Intelligent supervision system and method for distribution network project review

Abstract

The invention belongs to the technical field of power grid supervision, and discloses an intelligent supervision system and method for distribution network project review, and the system comprises a business expansion project receiving module, a data processing module, a project analysis module and an information output module. The method comprises the following steps: determining key project information of a distribution network project, then obtaining a corresponding analogy project based on the key project information, calculating a key coefficient of field investigation data according to the investigation series of the field investigation data in the analogy project, and determining key collection data based on the key coefficient of the field investigation data; and then the key collection data is transmitted to the terminal equipment of the field personnel, and the field personnel check the key collection data through the terminal equipment, so that the completion degree of the field personnel for one-time collection of the field investigation data is improved, the distribution network project review efficiency is improved, and the project review period is accelerated.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grid supervision, and in particular relates to an intelligent supervision system and method for distribution network project review. Background Art

[0002] When reviewing distribution network projects, it is necessary not only to focus on evaluating and reviewing the materials submitted by the customer, but also to allocate corresponding human resources to conduct real-time inspections and data collection on the customer's site. Only then can the distribution network project be fully evaluated. However, since each customer's project is not exactly the same, if the distribution network staff only collects on-site data based on their work experience, subjective influences may cause on-site data to be missed, and the distribution network staff will need to go back to the site to collect additional data. This process will delay the progress of the distribution network project review, thereby reducing overall work efficiency. Summary of the invention

[0003] The purpose of the present invention is to solve the deficiencies in the prior art and to provide an intelligent supervision system and method for distribution network project review.

[0004] In order to achieve the above object, the present invention is achieved through the following technical solutions:

[0005] In a first aspect, the present invention provides a distribution network project review intelligent supervision system, including a business expansion project receiving module, a data processing module, a project analysis module and an information output module;

[0006] The business expansion project receiving module is used to receive application information for distribution network project review and transmit it to the data processing module, wherein the application information includes basic information and application materials;

[0007] The data processing module is used to extract key data from the application materials based on the basic information to obtain key project information, and the data processing module transmits the key project information to the project analysis module;

[0008] The project analysis module is used to obtain information matching objects based on basic information, and then perform information similarity processing on key project information and information matching objects to obtain analog projects, extract field survey data in the analog projects, and set survey levels for field survey data according to the number of collection times by power grid staff, and then integrate the field survey data in all analog projects to obtain a level set of field survey data, process the level frequency of each survey level in the level set, and finally obtain the key coefficient of the field survey data, determine the key collection data according to the key coefficient of the field survey data, and transmit the key collection data to the information output module by the project analysis module;

[0009] The information output module is used to transmit the key collected data to the terminal equipment of the on-site personnel for viewing by the on-site personnel.

[0010] Preferably, the data processing module is used to extract key data from the application materials based on the basic information to obtain key project information, specifically:

[0011] Using basic information as information keywords, natural language processing technology is used to extract key data from the application materials, and the extracted key data is marked as key project information.

[0012] Preferably, the project analysis module is used to obtain information matching objects according to basic information, and then perform information similarity processing on key project information and information matching objects to obtain analogous projects, specifically:

[0013] Extract basic information and use it as information retrieval conditions to perform data retrieval in the cloud platform to determine information matching objects;

[0014] The bag-of-words model algorithm is used to convert the information matching object and the key project information into a data vector, and then the cosine similarity algorithm is used to calculate the information matching object and the key project information in turn to determine the information similarity value;

[0015] The information similarity value is compared with the similarity threshold X1, and the information matching objects corresponding to the information similarity value greater than or equal to the similarity threshold X1 are taken and marked as analogy items.

