A method, device, computer equipment and storage medium for early warning of enterprise electricity consumption

Abstract

The embodiment of the present invention provides a method, device, computer equipment and medium for early warning of electricity consumption of enterprises, which includes: obtaining electricity consumption data of all users, performing similarity analysis on the electricity consumption data of all users, determining key enterprise users from all users, extracting electricity consumption data of key enterprise users and monitoring the electricity consumption data of key enterprise users, confirming whether the electricity consumption of key enterprise users is abnormal according to the monitoring results, and outputting corresponding early warning information. By performing similarity analysis on the electricity consumption data of all users and then determining key enterprise users, accurately and real-timely obtaining the electricity consumption data of key enterprise users for monitoring, and outputting early warning information in time when abnormal electricity consumption occurs, the electricity consumption analysis and early warning of key enterprise users are realized, so as to grasp the changes in their production status at any time.

Description

Technical Field

[0001] Embodiments of the present invention relate to the technical field of electricity, and in particular, to a method, device, computer equipment and storage medium for early warning of electricity consumption in an enterprise. Background Art

[0002] Recently, as the COVID-19 situation has gradually stabilized and improved, daily epidemic prevention and control and the resumption of work and production of enterprises have become the main tasks of current social production in order to minimize the impact on economic operations.

[0003] As most companies resume work and production, it is necessary to accurately monitor the resumption of work and production of enterprises in order to understand the production and operation status of enterprises. Since the operation of enterprises is inseparable from electricity, electricity usage is an important indicator for objectively and accurately evaluating the production status of enterprises. The existing enterprise electricity consumption analysis mainly relies on report statistical analysis, which lacks real-time performance and is difficult to accurately analyze and warn the production status of enterprises based on electricity consumption.

[0004] Therefore, the prior art still needs to be improved and developed. Summary of the invention

[0005] In view of the deficiencies of the above-mentioned background technology, the embodiments of the present invention propose a method, apparatus, computer equipment and storage medium for early warning of enterprise electricity consumption to solve the problem that it is difficult to accurately analyze and warn of enterprise electricity consumption in real time.

[0006] In a first aspect, an embodiment of the present invention provides an enterprise electricity consumption early warning method, comprising:

[0007] Obtain electricity consumption data of all users;

[0008] Performing similarity analysis on the electricity consumption data of all users, and determining key enterprise users from among all users;

[0009] Extracting the electricity consumption data of the key enterprise users and monitoring the electricity consumption data of the key enterprise users;

[0010] According to the monitoring results, it is confirmed whether the power consumption of the key enterprise users is abnormal, and the corresponding early warning information is output.

[0011] In a second aspect, an embodiment of the present invention further provides an enterprise electricity consumption early warning device, comprising:

[0012] An acquisition module is used to obtain the electricity consumption data of all users;

[0013] An analysis module, used to perform similarity analysis on the electricity consumption data of all users, and determine key enterprise users from all users;

[0014] An extraction module, used to extract the electricity consumption data of the key enterprise users and monitor the electricity consumption data of the key enterprise users;

[0015] The early warning module is used to confirm whether the power consumption of the key enterprise users is abnormal according to the monitoring results, and output corresponding early warning information.

[0016] In a third aspect, an embodiment of the present invention further provides a computer device, the computer device comprising:

[0017] one or more processors;

[0018] a memory for storing one or more programs,

[0019] When the one or more programs are executed by the one or more processors, the one or more processors implement the enterprise electricity consumption early warning method as described in the first aspect.

[0020] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the enterprise electricity consumption warning method as described in the first aspect is implemented.

