Decision suggestion generation method and device for adding site service

Abstract

The invention discloses a decision suggestion generation method and device for adding site services, and the method comprises the steps: obtaining quantitative data corresponding to a to-be-added service item for each to-be-added service item, including demand data, competitive data, target site capability data and cost income data, carrying out the fuzzy processing of the quantitative data, and obtaining a decision suggestion of the to-be-added service item; obtaining a fuzzy set group G1 corresponding to demand data, obtaining a fuzzy set group G2 corresponding to competitive data, obtaining a fuzzy set group G3 corresponding to target site capability data, obtaining a fuzzy set group G4 corresponding to cost income data, performing fuzzy logic reasoning on the fuzzy set groups G1, G2, G3 and G4 corresponding to the to-be-added service item, and obtaining a fuzzy set group G4 corresponding to the to-be-added service item; the decision suggestion corresponding to the to-be-added service item is generated according to the to-be-added service item, fuzzy logic reasoning can be carried out according to market dynamic requirements, competitive environments, operation capability and income, the complexity and uncertainty of the market environment are reduced, and accurate and scientific decision suggestions for adding site services can be provided.

Description

Technical Field

[0001] This article relates to the field of decision-making suggestion generation in the service industry, and in particular to a method and apparatus for generating decision-making suggestions for adding site services. Background Technology

[0002] With the increase in car ownership, car owners' demand for car services is growing. Various car service stations are facing the problem of expanding their service offerings to meet customer needs. However, traditional decision-making models are difficult to cope with the uncertainty and complexity of the market. Existing decision-making models mainly rely on regional vehicle traffic data and car users' daily travel routes for site selection. They are unable to generate suggestions for adding car services to existing service stations, and they do not consider the distribution and business strategies of competitors when selecting sites. The lack of comprehensive analysis of competitors affects the comprehensiveness and accuracy of site selection decisions. They do not consider the actual service needs of users and the actual economic environment, and the generated decision recommendations lack scientific basis. Summary of the Invention

[0003] This application provides a method and apparatus for generating decision suggestions for adding site services. It can comprehensively perform fuzzy logic reasoning based on dynamic market demand, competitive environment, target site operation capabilities and revenue, reducing the complexity and uncertainty of the market environment, and providing comprehensive, accurate and scientific decision suggestions for adding site services.

[0004] On the one hand, embodiments of this application provide a method for generating decision suggestions for adding site services, including: Obtain a set of candidate services for a target site, wherein the set of candidate services includes multiple service items to be added to the target site; For each of the service items to be added, perform the following steps: Obtain the quantitative data corresponding to the service item to be added, including demand data, competitive data, target site capability data, and cost-benefit data; The quantitative data corresponding to the service item to be added is fuzzified to obtain the membership array D1 and fuzzy set group G1 corresponding to the demand data; the membership array D2 and fuzzy set group G2 corresponding to the competitive data; the membership array D3 and fuzzy set group G3 corresponding to the target site capability data; and the membership array D4 and fuzzy set group G4 corresponding to the cost and benefit data. Fuzzy logic reasoning is performed on the fuzzy set group G1, G2, G3, and G4 corresponding to the service item to be added to generate decision suggestions corresponding to the service item to be added.

[0005] On the other hand, embodiments of this application also provide a decision suggestion generation apparatus for adding site services, including a memory and a processor: The memory is used to store the decision suggestion generation program for adding site services; The processor is used to read the decision suggestion generation program for adding site services and perform the decision suggestion generation method for adding site services as described in the above embodiments.

[0006] Compared with related technologies, the decision suggestion generation method and apparatus for adding site services according to the embodiments of this application can comprehensively perform fuzzy logic reasoning based on dynamic market demand, competitive environment, target site operation capabilities and revenue, reducing the complexity and uncertainty of the market environment, and providing comprehensive, accurate and scientific decision suggestions for adding site services. The generated decision suggestions can recommend the target site to add service items with high demand, low competition, low upgrade and transformation requirements and high revenue, helping the target site operator to adjust service strategies in a timely manner, reducing the blindness of adding site services, maintaining the site's market competitiveness while obtaining good economic benefits.

