Natural gas user portrait construction method and device, equipment and medium

Abstract

The invention provides a natural gas user portrait construction method and device, equipment and a medium. The method comprises the steps of obtaining target basic information data, target consumption data and target behavior characteristic data of a natural gas user; establishing a user index system of the natural gas user portrait from the basic information dimension, the consumption dimension and the behavior dimension; on the basis of the target basic information data, the target consumption data and the target behavior characteristic data, index calculation of the natural gas user under the user index system is carried out, and index data under each label dimension is obtained; and generating a user portrait of the natural gas user in multiple dimensions by using the index data in each label dimension. According to the method and the device, the gas consumption characteristics of the users in the natural gas market are mainly used, the users are described in multiple aspects by utilizing different label extraction modes, and the original information of the users is fully mined and processed.

Description

Technical Field

[0001] The present application relates to the technical field of user portraits, and in particular to a method, device, equipment and medium for constructing a natural gas user portrait. Background Art

[0002] User portrait is a collection of personal information extracted from the aggregation of user behavior data, basic data, consumption data, etc. Its connotation mainly includes three factors, namely the attributes of the user, the characteristics of the user, and the label that can represent the user. The main significance of user portrait is to use specific user portraits to depict the preferences of individual users or groups of users, thus becoming an important means and tool for corporate market development and expansion of marketing scale. With the advent of the big data era, the massive user information generated by various information websites and platforms further provides data support for the construction of user portraits. User portraits have been actively promoted in many fields such as e-commerce recommendations, medical health, library management, hotel management, etc. Some industrial industries (such as electricity, new energy, etc.) have also begun to use user portraits to solve production and operation problems.

[0003] In the field of natural gas, user portraits can be used to describe the user's gas usage characteristics, credit profile, financial characteristics, development potential, etc., so as to understand the differentiated needs of users and display three-dimensional users in an all-round way. The traditional classification of natural gas users by gas companies is based on industry types, such as chemical users, power generation users, urban gas users, LNG users, etc. With the rise of intelligent algorithms, some scholars have begun to use spectral clustering, k-means clustering, GMM clustering and other models to complete the segmentation of gas users, and use clustering results to guide marketing.

[0004] In general, the current user characteristics analysis methods in the natural gas field are often mechanical and static. When conducting characteristic analysis, companies generally use traditional industry classification to study the consumption characteristics of different users, or characterize the overall attributes of group users based on certain characteristics (gas consumption level, gas purchase price, etc.). Therefore, the precise characterization of individual users is not sufficient during the research process, resulting in a lack of decisive user demand and preference guidance for natural gas sales companies when formulating market development and marketing strategies, making it difficult to form accurate user sales plans. Summary of the invention

[0005] In view of this, the purpose of this application is to provide a method, device, equipment and medium for constructing a natural gas user portrait, which is based on the gas usage characteristics of natural gas market users, uses different label extraction methods to describe users in many aspects, and fully mines and processes the original information of users. It can improve the problems of single classification and static classification of users in the natural gas sales market, provide portrait support for scenario analysis guided by the needs of natural gas users, and help enterprises further improve their differentiated service capabilities.

[0006] In a first aspect, an embodiment of the present application provides a method for constructing a natural gas user portrait, the method comprising:

[0007] Obtaining original basic information data, original consumption data, and original behavior characteristic data of natural gas users, and performing data preprocessing to obtain target basic information data, target consumption data, and target behavior characteristic data;

[0008] Establish a user index system for natural gas user portraits from the dimensions of basic information, consumption, and behavior;

[0009] Based on the target basic information data, the target consumption data and the target behavior characteristic data, the index of the natural gas user under the user index system is calculated to obtain the index data under each label dimension;

[0010] The indicator data under each label dimension is used to generate a user portrait of the natural gas user in multiple dimensions.

[0011] Furthermore, the indicator data under the basic information dimension includes user name, gas consumption area, gas consumption pipeline set, gas consumption station set, user value and user value label;

[0012] The indicator data under the consumption dimension include annual gas consumption, annual gas consumption label, annual gas consumption growth rate label, quarterly gas consumption proportion label, quarterly gas consumption growth rate label, monthly gas consumption proportion label and monthly gas consumption growth rate label;

[0013] The indicator data under the behavior dimension include plan compliance rate and reduction data. The plan compliance rate includes annual average compliance rate, monthly average compliance rate and plan compliance degree. The reduction data includes maximum reduction rate, average reduction rate, proportion of reduction days, reduction frequency and reduction degree.

[0014] Furthermore, the indicator data under the basic information dimension is calculated by the following steps:

[0015] Acquire the user name and the gas consumption area from the target basic information data;

[0016] Acquire multiple route pipeline information and multiple route station field information corresponding to the natural gas user from the target basic information data, merge multiple route pipeline information to obtain the gas route pipeline set, and merge multiple route station field information to obtain the gas route station field set;

[0017] Determine the time interval between the last consumption of the natural gas user, the consumption frequency and the consumption amount within a preset time period from the target consumption data;

[0018] Calculate the user value of the natural gas user based on the most recent consumption time interval, the consumption frequency and the consumption amount;

[0019] The preset corresponding relationship of the labels is utilized to determine the user value label of the natural gas user based on the time interval of the most recent consumption, the consumption frequency and the consumption amount.

[0020] Furthermore, the indicator data under the consumption dimension is calculated through the following steps:

[0021] Obtaining the current annual gas consumption and the historical annual gas consumption of the natural gas user from the target consumption data, and calculating the annual gas consumption growth rate of the natural gas user based on the current annual gas consumption and the historical annual gas consumption;

[0022] Based on the current annual gas consumption and the annual gas consumption growth rate, using a k-means clustering algorithm to obtain an annual gas consumption label and an annual gas consumption growth rate label of the natural gas user;

[0023] Obtaining the current quarterly gas consumption, historical quarterly gas consumption, current monthly gas consumption and historical monthly gas consumption of the natural gas user from the target consumption data;

[0024] Calculate the quarterly gas consumption ratio of the natural gas user based on the current quarterly gas consumption and the current annual gas consumption, and calculate the monthly gas consumption ratio of the natural gas user based on the current monthly gas consumption and the current annual gas consumption;

[0025] Calculating the quarterly gas consumption growth rate of the natural gas user based on the current quarterly gas consumption and the historical quarterly gas consumption, and calculating the monthly gas consumption growth rate of the natural gas user based on the current monthly gas consumption and the historical monthly gas consumption;

[0026] Based on the quarterly gas consumption proportion and the quarterly gas consumption growth rate, a k-means clustering algorithm is used to obtain the quarterly gas consumption proportion label and the quarterly gas consumption growth rate label of the natural gas user;

[0027] Based on the monthly gas consumption proportion and the monthly gas consumption growth rate, a k-means clustering algorithm is used to obtain a monthly gas consumption proportion label and a monthly gas consumption growth rate label of the natural gas user.