[0021] In an embodiment of the present invention, when it is monitored that the real-time electricity consumption data of key enterprise users is less than the minimum value in the historical electricity consumption data, it means that the key enterprise users may have poor production conditions, production reduction, etc., and therefore it is judged as abnormal electricity consumption, and a first warning information is output to facilitate understanding of the production and operation conditions of the enterprise. In the early stage of the enterprise's operation difficulties, the first warning information is used to prompt the relevant departments to understand in time to ensure that the key enterprise users can adjust the production and operation conditions in time; and when the growth rate in the real-time electricity consumption data of key enterprise users is monitored to be greater than the preset growth rate threshold, this is a situation of sudden increase in electricity consumption. If the key enterprise users do not have new equipment or increase production capacity, potential dangerous factors such as line leakage or equipment failure and aging may occur, and therefore it is also judged as abnormal electricity consumption, and a second warning information is output to facilitate the power supply department to promptly check the status of the corresponding key enterprise users' electricity equipment to ensure the production safety of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A flowchart of an enterprise electricity consumption early warning method provided in Embodiment 1 of the present invention;

[0023] Figure 2 A schematic diagram of functional modules of an enterprise electricity consumption early warning device provided in Embodiment 2 of the present invention;

[0024] Figure 3 A schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0025] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0026] Embodiment 1

[0027] Figure 1 This is a flow chart of an enterprise electricity consumption early warning method provided in Embodiment 1 of the present invention. This embodiment can be applied to situations where it is difficult to accurately analyze and warn the enterprise electricity consumption in real time. The method can be executed by an enterprise electricity consumption early warning device, which can be implemented by software and / or hardware and can be configured in a computer device. Specifically, it includes the following steps:

[0028] S100: Obtain electricity consumption data of all users.

[0029] In this embodiment, the power supply department will collect electricity consumption data of all electricity users during daily operations and save it in a database. Therefore, when conducting enterprise electricity consumption warning, the electricity consumption data of all users stored in the database can be efficiently and conveniently called directly for subsequent analysis and processing. The specific electricity consumption data obtained includes the real-time electricity consumption data of all users, that is, the latest electricity consumption data is obtained according to the current timestamp (for example, electricity consumption data within 1 hour or 2 hours, etc.), and the historical electricity consumption data of all users within a preset time period, that is, the time period for obtaining historical electricity consumption data can be flexibly set, for example, obtaining historical electricity consumption data of all users within the past month, three months, or half a year, etc. The specific preset time period can be flexibly adjusted according to analysis needs to meet the analysis needs of different time periods, thereby improving the flexibility and adaptability of enterprise electricity consumption warning analysis.

[0030] S200: Perform similarity analysis on the electricity consumption data of all users, and identify key corporate users from among all users.

[0031] In this embodiment, after obtaining the electricity consumption data of all users, based on the production electricity consumption characteristics of key enterprise users, a similarity analysis is performed on the electricity consumption data of all users, and the corresponding key enterprise users are quickly and accurately screened from all users, so that the electricity consumption data of key enterprise users can be analyzed and monitored, providing accurate analysis objects for realizing real-time and accurate enterprise electricity consumption analysis and early warning.

[0032] In one embodiment, similarity analysis is performed on the electricity consumption data of all users to determine key enterprise users from all users, including:

[0033] Extract features from the real-time and historical electricity consumption data of all users to obtain user feature vectors;

[0034] Perform similarity analysis on user feature vectors and identify key enterprise users among all users based on the similarity analysis results.

[0035] In this embodiment, when specifically determining key enterprise users, feature extraction is performed on the electricity consumption data of all users, including real-time electricity consumption data and historical electricity consumption data, to extract user feature vectors corresponding to each electricity user. The user feature vectors represent the historical electricity consumption characteristics and real-time electricity consumption characteristics of each electricity user. The feature vectors are used to more efficiently process the electricity consumption data, thereby improving data processing efficiency. Thereafter, similarity analysis is performed on the extracted user feature vectors, thereby classifying all users according to the results of the similarity analysis. Based on the similarity analysis results, it is determined that the classified users that meet the electricity consumption characteristics of key enterprises are key enterprise users. For example, the electricity consumption characteristics of key enterprises may be that the electricity consumption per unit time is greater than the preset electricity consumption, or the historical electricity consumption is greater than a preset threshold, etc. Efficient similarity analysis is performed on the user feature vectors, thereby quickly and accurately locking in the corresponding key enterprise users among all users, thereby improving the efficiency of electricity consumption analysis of key enterprise users.

