Distribution network graph model data intelligent management system

Abstract

The invention discloses a distribution network graph model data intelligent management system, which belongs to the technical field of distribution network graph model data management and comprises an application analysis module, an optimization analysis module and an optimization management module. The application analysis module is used for performing application analysis on the graphic model data and determining graphic model optimization items which are data items needing graphic model data transmission optimization; the optimization analysis module is used for carrying out optimization analysis on the graph-model optimization item, acquiring graph-model process associated data of the graph-model optimization item, and generating a graph-model process information graph of the graph-model optimization item according to the graph-model process associated data; identifying transmission items of the graph model optimization items according to the graph model process information graph; determining a reference optimization mode of the transmission item; determining an evaluation sequence of the transmission items according to the reference optimization mode; performing optimization analysis according to the evaluation sequence to form an optimization combination curve; and the optimization management module is used for performing optimization management on the graph model optimization item.

Description

Technical Field

[0001] The present invention belongs to the technical field of distribution network image model data management, and in particular is an intelligent management system for distribution network image model data. Background Art

[0002] With the large-scale construction of distribution automation and smart grid, the intelligent management system of distribution network model data plays an increasingly important role in the power industry. The system realizes the unified exchange, verification, update and maintenance of distribution network model data by integrating multiple data sources, such as geographic information system (GIS), dispatching automation system, power metering system, etc. However, although the system has achieved remarkable results in improving the level of distribution network operation management and ensuring the safe and stable operation of the power grid, there are still some problems that need to be solved. Among them, the timeliness problem is particularly prominent. In the actual operation of the distribution network, the distribution network structure often changes due to the increase and decrease of equipment, line transformation and other reasons. However, the current intelligent management system of distribution network model data has a lag in data update and cannot reflect the latest status of the distribution network in real time. Especially when manual adjustments are made to the household side, the frequent and complex adjustments can easily lead to untimely data updates. This not only affects the accuracy and consistency of the distribution network model data, but also may pose a potential threat to the safe and stable operation of the power grid.

[0003] Based on this, in order to solve the above problems, the present invention provides an intelligent management system for distribution network model data. Summary of the invention

[0004] In order to solve the problems existing in the above-mentioned solutions, the present invention provides an intelligent management system for distribution network model data.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A distribution network diagram data intelligent management system, including an application analysis module, an optimization analysis module and an optimization management module;

[0007] The application analysis module is used to perform application analysis on the image model data and determine the image model optimization items, wherein the image model optimization items are data items that need to be optimized for image model data transmission;

[0008] Furthermore, the method for determining the graph model optimization item includes:

[0009] Acquire application records in real time and set optimization item definitions of graph model optimization items, where the optimization items are defined as data items that cause application abnormalities due to untimely update of graph model data;

[0010] Establishing an identification and judgment model, analyzing application records and optimization item definitions through the identification and judgment model to determine candidate items; classifying the application records according to the candidate items to obtain candidate analysis data corresponding to the candidate items, wherein the candidate analysis data is composed of application records belonging to the corresponding candidate items;

[0011] Determine the selection probability and selection value of the candidate item according to the candidate analysis data; calculate the optimization value of the candidate item according to the optimization formula, and the optimization formula is:

[0012] YB=DZ×(e μ -1);

[0013] In the formula: YB is the optimized value; DZ is the candidate value; μ is the candidate probability; e is the natural constant;

[0014] The candidate items whose optimization values ​​are greater than the threshold X1 are marked as graph model optimization items.

[0015] Furthermore, the expression of the recognition judgment model is:

[0016]

[0017] In the formula: (s, Y) is the input data, s is the application record; Y is the optimization item definition; s→Y means that the corresponding application record meets the optimization item definition; the output data is the identification judgment value YA(s, Y), and the identification judgment value is 1 or 0.

[0018] When the recognition judgment value is 1, the data item of the corresponding application record is marked as a pending item;

[0019] When the recognition judgment value is 0, no corresponding operation is performed.