[0007] Other features and advantages of this application will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the application. Other advantages of this application can be realized and obtained by means of the embodiments described in the description and the accompanying drawings. Attached Figure Description

[0008] The accompanying drawings are used to provide an understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0009] Figure 1 A flowchart illustrating a method for generating decision suggestions for adding site services according to an embodiment of this application; Figure 2 This is a schematic diagram of a decision suggestion generation device for adding site services according to an embodiment of this application. Detailed Implementation

[0010] This application describes several embodiments, but these descriptions are exemplary and not limiting, and it will be apparent to those skilled in the art that many more embodiments and implementations are possible within the scope of the embodiments described herein. Although many possible combinations of features are shown in the drawings and discussed in the detailed description, many other combinations of the disclosed features are also possible. Unless specifically limited, any feature or element of any embodiment may be used in combination with, or may replace, any feature or element of any other embodiment.

[0011] This application includes and contemplates combinations of features and elements known to those skilled in the art. The embodiments, features, and elements disclosed in this application can also be combined with any conventional features or elements to form unique inventive solutions. Any feature or element of any embodiment can also be combined with features or elements from other inventive solutions to form another unique inventive solution. Therefore, it should be understood that any feature shown and / or discussed in this application can be implemented individually or in any suitable combination. Therefore, the embodiments are not limited except by the limitations imposed by the appended claims and their equivalents. Furthermore, various modifications and changes can be made within the scope of the appended claims.

[0012] Furthermore, in describing representative embodiments, the specification may have presented methods and / or processes as a specific sequence of steps. However, the method or process should not be limited to the specific order of steps described herein, to the extent that it does not depend on such a specific order. As will be understood by those skilled in the art, other sequences of steps are also possible. Therefore, the specific order of steps set forth in the specification should not be construed as a limitation of the claims. Moreover, the claims concerning the method and / or process should not be limited to the steps performed in the written order, and those skilled in the art will readily understand that these orders can be varied and still remain within the spirit and scope of the embodiments of this application.

[0013] This application provides a method for generating decision suggestions for adding site services, such as... Figure 1 As shown, steps S100-S400 are included: S100: Obtain a set of candidate services for the target site, wherein the set of candidate services includes multiple service items to be added to the target site; For each of the service items to be added, perform steps S200-S400: S200: Obtain the quantitative data corresponding to the service item to be added, including demand data, competitive data, target site capability data, and cost-benefit data; S300: Perform fuzzification processing on the quantitative data corresponding to the service item to be added to obtain the membership array D1 and fuzzy set group G1 corresponding to the demand data; obtain the membership array D2 and fuzzy set group G2 corresponding to the competitive data; obtain the membership array D3 and fuzzy set group G3 corresponding to the target site capability data; obtain the membership array D4 and fuzzy set group G4 corresponding to the cost and benefit data; S400: Perform fuzzy logic reasoning on the fuzzy set group G1, G2, G3, G4 corresponding to the service item to be added, and generate decision suggestions corresponding to the service item to be added.

[0014] In this embodiment, the target site can be a gas station, CNG station, charging station, auto repair shop, etc.; the service to be added can be a car wash service, antifreeze change service, engine oil change service, car detailing service, tire change service, etc.; the decision suggestion is a decision suggestion for the target site, including whether to suggest adding a certain service and the risks of adding a certain service; wherein, the target site, the service to be added, and the decision suggestion mentioned above are all exemplary descriptions and are not intended to limit this application, and will not be elaborated further.

[0015] In this embodiment, steps S200-S400 are steps performed for each service item to be added. For each service item to be added, four quantitative data are obtained: demand data, competitiveness data, target site capability data, and cost-benefit data. The demand data represents the degree of demand for the service item to be added; the competitiveness data represents the intensity of market competition for the service item to be added; the target site capability data represents the ability to operate the service item to be added with the current target site resources; and the cost-benefit data represents the economic benefits that the target site would bring if the service item to be added were added, such as the predicted annual net profit or the predicted return on investment.