[0036] In one embodiment, feature extraction is performed on the real-time power consumption data and historical power consumption data of all users to obtain user feature vectors, including:

[0037] Construct an electricity consumption data matrix based on the real-time electricity consumption data and historical electricity consumption data of all users;

[0038] After performing data conversion on the electricity consumption data matrix, a target feature space is generated;

[0039] The feature vector in the target feature space is extracted to obtain the user feature vector.

[0040] In this embodiment, when performing feature extraction, a corresponding electricity consumption data matrix is ​​first constructed based on the real-time electricity consumption data and historical electricity consumption data of all users to represent the historical parameters and real-time parameters of each user. The electricity consumption data matrix is ​​then converted. For example, principal component analysis, linear discriminant analysis, etc. can be used to convert the electricity consumption data matrix composed of real-time electricity consumption data and historical electricity consumption data to obtain a new target feature space, and user feature vectors are extracted from the target feature space for subsequent similarity analysis.

[0041] Specifically, when performing data conversion, the basis vector weighted calculation formula is used The power consumption data matrix A is transformed to form an orthogonal matrix β after all basis vectors are orthogonal, where n is the dimension and α is the weighting coefficient. is the basis vector; then the orthogonal basis of the orthogonal matrix is ​​obtained to generate the target feature space, and the user feature vector is further extracted from the target feature space. Specifically, the user feature vector W is obtained by projecting the vector X in the power consumption data matrix A and the average difference δ to the target feature space. The specific formula is W = δ T (X-ω), where X is the vector in the electricity consumption data matrix A, δ is the average difference, and ω is the projected vector, so that the user feature vector containing the user's real-time electricity consumption and historical electricity consumption characteristics is extracted in the target feature space, providing a reliable data basis for subsequent similarity analysis.

[0042] In one embodiment, similarity analysis is performed on user feature vectors, and key enterprise users are determined from among all users based on the similarity analysis results, including:

[0043] The similarity matrix is ​​generated by calculating the spatial distance between different user feature vectors;

[0044] After clustering according to the similarity matrix, several electricity user clusters are obtained;

[0045] It is confirmed whether the similarity between the cluster center vector of each electricity user cluster and the preset feature vector is greater than the preset similarity. If so, it is confirmed that all the associated users in the electricity user cluster are key enterprise users.

[0046] In this embodiment, when performing similarity analysis, the spatial distance between the feature vectors of different users is first calculated, such as calculating the Euclidean distance, the Mahalanobis distance, etc., so as to obtain the spatial distance between the electricity consumption data of different users, that is, the similarity of the electricity consumption characteristics between different users is calculated, and a corresponding similarity matrix is ​​generated based on the spatial distance between the feature vectors of different users. Further clustering calculation is performed on the generated similarity matrix, and specifically, for example, the KNN clustering algorithm, the K-means clustering algorithm, etc. can be used to divide all users according to the degree of similarity to obtain a number of electricity user clusters, that is, each electricity user cluster represents similar electricity consumption characteristics, and each electricity user cluster has a cluster center. The user feature vector of the cluster center represents the average power consumption characteristics of all users in the entire power user cluster. When confirming the key enterprise users, the similarity between the user feature vector of the cluster center in each power user cluster and the preset feature vector is calculated. Specifically, the similarity calculation standard is constructed through the Euclidean distance, that is, the Euclidean distance between the cluster center vector and the preset feature vector is calculated as the similarity between the two. The similarity is compared with the preset similarity. If it is greater than the preset similarity, it indicates that all the associated users in the power user cluster are key enterprise users. Through the similarity analysis and clustering judgment of spatial distance, the key enterprise users can be quickly and accurately extracted from all users, so as to conduct targeted power consumption analysis.