[0020] The optimization analysis module is used to optimize and analyze the image model optimization items, obtain the image model process associated data of the image model optimization items, generate the image model process information graph of the image model optimization items according to the image model process associated data; and identify the transmission items of the image model optimization items according to the image model process information graph;

[0021] Determining a baseline optimization method for the transmission items; determining an evaluation order for the transmission items according to the baseline optimization method;

[0022] Perform optimization analysis according to the evaluation sequence to form an optimization combination curve.

[0023] Further, the method for determining the baseline optimization mode of the transmission item includes:

[0024] The platform establishes a transmission time detail table, which is used to count the benchmark time corresponding to different transmission items;

[0025] Match the baseline time consumption of the transmission item according to the detailed list of transmission time consumption; identify the historical time consumption of the transmission item;

[0026] Calculate the time consumption ratio of the transmission item according to the ratio formula, and the ratio formula is:

[0027] BZ = LZ ÷ HZ;

[0028] In the formula: BZ is the time consumption ratio; HZ is the baseline time consumption; LZ is the historical time consumption;

[0029] When the time consumption ratio is not greater than 1, the baseline optimization method is none;

[0030] When the time consumption ratio is greater than 1, determine the baseline optimization method according to the time consumption ratio.

[0031] Further, the method for determining the baseline optimization method of the transmission item includes:

[0032] Determine the alternative optimization methods available for the transmission item; identify the optimization duration of the alternative optimization methods;

[0033] Estimate the optimization cost and optimization difficulty value corresponding to the alternative optimization methods;

[0034] Calculate the method value of the alternative optimization method according to the first formula, and the first formula is:

[0035]

[0036] In the formula: WA is the method value; b1 and b2 are both proportionality coefficients, and the value range is 0 < b1 < 1, 0 < b2 < 1; NB is the optimization difficulty value; CB is the optimization cost;

[0037] Form an alternative coordinate according to the method value and optimization duration of the alternative optimization method; input the alternative coordinate into the coordinate system, and form an alternative analysis curve according to the alternative coordinate;

[0038] Calculate the slope of the alternative analysis curve at the alternative coordinate, marked as the alternative analysis value; determine the baseline optimization method according to the alternative analysis value.

[0039] Further, the method for determining the evaluation order of the corresponding transmission item according to the baseline optimization method includes:

[0040] Calculate the method value of the baseline optimization method, and identify the optimization duration of the baseline optimization method;

[0041] Calculate the priority value of the transmission item according to the priority formula, and the priority formula is:

[0042] WY = T ÷ (WA + 1);

[0043] Where: WY is the priority value; T is the optimization duration; WA is the mode value;

[0044] The evaluation order of the transmission items is determined according to the order of priority values.

[0045] Furthermore, the method of performing optimization analysis according to the evaluation order includes:

[0046] Step SA1: generating an evaluation sequence according to the evaluation order; forming a merged combination from the transmission items ranked first in the evaluation sequence, and forming a new evaluation sequence; determining a combined optimization value and a combined condition value of the merged combination;

[0047] Set up an optimization coordinate system, where the horizontal axis of the optimization coordinate system is the combination condition value and the vertical axis is the combination optimization value; bring the combination optimization value and the combination condition value corresponding to the initial combination into the combination coordinate system;

[0048] Step SA2: combining the first-ranked transmission item in the evaluation sequence with the merged combination to form a new merged combination and a new evaluation sequence, determining the combined optimization value and the combined condition value of the merged combination; and bringing the combined optimization value and the combined condition value of the merged combination into a new combined coordinate system;

[0049] Step SA3: loop step SA2 until there is no transmission item in the evaluation sequence, and form an optimized combination curve according to each combination coordinate in the optimization coordinate system.

[0050] Furthermore, the combined optimization value formula is:

[0051]

[0052] Wherein: UH is the combined optimization value; Ti is the optimization duration of the corresponding transmission item in the combined combination, i=1, 2, ..., n, and n is the number of transmission items in the combined combination.

[0053] Furthermore, the formula for the combined condition value is:

[0054] ZT=ZT′+ZO;

[0055] Wherein: ZT is the combination condition value of the current merged combination; ZT′ is the condition combination value of the previous merged combination; ZO is the newly added combination value, and the newly added combination value is obtained by converting the newly added mode value of the current merged combination according to the preset conversion method.