[0028] Furthermore, the indicator data under the behavior dimension is calculated by the following steps:

[0029] Obtaining the daily demand reporting amount, actual daily completion amount and daily approval difference of the natural gas user from the target behavior characteristic data;

[0030] Calculate the daily plan compliance rate of the natural gas user based on the daily demand report and the daily actual daily completion volume;

[0031] Calculate the annual average compliance rate and monthly average compliance rate of the natural gas users based on the daily planned compliance rate;

[0032] Determine the plan compliance degree of the natural gas user based on the monthly average compliance rate by using the preset corresponding relationship of the compliance degree;

[0033] Calculate the daily reduction rate of the natural gas user based on the daily approved difference and the daily demand reported amount;

[0034] Determine the average compression reduction rate, the maximum compression reduction rate and the proportion of compression reduction days of the natural gas user based on the daily compression reduction rate;

[0035] Determine the compression reduction frequency of the natural gas user based on the compression reduction days ratio by using the preset corresponding relationship of the compression reduction frequency;

[0036] The preset corresponding relationship of the compression reduction degree is utilized, and the compression reduction degree of the natural gas user is determined based on the average compression reduction rate.

[0037] In a second aspect, the embodiment of the present application further provides a device for constructing a natural gas user portrait, the device comprising:

[0038] The data acquisition module is used to acquire the original basic information data, original consumption data and original behavior characteristic data of the natural gas user, and perform data preprocessing to obtain the target basic information data, target consumption data and target behavior characteristic data;

[0039] The indicator system establishment module is used to establish a user indicator system for natural gas user portraits from the dimensions of basic information, consumption, and behavior;

[0040] An indicator data calculation module, used to calculate the indicator of the natural gas user under the user indicator system based on the target basic information data, the target consumption data and the target behavior characteristic data, and obtain the indicator data under each label dimension;

[0041] The user image generation module is used to generate a user portrait of the natural gas user in multiple dimensions by using the indicator data in each label dimension.

[0042] Furthermore, the indicator data under the basic information dimension includes user name, gas consumption area, gas consumption pipeline set, gas consumption station set, user value and user value label;

[0043] The indicator data under the consumption dimension include annual gas consumption, annual gas consumption label, annual gas consumption growth rate label, quarterly gas consumption proportion label, quarterly gas consumption growth rate label, monthly gas consumption proportion label and monthly gas consumption growth rate label;

[0044] The indicator data under the behavior dimension include plan compliance rate and reduction data. The plan compliance rate includes annual average compliance rate, monthly average compliance rate and plan compliance degree. The reduction data includes maximum reduction rate, average reduction rate, proportion of reduction days, reduction frequency and reduction degree.

[0045] Furthermore, the indicator data calculation module is used to calculate the indicator data under the basic information dimension through the following steps:

[0046] Acquire the user name and the gas consumption area from the target basic information data;

[0047] Acquire multiple route pipeline information and multiple route station field information corresponding to the natural gas user from the target basic information data, merge multiple route pipeline information to obtain the gas route pipeline set, and merge multiple route station field information to obtain the gas route station field set;

[0048] Determine the time interval between the last consumption of the natural gas user, the consumption frequency and the consumption amount within a preset time period from the target consumption data;

[0049] Calculate the user value of the natural gas user based on the most recent consumption time interval, the consumption frequency and the consumption amount;

[0050] The preset corresponding relationship of the labels is utilized to determine the user value label of the natural gas user based on the time interval of the most recent consumption, the consumption frequency and the consumption amount.

[0051] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the method for constructing a natural gas user profile as described above are performed.

[0052] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method for constructing a natural gas user profile as described above are executed.

[0053] The embodiments of the present application provide a method, device, equipment and medium for constructing a natural gas user portrait. First, the original basic information data, original consumption data and original behavior characteristic data of the natural gas user are obtained, and data preprocessing is performed to obtain target basic information data, target consumption data and target behavior characteristic data; then, a user index system for the natural gas user portrait is established from the basic information dimension, the consumption dimension and the behavior dimension; based on the target basic information data, the target consumption data and the target behavior characteristic data, the index of the natural gas user under the user index system is calculated to obtain the index data under each label dimension; finally, the index data under each label dimension is used to generate a user portrait of the natural gas user in multiple dimensions.

[0054] Compared with the construction methods in the prior art, this application focuses on the gas usage characteristics of natural gas market users, uses different label extraction methods to describe users in multiple aspects, and fully mines and processes the original information of users. It can improve the single classification and static classification of users in the natural gas sales market, provide portrait support for scenario analysis guided by the needs of natural gas users, and help enterprises further improve their differentiated service capabilities.

[0055] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 A flowchart of a method for constructing a natural gas user portrait provided in an embodiment of the present application;

[0058] Figure 2 A schematic diagram of a user portrait of a natural gas user in multiple dimensions provided in an embodiment of the present application;

[0059] Figure 3 A schematic diagram of the structure of a natural gas user portrait construction device provided in an embodiment of the present application;

[0060] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.

[0062] First, the application scenarios to which this application is applicable are introduced. This application can be applied in the field of user portrait technology.