[0016] Preferably, the field survey data in the analogous project is extracted, and the survey level is set for the field survey data according to the number of collection times by the power grid staff. Then, the field survey data in all analogous projects are integrated to obtain a level set of the field survey data. The level frequency of each survey level in the level set is processed to finally obtain the key coefficient of the field survey data. According to the key coefficient of the field survey data, the key collection data is determined, specifically:

[0017] Extract the field survey data from the analogy project, divide the field survey data according to the number of times the grid staff collected the data, and mark them as survey levels;

[0018] Extract the field survey data from all category projects, merge the same field survey data, and obtain the survey levels corresponding to the same field survey data, and use the survey levels as elements to form a level set;

[0019] Select a set of levels of field survey data as the target set, and obtain the number of levels Dj of each survey level in the target set, where j represents the survey level; use the formula The series frequency Fj is obtained, and DZ represents the total number of elements in the target set;

[0020] Using the formula Calculate the focus coefficient Gf of the target data, where the target data is the field survey data corresponding to the target set, βj represents the weight factor of the survey level, and βj-1<βj; m is the total number of survey levels;

[0021] Process the series set of all the field survey data according to the above steps to obtain the key coefficient Gf of all the field survey data;

[0022] The focus coefficient Gf of the field survey data is compared with the data threshold Gy. If Gf>Gy, the corresponding field survey data is marked as key collection data. If Gf≤Gy, the corresponding field survey data is marked as regular data.

[0023] Preferably, the survey levels include a first level, a second level and a third level, the first level refers to the field survey data directly collected after one field survey by the power grid staff, the second level refers to the field survey data collected after two field surveys by the power grid staff, and the third level refers to the field survey data collected after three or more field surveys by the power grid staff.

[0024] In a second aspect, the present invention provides a distribution network project review intelligent supervision method, the method comprising the following steps:

[0025] Step 1: Identify and receive the application information for distribution network project review, and extract the basic information in the application information. Use the basic information as information keywords to extract key data from the application materials to obtain key project information;

[0026] Step 2: Use basic information as information retrieval conditions to obtain information matching objects, perform information similarity processing on key project information and information matching objects, and obtain analogous projects;

[0027] Step 3: Extract the field survey data in the analogy project and set the survey level for the field survey data according to the number of collection times by the power grid staff;

[0028] Step 4: Integrate the field survey data in all analogous projects to obtain a series set of field survey data, then process the series frequency of each survey series in the series set, and finally obtain the key coefficient of the field survey data;

[0029] Step 5: Determine the key data to be collected based on the key coefficient of the on-site survey data, then obtain the terminal equipment of the on-site personnel and transmit the key data to the terminal equipment of the on-site personnel.

[0030] Preferably, in step 1, natural language processing technology is used to extract key data from the application materials.

[0031] Preferably, step 2 is specifically as follows: step 2.1, extracting basic information, and using the basic information as information retrieval conditions, performing data retrieval in the cloud platform, and determining information matching objects;

[0032] Step 2.2: Use the bag-of-words model algorithm to convert the information matching object and the key project information into a data vector, and then use the cosine similarity algorithm to calculate the information matching object and the key project information in turn to determine the information similarity value;

[0033] Step 2.3: Compare the information similarity value with the similarity threshold X1, take the information matching objects corresponding to the information similarity value greater than or equal to the similarity threshold X1, and mark them as analogy items.

[0034] Preferably, step 4 is specifically as follows: step 4.1, using formula The series frequency Fj is obtained, Dj represents the series number of each exploration series in the series set, DZ represents the total number of elements in the series set; j represents the exploration series;

[0035] Step 4.2: Use the formula Calculate the focus coefficient Gf of the target data, where the target data is the field survey data corresponding to the survey level, βj represents the weight factor of the survey level, and βj-1<βj;

[0036] Step 4.3: Process the series set of all field investigation data according to steps 4.1 and 4.2 to obtain the key coefficients Gf of all field investigation data.

[0037] Preferably, step 5 specifically includes: setting a data threshold Gy, comparing the focus coefficient with the data threshold Gy, if the focus coefficient > Gy, marking the corresponding field survey data as focus collection data, if the focus coefficient ≤ Gy, marking the corresponding field survey data as regular data.