[0056] The optimization management module is used to optimize the management of the graphic model optimization items, and display the optimization combination curve of the graphic model optimization items to the corresponding management personnel. The management personnel determine the graphic model optimization items to be optimized and optimize the corresponding graphic model optimization items.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] Through the mutual cooperation between the application analysis module, the optimization analysis module and the optimization management module, the continuous optimization of the graph data management is achieved, the distribution network graph data is updated in time, and the potential safety hazards caused by data lag are avoided. This helps to reduce power grid failures caused by inaccurate or inconsistent data, thereby enhancing the safety and stability of the power grid. For frequent and complex adjustments such as the household side, the present invention facilitates the simplification of the data update process through automation and intelligent means; improves the efficiency and accuracy of data updates; at the same time, the implementation of the present invention helps to promote the construction and development of smart grids. By providing real-time and accurate distribution network graph data, it provides strong support for the dispatching, control, optimization, etc. of smart grids, and helps to realize the intelligent, automated and efficient operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] 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 only 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.

[0060] Figure 1 This is a principle block diagram of the present invention. DETAILED DESCRIPTION

[0061] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. 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 creative work are within the scope of protection of the present invention.

[0062] like Figure 1 As shown, a distribution network diagram data intelligent management system includes an application analysis module, an optimization analysis module and an optimization management module;

[0063] The application analysis module is used to analyze the application records of the application model data and determine each model optimization item. The model optimization item is the data item that needs to be optimized for model data transmission, such as the data item corresponding to the process from completion of the adjustment to entry into the model management system for the adjustment of the electric meter of the new residents in the jurisdiction.

[0064] In one embodiment, the graphic model optimization items can be determined based on existing technologies, such as directly set by feedback from the staff of the corresponding application end; the application end is the system, platform, etc. that has the corresponding graphic model data of the application; it is also possible to establish a corresponding intelligent model based on the existing intelligent algorithm to analyze the application records and determine the graphic model optimization items that meet the requirements.

[0065] In one embodiment, a method for determining a graph optimization item includes:

[0066] Connect to each application terminal and obtain each application record in real time. The application record includes application model data, application result data, usage data and other related data. The application result includes normal application, application abnormality, abnormal reason, abnormal loss, etc., that is, the corresponding application model data fails to achieve or meet the corresponding application purpose. It may be due to the model data or other reasons. Therefore, the corresponding abnormal reasons are supplemented, such as abnormalities caused by untimely update of model data and abnormalities caused by model data errors. Because the corresponding results are already available, the corresponding comprehensive application result data can be directly obtained;

[0067] Set the requirements for determining the graph model optimization items, that is, mark the abnormal situations caused by the untimely update of graph model data as optimization item definitions;

[0068] Establishing an identification and judgment model, wherein the identification and judgment model is used to analyze each application record according to the optimization item definition, determine whether the application record meets the optimization item definition, and when it is determined that the optimization item definition is met, determine the data item corresponding to the application record and mark it as a candidate item;

[0069] Through the identification and judgment model, each application record and optimization item definition are analyzed to determine each candidate item, and the corresponding application records are classified according to each candidate item to obtain the candidate analysis data corresponding to each candidate item; because each application record is analyzed, there may be a situation where multiple application records correspond to the same candidate item;

[0070] Determine the candidate probability and candidate value of the corresponding candidate item according to the candidate analysis data. The candidate probability refers to the probability of the data item becoming a candidate item, which is determined by comparing the number of candidate analysis data with the total number corresponding to the data item; the candidate value is set according to the loss of the candidate item, such as using the average value, mode, etc. to set the candidate value, or the staff can directly preset the candidate value of each data item and perform matching later;

[0071] The optimization value of the corresponding candidate item is calculated according to the optimization formula, and the optimization formula is:

[0072] YB=DZ×(e μ -1);

[0073] In the formula: YB is the optimized value; DZ is the candidate value; μ is the candidate probability; e is the natural constant;

[0074] The platform sets the threshold X1 according to user needs. That is, it is considered as a graph optimization item only when it exceeds the threshold X1. It is set by technical personnel in this field according to actual conditions or obtained by large-scale data simulation. If it is not set, the threshold X1 can be defaulted to 0.

