candidate entry in the second point table are calculated similarly to obtain two word sense vectors with the highest similarity.

4. The point table matching method of the Internet of Things platform according to claim 1 is characterized in that: After matching the entries of the virtual device point table with the entries of the terminal device point table with the highest similarity according to the word meaning vectors in the virtual device point table and the word meaning vectors in the terminal device point table, the method further includes: Proofreading the matching result; the matching result is the corresponding relationship after matching the entries of the virtual device point table with the entries of the terminal device point table.

5. The point table matching method of the Internet of Things platform according to claim 4 is characterized in that: If the matching relationship of at least one item is modified during the process of checking the matching results, the items whose matching relationship has not been modified are re-matched.

6. The point table matching method of the Internet of Things platform according to claim 1, characterized in that: After matching the entries of the virtual device point table with the entries of the terminal device point table with the highest similarity according to the word meaning vectors in the virtual device point table and the word meaning vectors in the terminal device point table, the method further includes: Save the matching results.

7. The point table matching method of the Internet of Things platform according to claim 1, characterized in that: Before performing semantic transformation on each entry in the virtual device point table and the terminal device point table established for the Internet of Things platform according to their respective hierarchical structures and grouping information to obtain the semantic vector of each entry in the virtual device point table and the semantic vector of each entry in the terminal device point table, the method further includes: A virtual device and a point table thereof are established in the Internet of Things; the hierarchical structure and grouping information of the virtual device point table are related to the hierarchical structure and grouping information of the terminal virtual device point table.

8. A point table matching system for an Internet of Things platform, characterized in that: include: The acquisition module is used to obtain the terminal device point list connected to the Internet of Things platform; A preprocessing module, used to preprocess the terminal device point table to determine the hierarchical structure and grouping information of the terminal device point table; A semantic transformation module is used to transform each entry of the virtual device point table and the terminal device point table established by the Internet of Things platform into a semantic transformation according to their respective hierarchical structures and grouping information, so as to obtain a semantic vector of each entry in the virtual device point table and a semantic vector of each entry in the terminal device point table; wherein the hierarchical structure of the virtual device point table is related to the hierarchical structure of the terminal device point table; each level includes at least one entry; and entries of the same level are divided into at least one group; The matching module is used to match the entries of the virtual device point table with the entries of the terminal device point table with the highest similarity according to the word meaning vectors in the virtual device point table and the word meaning vectors in the terminal device point table.

9. An electronic device, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon; When one or more programs are executed by one or more processors, the one or more processors implement the point table matching method of the Internet of Things platform as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: A computer program is stored thereon, wherein when the computer program is executed by a processor, the point table matching method of the Internet of Things platform as described in any one of claims 1 to 7 is implemented.

Images