[0038] The present invention has the following beneficial effects: the present invention determines key project information of the distribution network project by processing the received application information of the distribution network project review, then obtains the corresponding analog project based on the key project information, calculates the key coefficient of the field survey data according to the survey level of the field survey data in the analog project, and determines the key collection data based on the key coefficient of the field survey data, and then transmits the key collection data to the terminal device of the field personnel. The field personnel view the key collection data through the terminal device, thereby improving the completion degree of the field personnel in the one-time collection of the field survey data, thereby improving the distribution network project review efficiency and accelerating the project review cycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A flowchart of a distribution network project review intelligent supervision system;

[0040] Figure 2 The figure is a flow chart of an intelligent supervision method for distribution network project review. DETAILED DESCRIPTION

[0041] The present invention will be further described below in conjunction with the embodiments, but they are not intended to limit the present invention.

[0042] An intelligent supervision system for distribution network project review, comprising:

[0043] The business expansion project receiving module is used to receive the application information of the distribution network project review and transmit it to the data processing module. The application information includes basic information and application materials, such as power demand and power supply plan;

[0044] The data processing module is used to extract key data from the application materials based on the basic information to obtain key project information. At the same time, the data processing module transmits the key project information to the project analysis module;

[0045] Specifically, using basic information as information keywords, natural language processing technology is used to extract key data from the application materials, and the extracted key data is marked as key project information;

[0046] Specifically, we first use a pre-trained named entity recognition model, such as spaCy's en_core_web_sm model, to perform named entity recognition on the text, then use regular expressions to match keywords for the named entities in the application materials to obtain the key data of each named entity, and finally integrate and output the information, where the named entity is the basic information;

[0047] The project analysis module is used to obtain information matching objects based on basic information, and then perform information similarity processing on key project information and information matching objects to obtain analog projects, extract field survey data in the analog projects, and set survey levels for field survey data according to the number of collection times by power grid staff. After that, the field survey data in all analog projects are integrated to obtain a level set of field survey data, and the level frequency of each survey level in the level set is processed to finally obtain the key coefficient of the field survey data. According to the key coefficient of the field survey data, the key collection data is determined, and the project analysis module transmits the key collection data to the information output module;

[0048] Specifically, 1. Extract basic information and use the basic information as information retrieval conditions to perform data retrieval in the cloud platform to determine the information matching object, which is shared by the cloud platform and the distribution network project review intelligent supervision system;

[0049] 2. Use the bag-of-words model algorithm to convert the information matching object and the key project information into a data vector, and then use the cosine similarity algorithm to calculate the information matching object and the key project information in turn to determine the information similarity value;

[0050] 3. Compare the information similarity value with the similarity threshold X1, select the information matching objects whose information similarity value is greater than or equal to the similarity threshold X1, and mark them as analogy items;

[0051] The field survey data in the analogy project is extracted, and the field survey data is divided according to the number of times the power grid staff collects the data, and marked as survey levels, which include the first level, the second level, and the third level;

[0052] The first level refers to the on-site survey data collected directly after one on-site survey by the power grid staff; the second level refers to the on-site survey data collected after two on-site surveys by the power grid staff; the third level refers to the on-site survey data collected after three or more on-site surveys by the power grid staff;

[0053] 4. Integrate the field survey data: extract the field survey data from all categories of projects, merge the same field survey data, and obtain the survey levels corresponding to the same field survey data. Use the survey levels as elements to form a level set.

[0054] 5. Choose any set of levels of field survey data as the target set, and obtain the number of levels Dj of each survey level in the target set, where j is 1, 2, and 3, representing the first, second, and third levels, respectively; use the formula The series frequency Fj is obtained, and DZ represents the total number of elements in the target set;

[0055] Using the formula Calculate the focus coefficient Gf of the target data, where the target data is the field survey data corresponding to the target set, βj represents the weight factor of the survey level, and β2<β3;

[0056] 6. Process all the series sets of the on-site investigation data according to the above steps to obtain the key coefficients Gf of all the on-site investigation data;

[0057] Compare the focus coefficient Gf of the field survey data with the data threshold Gy. If Gf>Gy, the corresponding field survey data is marked as the focus collection data. If Gf≤Gy, the corresponding field survey data is marked as the regular data.