[0047] S300: extracting electricity consumption data of key enterprise users and monitoring the electricity consumption data of key enterprise users.

[0048] In this embodiment, after confirming the key corporate users, data extraction can be performed based on the electricity user's identification from all the electricity consumption data previously acquired. For example, the electricity consumption data of the key corporate users can be accurately located and extracted from the electricity consumption data of all users based on the user name, electricity user number, etc., and further monitored. For example, after the key corporate users are identified, their real-time electricity consumption data can be obtained at preset time intervals in the future time period, etc., to realize electricity consumption monitoring and analysis of key corporate users.

[0049] S400: Determine whether the power consumption of key enterprise users is abnormal based on the monitoring results, and output corresponding warning information.

[0050] In this embodiment, on the premise of accurately analyzing key corporate users, the electricity consumption of key corporate users can be monitored and analyzed in a targeted manner, and further based on the monitoring results of electricity consumption, it can be determined whether there are any abnormalities in their electricity consumption and production status. If it is confirmed that there is an abnormality in electricity consumption, the corresponding early warning information is output in time to conduct electricity consumption verification, production status tracking, etc. for the corresponding corporate users, so as to facilitate the grasp of the production and operation status of the enterprise at all times and ensure that good production and operation conditions can be maintained.

[0051] Specifically, when the real-time electricity consumption data of the key enterprise user is less than the minimum value in the historical electricity consumption data, it is determined that the key enterprise user is in an abnormal electricity consumption state, and the first warning information is output;

[0052] or,

[0053] When the growth rate in the real-time electricity consumption data of the key enterprise users is greater than the preset growth rate threshold, it is confirmed that the key enterprise users are in an abnormal electricity consumption state, and a second warning information is output.

[0054] In this embodiment, when the real-time electricity consumption data of key enterprise users is monitored to be less than the minimum value in the historical electricity consumption data, it means that the key enterprise users may have poor production conditions, reduced production, etc., and therefore it is judged as abnormal electricity consumption, and a first warning message is output to facilitate understanding of the production and operation conditions of the enterprise. In the early stage of the enterprise's operation difficulties, the relevant departments are promptly prompted through the first warning message to understand, so as to ensure that the key enterprise users can adjust their production and operation conditions in time; and when the growth rate in the real-time electricity consumption data of key enterprise users is monitored to be greater than the preset growth rate threshold, this is a case of a sudden increase in electricity consumption. If the key enterprise users do not have new equipment or increase production capacity, potential dangerous factors such as line leakage or equipment failure and aging may occur, and therefore it is also judged as abnormal electricity consumption, and a second warning message is output to facilitate the power supply department to promptly check the status of the corresponding key enterprise users' electricity equipment to ensure the production safety of the enterprise.

[0055] Embodiment 2

[0056] Figure 2 A functional module diagram of an enterprise power consumption early warning device provided in the second embodiment of the present invention may specifically include the following modules:

[0057] An acquisition module 11 is used to acquire the electricity consumption data of all users;

[0058] The analysis module 12 is used to perform similarity analysis on the electricity consumption data of all users and determine key enterprise users from all users;

[0059] An extraction module 13 is used to extract the electricity consumption data of key enterprise users and monitor the electricity consumption data of key enterprise users;

[0060] The early warning module 14 is used to confirm whether the power consumption of key enterprise users is abnormal according to the monitoring results, and output corresponding early warning information.

[0061] In one embodiment of the present invention, the acquisition module 11 includes:

[0062] The power consumption data acquisition module is used to obtain the real-time power consumption data of all users and the historical power consumption data within a preset time period.