[0063] User portrait is a collection of personal information extracted from the aggregation of user behavior data, basic data, consumption data, etc. Its connotation mainly includes three factors, namely the attributes of the user, the characteristics of the user, and the label that can represent the user. The main significance of user portrait is to use specific user portraits to depict the preferences of individual users or groups of users, thus becoming an important means and tool for corporate market development and expansion of marketing scale. With the advent of the big data era, the massive user information generated by various information websites and platforms further provides data support for the construction of user portraits. User portraits have been actively promoted in many fields such as e-commerce recommendations, medical health, library management, hotel management, etc. Some industrial industries (such as electricity, new energy, etc.) have also begun to use user portraits to solve production and operation problems.

[0064] In the field of natural gas, user portraits can be used to describe the user's gas usage characteristics, credit profile, financial characteristics, development potential, etc., so as to understand the differentiated needs of users and display three-dimensional users in an all-round way. The traditional classification of natural gas users by gas companies is based on industry types, such as chemical users, power generation users, urban gas users, LNG users, etc. With the rise of intelligent algorithms, some scholars have begun to use spectral clustering, k-means clustering, GMM clustering and other models to complete the segmentation of gas users, and use clustering results to guide marketing.

[0065] Research has found that the current user characteristics analysis methods in the natural gas field are often mechanical and static. When conducting characteristic analysis, companies generally use traditional industry classification to study the consumption characteristics of different users, or characterize the overall attributes of group users based on a certain characteristic (gas consumption level, gas purchase price, etc.). Therefore, the precise characterization of individual users is not sufficient during the research process, resulting in a lack of decisive user demand and preference guidance for natural gas sales companies when formulating market development and marketing strategies, making it difficult to form accurate user sales plans.

[0066] Based on this, the embodiment of the present application provides a method for constructing a natural gas user portrait, which mainly uses the gas usage characteristics of natural gas market users, uses different label extraction methods to describe users in multiple aspects, and fully mines and processes the original information of users. It can improve the problems of single classification and static classification of users in the natural gas sales market, provide portrait support for scenario analysis guided by the needs of natural gas users, and help enterprises further improve their differentiated service capabilities.

[0067] See also Figure 1 , Figure 1 This is a flow chart of a method for constructing a natural gas user profile provided in an embodiment of the present application. Figure 1 As shown in, the construction method provided in the embodiment of the present application includes:

[0068] S101, obtaining original basic information data, original consumption data and original behavior characteristic data of natural gas users, and performing data preprocessing to obtain target basic information data, target consumption data and target behavior characteristic data.

[0069] Here, the basic information data includes basic information such as the user name, gas usage area, gas usage, registration status, etc. of the natural gas user; the consumption data includes consumption data such as the daily gas usage of the natural gas user; and the behavior data includes behavioral data such as the daily demand and actual completion amount of the natural gas user.

[0070] For the above step S101, during the specific implementation, the original basic information data, original consumption data and original behavior characteristic data of the natural gas user are obtained, and data preprocessing is performed. Specifically, the erroneous data or excessive error data in the original basic information data, original consumption data and original behavior characteristics are eliminated to obtain the target basic information data, target consumption data and target behavior characteristic data.

[0071] S102, establishing a user indicator system for natural gas user portraits from the basic information dimension, consumption dimension and behavior dimension.

[0072] To build a user gas usage characteristic index system, it is necessary to refer to the actual gas usage characteristics of natural gas users. From the perspective of natural gas companies, combined with the current overall economic situation and historical sales experience, relevant data of users in the region can be obtained through backend databases such as corporate sales platforms. The survey data is classified and sorted according to indicators such as user gas usage areas, gas usage, registration status, and consumption behavior to establish a gas usage index system. For the above step S102, a user index system for natural gas user portraits is established from the basic information dimension, consumption dimension, and behavior dimension.

[0073] S103, calculating the index of the natural gas user under the user index system based on the target basic information data, the target consumption data and the target behavior characteristic data, and obtaining the index data under each label dimension.

[0074] For the above step S103, in the specific implementation, after obtaining the target basic information data, target consumption data and target behavior characteristic data in step S101, the index calculation of the natural gas user under the user index system is performed based on the target basic information data, target consumption data and target behavior characteristic data to obtain the index data under each label dimension. Here, the label dimensions are the basic information dimension, the consumption dimension and the behavior dimension.

[0075] Specifically, according to the embodiment provided by the present application, the indicator data under the basic information dimension includes user name, gas consumption area, gas consumption pipeline set, gas consumption station set, user value and user value label.

[0076] Here, basic information data such as gas consumption area, gas usage, registration status, etc. can be directly obtained after data processing. When user consumption data is known, the RFM model can be used to measure value and predict churn status to tap into the user's development potential.

[0077] As an optional embodiment, for the above step S103, the indicator data under the basic information dimension is calculated by the following steps:

[0078] A: Obtain the user name and the gas usage area from the target basic information data.

[0079] Here, for the above step A, in the specific implementation, basic information data such as user name and gas consumption area are directly obtained after data processing.

[0080] B: Acquire multiple route pipeline information and multiple route station information corresponding to the natural gas user from the target basic information data, merge the multiple route pipeline information to obtain the gas route pipeline set, and merge the multiple route station information to obtain the gas route station set.

[0081] The route pipelines and route stations need to be merged according to each row of data to determine all pipeline station combinations of the natural gas user. For the above step B, in the specific implementation, multiple route pipeline information and multiple route station information corresponding to the natural gas user are obtained from the target basic information data, and the multiple route pipeline information is merged to obtain a gas route pipeline set, and the multiple route station information is merged to obtain a gas route station set.

[0082] C: Determine the time interval between the last consumption of the natural gas user, the consumption frequency and the consumption amount within a preset time period from the target consumption data.

[0083] For the above step C, in the specific implementation, the most recent consumption time interval of the natural gas user, the consumption frequency and the consumption amount within the preset time period are determined from the target consumption data. Here, the main value attributes considered in the RFM model are three elements:

[0084] (1) R (Recency) refers to the interval between the last consumption time and the deadline. The shorter the interval between the last consumption time and the current analysis time, the more likely the user is to be interested in the product or service provided immediately. For this application, R refers to the interval between the last consumption time of the natural gas user and the current time. The larger R is, the longer the natural gas user has not made a transaction; the smaller R is, the more recent the natural gas user has made a transaction.