[0058] The information output module is used to transmit the key collected data to the terminal equipment of the on-site personnel for viewing.

[0059] A distribution network project review intelligent supervision method, the method comprising the following steps:

[0060] Step 1: Identify and receive the application information for distribution network project review, and extract the basic information in the application information. Use the basic information as information keywords to extract key data from the application materials to obtain key project information;

[0061] Step 2: Use the basic information as the information retrieval condition to obtain the information matching object, perform information similarity processing on the key project information and the information matching object, and obtain the analogous project;

[0062] Step 3: Extract the field survey data in the analogy project and set the survey level for the field survey data according to the number of collection times by the power grid staff;

[0063] Step 4: Integrate the field survey data in all analogous projects to obtain a series set of field survey data, then process the series frequency of each survey series in the series set, and finally obtain the key coefficient of the field survey data;

[0064] Step 5: Determine the key data to be collected based on the key coefficient of the on-site survey data, then obtain the terminal equipment of the on-site personnel and transmit the key data to the terminal equipment of the on-site personnel.

[0065] The above shows and describes the basic principles, main features and advantages of the present invention. However, the above is only a specific embodiment of the present invention, and the technical features of the present invention are not limited thereto. Any other implementation methods derived by any technician in the field without departing from the technical solution of the present invention should be included in the patent scope of the present invention.

Claims

1. An intelligent supervision system for distribution network project review, characterized in that: It includes business expansion project receiving module, data processing module, project analysis module and information output module; The business expansion project receiving module is used to receive application information for distribution network project review and transmit it to the data processing module, wherein the application information includes basic information and application materials; The data processing module is used to extract key data from the application materials based on the basic information to obtain key project information, and the data processing module transmits the key project information to the project analysis module; The project analysis module is used to obtain information matching objects based on basic information, and then perform information similarity processing on key project information and information matching objects to obtain analog projects, extract field survey data in the analog projects, and set survey levels for field survey data according to the number of collection times by power grid staff, and then integrate the field survey data in all analog projects to obtain a level set of field survey data, process the level frequency of each survey level in the level set, and finally obtain the key coefficient of the field survey data, determine the key collection data according to the key coefficient of the field survey data, and transmit the key collection data to the information output module by the project analysis module; The information output module is used to transmit the key collected data to the terminal equipment of the on-site personnel for viewing by the on-site personnel.

2. The intelligent supervision system for distribution network project review according to claim 1 is characterized in that: The data processing module is used to extract key data from the application materials based on the basic information to obtain key project information, specifically: Using basic information as information keywords, natural language processing technology is used to extract key data from the application materials, and the extracted key data is marked as key project information.

3. The intelligent supervision system for distribution network project review according to claim 1 is characterized in that: The project analysis module is used to obtain information matching objects based on basic information, and then perform information similarity processing between key project information and information matching objects to obtain analogous projects, specifically: Extract basic information and use it as information retrieval conditions to search data in the cloud platform and determine information matching objects; The bag-of-words model algorithm is used to convert the information matching object and the key project information into a data vector, and then the cosine similarity algorithm is used to calculate the information matching object and the key project information in turn to determine the information similarity value; The information similarity value is compared with the similarity threshold X1, and the information matching objects corresponding to the information similarity value greater than or equal to the similarity threshold X1 are taken and marked as analogy items.

