A method and system for auditing electricity consumption status of power users before and during the audit

Abstract

The present invention relates to the technical field of electric power consumption detection, and discloses a method and system for pre- and in-process auditing of the electricity consumption status of an electric power user. The method generates corresponding user attribute tags through user attribute information, and audits the historical information of electricity consumption status, combines the user attribute tags of each user with the historical audit tags at multiple different times to form multiple case tag relationship chains, clusters the multiple case tag relationship chains to obtain the case tag relationship chain corresponding to the best clustering center, filters out the historical audit tags contained in the case tag relationship chain corresponding to the best clustering center, obtains the current electricity consumption status information of each user corresponding to the filtered historical audit tags, audits the current electricity consumption status information, and obtains the audit results of the current electricity consumption status information, thereby improving the audit efficiency and audit accuracy of the electricity consumption status of the electric power user.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power consumption detection, and in particular to a method and system for pre- and in-process auditing of electric power users' electricity consumption status. Background Art

[0002] With the development of social economy and the continuous improvement of people's living standards, the demand for electricity in all walks of life is increasing, and the service requirements are getting higher and higher. This also leads to more problems with the standardization of electricity use and the compliance / compliance and satisfaction of electricity business. The probability of various problems occurring is greatly increased. If the problems are not discovered and solved in time, but are discovered afterwards and remedied, not only the work efficiency is low, but also the social satisfaction is low. Therefore, it is necessary to design a pre- and in-process audit method for electricity use.

[0003] In existing implementation schemes, electricity usage is subject to single or special inspections / inspections / audits, and generally, only overall anomalies are discovered, followed by gradual analysis to identify details of doubt, which is inefficient. Alternatively, routine inspections are conducted on a periodic basis, making it difficult to detect problems in a timely manner at the point in time when they occur. Afterwards, the problems or evidence disappear, making it difficult to achieve the preventive function of "preventing problems before they occur" and only serving as a warning or punishment afterwards. At the same time, no comprehensive comparison is conducted between the relevant reference quantities of each audit indicator, which makes it easy to miss some relevant doubts, resulting in reduced accuracy of the audit results on electricity usage.

[0004] However, in existing, similar, and normal implementation schemes, conducting pre- and in-process audits of electricity usage is difficult due to limited time and resources. This not only increases the workload of operational staff but also requires significant investment in hardware equipment, making it difficult to conduct continuous, comprehensive audits of millions of electricity users. Normally, the current standard approach to monitoring electricity usage by users involves meter reading at the end of a usage cycle (usually a month), primarily for billing purposes. Conventional verification is performed on a year-on-year and month-on-month basis. If a specific growth rate is detected, an on-site verification is required. If no hard issues are found (such as meter failures or evidence of electricity theft), the system assumes normal usage, making it difficult to quickly and effectively conduct audits targeting specific issues. Consequently, it is difficult to conduct comprehensive audits of large-scale electricity usage in a timely and effective manner to prevent problems. Summary of the Invention

[0005] The present invention provides a method and system for pre- and interim auditing of electricity users' electricity usage, which solves the current technical problem that it is difficult to quickly and effectively audit certain existing problems in electricity users' electricity usage, thereby making it difficult to conduct comprehensive audits of a large number of electricity usage conditions in a timely and effective manner to prevent problems from occurring.

[0006] In view of this, a first aspect of the present invention provides a method for auditing electricity consumption status of an electricity user before and during the audit, comprising the following steps:

[0007] Obtain user attribute information and power usage history information of each user;

[0008] Generate a corresponding user attribute tag based on the user attribute information;

[0009] Auditing the electricity usage history information, and generating historical audit tags corresponding to each user at multiple different times according to the audit results;

[0010] Combining the user attribute label of each user with the historical audit labels at multiple different moments to form multiple case label relationship chains, clustering the multiple case label relationship chains to obtain the case label relationship chain corresponding to the optimal cluster center;

[0011] Filter out the historical audit labels contained in the case label relationship chain corresponding to the best cluster center;

[0012] The current power usage status information corresponding to each user and the filtered historical audit tag is obtained, the current power usage status information is audited, and an audit result of the current power usage status information is obtained.