[0016] In this embodiment, steps S300 and S400 are executed based on a decision suggestion model, which includes at least a fuzzification module and an inference decision module. Step S300 is executed based on the fuzzification module, which includes a first fuzzification module, a second fuzzification module, a third fuzzification module, and a fourth fuzzification module. The first fuzzification module is used to fuzzify demand data, the second fuzzification module is used to fuzzify competitive data, the third fuzzification module is used to fuzzify target site capability data, and the fourth fuzzification module is used to fuzzify cost-benefit data. Step S400 is executed based on the inference decision module, which includes a fuzzy rule base, an inference module, a defuzzification module, and a decision suggestion generation module.

[0017] In one embodiment of this invention, the decision suggestion model can be set with an update cycle. At the beginning of each cycle, the decision suggestion model is updated, including the updates of each module of the decision suggestion model and the fuzzy rule base. When the decision suggestion generation method for adding site services in this application embodiment is executed in each cycle, the decision suggestion model obtained at the beginning of the current cycle is used. When updating the decision suggestion model, update data can be obtained. The update data includes market dynamic survey data from the previous cycle, expert opinions generated based on the market dynamic survey data from the previous cycle, and the operational data of the target site in the previous cycle. The decision suggestion model of the previous cycle is updated based on the update data to obtain the decision suggestion model corresponding to the current cycle.

[0018] In another embodiment of this application, before executing the decision suggestion generation method for adding site services according to this application, the accuracy of the currently saved latest decision suggestion model can be calculated, and the calculated accuracy can be compared with a preset accuracy threshold. If the accuracy is less than the preset accuracy threshold, the decision suggestion model is updated. If the accuracy is not less than the preset accuracy threshold, the decision suggestion model is sampled and the decision suggestion generation method for adding site services according to this application is executed. When calculating the accuracy, multiple historical decision suggestions generated based on the decision suggestion model can be obtained, and the accuracy can be calculated based on the multiple historical decision suggestions. If it is necessary to update the decision suggestion model, update data can be obtained, including market dynamic survey data within a predetermined time period before the current time, expert opinions generated based on the market dynamic survey data, and the operational data of the target site within the predetermined time period. The decision suggestion model is then updated based on the update data to obtain the updated decision suggestion model, and the decision suggestion generation method for adding site services according to this application is executed based on the updated decision suggestion model.

[0019] In this embodiment, by updating the decision recommendation model, the model can be dynamically optimized and adjusted according to market changes and the actual operation of the target site, thus ensuring the scientific nature, effectiveness, adaptability, and accuracy of the decision recommendation model.

[0020] The method for generating decision suggestions for adding site services in this embodiment can comprehensively consider market dynamics, competitive environment, target site operation capabilities, and revenue through fuzzy logic reasoning. This reduces the complexity and uncertainty of the market environment and provides comprehensive, accurate, and scientific decision suggestions for adding site services. The generated decision suggestions can recommend that target sites add services with high demand, low competition, low upgrade and transformation requirements, and high revenue. This helps target site operators adjust their service strategies in a timely manner, maintain the site's market competitiveness, and obtain good economic benefits.

[0021] In one exemplary embodiment, step S100 may include steps S110-S120: S110: Obtain the existing service set of all stations in the target area and the service demand set of the customer group in the target area, wherein the target station is located in the target area, the existing service set includes the existing service items of all stations in the target area, and the service demand set includes the service items demanded by the customer group in the target area. S120: Calculate the union of the existing service set and the service demand set, and remove the existing service items of the target site from the service items contained in the union, and form the candidate service set with the remaining service items.

[0022] In this embodiment, the target area includes not only the target site but also multiple other sites. These other sites can be competitors or potential competitors of the target site. For example, if the target site is a gas station, other gas stations in the target area are competitors. If the target site does not currently offer car detailing services but may add them soon, then the sites in the target area that currently offer car detailing services are potential competitors.

[0023] In this embodiment, the service items included in the candidate service set are all services that the target site does not currently provide, and the customer group may include private car owners and commercial vehicle owners.