[0075] The candidate items whose optimization values ​​are greater than the threshold X1 are marked as graph model optimization items.

[0076] In one embodiment, the identification and judgment model can be established based on the existing identification and judgment technology, and can implement the corresponding identification and judgment. It mainly compares the application result data in the application record with the optimization item definition. Normal applications do not need to be analyzed, and abnormal applications and corresponding abnormal causes are analyzed.

[0077] In one embodiment, the expression of the recognition judgment model is:

[0078]

[0079] Where: (s, Y) is the input data, s is the application record; Y is the optimization item definition; s→Y means that the corresponding application record meets the optimization item definition, and the judgment is made according to the corresponding abnormal application and the abnormal cause; the output data is the identification judgment value YA(s, Y), and the identification judgment value is 1 or 0.

[0080] When the recognition judgment value is 1, the data item of the corresponding application record is marked as a pending item;

[0081] When the recognition judgment value is 0, no corresponding operation is performed.

[0082] The optimization analysis module is used to optimize and analyze the diagram optimization items, identify the diagram optimization items, obtain data related to the diagram data transmission process corresponding to the diagram optimization items, and mark them as diagram process-related data, such as the transmission process and the transmission method and equipment of each transmission node; if the electrician uses the corresponding mobile phone program to enter the updated diagram data, the corresponding department will review and approve it step by step through the corresponding method, and after the approval is qualified, it will be transmitted to the distribution network diagram data management system;

[0083] Generate a graph model process information graph of the graph model optimization item according to the graph model process association data, the graph model process information graph is used to represent its transmission process, transmission nodes, transmission methods, used equipment and other related information; identify the various transmission items of the graph model optimization item that can optimize and shorten the transmission time, such as process optimization, transmission method optimization, use of more efficient equipment, etc. according to the graph model process information graph; use existing technology to identify and determine each transmission item;

[0084] Analyze each transmission item and determine a benchmark optimization method for each transmission item; determine an evaluation order for each transmission item based on each benchmark optimization method;

[0085] Perform optimization analysis according to the evaluation sequence to form an optimization combination curve.

[0086] In one embodiment, a baseline optimization method for a transmission item can be determined based on existing methods, such as establishing an optimization analysis model based on a neural network such as a CNN network or a DNN network, manually establishing a corresponding training set for training, and analyzing the corresponding transmission item through the optimization analysis model after successful training to obtain the most likely optimization method for the current transmission item if an optimization adjustment is performed, and marking the optimization method as a baseline optimization method; the baseline optimization method can also be directly specified manually.

[0087] In one embodiment, a method for determining a baseline optimization mode for a transmission item includes:

[0088] The platform pre-sets the benchmark time consumption of each possible transmission item, that is, the normal usage time of the transmission item, and integrates and establishes a detailed transmission time consumption table;

[0089] Match the benchmark time consumption of each transmission item according to the transmission time consumption details table; determine the actual time consumption of each transmission item according to historical data and mark it as historical time consumption;

[0090] The time consumption ratio of the corresponding transmission item is calculated according to the ratio formula. The ratio formula is:

[0091] BZ=LZ÷HZ;

[0092] In the formula: BZ is the time consumption ratio; HZ is the benchmark time consumption; LZ is the historical time consumption;

[0093] When the time consumption ratio is not greater than 1, no optimization is required, that is, the baseline optimization method is none;

[0094] When the time consumption ratio is greater than 1, determine the optional optimization method, and determine the benchmark optimization method based on the shortened proportion of the predicted time consumption of the optional optimization method and the time consumption ratio. That is, the shortened duration ratio must be no less than the duration ratio that exceeds 1, and the closest one is used as the benchmark optimization method; or directly use the optimization method with the duration closest to the benchmark duration as the benchmark optimization method.