[0013] Preferably, the user attribute information includes account number, account name, electricity address, electricity capacity, power supply voltage level, power supply attributes, power supply line, transformer attributes, number of transformers, capacity, metering point number, electricity category, implemented electricity price, payment method, list of power-consuming equipment, backup power supply, credit rating, payment status and payment reminder status;

[0014] The power usage history information includes active meter reading, reactive meter reading, total active power, total reactive power, peak / valley / flat power, maximum power load, minimum power load, CT ratio, PT ratio and comprehensive ratio.

[0015] Preferably, the steps of auditing the electricity usage history information and generating a plurality of historical audit labels corresponding to each user at different times according to the audit results specifically include:

[0016] Performing a threshold comparison on each power usage historical parameter in the power usage historical information at multiple different times according to a preset audit rule, and determining whether the power usage historical parameter is abnormal based on the comparison result;

[0017] If it is determined that the power usage historical parameter is abnormal, a historical audit tag at a corresponding moment is generated based on the abnormal power usage historical parameter.

[0018] Preferably, the method further comprises:

[0019] Building a case library and initializing the case library;

[0020] The case label relationship chains corresponding to each user are stored in the case library, the proportion of each identical case label relationship chain is calculated, and the proportion is updated in the case library.

[0021] Preferably, the steps of obtaining the current power usage status information of each user corresponding to the filtered historical audit tags, auditing the current power usage status information, and obtaining the audit results of the current power usage status information further include:

[0022] Determine abnormal power usage information based on the audit results of current power usage information;

[0023] Generating an audit tag based on the abnormal power usage information, and combining the user attribute tag of each user with the audit tag to form a case tag relationship chain;

[0024] The same case label relationship chains are accumulated and the proportion of the corresponding case label relationship chains is updated.

[0025] In a second aspect, the present invention further provides a system for auditing electricity users' electricity usage before and during the audit, comprising:

[0026] User information acquisition module, used to obtain user attribute information and power usage history information of each user;

[0027] A first label generation module, configured to generate a corresponding user attribute label based on the user attribute information;

[0028] A second label generation module is used to audit the electricity usage history information and generate historical audit labels corresponding to each user at multiple different times according to the audit results;

[0029] A relationship chain clustering module is used to combine the user attribute label of each user with the historical audit labels at multiple different times to form multiple case label relationship chains, cluster the multiple case label relationship chains, and obtain the case label relationship chain corresponding to the best cluster center;

[0030] The label filtering module is used to filter out the historical audit labels contained in the case label relationship chain corresponding to the best cluster center;

[0031] The power usage status audit module is used to obtain the current power usage status information of each user corresponding to the screened historical audit tags, audit the current power usage status information, and obtain the audit results of the current power usage status information.

[0032] Preferably, the user attribute information includes account number, account name, electricity address, electricity capacity, power supply voltage level, power supply attributes, power supply line, transformer attributes, number of transformers, capacity, metering point number, electricity category, implemented electricity price, payment method, list of power-consuming equipment, backup power supply, credit rating, payment status and payment reminder status;

[0033] The power usage history information includes active meter reading, reactive meter reading, total active power, total reactive power, peak / valley / flat power, maximum power load, minimum power load, CT ratio, PT ratio and comprehensive ratio.

[0034] Preferably, the second label generating module specifically includes:

[0035] an abnormality judgment module, configured to compare thresholds of various power usage historical parameters in the power usage historical information at multiple different moments according to preset audit rules, and to judge whether the power usage historical parameters are abnormal based on the comparison results;

[0036] The abnormal parameter label generation module is used to generate a historical audit label at a corresponding moment based on the abnormal power usage historical parameter if it is determined that the power usage historical parameter is abnormal.

[0037] Preferably, the system further includes:

[0038] A case library construction module, used for constructing a case library and initializing the case library;

[0039] The proportion updating module is used to store the case label relationship chains corresponding to each user in the case library, calculate the proportion of each identical case label relationship chain, and update the proportion in the case library.

[0040] Preferably, the system further includes:

[0041] An abnormality determination module, configured to determine abnormal power usage information based on the audit results of the current power usage information;

[0042] A relationship chain generation module is used to generate an audit tag based on the abnormal power usage status information, and combine the user attribute tag of each user with the audit tag to form a case tag relationship chain;

[0043] The relationship chain accumulation module is used to accumulate the relationship chains of the same case label and update the proportion of the corresponding case label relationship chains.

