Tobacco customer service staff demand prediction method

Abstract

A tobacco customer service staff demand prediction method comprises the following steps that X groups of county (or county-level city and district) data are collected, and the X groups of county (or county-level city and district) data comprise the number of existing customer service staff compilation, the planned cigarette sales volume, the territorial area, the number of service persons, the number of terminal customers, the terminal category structure, the customer grade structure, the urban and rural power grid customer structure, the customer volume structure and the retailer dispersity; the existing customer service staff compilation number is taken as a dependent variable, other data is taken as an independent variable, and correlation analysis is carried out by using SPSS. Obtaining n associated variables, and determining X groups of customer service coefficients H; and clustering the H by using a K-means clustering analysis method. And on the basis of an industry quota staff standard, measuring and calculating the quota staff standard of each type of customer service staff by using an expert scoring method in combination with a clustering result, and predicting the customer service staff required by each group. The scientificity and reliability of an analysis result are improved, the reliability and scientificity of decision making are improved, and finally the more accurate number of customer service staff is obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of personnel demand prediction, and particularly relates to a method for predicting the demand for tobacco customer service staff. Background Art

[0002] Tobacco customer service staff mainly undertake the responsibilities of communicating with cigarette retail customers, providing service support and related management in the tobacco industry. Factors such as development differences and different geographical conditions lead to different service widths of cigarette retail customer service staff and different work difficulties of grass-roots staff. Especially in the southwestern mountainous areas such as Yunnan, Guizhou, Sichuan, and Chongqing, due to the large differences in the administrative areas, urban and rural population distributions, and the volume of cigarette retail customers in each county and district, the demands for cigarette marketing customer service staff in grass-roots units of the tobacco industry are also different. If the recruitment activities of talents are carried out only when there is a shortage of customer service staff in grass-roots units, the time required is relatively long, which is likely to affect the production and operation activities of the unit. Therefore, it is necessary to scientifically predict the demand for customer service staff. However, how to improve the scientificity and accuracy of the demand for customer service staff in the mountainous tobacco industry is a technical problem existing in current employers in the tobacco industry. Summary of the Invention

[0003] Based on the above problems, the present invention aims to provide a method for predicting the demand for tobacco customer service staff, so as to solve the problem of inaccurate recruitment of current employers in the mountainous tobacco industry.

[0004] The technical solution adopted by the present invention is as follows: A method for predicting the demand for tobacco customer service staff, comprising the following steps:

[0005] Step 1, collect X groups of data of counties (or county-level cities, districts), and each group of data includes the existing customer service staff establishment number, cigarette planned sales volume, land area, service population number, number of terminal customers, terminal category structure, customer grade structure, urban and rural network customer structure, customer volume structure, and retail household dispersion degree within the current administrative region;

[0006] Step 2, use the existing customer service staff establishment number as the dependent variable, and use the cigarette planned sales volume, land area, service population number, number of terminal customers, terminal category structure, customer grade structure, urban and rural network customer structure, customer volume structure, and retail household dispersion degree as independent variables, and use the SPSS tool to perform a correlation analysis on the X groups of dependent variables and independent variables;

[0007] Step 3, according to the correlation analysis results, select the independent variables with a Pearson correlation coefficient greater than 0.5 to obtain n associated variables;

[0008] Step 4, determine the X groups of customer service coefficients H according to the associated variables obtained in Step 3;

[0009] Step 5, use the K-means clustering analysis method of SPSS to cluster the X groups of customer service coefficients H to obtain a clustering result;

[0010] Step 6: Based on the industry's quota and staffing guidance standards, and in combination with the clustering analysis results in Step 5, calculate the corresponding quota and staffing standards for customer service representatives in each category.

[0011] Step 7: Predict the number of customer service representatives required for each group according to the final clustering results.

[0012] Furthermore, in Step 1, the planned cigarette sales volume refers to the total volume of cigarettes planned to be sold by the tobacco company in one year; the land area refers to the total land area of a certain region (such as a province, city, or county); the number of service population refers to the total population served by the tobacco company or retail terminals; the number of terminal customers refers to the total number of retail terminals that directly sell cigarettes to consumers; the terminal category structure refers to the proportional distribution of various cigarette retail terminals; the customer grade structure refers to the proportional distribution of cigarette consumers or retail customers divided by consumption grades; the urban-rural network customer structure: refers to the proportional distribution of cigarette retail customers in urban and rural areas, the proportion of licensed households in the urban network = the number of licensed households in the urban network / the total number of retail customers * 100%, the proportion of licensed households in the rural network = the number of licensed households in the rural network / the total number of retail customers * 100%; the customer volume structure refers to the proportional distribution of cigarette retail customers divided by sales scale; the retail customer dispersion refers to the degree of concentration or dispersion of cigarette retail terminals in geographical distribution, and the retail customer dispersion = the number of retail customers / the land area of the county (district).