[0024] In one exemplary embodiment, step S200 may include steps S210-S240: S210: Obtain the demand parameters of the service item to be added, input the demand parameters into the first formula for calculation, and use the calculated value as the demand data corresponding to the service item to be added. The demand parameters include the total demand frequency of the service item to be added, the demand frequency corresponding to each season, and the economic prosperity value. S220: Obtain the competitive parameters of the service item to be added, input the competitive parameters into the second formula for calculation, and use the calculated value as the competitive data corresponding to the service item to be added. The competitive parameters include the market share of the service item to be added, the service quality data of competitors, the service pricing data, and the customer satisfaction data. S230: Obtain the target site parameters of the service item to be added, input the target site parameters into the third formula for calculation, and use the calculated value as the target site capability data corresponding to the service item to be added. The target site parameters include target site area data, human resources data and current facility data. S240: Obtain the cost-benefit parameters of the service item to be added, input the cost-benefit parameters into the fourth formula for calculation, and use the calculated value as the cost-benefit data corresponding to the service item to be added. The cost-benefit parameters include the initial investment cost, annual operating cost, and expected annual revenue.

[0025] In one embodiment of this example, the first formula, the second formula, the third formula, and the fourth formula can be pre-saved in the decision suggestion model. The decision suggestion model can also include a quantitative data generation module, which can include the first formula, the second formula, the third formula, and the fourth formula.

[0026] In another embodiment of this example, the quantitative data generation module is a module parallel to the decision suggestion model. The quantitative data generation module may include a first formula, a second formula, a third formula, and a fourth formula that are saved in advance.

[0027] In this embodiment, the first formula can be: Demand data = w 11 *Total demand frequency + w 12 *Spring demand frequency + w 13 *Summer demand frequency + w 14 *Autumn demand frequency + w 15 *Winter demand frequency + w 16 *Economic sentiment index, w 11 +w 12 +w 13 +w 14 +w 15 +w 16 =1; For each service item to be added, the weight w of each requirement parameter can be different. For example, for the antifreeze replacement service, since the demand for this service is higher in autumn and winter, w... 14 and w 15 The value of w 12 and w 13 High; for example, the demand for air conditioning filter replacement service is higher in summer and winter. 13 and w 15 The value of w 12 and w 14 High; for example, compared to car wash services, car detailing services are more in demand during periods of economic prosperity, while car wash services are less affected by economic conditions. Therefore, the demand for car detailing services is higher during periods of economic prosperity. 16 It can be compared to car wash services. 16 high.

[0028] In this embodiment, the demand data is calculated according to the first formula, which can accurately identify high service demand in the market and take into account the impact of seasonal changes and economic conditions on service demand. This helps target sites to dynamically adjust the added service items, overcomes the limitations of traditional methods that rely solely on historical data, and provides more forward-looking demand data for the added service items.

[0029] In this embodiment, the second formula can be: Competitive data = w 21 *Market share + w 22 *Competitor service quality data + w 23 *Service pricing data + w 24 *Customer satisfaction data, w 21 +w 22 +w 23 +w 24 =1; where, for each service item to be added, the market share can be the proportion of the number of sites offering the service item to be added in the target area to the total number of sites in the target area, the service quality data and customer satisfaction data of competitors can be the average data of sites offering the service item to be added in the target area, and the service pricing data can be the reciprocal of the average price of sites offering the service item to be added in the target area; the higher the market share, the higher the service quality data of competitors, the higher the service pricing data, and the higher the customer satisfaction data, the greater the competitive data obtained, which represents the stronger the competition.

[0030] In this embodiment, competitive data is calculated based on the second formula, and the service status and market share of competitors for the service items to be added are comprehensively analyzed. This can identify market gaps and avoid competitive risks. Compared with conventional qualitative competitive analysis, it can obtain quantitative competitive data, which is more scientific and comprehensive.

[0031] In this embodiment, the third formula can be: Target site capability data = w 31 *Target site area data + w 32 *Human Resources Data + w 33 *Current facility data, w 31 +w 32 +w 33=1; Wherein, for each service item to be added, the target site area data can be the area that the target site can provide for the service item to be added; the human resources data can be a combination of the number of employees and their service capacity that the target site can provide for the service item to be added, representing the data that the current number of employees and their service capacity of the target site can support the addition of the service item to be added. If it is necessary to increase the number of employees and / or train employees, the human resources data will be lower. If the number of employees and their service capacity are sufficient to support the service item to be added, the human resources data will be higher; the current facility data is the data that the existing facilities of the target site can provide to support the addition of the service item to be added. For example, if it is necessary to purchase new equipment, the current facility data = 0. If it is necessary to upgrade the current facilities, the current facility data = 50. If the current facilities can support the service item to be added, the current facility data = 100.