[0044] It can be seen from the above technical solutions that the present invention has the following advantages:

[0045] The method generates corresponding user attribute labels through user attribute information, and audits the historical information of electricity usage status, generates historical audit labels corresponding to multiple different moments for each user according to the audit results, combines the user attribute labels of each user with the historical audit labels at multiple different moments by field combination, forms multiple case label relationship chains, clusters the multiple case label relationship chains, obtains the case label relationship chain corresponding to the best cluster center, filters out the historical audit labels contained in the case label relationship chain corresponding to the best cluster center, obtains the current electricity usage status information corresponding to each user and the filtered historical audit labels, audits the current electricity usage status information, and obtains the audit results of the current electricity usage status information, thereby filtering out the most representative historical audit labels of the users, auditing their corresponding electricity usage status information, using the pre-audit to form the case label relationship chain, filtering out the most relevant case label relationship chain for the users, and then performing an in-process audit based on the case label relationship chain, thereby improving the audit efficiency and audit accuracy of the electricity usage status of power users. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A flowchart of a method for pre- and interim auditing of power consumption status of power users provided by an embodiment of the present invention;

[0047] Figure 2 A schematic structural diagram of a system for pre- and interim auditing of electricity consumption by power users provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only 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 making creative efforts shall fall within the scope of protection of the present invention.

[0049] For easier understanding, see Figure 1 The present invention provides a method for auditing the power consumption status of power users before and during the audit, comprising the following steps:

[0050] S1. Obtain user attribute information and power usage history information of each user.

[0051] Among them, user attribute information and electricity usage history information both include multiple parameters. User attribute information describes the user's basic information, including but not limited to household number, household name, electricity usage address, electricity usage capacity, power supply voltage level, power supply attributes, power supply lines, transformer attributes, number of transformers, capacity, metering point number, electricity usage category, implemented electricity price, payment method, list of power-consuming equipment, backup power supply, credit rating, payment status and collection status.

[0052] The historical information on electricity usage describes the user's electricity usage status. The historical information on electricity usage status includes but is not limited to active meter readings, reactive meter readings, total active power, total reactive power, peak / valley / flat power, maximum power load, minimum power load, CT ratio, PT ratio, and comprehensive ratio.

[0053] S2. Generate corresponding user attribute tags based on user attribute information.

[0054] It is understandable that user attribute information generally does not change over time. User attribute labels include special transformer households / public transformer households, industrial and commercial households / residential households, xx types of metering (Class I, II, III, IV, V), transfer households, with / without equipment list, and multiple people in one household.

[0055] S3. Audit the historical information of electricity usage and generate historical audit tags corresponding to each user at multiple different times based on the audit results.

[0056] It is understandable that the historical information on electricity usage can change over time, so the historical information on electricity usage includes the historical information on electricity usage at multiple different times, so that the historical information on electricity usage at multiple different times can be audited. Based on the audit results, it can be determined whether the historical information on electricity usage is abnormal, and abnormal historical information on electricity usage can generate corresponding historical audit tags, such as: households with heavy loads / households with light loads, households with excessive capacity, suspected power generators, households with electricity theft / suspected electricity theft, households with breach of contract, households with power outages, overcapacity, total meter difference, abnormal power factor, abnormal fluctuation, abnormal analogy, high consumption, abnormal meter reading, abnormal billing, abnormal charging, abnormal power outage, and missing notification.

[0057] S4. Combine the user attribute label of each user with the historical audit labels at multiple different times to form multiple case label relationship chains. Cluster the multiple case label relationship chains to obtain the case label relationship chain corresponding to the best cluster center.

[0058] Among them, the user attribute label of each user is unique, while the historical audit label may be the same or different at multiple different times. By combining the user attribute label of each user with the historical audit labels at multiple different times, a case label relationship chain corresponding to each time is formed, such as: Overcapacity audit - dedicated transformer households & industrial and commercial households & previously overloaded households & suspected power generation households - overcapacity electricity consumption in the xx period of xx year xx month xx day.