[0013] Furthermore, in Step 3, after screening out n correlated variables according to the Pearson correlation coefficient, use the expert scoring method to score the selected variables to further optimize the variable selection and obtain the final correlated variables.

[0014] Furthermore, in Step 4, the formula for determining the customer service coefficient H for each group is as follows: hi = correlated variable i / average value of correlated variable i;

[0015]

[0016] where H: customer service coefficient;

[0017] hi: proportion coefficient of correlated variable i;

[0018] qi: weight of correlated variable i;

[0019] n: number of correlated variables;

[0020] The correlation coefficient of correlated variable i is obtained from the correlation analysis in Step 2.

[0021] Furthermore, when using the K-means clustering analysis of SPSS in Step 5, set the value of K to 3 - 5 categories.

[0022] Furthermore, in Step 6, the industry's quota and staffing guidance standard is to allocate one customer service representative for every 180 households.

[0023] Further, after obtaining the quota and staffing standards corresponding to each clustering category in Step 6, the quota and staffing standards corresponding to each clustering category are scored using the expert scoring method to determine the final clustering category and the corresponding quota and staffing standards.

[0024] Advantages of the present invention: By using the SPSS tool to perform a correlation analysis on the independent variables related to the number of customer service staff, data with low correlation is screened out to determine the customer service coefficient of the customer service staff. Then, through the K-means clustering analysis of SPSS, based on the industry's customer staff allocation guidance standard, the quota and staffing standards corresponding to different K values are calculated in combination with the clustering analysis results. Finally, through organizational expert discussion and analysis, the expert scoring method is used to determine the final quota and staffing standards, and the number of customer service staff is determined according to the final quota and staffing standards. The use of the SPSS tool improves the scientificity and reliability of the analysis results of the independent variables related to the number of service staff. The use of the expert scoring method further enhances the reliability and scientificity of the decision-making in combination with the actual situation, and finally obtains a more accurate number of customer service staff. This enables the enterprise to plan ahead in recruitment and personnel allocation, avoiding problems such as untimely recruitment and unreasonable personnel allocation. Specific implementation manner

[0025] A method for predicting the demand for tobacco customer service staff includes the following steps:

[0026] Step 1, collect data, including the existing customer service staff establishment numbers, cigarette planned sales volumes, land areas, service population numbers, terminal customer numbers, terminal category structures, customer grade structures, urban and rural network customer structures, customer volume structures, and retailer dispersion degrees of 89 county-level bureaus (branch companies) under the Guizhou Provincial Tobacco Company.

[0027] Among them:

[0028] Cigarette planned sales volume: refers to the total volume of cigarettes planned to be sold by the tobacco company within a certain period (usually one year). It reflects market demand and the company's sales target, and is an important basis for formulating production, procurement, and marketing strategies. Service area: refers to the total land area of a certain region (such as a province, city, or county). In the tobacco industry, the land area is related to the customer distribution, cigarette distribution range, and market coverage difficulty, affecting service efficiency, logistics costs, market layout, and the improvement of retailer satisfaction.

[0029] Service population number: refers to the total population served by the tobacco company or retail terminal. It is used to evaluate the market scale and potential consumer demand and helps formulate sales strategies.

[0030] Terminal customer number: refers to the total number of retail terminals (such as grocery stores, convenience stores, supermarkets, tobacco and alcohol stores) that directly sell cigarettes to consumers. It reflects the market coverage range and the density of the sales network.

[0031] Terminal category structure: Refers to the proportional distribution of various types of cigarette retail terminals. It includes: direct-operated terminals, Qiancai cooperative and Qiancai convenient terminals, high-quality modern terminals, and ordinary terminals; helps analyze the sales contributions of different terminal types and optimize resource allocation.

[0032] Customer grade structure: Refers to the proportion of cigarette consumers or retail customers divided by consumption grades (such as high-end, mid-end, low-end). Used to formulate differentiated marketing strategies to meet the needs of different consumer groups.

[0033] Urban and rural network customer structure: Refers to the proportional distribution of cigarette retail customers in urban and rural areas.

[0034] Urban network licensed household structure = Number of urban network licensed households / Total number of retail customers * 100%;

[0035] Rural network licensed household structure = Number of rural network licensed households / Total number of retail customers * 100%; Reflects the differences between urban and rural markets and helps formulate targeted sales and service strategies.

[0036] Customer volume structure: Refers to the proportion of cigarette retail customers divided by sales scale (such as large customers, medium customers, small customers). Used to identify key customers and optimize customer management and services.

[0037] Retailer dispersion: Refers to the degree of concentration or dispersion of cigarette retail terminals in geographical distribution. Retailer dispersion = Number of retail customers / Land area of the county (district). A high dispersion means that retail terminals are widely distributed and sparse, which may affect service efficiency and increase distribution service costs; a low dispersion means that retail terminals are concentrated, facilitating management and distribution services.