[0085] (2) F (Frequency) refers to the number of times a user consumes within a certain period of time. The more frequent the consumption, the higher the satisfaction and loyalty of the user. For this application, F refers to the number of times a user consumes within a preset time period. The larger the F, the more frequent the natural gas user's transactions; the smaller the F, the less active the natural gas user's transactions.

[0086] (3) M (Monetary) refers to the amount of money spent by a user within a certain period of time. The more money a customer spends, the greater his or her spending power. For this application, M refers to the amount of money a user spends within a preset time period. The larger M is, the higher the value of the natural gas user; the smaller M is, the lower the value of the natural gas user.

[0087] Specifically, here the current date is used as the reference date, and the three values ​​of R, F, and M are calculated using the following calculation formula:

[0088] R_score = reference date – the user’s most recent consumption time;

[0089] F_score = the total number of times a user consumes in a certain period of time;

[0090] M_score = the total amount of money spent by the user in a certain period of time.

[0091] D: Calculate the user value of the natural gas user based on the most recent consumption time interval, the consumption frequency, and the consumption amount.

[0092] Here, for the above step D, in the specific implementation, after calculating the most recent consumption time interval, consumption frequency and consumption amount in the above step C, the user value of the natural gas user is calculated based on the most recent consumption time interval, consumption frequency and consumption amount.

[0093] Here, according to the embodiments provided in the present application, when calculating the RFM index, natural gas users are generally divided according to the data of each dimension to obtain different levels. For example, the Recency index can be divided into 5 levels, 1-5, according to the data situation, where 5 represents the most recent customer; similarly, the Frequency index and the Monetary index can also be divided into 5 levels, respectively, and the three values ​​of the user are divided into different intervals to obtain the value value. Specifically, the user value of natural gas users is calculated by the following formula: RFM = 100 × R_score + 10 × F_score + 1 × M_score. Among them, RFM represents user value.

[0094] E: Using the preset corresponding relationship of the labels, the user value label of the natural gas user is determined based on the time interval of the most recent consumption, the consumption frequency and the consumption amount.

[0095] For the above step E, in the specific implementation, the preset label correspondence relationship is used to determine the user value label of the natural gas user based on the natural gas user's most recent consumption time interval, consumption frequency and consumption amount. Please refer to Table 1 below, which is a user value label preset correspondence relationship table provided in the embodiment of the present application.

[0096] Table 1: User value label preset correspondence table

[0097] R F M User value label high high high High value users Low high high Focus on retaining users high Low high Focus on developing users Low Low high Focus on retaining users high high Low General value users Low high Low Generally keep users high Low Low General development users Low Low Low Potential Users

[0098] As shown in Table 1 above, the user value label of the natural gas user is determined based on the degree of the three data corresponding to the last consumption time interval, consumption frequency and consumption amount. For example, if the degree corresponding to the last consumption time interval of the natural gas user is "high", the degree corresponding to the consumption frequency is "high", and the degree corresponding to the "consumption frequency" is "high", then the user value label corresponding to the natural gas user is reflected as "high-value user".

[0099] Specifically, according to the embodiment provided in the present application, the indicator data under the consumption dimension includes annual gas consumption, annual gas consumption label, annual gas consumption growth rate label, quarterly gas consumption proportion label, quarterly gas consumption growth rate label, monthly gas consumption proportion label and monthly gas consumption growth rate label.

[0100] Here, consumption data such as annual gas consumption, quarterly gas consumption, and monthly gas consumption can be extracted by grouping and aggregation, and user labels can be extracted using algorithms such as data dimension reduction and clustering. Gas consumption level is the main source of profit for enterprises and an important means of measuring user value. Therefore, the indicators of the consumption dimension mainly include annual gas consumption (annual gas consumption label, annual gas consumption growth rate label), quarterly gas consumption (quarterly gas consumption proportion label, quarterly gas consumption growth rate label), monthly gas consumption (monthly gas consumption proportion label, monthly gas consumption growth rate), etc., which reflect the consumption level of users in different time dimensions.

[0101] As an optional embodiment, with respect to the above step S103, the indicator data under the consumption dimension is calculated by the following steps:

[0102] a: Obtain the current annual gas consumption and the historical annual gas consumption of the natural gas user from the target consumption data, and calculate the annual gas consumption growth rate of the natural gas user based on the current annual gas consumption and the historical annual gas consumption.

[0103] For the above step a, in the specific implementation, the current annual gas consumption and historical annual gas consumption of the natural gas user are obtained from the target consumption data. The annual gas consumption growth rate of the natural gas user is calculated based on the current annual gas consumption and the historical annual gas consumption. Specifically, the difference between the current annual gas consumption and the historical annual gas consumption is determined, and then the ratio between the difference and the historical annual gas consumption is determined as the annual gas consumption growth rate.

[0104] b: Based on the current annual gas consumption and the annual gas consumption growth rate, the k-means clustering algorithm is used to obtain the annual gas consumption label and the annual gas consumption growth rate label of the natural gas user.

[0105] Specifically, for the above step b, in the specific implementation, the k-means clustering method is used to obtain user labels. Based on the current annual gas consumption and annual gas consumption growth rate of natural gas users, the k-means clustering algorithm is used to obtain the annual gas consumption label and annual gas consumption growth rate label of natural gas users.

[0106] Here, according to the embodiment provided by the present application, the steps of obtaining the tag are as follows:

[0107] 1) Select cluster centers. Use the elbow method to determine the number of initial cluster centers k and express it as

[0108] 2) Calculate each sample data x i The distance to other clusters is used to divide it into the cluster closest to it:

[0109]

[0110] Where t is the current iteration number, k is the kth cluster;

[0111] 3) After each division is completed, update the mean vector of each cluster:

[0112]

[0113] 4) Repeat the second and third steps. When the number of iterations reaches the critical value or the cluster center no longer changes, the clustering model is constructed.

[0114] 5) Use the constructed clustering model to cluster the user's current annual gas consumption and annual gas consumption growth rate. Since the clustering model is an unsupervised clustering, it is necessary to combine the category characteristics of each type of user and the difference characteristics between categories to analyze user behavior and determine the user's annual label.

[0115] c: Obtain the current quarterly gas consumption, historical quarterly gas consumption, current monthly gas consumption and historical monthly gas consumption of the natural gas user from the target consumption data.