[0059] At the same time, in order to obtain more representative historical audit labels for users and facilitate faster auditing, multiple case label relationship chains are clustered, ultimately obtaining the case label relationship chain corresponding to the optimal cluster center. K-Means clustering can be used as the clustering method, which is not limited here.

[0060] S5. Filter out the historical audit labels contained in the case label relationship chain corresponding to the best cluster center.

[0061] It can be understood that the case label relationship chain is composed of historical audit labels.

[0062] S6. Obtain the current power usage status information of each user corresponding to the screened historical audit tags, audit the current power usage status information, and obtain the audit result of the current power usage status information.

[0063] It should be noted that the current power usage status information corresponding to the filtered historical audit tags of each user can be audited first, and a call for test can be conducted based on the current power usage status information. The time period for each call for test can be set to 5 minutes to 60 minutes. After the call for test, the current power usage status information is audited according to the rules to obtain the audit results.

[0064] In actual applications, an audit exception list can be generated based on the audit results, and the abnormal items in the audit exception list can be handled. The handling methods include but are not limited to:

[0065] 1) The handling method of overcapacity (overload) electricity consumption: notification of capacity increase, electricity fee calculation and inspection, and investigation and punishment of electricity consumption in violation of regulations.

[0066] 2) How to deal with a large difference in electricity consumption between the main meter and the user meter: Pay attention to verify whether electricity can be stolen, check for possible leakage, and check whether there is a meter failure.

[0067] 3) How to deal with short-term internal power outages: Obtain the capacity of the current limiter or air switch at the time of power outage, compare the reported capacity to see if it is due to overcapacity or internal leakage protection tripping, analyze and verify to find out the safety hazards, and assist users in using electricity safely.

[0068] 4) How to deal with large differences in electricity consumption between peaks and valleys: Analyze the feasibility of implementing time-of-use electricity prices to help users use electricity economically.

[0069] 5) How to deal with the inconsistency of peak and trough levels of user electricity load: Discovering the patterns can make more efficient use of power distribution resources, reduce investment and waste, and maximize the use of power resources while ensuring safety.

[0070] 6) Handling of missing or incomplete notifications: Point out that internal work reminders, power outage notifications, etc. are not sent in full, resulting in workflow jumps, affecting user experience, and may cause customer service issues. Immediately analyze the causes and make improvements.

[0071] It should be noted that this method generates corresponding user attribute labels through user attribute information, and audits the historical information of electricity usage status, generates historical audit labels corresponding to multiple different times for each user according to the audit results, combines the user attribute labels of each user with the historical audit labels at multiple different times by field combination, forms multiple case label relationship chains, and clusters the multiple case label relationship chains to obtain the case label relationship chain corresponding to the best cluster center, filters out the historical audit labels contained in the case label relationship chain corresponding to the best cluster center, obtains the current electricity usage status information corresponding to each user and the filtered historical audit labels, audits the current electricity usage status information, and obtains the audit results of the current electricity usage status information, thereby filtering out the most representative historical audit labels of the user and auditing its corresponding electricity usage status information, using the prior audit to form the case label relationship chain, and then filtering out the most relevant case label relationship chain for the user, and then performing an in-process audit based on the case label relationship chain, thereby improving the audit efficiency and audit accuracy of the electricity usage status of power users.

[0072] This method is an active audit method that audits electricity usage before and during the process. It is low-cost and highly efficient. It is professionally designed without investing additional manpower and existing equipment. It makes it possible and normal to achieve large-scale and comprehensive active audits of electricity usage before and during the process in an automated manner, avoiding the previous situation where only manual analysis of doubts / reporting-style post-audits or a small number of individual pre-audits or post-audits were required.

[0073] In a specific embodiment, step S3 specifically includes:

[0074] S301. Perform threshold comparison on each power usage historical parameter in power usage historical information at multiple different moments according to preset audit rules, and determine whether the power usage historical parameter is abnormal based on the comparison result.

[0075] Among them, the audit rule is to set a threshold value for each historical parameter of the power usage status, compare the historical parameter of the power usage status with the set threshold value, and if it exceeds the threshold value, it is determined that the historical parameter of the power usage status is abnormal.