[0095] In one embodiment, a method for determining a baseline optimization mode for a transmission item includes:

[0096] Determine the optional optimization methods of the transmission item and mark them as the optimization methods to be selected. For example, use big data and other methods to determine various applicable transmission methods of the transmission item, identify their corresponding time consumption, and then compare and determine the optimization methods to be selected.

[0097] Estimate the optimization cost and optimization difficulty value corresponding to each candidate optimization method. The optimization cost can be estimated based on the prior art; the optimization difficulty value is set according to the implementation difficulty of adjusting from the existing to the candidate optimization method, and then the corresponding difficulty quantification is performed to obtain the optimization difficulty value. For example, the platform can preset different optimization difficulty standards and corresponding optimization difficulty values, and then perform an optimization difficulty similarity match to determine the corresponding optimization difficulty value. It is also possible to preset the value range of the optimization difficulty value, preset different standards, and calculate the optimization difficulty values of different candidate optimization methods in combination with interpolation methods, etc. It is also possible to evaluate the optimization difficulty value based on other existing methods, such as using a neural network or the like to establish a difficulty evaluation model, and training through an artificial method to establish a corresponding training set. The training set includes input data and output data. The input data is the candidate optimization method and the existing corresponding transmission method; the output data is the optimization difficulty value; and analysis is performed through the difficulty evaluation model after successful training.

[0098] Identify the optimization duration of each candidate optimization method, that is, estimate the shortened duration.

[0099] Remove the dimension and take its numerical value for calculation. Calculate the method value of the corresponding candidate optimization method according to the first formula. The first formula is:

[0100]

[0101] In the formula: WA is the method value; b1 and b2 are both proportionality coefficients, and the value range is 0 < b1 < 1, 0 < b2 < 1; NB is the optimization difficulty value; CB is the optimization cost.

[0102] Set the corresponding candidate coordinates for the candidate optimization method according to the method value and the optimization duration, that is, the horizontal axis is the method value and the vertical axis is the optimization duration; input each candidate coordinate into the coordinate system, and form a candidate analysis curve according to each candidate coordinate.

[0103] Calculate the slope of the candidate analysis curve at each candidate coordinate, and mark it as the candidate analysis value; select the candidate optimization method corresponding to the candidate coordinate with the largest candidate analysis value as the reference optimization method.

[0104] In one embodiment, the method for determining the evaluation order of each transmission item according to each reference optimization method includes:

[0105] Calculate the method value of each reference optimization method according to the method value calculation method in the above embodiment; identify the optimization duration of the reference optimization method.

[0106] Calculate the priority value of the corresponding transmission item according to the priority formula. The priority formula is:

[0107] WY = T÷(WA + 1);

[0108] Where: WY is the priority value; T is the optimization duration; WA is the mode value;

[0109] The evaluation order of the corresponding transmission items is determined according to the order of the priority values.

[0110] In one embodiment, the method for performing optimization analysis according to the evaluation order includes:

[0111] Step SA1: Generate an evaluation sequence according to the evaluation order; form a merged combination from the transmission items ranked first in the evaluation sequence, remove the combined transmission items from the evaluation sequence, and form a new evaluation sequence; that is, initially one transmission item forms a merged combination; determine the combined optimization value and the combined condition value of the merged combination;

[0112] The combined optimization value is the sum of the optimized durations of each transmission item in the combination; that is, the combined optimization value formula is:

[0113]

[0114] Where: UH is the combined optimization value; Ti is the optimization duration of the corresponding transmission item in the corresponding combined combination, i = 1, 2, ..., n, n is the number of transmission items in the combined combination;

[0115] The combination condition value is set according to the mode value added again compared with the previous combination. The platform party presets the horizontal axis increase range corresponding to different newly added mode values. As the mode value increases, the horizontal axis range corresponding to the same unit mode value increases. For example, 1 mode value corresponds to 1 horizontal axis unit length in the previous period. As the mode value increases, 1 mode value corresponds to 5 horizontal axis unit lengths. The platform party presets the combination adjustment value corresponding to different mode values, and can also set the corresponding magnification coefficient according to different mode value intervals, so as to determine the corresponding combination condition value. The combination condition value is the previous combination condition value plus the number of unit lengths corresponding to the newly added mode value; it can be expressed as:

[0116] ZT=ZT′+ZO;

[0117] Where: ZT is the combination condition value of the current combination, ZT′ is the condition combination value of the previous combination, and ZO is the added condition combination value determined according to the newly added mode value;

[0118] That is, it is necessary to first determine the newly added method value, convert the method value according to the conversion method preset by the platform, obtain the newly added combination value, add it to the conditional combination value of the previous combination to obtain the conditional combination value of the current merged combination.