[0116] e: Calculate the quarterly gas consumption ratio of the natural gas user based on the current quarterly gas consumption and the current annual gas consumption, and calculate the monthly gas consumption ratio of the natural gas user based on the current monthly gas consumption and the current annual gas consumption.

[0117] f: Calculate the quarterly gas consumption growth rate of the natural gas user based on the current quarterly gas consumption and the historical quarterly gas consumption, and calculate the monthly gas consumption growth rate of the natural gas user based on the current monthly gas consumption and the historical monthly gas consumption.

[0118] Specifically, for the above steps c to f, during the specific implementation, the current quarterly gas consumption, historical quarterly gas consumption, current monthly gas consumption and historical monthly gas consumption of the natural gas user are obtained from the target consumption data. Then, the quarterly gas consumption ratio of the natural gas user is calculated based on the current quarterly gas consumption and the current annual gas consumption. Specifically, the ratio between the current quarterly gas consumption and the current annual gas consumption is used as the quarterly gas consumption ratio. The monthly gas consumption ratio of the natural gas user is calculated based on the current monthly gas consumption and the current annual gas consumption. Specifically, the ratio between the current monthly gas consumption and the current annual gas consumption is used as the monthly gas consumption ratio. Then, the quarterly gas consumption growth rate of the natural gas user is calculated based on the current quarterly gas consumption and the historical quarterly gas consumption, and the monthly gas consumption growth rate of the natural gas user is calculated based on the current monthly gas consumption and the historical monthly gas consumption.

[0119] g: Based on the quarterly gas consumption proportion and the quarterly gas consumption growth rate, a k-means clustering algorithm is used to obtain the quarterly gas consumption proportion label and the quarterly gas consumption growth rate label of the natural gas user.

[0120] h: Based on the monthly gas consumption proportion and the monthly gas consumption growth rate, a k-means clustering algorithm is used to obtain the monthly gas consumption proportion label and the monthly gas consumption growth rate label of the natural gas user.

[0121] Specifically, for the above steps g to h, in the specific implementation, the k-means clustering method is used to obtain user labels. Based on the quarterly gas consumption proportion and quarterly gas consumption growth rate of natural gas users, the k-means clustering algorithm is used to obtain the quarterly gas consumption proportion label and quarterly gas consumption growth rate label of natural gas users. Based on the monthly gas consumption proportion and monthly gas consumption growth rate, the k-means clustering algorithm is used to obtain the monthly gas consumption proportion label and monthly gas consumption growth rate label of natural gas users.

[0122] Here, according to the embodiment provided by the present application, the model for obtaining the user's monthly label and quarterly label is a k-means clustering model, and its main calculation formula is the same as the formula used to determine the annual gas consumption label and the annual gas consumption growth rate label in the above steps. After the clustering model is constructed, the same features within the observation category and the different features between categories are observed to determine the user's monthly label and quarterly label.

[0123] Specifically, according to the embodiment provided by the present application, the indicator data under the behavior dimension include plan compliance rate and reduction status data, the plan compliance rate includes the annual average compliance rate, the monthly average compliance rate and the plan compliance degree, and the reduction status data includes the highest reduction rate, the average reduction rate, the proportion of reduction days, the reduction frequency and the reduction degree.

[0124] In addition to gas consumption data, this application proposes the concepts of user plan compliance rate and reduction rate in combination with user daily demand and daily designated data. ① The plan compliance rate is the ratio of the user's daily demand report to the actual daily completion, including the annual average compliance rate, monthly average compliance rate, compliance trend and degree of compliance, etc.; ② The reduction rate is the ratio of the daily approval difference to the user's daily demand report, including the average reduction rate, the proportion of reduction days, the reduction frequency, the reduction degree, etc. These two types of indicators respectively reflect the user's own execution of the reported demand and the sales company's attention to the user.

[0125] As an optional embodiment, for the above step S103, the indicator data under the behavior dimension is calculated by the following steps:

[0126] I: Obtain the daily demand reporting amount, actual daily completion amount and daily approval difference of the natural gas user from the target behavior characteristic data.

[0127] II: Calculate the daily plan compliance rate of the natural gas user based on the daily demand report and the daily actual daily completion.

[0128] III: Calculate the annual average compliance rate and monthly average compliance rate of the natural gas users based on the daily planned compliance rate.

[0129] For the above steps I to III, in the specific implementation, the daily demand report amount, actual daily completion amount and daily approval difference of the natural gas user are obtained from the target behavior characteristic data of the natural gas user. The daily plan compliance rate of the natural gas user is calculated based on the daily demand report amount and the daily actual daily completion amount. Specifically, the ratio between the daily demand report amount of the natural gas user on a certain day and the actual daily completion amount on that day is determined as the plan compliance rate of that day. Then, the annual average compliance rate and the monthly average compliance rate of the natural gas user are calculated based on the daily plan compliance rate.

[0130] IV: utilizing the preset correspondence relationship of the compliance degree to determine the plan compliance degree of the natural gas user based on the monthly average compliance rate.

[0131] Here, according to the embodiment provided by the present application, the preset corresponding relationship of the degree of compliance is based on the average monthly plan compliance rate as the basis for division, specifically: average monthly compliance rate <0.6, the degree of plan compliance is low compliance; 0.6 < average monthly compliance rate <0.8, the degree of plan compliance is medium compliance; 0.8 < average monthly compliance rate <1, the degree of plan compliance is high compliance; average monthly compliance rate >1, the degree of plan compliance is extremely high compliance.

[0132] Regarding the above step IV, during the specific implementation, the preset corresponding relationship of the above compliance degree is used to determine the plan compliance degree of the natural gas user based on the monthly average compliance rate.

[0133] V: The daily reduction rate of the natural gas user is calculated based on the daily approved difference and the daily demand reported.

[0134] VI: Determine the average compression reduction rate, the maximum compression reduction rate and the proportion of compression reduction days of the natural gas user based on the daily compression reduction rate.