[0032] In this embodiment, the target site capability data is calculated according to the third formula, which can objectively evaluate the target site's ability to add a certain service item based on the target site's area, human resource configuration, and current facility configuration.

[0033] In this embodiment, the cost-benefit data can be the return on investment (ROI), and the fourth formula can be the formula for calculating the ROI: ROI = (Expected annual revenue - Initial investment cost - Annual operating cost) / Initial investment cost. For example, for a service item to be added, the expected annual revenue is 15,000 yuan, the initial investment cost is 10,000 yuan, and the annual operating cost is 2,000 yuan. Inputting the above parameters into the fourth formula, the ROI is 30%. The expected annual revenue can include the direct and indirect revenue brought by adding the service item to be added. The direct revenue is the revenue of the service item to be added, and the indirect revenue is the revenue brought by the increase in customer traffic after adding the service item to be added, which brings about an increase in other services at the target site. For example, a gas station added an antifreeze replacement service, which brought about an increase in customer traffic. The new customers will refuel at the gas station, which brings about an increase in indirect revenue.

[0034] In this embodiment, the cost-benefit data is calculated based on the fourth formula, which can accurately predict the benefits brought by adding a certain service item to be added, thus avoiding blind addition of services and economic losses.

[0035] In one exemplary embodiment, step S300 may include steps S311-S312: S311: Input the demand data corresponding to the service item to be added into the preset membership function F respectively. 11 F 12 F 13 Obtain the corresponding membership degree D 11 D 12 D 13 ; S312: If D 11 ≠0, the service item to be added is related to D 11 The correspondence is set in the preset fuzzy set G. 11 Inside; if D 12 ≠0, the service item to be added is related to D 12 The correspondence is set in the preset fuzzy set G. 12 Inside; if D 13 ≠0, the service item to be added is related to D 13 The correspondence is set in the preset fuzzy set G. 13 Inside.

[0036] In this embodiment, the membership array D1 may include D 11 D 12 and D 13 The fuzzy set group G1 may include the fuzzy set G 11 G 12 and G 13 The fuzzy set G 11 The membership function is F 11 The fuzzy set G 12 The membership function is F 12 The fuzzy set G 13 The membership function is F 13 .

[0037] In this embodiment, the membership function F 11 It can be: If the required data is greater than or equal to X1, the membership degree D 11 =A1; If X2 ≤ required data < X1, membership degree D 11 =A2; If the required data < X2, the membership degree D 11 =A3; where 1≥A1>A2>A3≥0.

[0038] The membership function F 12 It can be: If the required data is greater than or equal to X1, the membership degree D 12 =A4; If X2 ≤ required data < X1, the membership degree D 12 =A5; If the required data < X2, the membership degree D 12 =A6; where 1≥A5>A4≥0, 1≥A5>A6≥0; The membership function F 13 It can be: If the required data is greater than or equal to X1, the membership degree D 13 =A7; If X2 ≤ required data < X1, membership degree D 13 =A8; If the required data < X2, the membership degree D 13= A9; where, 1 ≥ A9 > A8 > A7 ≥ 0.

[0039] In this embodiment, both X1 and X2 can be preset demand thresholds, and X1 > X2.

[0040] In this embodiment, a fuzzy set group G1 and a fuzzy variable "demand intensity" can be preset for the demand data. The fuzzy set group G1 includes three preset fuzzy sets G 11 , G 12 , G 13 , and a linguistic variable and a membership function are preset for each fuzzy set. Among them, the linguistic variable of G 11 can be "high", and the membership function can be F 11 ; the linguistic variable of G 12 can be "medium", and the membership function can be F 12 ; the linguistic variable of G 13 can be "low", and the membership function can be F 13 .