[0076] Audit rules include but are not limited to:

[0077] 1) Abnormal difference between the total meter and the user meter: If the total meter and the user meter have a large difference in electricity within a period of time, there may be electricity theft or leakage, or meter failure.

[0078] The audit rule is: if |total metered electricity - ∑user metered electricity| ≥ threshold, the meter total score is abnormal; if |total metered electricity - ∑user metered electricity| ÷ |total metered electricity| ≥ threshold (percentage), the meter total score is abnormal.

[0079] 2) Overcapacity:

[0080] The audit rule is: if the user's metered electricity consumption in a time period ÷ electricity consumption time period Δt ≥ threshold (reported capacity, contracted capacity, or operating capacity), then it is determined to be overcapacity.

[0081] 3) Abnormal power factor:

[0082] The audit rules are: Then it is determined that the power factor is abnormal; It is determined that the power factor is abnormal.

[0083] Abnormal power fluctuation:

[0084] The audit rules are: if |current period's electricity consumption - previous period's electricity consumption| ≥ threshold, the electricity consumption fluctuation is considered abnormal; if |current period's electricity consumption - previous period's electricity consumption| ÷ |previous period's electricity consumption| ≥ threshold (percentage), the electricity consumption fluctuation is considered abnormal.

[0085] Analogy exception:

[0086] The audit rule is: electricity consumption: water consumption: gas consumption = E:W:G, threshold EW (high value) ≥ E / W ≥ threshold EW (low value), then the analog abnormality is determined, among which threshold EG (high value) ≥ E / G ≥ threshold EG (low value).

[0087] All of the above thresholds are designed to automatically take values ​​from the results of big data averaging of audited normal users.

[0088] S302: If it is determined that the historical parameters of the power usage status are abnormal, a historical audit tag at a corresponding moment is generated based on the abnormal historical parameters of the power usage status.

[0089] It should be noted that only abnormal power usage historical parameters generate historical audit labels, while normal power usage historical parameters do not generate historical audit labels, which makes the user's case label relationship chain more streamlined and improves the accuracy of label screening.

[0090] In a specific embodiment, the method further comprises:

[0091] S71. Build a case library and initialize the case library.

[0092] Among them, after the case library is initialized, it is an empty set.

[0093] S72. Store multiple case label relationship chains corresponding to each user in the case library, calculate the proportion of each identical case label relationship chain, and update the proportion in the case library.

[0094] It should be noted that after each audit is completed by the user, a case label relationship chain consisting of audit labels is formed, and the case library is self-updated and accumulated. The proportion of each identical case label relationship chain is calculated and the proportion is updated in the case library. For example: Overcapacity audit - dedicated transformer households & industrial and commercial households & households with previous overloads & suspected power generation households - overcapacity electricity consumption in xx / xx / xx period, 45 cases, accounting for 11.6%.

[0095] In actual applications, a new or next round of cyclic audits is carried out, and the case library is accumulated based on continuous self-updating. For each or new pre- and in-process audit "audit parameter + label set" special project, the possibility probability is given based on the case library, and the reference focus and spot check direction of the implemented special audit are provided, which greatly reduces the audit cost of discovering actual problems and improves the accuracy of the audit results.

[0096] In a specific embodiment, step S6 further includes:

[0097] S7. Determine abnormal power usage information based on the audit results of the current power usage information.

[0098] S8. Generate an audit tag based on the abnormal power usage information, combine the user attribute tag of each user with the audit tag to form a case tag relationship chain.

[0099] S9. Accumulate the same case label relationship chains and update the proportion of the corresponding case label relationship chains.

[0100] It should be noted that when an abnormality occurs in the current electricity usage information, an audit tag will be formed, and the user attribute tag of each user will be combined with the audit tag field to form a case tag relationship chain. The same case tag relationship chain will then be accumulated, and the proportion of the corresponding case tag relationship chain will be updated. This will continue to accumulate and repeat, and the user's continuous electricity usage status can be predicted and prejudged. It can warn of some dangerous problems, prompt safety hazards, collect evidence and deal with violations in a timely manner, and provide optimization suggestions for areas that can be improved, so as to better provide users with high-quality services and even value-added services. It can also be continuously revised and accumulated over a long period of time through practice, and continuously classified to form a big data statistical library, so as to accumulate a larger database for future applications. In this way, the large database of electricity usage status of power users with regional characteristics can better serve both power supply and power users.