[0135] For the above steps V to VII, in the specific implementation, the daily reduction rate of the natural gas user is calculated based on the daily approval difference and the daily demand report. Specifically, the ratio between the daily approval difference of the natural gas user on a certain day and the daily demand report on that day is determined as the reduction rate of that day. Then, the average reduction rate, the maximum reduction rate and the proportion of reduction days of the natural gas user are determined based on the daily reduction rate.

[0136] VII: Utilizing the preset corresponding relationship of compression reduction frequency, the compression reduction frequency of the natural gas user is determined based on the proportion of the compression reduction days.

[0137] Here, according to the embodiment provided in the present application, the preset corresponding relationship of the compression reduction frequency is based on the proportion of compression reduction days, specifically: if the proportion of compression reduction days is <0.2, the compression reduction frequency is low-frequency compression; if the proportion of compression reduction days is 0.2<0.4, the compression reduction frequency is medium-frequency compression; if the proportion of compression reduction days is >0.4, the compression reduction frequency is high-frequency compression.

[0138] Regarding the above step VII, during the specific implementation, the above preset corresponding relationship of compression reduction frequency is utilized to determine the compression reduction frequency of natural gas users based on the proportion of compression reduction days of natural gas users.

[0139] VIII: Using the preset corresponding relationship of the compression reduction degree, the compression reduction degree of the natural gas user is determined based on the average compression reduction rate.

[0140] Here, according to the embodiment provided in the present application, the preset corresponding relationship of the compression reduction degree is based on the average compression reduction rate, specifically: average compression reduction rate <0.1, the compression reduction degree is low pressure reduction; 0.1<average compression reduction rate<0.2, the compression reduction degree is medium pressure reduction; 0.2<average compression reduction rate<0.4, the compression reduction degree is high pressure reduction; average compression reduction rate>0.4, the compression reduction degree is extremely high pressure reduction.

[0141] Regarding the above step VII, during the specific implementation, the preset corresponding relationship of the above compression reduction degree is utilized to determine the compression reduction degree of the natural gas users based on the average compression reduction rate of the natural gas users.

[0142] In this way, according to the above steps of calculating label data provided by the embodiment of the present application, various methods are used to extract labels from user attributes. Since user data has time series characteristics, the RFM analysis model in customer behavior theory is applied to the marketing management of natural gas users. By calculating the user's consumption frequency, consumption amount, consumption time interval, etc., the user's needs and consumption preferences are analyzed, and the amount of user basic label information is increased at the same time; k-means clustering is performed on the gas consumption scale, growth rate changes, etc., and time series analysis and clustering are performed on data with time series characteristics such as plan compliance rate trends; the analysis of user behavior characteristics is completed by introducing definitions such as compression reduction rate and plan compliance rate.

[0143] S104, using the indicator data under each tag dimension to generate a user portrait of the natural gas user in multiple dimensions.

[0144] For the above step S104, in the specific implementation, after the indicator data of the natural gas user under each label dimension are calculated, the indicator data under each label dimension can be used to generate a user portrait of the natural gas user in multiple dimensions, and the user's final performance in terms of load level, gas usage characteristics, and gas usage stability can be obtained. The portrait can be used to guide subsequent user evaluation, classification and other work.

[0145] See also Figure 2 , Figure 2 This is a schematic diagram of a user portrait of a natural gas user in multiple dimensions provided in an embodiment of the present application. Figure 2 As shown in the figure, the user portrait of natural gas user A finally determined includes three dimensions, namely basic information dimension, consumption dimension and behavior dimension. Among them, under the basic information dimension, the user name of natural gas user A is A, the gas use area is city B, the gas pipeline set is pipeline C-pipeline F, the gas station set is station G-station H, the user value is 522, and the user value label is a high-value user. Under the consumption dimension, the annual gas consumption of natural gas user A is 137.0626 million square meters, the annual gas consumption label is medium gas consumption, the annual gas consumption growth rate label is slightly fluctuating gas consumption, the quarterly gas consumption proportion label is similar and high in the first and fourth quarters, the quarterly gas consumption growth rate label is slightly increasing gas consumption, the monthly gas consumption proportion label is high in the middle of the month, and the monthly gas consumption growth rate label is slightly increasing gas consumption. In the behavioral dimension, the average annual compliance rate of natural gas user A is 68.78%, the average monthly compliance rate is 77.18%, the planned compliance level is medium, the highest reduction rate is 20.45%, the average reduction rate is 6.29%, the proportion of reduction days is 44.10%, the reduction frequency is high-frequency reduction, and the reduction degree is low reduction.

[0146] The method for constructing a natural gas user portrait provided in an embodiment of the present application first obtains original basic information data, original consumption data, and original behavior characteristic data of the natural gas user, and performs data preprocessing to obtain target basic information data, target consumption data, and target behavior characteristic data; then, establishes a user index system for the natural gas user portrait from the basic information dimension, the consumption dimension, and the behavior dimension; calculates the index of the natural gas user under the user index system based on the target basic information data, the target consumption data, and the target behavior characteristic data, to obtain the index data under each label dimension; finally, uses the index data under each label dimension to generate a user portrait of the natural gas user in multiple dimensions.

[0147] Compared with the construction methods in the prior art, this application focuses on the gas usage characteristics of natural gas market users, uses different label extraction methods to describe users in multiple aspects, and fully mines and processes the original information of users. It can improve the single classification and static classification of users in the natural gas sales market, provide portrait support for scenario analysis guided by the needs of natural gas users, and help enterprises further improve their differentiated service capabilities.

[0148] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of a natural gas user profile construction device provided in an embodiment of the present application. Figure 3 As shown in , the construction device 300 includes:

[0149] The data acquisition module 301 is used to acquire original basic information data, original consumption data and original behavior characteristic data of natural gas users, and perform data preprocessing to obtain target basic information data, target consumption data and target behavior characteristic data;

[0150] An indicator system establishment module 302 is used to establish a user indicator system for natural gas user portraits from the basic information dimension, consumption dimension and behavior dimension;

[0151] An index data calculation module 303 is used to calculate the index of the natural gas user under the user index system based on the target basic information data, the target consumption data and the target behavior characteristic data, and obtain the index data under each label dimension;

[0152] The user image generation module 304 is used to generate a user portrait of the natural gas user in multiple dimensions by using the indicator data in each tag dimension.