4. The intelligent supervision system for distribution network project review according to claim 1 is characterized in that: The field survey data in the analogy project are extracted, and the survey level is set for the field survey data according to the number of collection times by the power grid staff. Then the field survey data in all analogy projects are integrated to obtain a level set of field survey data. The level frequency of each survey level in the level set is processed to finally obtain the key coefficient of the field survey data. According to the key coefficient of the field survey data, the key collection data is determined, specifically: Extract the field survey data from the analogy project, divide the field survey data according to the number of times the grid staff collected the data, and mark them as survey levels; Extract the field survey data from all category projects, merge the same field survey data, and obtain the survey levels corresponding to the same field survey data, and use the survey levels as elements to form a level set; Select a set of levels of field survey data as the target set, and obtain the number of levels Dj of each survey level in the target set, where j represents the survey level; use the formula The series frequency Fj is obtained, and DZ represents the total number of elements in the target set; Using the formula Calculate the focus coefficient Gf of the target data, where the target data is the field survey data corresponding to the target set, βj represents the weight factor of the survey level, and βj-1<βj; m is the total number of survey levels; Process the series set of all the field survey data according to the above steps to obtain the key coefficient Gf of all the field survey data; The focus coefficient Gf of the field survey data is compared with the data threshold Gy. If Gf>Gy, the corresponding field survey data is marked as key collection data. If Gf≤Gy, the corresponding field survey data is marked as regular data.

5. The intelligent supervision system for distribution network project review according to claim 6 is characterized in that: The survey levels include the first level, the second level and the third level. The first level refers to the on-site survey data directly collected after one on-site survey by the power grid staff, the second level refers to the on-site survey data collected after two on-site surveys by the power grid staff, and the third level refers to the on-site survey data collected after three or more on-site surveys by the power grid staff.

6. A method for intelligent supervision of distribution network project review is implemented using the system described in any one of claims 1 to 5, characterized in that: The method comprises the following steps: Step 1: Identify and receive the application information for distribution network project review, and extract the basic information in the application information. Use the basic information as information keywords to extract key data from the application materials to obtain key project information; Step 2: Use basic information as information retrieval conditions to obtain information matching objects, perform information similarity processing on key project information and information matching objects, and obtain analogous projects; Step 3: Extract the field survey data in the analogy project and set the survey level for the field survey data according to the number of collection times by the power grid staff; Step 4: Integrate the field survey data in all analogous projects to obtain a series set of field survey data, then process the series frequency of each survey series in the series set, and finally obtain the key coefficient of the field survey data; Step 5: Determine the key data to be collected based on the key coefficient of the on-site survey data, then obtain the terminal equipment of the on-site personnel and transmit the key data to the terminal equipment of the on-site personnel.

7. The intelligent supervision method for distribution network project review according to claim 6 is characterized in that: In step 1, natural language processing technology is used to extract key data from the application materials.

8. The intelligent supervision method for distribution network project review according to claim 6 is characterized in that: Step 2 is as follows: Step 2.1, extract basic information, and use the basic information as information retrieval conditions, perform data retrieval in the cloud platform, and determine the information matching object; Step 2.2: Use the bag-of-words model algorithm to convert the information matching object and the key project information into a data vector, and then use the cosine similarity algorithm to calculate the information matching object and the key project information in turn to determine the information similarity value; Step 2.3: Compare the information similarity value with the similarity threshold X1, take the information matching objects corresponding to the information similarity value greater than or equal to the similarity threshold X1, and mark them as analogy items.

9. The intelligent supervision method for distribution network project review according to claim 6 is characterized in that: Step 4 is as follows: Step 4.1: Use the formula The series frequency Fj is obtained, Dj represents the series number of each exploration series in the series set, DZ represents the total number of elements in the series set; j represents the exploration series; Step 4.2: Use the formula Calculate the focus coefficient Gf of the target data, where the target data is the field survey data corresponding to the survey level, βj represents the weight factor of the survey level, and βj-1<βj; Step 4.3: Process the series set of all field investigation data according to steps 4.1 and 4.2 to obtain the key coefficients Gf of all field investigation data.

10. The intelligent supervision method for distribution network project review according to claim 6 is characterized in that: Step 5 is as follows: The data threshold Gy is set, and the focus coefficient is compared with the data threshold Gy. If the focus coefficient is greater than Gy, the corresponding on-site investigation data is marked as key collection data. If the focus coefficient is less than or equal to Gy, the corresponding on-site investigation data is marked as regular data.

Images