[0063] In one embodiment of the present invention, the analysis module 12 includes:

[0064] A first user feature vector acquisition module, used for extracting features from the real-time power consumption data and historical power consumption data of all users to obtain user feature vectors;

[0065] The first key enterprise user determination module is used to perform similarity analysis on the user feature vectors and determine key enterprise users from all the users according to the similarity analysis results.

[0066] In one embodiment of the present invention, the user feature vector first acquisition module includes:

[0067] An electricity consumption data matrix construction module is used to construct an electricity consumption data matrix according to the real-time electricity consumption data and historical electricity consumption data of all users;

[0068] A first target feature space generation module, used for performing data conversion on the power consumption data matrix to generate a target feature space;

[0069] The second user feature vector acquisition module is used to extract the feature vector in the target feature space to obtain the user feature vector.

[0070] In one embodiment of the present invention, the target feature space first generation module includes:

[0071] Orthogonal matrix acquisition module, used to calculate the formula by weighting the basis vector The power consumption data matrix A is transformed to form an orthogonal matrix β after all basis vectors are orthogonal, where n is the dimension and α is the weighting coefficient. is the basis vector;

[0072] The second target feature space generation module is used to obtain the orthogonal basis of the orthogonal matrix to generate the target feature space.

[0073] In one embodiment of the present invention, the key enterprise user first determination module includes:

[0074] A similarity matrix generation module is used to generate a similarity matrix after calculating the spatial distance between feature vectors of different users;

[0075] An electricity user cluster acquisition module, used to obtain a plurality of electricity user clusters after clustering processing according to the similarity matrix;

[0076] The cluster center phasor judgment module is used to confirm whether the similarity between the cluster center vector of each electricity user cluster and the preset feature vector is greater than the preset similarity. If so, the second determination module for key enterprise users is called.

[0077] The second key enterprise user determination module is used to confirm that all associated users in the electricity user cluster are key enterprise users.

[0078] In one embodiment of the present invention, the early warning module 14 includes:

[0079] A first warning information generating module, configured to determine that the key enterprise user is in an abnormal power consumption state and output a first warning information when the real-time power consumption data of the key enterprise user is less than the minimum value in the historical power consumption data;

[0080] The second warning information generating module is used to confirm that the key enterprise user is in an abnormal power consumption state and output a second warning information when the growth rate in the real-time power consumption data of the key enterprise user is greater than a preset growth rate threshold.

[0081] The enterprise electricity consumption warning device provided in the embodiment of the present invention can execute the enterprise electricity consumption warning method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0082] Embodiment 3

[0083] Figure 3 A schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention. Figure 3 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 3 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0084] like Figure 3 As shown, the computer device 12 is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0085] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0086] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0087] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 3not shown, usually called a "hard drive"). Although Figure 3 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0088] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0089] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the computer device 12, and / or may communicate with any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. In addition, the computer device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the computer device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0090] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the enterprise electricity consumption early warning method provided in the embodiment of the present invention.

[0091] Embodiment 4

[0092] Embodiment 4 of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned enterprise electricity consumption warning method are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0093] Among them, computer-readable storage media may include, for example, but are not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: 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 this document, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or device.

[0094] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for early warning of enterprise electricity consumption based on similarity analysis, characterized in that: include: Obtain electricity consumption data of all users; Performing similarity analysis on the electricity consumption data of all users, and determining key enterprise users from among all users; Extracting the electricity consumption data of the key enterprise users and monitoring the electricity consumption data of the key enterprise users; Determine whether the power consumption of the key enterprise users is abnormal according to the monitoring results, and output corresponding warning information; The obtaining of electricity consumption data of all users specifically includes: Obtain real-time electricity consumption data for all users and historical electricity consumption data within a preset time period; The performing similarity analysis on the electricity consumption data of all users to determine key enterprise users from all users includes: Extracting features from the real-time power consumption data and historical power consumption data of all users to obtain user feature vectors; Performing similarity analysis on the user feature vectors, and determining key enterprise users from among all the users according to the similarity analysis results; The performing similarity analysis on the user feature vectors and determining key enterprise users from among all the users according to the similarity analysis results includes: The similarity matrix is ​​generated by calculating the spatial distance between different user feature vectors; After clustering processing is performed according to the similarity matrix, a plurality of electricity user clusters are obtained; It is confirmed whether the similarity between the cluster center vector of each electricity user cluster and the preset feature vector is greater than the preset similarity. If so, it is confirmed that all the associated users in the electricity user cluster are key enterprise users.