[0153] Furthermore, the indicator data under the basic information dimension includes user name, gas consumption area, gas consumption pipeline set, gas consumption station set, user value and user value label;

[0154] The indicator data under the consumption dimension include annual gas consumption, annual gas consumption label, annual gas consumption growth rate label, quarterly gas consumption proportion label, quarterly gas consumption growth rate label, monthly gas consumption proportion label and monthly gas consumption growth rate label;

[0155] The indicator data under the behavior dimension include plan compliance rate and reduction data. The plan compliance rate includes annual average compliance rate, monthly average compliance rate and plan compliance degree. The reduction data includes maximum reduction rate, average reduction rate, proportion of reduction days, reduction frequency and reduction degree.

[0156] Furthermore, the indicator data calculation module 303 is used to calculate the indicator data under the basic information dimension through the following steps:

[0157] Acquire the user name and the gas consumption area from the target basic information data;

[0158] Acquire multiple route pipeline information and multiple route station field information corresponding to the natural gas user from the target basic information data, merge multiple route pipeline information to obtain the gas route pipeline set, and merge multiple route station field information to obtain the gas route station field set;

[0159] Determine the time interval between the last consumption of the natural gas user, the consumption frequency and the consumption amount within a preset time period from the target consumption data;

[0160] Calculate the user value of the natural gas user based on the most recent consumption time interval, the consumption frequency and the consumption amount;

[0161] The preset corresponding relationship of the labels is utilized to determine the user value label of the natural gas user based on the time interval of the most recent consumption, the consumption frequency and the consumption amount.

[0162] Furthermore, the indicator data calculation module 303 calculates the indicator data under the consumption dimension through the following steps:

[0163] Obtaining the current annual gas consumption and the historical annual gas consumption of the natural gas user from the target consumption data, and calculating the annual gas consumption growth rate of the natural gas user based on the current annual gas consumption and the historical annual gas consumption;

[0164] Based on the current annual gas consumption and the annual gas consumption growth rate, using a k-means clustering algorithm to obtain an annual gas consumption label and an annual gas consumption growth rate label of the natural gas user;

[0165] Obtaining the current quarterly gas consumption, historical quarterly gas consumption, current monthly gas consumption and historical monthly gas consumption of the natural gas user from the target consumption data;

[0166] Calculate the quarterly gas consumption ratio of the natural gas user based on the current quarterly gas consumption and the current annual gas consumption, and calculate the monthly gas consumption ratio of the natural gas user based on the current monthly gas consumption and the current annual gas consumption;

[0167] Calculating the quarterly gas consumption growth rate of the natural gas user based on the current quarterly gas consumption and the historical quarterly gas consumption, and calculating the monthly gas consumption growth rate of the natural gas user based on the current monthly gas consumption and the historical monthly gas consumption;

[0168] Based on the quarterly gas consumption proportion and the quarterly gas consumption growth rate, a k-means clustering algorithm is used to obtain the quarterly gas consumption proportion label and the quarterly gas consumption growth rate label of the natural gas user;

[0169] Based on the monthly gas consumption proportion and the monthly gas consumption growth rate, a k-means clustering algorithm is used to obtain a monthly gas consumption proportion label and a monthly gas consumption growth rate label of the natural gas user.

[0170] Furthermore, the indicator data calculation module 303 calculates the indicator data under the behavior dimension through the following steps:

[0171] Obtaining the daily demand reporting amount, actual daily completion amount and daily approval difference of the natural gas user from the target behavior characteristic data;

[0172] Calculate the daily plan compliance rate of the natural gas user based on the daily demand report and the daily actual daily completion volume;

[0173] Calculate the annual average compliance rate and monthly average compliance rate of the natural gas users based on the daily planned compliance rate;

[0174] Determine the plan compliance degree of the natural gas user based on the monthly average compliance rate by using the preset corresponding relationship of the compliance degree;

[0175] Calculate the daily reduction rate of the natural gas user based on the daily approved difference and the daily demand reported amount;

[0176] Determine the average compression reduction rate, the maximum compression reduction rate and the proportion of compression reduction days of the natural gas user based on the daily compression reduction rate;

[0177] Determine the compression reduction frequency of the natural gas user based on the compression reduction days ratio by using the preset corresponding relationship of the compression reduction frequency;

[0178] The preset corresponding relationship of the compression reduction degree is utilized, and the compression reduction degree of the natural gas user is determined based on the average compression reduction rate.

[0179] See also Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 4 As shown in , the electronic device 400 includes a processor 410 , a memory 420 and a bus 430 .

[0180] The memory 420 stores machine-readable instructions executable by the processor 410. When the electronic device 400 is running, the processor 410 communicates with the memory 420 via the bus 430. When the machine-readable instructions are executed by the processor 410, the above-mentioned Figure 1 The steps of the method for constructing a natural gas user portrait in the method embodiment shown, and the specific implementation method can be found in the method embodiment, which will not be repeated here.

[0181] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 1 The steps of the method for constructing a natural gas user portrait in the method embodiment shown, and the specific implementation method can be found in the method embodiment, which will not be repeated here.

[0182] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0183] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0184] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0185] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0186] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can essentially be embodied in the form of a software product, or in other words, the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0187] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for constructing a natural gas user portrait, characterized in that: The construction method comprises: Obtaining original basic information data, original consumption data, and original behavior characteristic data of natural gas users, and performing data preprocessing to obtain target basic information data, target consumption data, and target behavior characteristic data; Establish a user index system for natural gas user portraits from the dimensions of basic information, consumption, and behavior; Based on the target basic information data, the target consumption data and the target behavior characteristic data, the index of the natural gas user under the user index system is calculated to obtain the index data under each label dimension; The indicator data under each label dimension is used to generate a user portrait of the natural gas user in multiple dimensions.

2. The construction method according to claim 1, characterized in that: The indicator data under the basic information dimension include user name, gas consumption area, gas consumption pipeline set, gas consumption station set, user value and user value label; The indicator data under the consumption dimension include annual gas consumption, annual gas consumption label, annual gas consumption growth rate label, quarterly gas consumption proportion label, quarterly gas consumption growth rate label, monthly gas consumption proportion label and monthly gas consumption growth rate label; The indicator data under the behavior dimension include plan compliance rate and reduction data. The plan compliance rate includes annual average compliance rate, monthly average compliance rate and plan compliance degree. The reduction data includes maximum reduction rate, average reduction rate, proportion of reduction days, reduction frequency and reduction degree.