[0041] In this embodiment, for example, X1 can be 70, X2 can be 40, A1 can be 0.8, A2 can be 0.2, A3 can be 0.0, A4 can be 0.2, A5 can be 0.8, A6 can be 0.2, A7 can be 0.0, A8 can be 0.2, A9 can be 0.8. Correspondingly, the membership functions F 11 , F 12 , F 13 can be as follows: F 11 : If the demand data ≥ 70, the membership degree D 11 = 0.8; If 40 ≤ demand data < 70, the membership degree D 11 = 0.2; If the demand data < 40, the membership degree D 11 = 0.0; F 12 : If the demand data ≥ 70, the membership degree D 12 = 0.2; If 40 ≤ demand data < 70, the membership degree D 12 = 0.8; If the demand data < 40, the membership degree D 12 = 0.2; F 13 : If the demand data ≥ 70, the membership degree D 13 = 0.0; If 40 ≤ demand data < 70, the membership degree D 13 = 0.2; If the demand data < 40, the membership degree D13 =0.8; For example, if the required data for a service item to be added is 75 according to the first formula, then according to the membership function F... 11 Obtain the membership degree D 11 =0.8, according to the membership function F 12 Obtain the membership degree D 12 =0.2, according to the membership function F 13 Obtain the membership degree D 13 =0.0, then the membership array D1=(D 11 D 12 D 13 = (0.8, 0.2, 0.0).

[0042] In one exemplary embodiment, step S300 may include steps S321-S322: S321: Input the competitive data corresponding to the service item to be added into the preset membership function F respectively. 21 F 22 F 23 Obtain the corresponding membership degree D 21 D 22 D 23 ; S322: If D 21 ≠0, the service item to be added is related to D 21 The correspondence is set in the preset fuzzy set G. 21 Inside; if D 22 ≠0, the service item to be added is related to D 22 The correspondence is set in the preset fuzzy set G. 22 Inside; if D 23 ≠0, the service item to be added is related to D 23 The correspondence is set in the preset fuzzy set G. 23 Inside.

[0043] In this embodiment, the membership array D2 may include D 21 D 22 and D 23 The fuzzy set group G2 may include the fuzzy set G 21 G 22 and G 23 The fuzzy set G 21 The membership function is F 21 The fuzzy set G 22 The membership function is F 22 The fuzzy set G 23 The membership function is F 23 .

[0044] In this embodiment, the membership function F 21 can be: if the competitive data ≥ X3, the membership degree D 21 = B1; if X4 ≤ competitive data < X3, the membership degree D 21 = B2; if the competitive data < X4, the membership degree D 21 = B3; where 1 ≥ B1 > B2 > B3 ≥ 0; The membership function F 22 can be: if the competitive data ≥ X3, the membership degree D 22 = B4; if X4 ≤ competitive data < X3, the membership degree D 22 = B5; if the competitive data < X4, the membership degree D 22 = B6; where 1 ≥ B5 > B4 ≥ 0, 1 ≥ B5 > B6 ≥ 0; The membership function F 23 can be: if the competitive data ≥ X3, the membership degree D 23 = B7; if X4 ≤ competitive data < X3, the membership degree D 23 = B8; if the competitive data < X4, the membership degree D 23 = B9; where 1 ≥ B9 > B8 > B7 ≥ 0.

[0045] In this embodiment, X3 and X4 can both be preset competitive thresholds, and X3 > X4.

[0046] In this embodiment, a fuzzy set group G2 and a fuzzy variable "competition intensity" can be preset for the competitive data. The fuzzy set group G2 includes three preset fuzzy sets G 21 , G 22 , G 23 , and a linguistic variable and a membership function are preset for each fuzzy set. Among them, the linguistic variable of G 21 can be "strong", and the membership function can be F 21 ; the linguistic variable of G 22 can be "medium", and the membership function can be F 22 ; the linguistic variable of G 23 can be "weak", and the membership function can be F 23 .