[0119] Set the optimization coordinate system, the horizontal axis of the optimization coordinate system is the combination condition value, and the vertical axis is the combination optimization value;

[0120] The combined optimization value and the combined condition value corresponding to the merged combination are formed into a combined coordinate and brought into the optimization coordinate system;

[0121] Step SA2: Combine the first-ranked transmission item in the evaluation sequence with the merged combination to form a new merged combination and a new evaluation sequence, determine the combined optimization value and combined condition value of the new merged combination; form a new combined coordinate with the combined optimization value and combined condition value corresponding to the new merged combination and bring it into the optimization coordinate system;

[0122] Step SA3: loop step SA2 until there is no transmission item in the evaluation sequence, and form an optimized combination curve according to each combination coordinate in the optimization coordinate system.

[0123] The optimization management module is used to optimize the management of the graphic model optimization items, and display the optimization combination curve of each graphic model optimization item to the corresponding management personnel. The management personnel determine the graphic model optimization items to be optimized and optimize the corresponding graphic model optimization items.

[0124] In one embodiment, the recommended points can be marked in the optimization combination curve, such as determining the minimum duration that needs to be shortened based on application records, determining the minimum combination optimization value, marking the optimization combination curve based on the minimum combination optimization value, and selecting the coordinate point with the largest slope from the curve segment that meets the requirements as the recommended point.

[0125] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0126] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A distribution network model data intelligent management system, characterized in that: Including application analysis module, optimization analysis module and optimization management module; The application analysis module is used to perform application analysis on the image model data and determine the image model optimization items, wherein the image model optimization items are data items that need to be optimized for image model data transmission; The optimization analysis module is used to optimize and analyze the image model optimization items, obtain the image model process associated data of the image model optimization items, generate the image model process information graph of the image model optimization items according to the image model process associated data; and identify the transmission items of the image model optimization items according to the image model process information graph; determining a baseline optimization method for the transmission item; Determining an evaluation order of the transmission items according to the benchmark optimization method; Perform optimization analysis according to the evaluation sequence to form an optimization combination curve; The optimization management module is used to optimize the management of the graphic model optimization items, and display the optimization combination curve of the graphic model optimization items to the corresponding management personnel. The management personnel determine the graphic model optimization items to be optimized and optimize the corresponding graphic model optimization items.

2. According to claim 1, a distribution network model data intelligent management system is characterized in that: Methods for determining graph model optimization items include: Acquire application records in real time and set optimization item definitions of graph model optimization items, where the optimization items are defined as data items that cause application abnormalities due to untimely update of graph model data; Establishing an identification and judgment model, analyzing application records and optimization item definitions through the identification and judgment model to determine candidate items; classifying the application records according to the candidate items to obtain candidate analysis data corresponding to the candidate items, wherein the candidate analysis data is composed of application records belonging to the corresponding candidate items; Determine the selection probability and selection value of the candidate item according to the candidate analysis data; calculate the optimization value of the candidate item according to the optimization formula, and the optimization formula is: YB=DZ×(e μ -1); In the formula: YB is the optimized value; DZ is the candidate value; μ is the candidate probability; e is the natural constant; The candidate items whose optimization values ​​are greater than the threshold X1 are marked as graph model optimization items.

3. According to claim 2, a distribution network model data intelligent management system is characterized in that: The expression of the recognition judgment model is: Where: (s, Y) is the input data, s is the application record; Y is the optimization item definition; s→Y means that the corresponding application record meets the optimization item definition; the output data is the identification judgment value YA(s, Y), and the identification judgment value is 1 or 0; When the recognition judgment value is 1, the data item of the corresponding application record is marked as a pending item; When the recognition judgment value is 0, no corresponding operation is performed.