3. The construction method according to claim 2, characterized in that: The indicator data under the basic information dimension is calculated through the following steps: Acquire the user name and the gas consumption area from the target basic information data; Acquire multiple route pipeline information and multiple route station field information corresponding to the natural gas user from the target basic information data, merge multiple route pipeline information to obtain the gas route pipeline set, and merge multiple route station field information to obtain the gas route station field set; Determine the time interval between the last consumption of the natural gas user, the consumption frequency and the consumption amount within a preset time period from the target consumption data; Calculate the user value of the natural gas user based on the most recent consumption time interval, the consumption frequency and the consumption amount; The preset corresponding relationship of the labels is utilized to determine the user value label of the natural gas user based on the time interval of the most recent consumption, the consumption frequency and the consumption amount.

4. The construction method according to claim 2, characterized in that: The indicator data under the consumption dimension is calculated through the following steps: Obtaining the current annual gas consumption and the historical annual gas consumption of the natural gas user from the target consumption data, and calculating the annual gas consumption growth rate of the natural gas user based on the current annual gas consumption and the historical annual gas consumption; Based on the current annual gas consumption and the annual gas consumption growth rate, using a k-means clustering algorithm to obtain an annual gas consumption label and an annual gas consumption growth rate label of the natural gas user; Obtaining the current quarterly gas consumption, historical quarterly gas consumption, current monthly gas consumption and historical monthly gas consumption of the natural gas user from the target consumption data; Calculate the quarterly gas consumption ratio of the natural gas user based on the current quarterly gas consumption and the current annual gas consumption, and calculate the monthly gas consumption ratio of the natural gas user based on the current monthly gas consumption and the current annual gas consumption; Calculating the quarterly gas consumption growth rate of the natural gas user based on the current quarterly gas consumption and the historical quarterly gas consumption, and calculating the monthly gas consumption growth rate of the natural gas user based on the current monthly gas consumption and the historical monthly gas consumption; Based on the quarterly gas consumption proportion and the quarterly gas consumption growth rate, a k-means clustering algorithm is used to obtain the quarterly gas consumption proportion label and the quarterly gas consumption growth rate label of the natural gas user; Based on the monthly gas consumption proportion and the monthly gas consumption growth rate, a k-means clustering algorithm is used to obtain the monthly gas consumption proportion label and the monthly gas consumption growth rate label of the natural gas user.

5. The construction method according to claim 2, characterized in that: The indicator data under the behavior dimension is calculated through the following steps: Obtaining the daily demand reporting amount, actual daily completion amount and daily approval difference of the natural gas user from the target behavior characteristic data; Calculate the daily plan compliance rate of the natural gas user based on the daily demand report and the daily actual daily completion volume; Calculate the annual average compliance rate and monthly average compliance rate of the natural gas users based on the daily planned compliance rate; Determine the plan compliance degree of the natural gas user based on the monthly average compliance rate by using the preset corresponding relationship of the compliance degree; Calculate the daily reduction rate of the natural gas user based on the daily approved difference and the daily demand reported amount; Determine the average compression reduction rate, the maximum compression reduction rate and the proportion of compression reduction days of the natural gas user based on the daily compression reduction rate; Determine the compression reduction frequency of the natural gas user based on the compression reduction days ratio by using the preset corresponding relationship of the compression reduction frequency; The preset corresponding relationship of the compression reduction degree is utilized, and the compression reduction degree of the natural gas user is determined based on the average compression reduction rate.

6. A device for constructing a natural gas user portrait, characterized in that: The construction device comprises: The data acquisition module is used to acquire the original basic information data, original consumption data and original behavior characteristic data of the natural gas user, and perform data preprocessing to obtain the target basic information data, target consumption data and target behavior characteristic data; The indicator system establishment module is used to establish a user indicator system for natural gas user portraits from the dimensions of basic information, consumption, and behavior; An indicator data calculation module, used to calculate the indicator of the natural gas user under the user indicator system based on the target basic information data, the target consumption data and the target behavior characteristic data, and obtain the indicator data under each label dimension; The user image generation module is used to generate a user portrait of the natural gas user in multiple dimensions by using the indicator data in each label dimension.

7. The construction device according to claim 6, characterized in that The indicator data under the basic information dimension include user name, gas consumption area, gas consumption pipeline set, gas consumption station set, user value and user value label; The indicator data under the consumption dimension include annual gas consumption, annual gas consumption label, annual gas consumption growth rate label, quarterly gas consumption proportion label, quarterly gas consumption growth rate label, monthly gas consumption proportion label and monthly gas consumption growth rate label; The indicator data under the behavior dimension include plan compliance rate and reduction data. The plan compliance rate includes annual average compliance rate, monthly average compliance rate and plan compliance degree. The reduction data includes maximum reduction rate, average reduction rate, proportion of reduction days, reduction frequency and reduction degree.

8. The construction device according to claim 7, characterized in that The indicator data calculation module is used to calculate the indicator data under the basic information dimension through the following steps: Acquire the user name and the gas consumption area from the target basic information data; Acquire multiple route pipeline information and multiple route station field information corresponding to the natural gas user from the target basic information data, merge multiple route pipeline information to obtain the gas route pipeline set, and merge multiple route station field information to obtain the gas route station field set; Determine the time interval between the last consumption of the natural gas user, the consumption frequency and the consumption amount within a preset time period from the target consumption data; Calculate the user value of the natural gas user based on the most recent consumption time interval, the consumption frequency and the consumption amount; The preset corresponding relationship of the labels is utilized to determine the user value label of the natural gas user based on the time interval of the most recent consumption, the consumption frequency and the consumption amount.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate through the bus. When the machine-readable instructions are run by the processor, the steps of the method for constructing a natural gas user profile as described in any one of claims 1 to 5 are executed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for constructing a natural gas user portrait as described in any one of claims 1 to 5 are executed.

Images