[0047] In this embodiment, for example, X3 can be 70, X4 can be 40, B1 can be 0.8, B2 can be 0.2, B3 can be 0.0, B4 can be 0.2, B5 can be 0.8, B6 can be 0.2, B7 can be 0.0, B8 can be 0.2, B9 can be 0.8. Correspondingly, the membership functions F 21 , F 22 , F 23It can be as follows: F 21 If the number of competing data points is ≥70, the membership degree D is... 21 =0.8; If 40 ≤ competitive data < 70, the membership degree D 21 =0.2; If the number of competing data is less than 40, the membership degree D 21 =0.0; F 22 If the number of competing data is ≥70, the membership degree D 22 =0.2; If 40 ≤ competitive data < 70, the membership degree D 22 =0.8; If the number of competing data is less than 40, the membership degree D 22 =0.2; F 23 If the number of competing data points is ≥70, the membership degree D is... 23 =0.0; If 40 ≤ competitive data < 70, the membership degree D 23 =0.2; If the number of competing data is less than 40, the membership degree D 23 =0.8; For example, if the competitiveness data calculated according to the second formula is 50 for a service item to be added, then according to the membership function F... 21 Obtain the membership degree D 21 =0.2, according to the membership function F 22 Obtain the membership degree D 22 =0.8, according to the membership function F 23 Obtain the membership degree D 23 =0.2, then the membership array D2=(D 21 D 22 D 23 = (0.2, 0.8, 0.2).

[0048] In one exemplary embodiment, step S300 may include steps S331-S332: S331: Input the target site capability data corresponding to the service item to be added into the preset membership function F respectively. 31 F 32 F 33 Obtain the corresponding membership degree D 31 D 32 D 33 ; S332: If D 31 ≠0, the service item to be added is related to D 31The correspondence is set in the preset fuzzy set G. 31 Inside; if D 32 ≠0, the service item to be added is related to D 32 The correspondence is set in the preset fuzzy set G. 32 Inside; if D 33 ≠0, the service item to be added is related to D 33 The correspondence is set in the preset fuzzy set G 33 Inside.

[0049] In this embodiment, the membership array D3 may include D 31 D 32 and D 33 The fuzzy set group G3 may include the fuzzy set G 31 G 32 and G 33 The fuzzy set G 31 The membership function is F 31 The fuzzy set G 32 The membership function is F 32 The fuzzy set G 33 The membership function is F 33 .

[0050] In this embodiment, the membership function F 31 It can be: If the target site's capability data is ≥ X5, the membership degree D 31 =C1; If X6 ≤ target site capability data < X5, membership degree D 31 =C2; If the target site capability data < X6, the membership degree D 31 =C3; where 1≥C1>C2>C3≥0; The membership function F 32 It can be: If the target site's capability data is ≥ X5, the membership degree D 32 =C4; If X6 ≤ target site capability data < X5, membership degree D 32 =C5; If the target site capability data < X6, the membership degree D 32 =C6; where 1≥C5>C4≥0, 1≥C5>C6≥0; The membership function F 33 It can be: If the target site's capability data is ≥ X5, the membership degree D 33 =C7; If X6 ≤ target site capability data < X5, membership degree D 33 =C8; If the target site capability data < X6, the membership degree D 33 =C9; where 1≥C9>C8>C7≥0.

[0051] In this embodiment, X5 and X6 can both be preset target site capability thresholds, and X5 > X6.

[0052] In this embodiment, a fuzzy set group G3 and a fuzzy variable "operational capability" can be pre-set for the target site capability data. The fuzzy set group G3 includes three preset fuzzy sets G 31 G 32 G 33 And pre-define linguistic variables and membership functions for each fuzzy set, where G 31 The linguistic variable can be "sufficient", and the membership function can be F. 31 G 32 The linguistic variable can be "general", and the membership function can be F. 32 G 33 The linguistic variable can be "scarcity", and the membership function can be F. 33 .