[0038] Step 2: Taking the existing number of customer service staff in 89 county-level bureaus (branch companies) in Guizhou Province as the dependent variable, and taking 9 factors such as "planned cigarette sales volume, land area (service area), number of service population, number of terminal customers, terminal category structure, customer grade structure, urban and rural network customer structure, customer volume structure, retailer dispersion" as independent variables, use the SPSS tool to conduct a correlation analysis on the dependent variable and independent variables.

[0039] Table 1: Results of correlation analysis between the number of customer service staff and various factors

[0040]

[0041]

[0042] Step 3: Determine the final independent variables according to the results of the correlation analysis;

[0043] Through analysis, factors such as "planned cigarette sales volume, number of served population, number of terminal customers, terminal category structure, customer grade structure, customer volume structure, urban-rural network customer structure, and retail customer dispersion degree" all have a certain correlation with the number of customer service representatives.

[0044] Based on the correlation analysis, the expert scoring method was used to screen the associated variables again. Internal experts in the marketing line were organized to conduct a centralized discussion and believed that: A. In accordance with industry requirements, it is necessary to strengthen the construction and management of the rural network market, improve the customer service intensity and service level in the rural network market. In the future, customer service representatives will increase the workload and difficulty of customer service for rural network customers to a certain extent. Therefore, the proportion of the rural network has a greater impact on the number of customer service representatives. B. According to the requirements and standards of retail customer service, customer service representatives need to invest more service time and energy in terminal customers in the 11-30 grade range. The proportion of terminal customers in the 11-30 grade range has a greater impact on the work of customer service representatives. C. The overall transportation conditions in Guizhou Province are not ideal. The more dispersed the retail customers are, the more customer service workload and working hours need to be invested. The retail customer dispersion degree has a greater impact on the work of customer service representatives.

[0045] Based on the above analysis and research, "the proportion of customers in the 11-30 grade range, the proportion of rural network customers, and the retail customer dispersion degree" are used as key associated factors.

[0046] Step 4: Determine the customer service coefficient H of customer service representatives according to the final associated variables obtained in Step 3;

[0047] Calculation formula for the customer service coefficient of customer service representatives:

[0048]

[0049] hi = associated variable i / average value of associated variable i;

[0050]

[0051] Where H: customer service coefficient;

[0052] hi: proportion coefficient of associated variable i;

[0053] qi: weight of associated variable i;

[0054] n: number of associated variables;

[0055] It is known from Step 3 that n = 3;

[0056] h1: proportion coefficient of terminal customers in the 11-30 grade range;

[0057] After analysis by expert discussion, it is believed that the higher the customer grade, the more service time and energy will be invested. Therefore, the h1: proportion coefficient of terminal customers in the 11-30 grade range was adjusted as follows:

[0058] h1 = (Proportion of end - users in the 11 - 20 range in the whole county (district)) * 20%+(Proportion of end - users in the 21 - 25 range) * 30%+(Proportion of end - users in the 26 - 30 range) * 50% / Average proportion of the whole province;

[0059] h2: Coefficient of the proportion of rural network customers;

[0060] h2 = Proportion of rural network customers in the whole county (district) / Average proportion of rural network customers in the whole province;

[0061] h3: Coefficient of retailer dispersion;

[0062] h3 = Retailer dispersion in the whole county (district) / Average retailer dispersion in the whole province, Retailer dispersion = Number of retail customers / Land area of the county (district);

[0063] Table 2: Correlation factor coefficients and weights of associated variables

[0064]

[0065] Finally, we get: H = h1×40% + h2×40% + h3×20%.

[0066] Step 5: Use the K - means clustering analysis method of SPSS to cluster 89 units in Guizhou Province according to the customer service coefficient H, and obtain the clustering results; see Tables 3, 4 and 5 for details. ① Clustering analysis of "customer service coefficient" - divided into 3 categories

[0067] Table 3: Clustering analysis table of three - category customer service coefficients

[0068]

[0069] ② Clustering analysis of "customer service coefficient" - divided into 4 categories

[0070] Table 4: Clustering analysis of four - category customer service coefficients

[0071]

[0072] ③ Clustering analysis of "customer service coefficient" - divided into 5 categories

[0073] Table 5: Clustering analysis results of five - category customer service coefficients

[0074]

[0075] Step 6: Based on the benchmark of allocating one customer service staff for every 180 households (industry guiding standard), combined with the clustering analysis results, calculate the corresponding quota and staffing standards for each category;

[0076] Table 6: Calculation of quota and staffing standards based on clustering analysis results

[0077]

[0078] Step 7, determine the final quota and staffing standards;

[0079] Based on the above clustering analysis results, organize internal experts in the marketing line to conduct discussions and analyses. After discussion and analysis, it is considered that the clustering result of clustering into 4 categories is more in line with the actual situation of Guizhou Tobacco and Qiannan Tobacco. However, it is considered that the quota and staffing calculation standard for the 4th category is too high, and the quota and staffing standard for the 4th category should be adjusted to limit the high according to the arithmetic progression increasing rule.