4. The intelligent management system for distribution network model data according to claim 1, characterized in that: Methods for determining a baseline optimization for a transfer item include: The platform establishes a transmission time detail table, which is used to count the benchmark time corresponding to different transmission items; Matching the benchmark time consumption of the transmission item according to the transmission time consumption list; identifying the historical time consumption of the transmission item; The time consumption ratio of the transmission item is calculated according to the ratio formula, and the ratio formula is: BZ=LZ÷HZ; In the formula: BZ is the time consumption ratio; HZ is the benchmark time consumption; LZ is the historical time consumption; When the time consumption ratio is not greater than 1, the benchmark optimization method is none; When the time consumption ratio is greater than 1, a benchmark optimization method is determined according to the time consumption ratio.

5. The intelligent management system for distribution network image data according to claim 1 is characterized in that: Methods for determining a baseline optimization for a transfer item include: Determine a candidate optimization method for the transmission item; identify the optimization duration of the candidate optimization method; Estimate the optimization cost and optimization difficulty value corresponding to the to-be-selected optimization method; Calculate the method value of the to-be-selected optimization method according to the first formula, and the first formula is: In the formula: WA is the method value; b1 and b2 are both proportionality coefficients, and the value ranges are 0 < b1 < 1, 0 < b2 < 1; NB is the optimization difficulty value; CB is the optimization cost; Form a to-be-selected coordinate based on the method value and optimization duration of the to-be-selected optimization method; input the to-be-selected coordinate into the coordinate system, and form a to-be-selected analysis curve according to the to-be-selected coordinate; Calculate the slope of the to-be-selected analysis curve at the to-be-selected coordinate, marked as the to-be-selected analysis value; determine the benchmark optimization method according to the to-be-selected analysis value.

6. The intelligent management system for distribution network image data according to claim 1, characterized in that: The method for determining the evaluation order of the corresponding transmission item according to the benchmark optimization method includes: Calculate the method value of the benchmark optimization method and identify the optimization duration of the benchmark optimization method; Calculate the priority value of the transmission item according to the priority formula, and the priority formula is: WY = T ÷ (WA + 1); In the formula: WY is the priority value; T is the optimization duration; WA is the method value; Determine the evaluation order of the transmission item according to the magnitude order of the priority value.

7. The intelligent management system for distribution network image data according to claim 1 is characterized in that: The method for performing optimization analysis according to the evaluation order includes: Step SA1: Generate an evaluation sequence according to the evaluation order; form a merged combination from the transmission item ranked first in the evaluation sequence, and form a new evaluation sequence; determine the combined optimization value and combined condition value of the merged combination; Set up an optimization coordinate system, where the horizontal axis of the optimization coordinate system is the combined condition value and the vertical axis is the combined optimization value; bring the combined optimization value and combined condition value corresponding to the initial combination into the optimization coordinate system as a combined coordinate; Step SA2: Combine the transmission item ranked first in the evaluation sequence with the merged combination to form a new merged combination and a new evaluation sequence, and determine the combined optimization value and combined condition value of the merged combination; bring the combined optimization value and combined condition value of the merged combination into the optimization coordinate system as a new combined coordinate; Step SA3: Loop step SA2 until there are no transmission items in the evaluation sequence, and form an optimization combination curve according to each combined coordinate in the optimization coordinate system.

8. The intelligent management system for distribution network image data according to claim 7 is characterized in that: The combined optimization value formula is: In the formula: UH is the combined optimization value; Ti is the optimization duration of the corresponding transmission item in the merged combination, i = 1, 2,..., n, and n is the number of transmission items in the merged combination.

9. The intelligent management system for distribution network image data according to claim 7, characterized in that: The combined condition value formula is: ZT = ZT′ + ZO; In the formula: ZT is the combined condition value of the current merged combination; ZT′ is the condition combination value of the previous merged combination, and ZO is obtained by transforming the method value newly added to the current merged combination according to a preset transformation method for the newly added combination value.

Images