2. The enterprise electricity consumption early warning method based on similarity analysis according to claim 1 is characterized in that: The feature extraction of the real-time power consumption data and the historical power consumption data of all users to obtain the user feature vector includes: Constructing an electricity consumption data matrix according to the real-time electricity consumption data and historical electricity consumption data of all users; Performing data conversion on the electricity consumption data matrix to generate a target feature space; The feature vector in the target feature space is extracted to obtain the user feature vector.

3. The enterprise electricity consumption early warning method based on similarity analysis according to claim 2 is characterized in that: The step of converting the power consumption data matrix to generate a target feature space includes: The weighted calculation formula is based on the basis vector The power consumption data matrix A is transformed to form an orthogonal matrix β after all basis vectors are orthogonal. ， in n is the dimension, α is the weighting coefficient, is the basis vector; An orthogonal basis of the orthogonal matrix is ​​obtained to generate the target feature space.

4. The enterprise electricity consumption early warning method based on similarity analysis according to claim 1 is characterized in that: The step of confirming whether the power consumption of the key enterprise users is abnormal according to the monitoring results and outputting corresponding warning information includes: When the real-time electricity consumption data of the key enterprise user is less than the minimum value in the historical electricity consumption data, it is determined that the key enterprise user is in an abnormal electricity consumption state, and a first warning information is output; or, When the growth rate in the real-time electricity consumption data of the key enterprise user is greater than a preset growth rate threshold, it is confirmed that the key enterprise user is in an abnormal electricity consumption state, and a second warning information is output.

5. An enterprise electricity consumption early warning device based on similarity analysis, characterized in that: include: An acquisition module is used to obtain the electricity consumption data of all users; An analysis module, used to perform similarity analysis on the electricity consumption data of all users, and determine key enterprise users from all users; An extraction module, used to extract the electricity consumption data of the key enterprise users and monitor the electricity consumption data of the key enterprise users; An early warning module is used to confirm whether the power consumption of the key enterprise users is abnormal according to the monitoring results, and output corresponding early warning information; Wherein, the acquisition module includes: The power consumption data acquisition module is used to obtain the real-time power consumption data of all users and the historical power consumption data within a preset time period; The analysis module comprises: A first user feature vector acquisition module, used for extracting features from the real-time power consumption data and historical power consumption data of all users to obtain user feature vectors; A first key enterprise user determination module, configured to perform similarity analysis on the user feature vectors and determine key enterprise users from among all users based on the similarity analysis results; The first key enterprise user determination module includes: A similarity matrix generation module is used to generate a similarity matrix after calculating the spatial distance between feature vectors of different users; An electricity user cluster acquisition module, used to obtain a plurality of electricity user clusters after clustering according to the similarity matrix; The cluster center phasor judgment module is used to confirm whether the similarity between the cluster center vector of each power user cluster and the preset feature vector is greater than the preset similarity. If so, the second determination module for key enterprise users is called; The second key enterprise user determination module is used to confirm that all associated users in the electricity user cluster are key enterprise users.

6. An enterprise electricity consumption early warning system, characterized in that: The system includes at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the enterprise electricity consumption early warning method described in any one of claims 1-4.

7. A non-volatile computer-readable storage medium, characterized in that: The non-volatile computer-readable storage medium stores computer-executable instructions, which, when executed by one or more processors, enable the one or more processors to execute the enterprise electricity consumption warning method described in any one of claims 1-4.

Images