[0101] The above is a detailed description of an embodiment of a method for pre- and interim auditing of electricity usage of an electricity user provided by the present invention. The following is a detailed description of an embodiment of a system for pre- and interim auditing of electricity usage of an electricity user provided by the present invention.

[0102] For easier understanding, see Figure 2 The present invention also provides a system for auditing electricity users' electricity usage before and during the audit, including:

[0103] The user information acquisition module 100 is used to obtain user attribute information and power usage history information of each user;

[0104] A first tag generation module 200 is configured to generate a corresponding user attribute tag based on user attribute information;

[0105] The second label generation module 300 is used to audit the historical information of power usage and generate historical audit labels corresponding to each user at multiple different times according to the audit results;

[0106] The relationship chain clustering module 400 is used to combine the user attribute label of each user with the historical audit labels at multiple different times to form multiple case label relationship chains, cluster the multiple case label relationship chains, and obtain the case label relationship chain corresponding to the optimal cluster center;

[0107] The label screening module 500 is used to screen out the historical audit labels contained in the case label relationship chain corresponding to the best cluster center;

[0108] The power usage status audit module 600 is used to obtain the current power usage status information of each user corresponding to the screened historical audit tags, audit the current power usage status information, and obtain the audit result of the current power usage status information.

[0109] In a specific embodiment, the user attribute information includes the account number, account name, electricity address, electricity capacity, power supply voltage level, power supply attributes, power supply line, transformer attributes, number of transformers, capacity, metering point number, electricity category, implemented electricity price, payment method, list of power-consuming equipment, backup power supply, credit rating, payment status, and payment reminder status;

[0110] The historical information on power usage includes active meter readings, reactive meter readings, total active power, total reactive power, peak / valley / flat power, maximum power load, minimum power load, CT ratio, PT ratio, and comprehensive ratio.

[0111] In a specific embodiment, the second label generation module specifically includes:

[0112] The abnormality judgment module is used to compare the threshold values ​​of various power usage historical parameters in the power usage historical information at multiple different times according to the preset audit rules, and judge whether the power usage historical parameters are abnormal based on the comparison results;

[0113] The abnormal parameter label generation module is used to generate a historical audit label at a corresponding moment based on the abnormal historical parameters of the power usage status if it is determined that the historical parameters of the power usage status are abnormal.

[0114] In a specific embodiment, the system further includes:

[0115] Case library construction module, used to build the case library and initialize the case library;

[0116] The proportion update module is used to store multiple case label relationship chains corresponding to each user in the case library, calculate the proportion of each identical case label relationship chain, and update the proportion in the case library.

[0117] In a specific embodiment, the system further includes:

[0118] An abnormality determination module is used to determine abnormal power usage information based on the audit results of the current power usage information;

[0119] A relationship chain generation module is used to generate audit tags based on abnormal power usage information, and combine the user attribute tag and audit tag of each user to form a case tag relationship chain;

[0120] The relationship chain accumulation module is used to accumulate the relationship chains of the same case label and update the proportion of the corresponding case label relationship chains.

[0121] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working process of the system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0122] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0123] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0124] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0125] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for auditing electricity consumption of power users before and during the process, characterized in that: The following steps are involved: Obtain user attribute information and power usage history information of each user; Generate a corresponding user attribute tag based on the user attribute information; Audit the historical information of power usage and generate historical audit tags corresponding to each user at multiple different times according to the audit results, including: Performing a threshold comparison on each power usage historical parameter in the power usage historical information at multiple different times according to a preset audit rule, and determining whether the power usage historical parameter is abnormal based on the comparison result; If it is determined that the power usage historical parameter is abnormal, generating a historical audit tag at a corresponding moment based on the abnormal power usage historical parameter; Combining the user attribute label of each user with the historical audit labels at multiple different moments to form multiple case label relationship chains, clustering the multiple case label relationship chains to obtain the case label relationship chain corresponding to the optimal cluster center; Filter out the historical audit labels contained in the case label relationship chain corresponding to the best cluster center; The current power usage status information corresponding to each user and the filtered historical audit tag is obtained, the current power usage status information is audited, and an audit result of the current power usage status information is obtained.