[0080] Table 7: Calculated quota and staffing standards for the final clustering analysis results

[0081]

[0082]

[0083]

[0084] Predict the required customer service staff in county-level units according to the final clustering results, and select the prediction results of the customer service staff in the county-level bureaus (branches) of Qiannan Prefecture, Guizhou Province for display.

[0085] Table 8: Prediction results table of the customer service staff in the county-level bureaus (branches) of Qiannan Prefecture, Guizhou Province

[0086]

[0087] The above content is a further detailed description of the present invention in combination with specific preferred implementation manners, and it cannot be determined that the specific implementation of the present invention is only limited to these descriptions. For those of ordinary skill in the technical field to which the present invention belongs, without departing from the concept of the present invention, several simple deductions or substitutions can still be made, and all should be regarded as belonging to the protection scope of the present invention.

Claims

1. A method for predicting demand for tobacco customer service personnel, characterized in that: The following steps are involved: Step 1: collect X groups of county (or county-level city, district) data, each group of data includes the number of existing customer service staff in the current administrative area, planned cigarette sales volume, land area, service population, number of terminal customers, terminal category structure, customer grade structure, urban and rural network customer structure, customer volume structure and retail household dispersion; Step 2: With the number of existing customer service staff as the dependent variable, and the planned cigarette sales volume, land area, service population, number of terminal customers, terminal category structure, customer grade structure, urban and rural network customer structure, customer volume structure and retail household dispersion as independent variables, SPSS tools were used to conduct correlation analysis on the dependent and independent variables of group X; Step 3: According to the correlation analysis results, select the independent variables with a Pearson correlation coefficient greater than 0.5 to obtain n associated variables; Step 4: Determine the customer service coefficient H of group X based on the associated variables obtained in step 3; Step 5: Use SPSS K-means cluster analysis method to cluster the customer service coefficient H of group X and obtain the clustering results; Step 6: Based on the industry quota staffing guidance standards and combined with the cluster analysis results of step 5, calculate the quota staffing standards for customer service staff of each category; Step seven: predict the number of customer service staff required for each group based on the final clustering results.

2. A tobacco customer service demand forecasting method according to claim 1, characterized in that: In the step 1, the planned sales volume of cigarettes refers to the total volume of cigarettes that the tobacco company plans to sell within one year; the land area refers to the total land area of ​​a certain region (such as a province, city, or county); the number of population served refers to the total population served by the tobacco company or retail terminals; the number of terminal customers refers to the total number of retail terminals that sell cigarettes directly to consumers; The terminal category structure refers to the proportional distribution of various types of cigarette retail terminals; the customer grade structure refers to the proportion of cigarette consumers or retail customers divided by consumption grade; the urban and rural network customer structure: refers to the proportional distribution of cigarette retail customers in urban and rural areas, the structure of urban network licensed households = the number of urban network licensed households / the total number of retail customers*100%, the structure of rural network licensed households = the number of rural network licensed households / the total number of retail customers*100%; the customer volume structure refers to the proportion of cigarette retail customers divided by sales scale; the dispersion of retailers refers to the degree of concentration or dispersion of cigarette retail terminals in geographical distribution, the dispersion of retailers = the number of retail customers / county (district) land area.

3. A tobacco customer service demand forecasting method according to claim 1, characterized in that: In the step three, after n associated variables are screened out according to the Pearson correlation coefficient, the screened variables are scored using the expert scoring method to further optimize the variable selection and obtain the final associated variables.

4. A tobacco customer service demand forecasting method according to claim 1, characterized in that: The formula for determining the customer service coefficient H of each group in step 4 is: hi = associated variable i / average value of associated variable i; qi=correlation coefficient of associated variable i / Where H: customer service coefficient; hi: coefficient of association variable i; qi: weight of associated variable i; n: the number of associated variables; The correlation coefficient of associated variable i is obtained from the correlation analysis in step 2.

5. A tobacco customer service demand forecasting method according to claim 1, characterized in that: When using the K-means cluster analysis of SPSS in step 5, the K value is set to 3-5 categories.

6. A tobacco customer service demand forecasting method according to claim 1, characterized in that: The industry's quota staffing guidance standard in step six is ​​to assign one customer service representative to every 180 households.

7. A tobacco customer service demand forecasting method according to claim 1, characterized in that: After obtaining the quota and staffing standards corresponding to each cluster category in step 6, the expert scoring method is used to score the quota and staffing standards corresponding to each cluster category to determine the final cluster category and the corresponding quota and staffing standards.

Images