2. The method for auditing the power consumption status of power users before and during the process according to claim 1 is characterized in that: The user attribute information includes account number, account name, electricity address, electricity capacity, power supply voltage level, power supply attributes, power supply line, transformer attributes, number of transformers, capacity, metering point number, electricity category, implemented electricity price, payment method, list of power-consuming equipment, backup power supply, credit rating, payment status and payment reminder status; The power usage history information includes active meter reading, reactive meter reading, total active power, total reactive power, peak / valley / flat power, maximum power load, minimum power load, CT ratio, PT ratio and comprehensive ratio.

3. The method for auditing the power consumption status of power users before and during the process according to claim 1 is characterized in that: Also includes: Building a case library and initializing the case library; The case label relationship chains corresponding to each user are stored in the case library, the proportion of each identical case label relationship chain is calculated, and the proportion is updated in the case library.

4. The method for auditing the power consumption status of power users before and during the process according to claim 3 is characterized in that: The steps of obtaining the current power usage status information corresponding to each user and the filtered historical audit tags, auditing the current power usage status information, and obtaining the audit results of the current power usage status information, further include: Determine abnormal power usage information based on the audit results of current power usage information; Generating an audit tag based on the abnormal power usage information, and combining the user attribute tag of each user with the audit tag to form a case tag relationship chain; The same case label relationship chains are accumulated and the proportion of the corresponding case label relationship chains is updated.

5. A system for auditing electricity users' electricity consumption before and during the process, characterized by: include: User information acquisition module, used to obtain user attribute information and power usage history information of each user; A first label generation module, configured to generate a corresponding user attribute label based on the user attribute information; A second label generation module is used to audit the electricity usage history information and generate historical audit labels corresponding to each user at multiple different times according to the audit results; The second label generation module specifically includes: an abnormality judgment module, configured to compare thresholds of various power usage historical parameters in the power usage historical information at multiple different moments according to preset audit rules, and to judge whether the power usage historical parameters are abnormal based on the comparison results; An abnormal parameter label generation module is used to generate a historical audit label at a corresponding moment based on the abnormal power usage historical parameter if it is determined that the power usage historical parameter is abnormal; A relationship chain clustering module is used to combine the user attribute label of each user with the historical audit labels at multiple different times to form multiple case label relationship chains, cluster the multiple case label relationship chains, and obtain the case label relationship chain corresponding to the best cluster center; The label filtering module is used to filter out the historical audit labels contained in the case label relationship chain corresponding to the best cluster center; The power usage status audit module is used to obtain the current power usage status information of each user corresponding to the screened historical audit tags, audit the current power usage status information, and obtain the audit results of the current power usage status information.

6. The system for auditing electricity consumption status of power users before and during the process according to claim 5 is characterized in that: The user attribute information includes account number, account name, electricity address, electricity capacity, power supply voltage level, power supply attributes, power supply line, transformer attributes, number of transformers, capacity, metering point number, electricity category, implemented electricity price, payment method, list of power-consuming equipment, backup power supply, credit rating, payment status and payment reminder status; The power usage history information includes active meter reading, reactive meter reading, total active power, total reactive power, peak / valley / flat power, maximum power load, minimum power load, CT ratio, PT ratio and comprehensive ratio.

7. The system for auditing electricity consumption status of power users before and during the process according to claim 5 is characterized in that: Also includes: A case library construction module, used for constructing a case library and initializing the case library; The proportion updating module is used to store the case label relationship chains corresponding to each user in the case library, calculate the proportion of each identical case label relationship chain, and update the proportion in the case library.

8. The system for auditing electricity consumption of power users before and during the process according to claim 7, further comprising: An abnormality determination module is used to determine abnormal power usage information based on the audit results of the current power usage information; A relationship chain generation module is used to generate an audit tag based on the abnormal power usage status information, and combine the user attribute tag of each user with the audit tag to form a case tag relationship chain; The relationship chain accumulation module is used to accumulate the relationship chains of the same case label and update the proportion of the corresponding case label relationship chains.

Images