[0053] In this embodiment, for example, X5 can be 70, X6 can be 40, C1 can be 1.0, C2 can be 0.5, C3 can be 0.0, C4 can be 0.2, C5 can be 1.0, C6 can be 0.2, C7 can be 0.0, C8 can be 0.5, and C9 can be 1.0. Correspondingly, the membership function F 31 F 32 F 33 It can be as follows: F 31 If the target site's capability data is ≥70, the membership degree D 31 =1.0; If 40 ≤ target site capability data < 70, membership degree D 31 =0.5; If the target site's capability data is less than 40, the membership degree D 31 =0.0; F 32 If the target site's capability data is ≥70, the membership degree D 32 =0.2; If 40 ≤ target site capability data < 70, membership degree D 32 =1.0; If the target site's capability data is less than 40, the membership degree D 32 =0.2; F 33 If the target site's capability data is ≥70, the membership degree D 33 =0.0; If 40 ≤ target site capability data < 70, membership degree D 33 =0.5; If the target site's capability data is less than 40, the membership degree D33 =1.0; For example, if the target site capability data calculated according to the third formula is 20, then according to the membership function F... 31 Obtain the membership degree D 31 =0.0, according to the membership function F 32 Obtain the membership degree D 32 =0.2, according to the membership function F 33 Obtain the membership degree D 33 =1.0, then the membership array D3=(D 31 D 32 D 33 ) = (0.0, 0.2, 1.0).

[0054] In one exemplary embodiment, step S300 may include steps S341-S342: S341: Input the cost and revenue data corresponding to the service item to be added into the preset membership function F respectively. 41 F 42 F 43 Obtain the corresponding membership degree D 41 D 42 D 43 ; S342: If D 41 ≠0, the service item to be added is related to D 41 The correspondence is set in the preset fuzzy set G. 41 Inside; if D 42 ≠0, the service item to be added is related to D 42 The correspondence is set in the preset fuzzy set G. 42 Inside; if D 43 ≠0, the service item to be added is related to D 43 The correspondence is set in the preset fuzzy set G. 43 Inside.

[0055] In this embodiment, the membership array D4 may include D 41 D 42 and D 43 The fuzzy set group G4 may include the fuzzy set G 41 G 42 and G 43 The fuzzy set G 41 The membership function is F 41 The fuzzy set G 42 The membership function is F 42 The fuzzy set G 43 The membership function is F 43 .

[0056] In this embodiment, the membership function F 41 can be: If the cost-benefit data ≥ X7, the membership degree D 41 = E1; if X8 ≤ cost-benefit data < X7, the membership degree D 41 = E2; if the cost-benefit data < X8, the membership degree D 41 = E3; where 1 ≥ E1 > E2 > E3 ≥ 0; The membership function F 42 can be: If the cost-benefit data ≥ X7, the membership degree D 42 = E4; if X8 ≤ cost-benefit data < X7, the membership degree D 42 = E5; if the cost-benefit data < X8, the membership degree D 42 = E6; where 1 ≥ E5 > E4 ≥ 0, 1 ≥ E5 > E6 ≥ 0; The membership function F 43 can be: If the cost-benefit data ≥ X7, the membership degree D 43 = E7; if X8 ≤ cost-benefit data < X7, the membership degree D 43 = E8; if the cost-benefit data < X8, the membership degree D 43 = E9; where 1 ≥ E9 > E8 > E7 ≥ 0.

[0057] In this embodiment, both X7 and X8 can be preset cost-benefit thresholds, and X7 > X8.

[0058] In this embodiment, a fuzzy set group G4 and a fuzzy variable "benefit" can be preset for the target site capacity data. The fuzzy set group G4 includes three preset fuzzy sets G 41 , G 42 , G 43 , and a linguistic variable and a membership function are preset for each fuzzy set. Among them, the linguistic variable of G 41 can be "high", and the membership function can be F 41 ; the linguistic variable of G 42 can be "medium", and the membership function can be F 42 ; the linguistic variable of G 43 can be "low", and the membership function can be F 43 .

[0059] In this embodiment, when the cost-benefit data is the rate of return on investment, the preset cost-benefit threshold can be a preset rate of return on investment threshold. That is, X7 and X8 can both be preset rate of return on investment thresholds. For example, X7 can be 25%, X8 can be 10%, E1 can be 0.8, E2 can be 0.5, E3 can be 0.0, E4 can be 0.2, E5 can be 0.8, E6 can be 0.2, E7 can be 0.0, E8 can be 0.5, and E9 can be 0.8. Correspondingly, the membership function F... 41 F 42 F 43 It can be as follows: F 41 If the rate of return on investment is ≥25%, the membership degree D 41 =0.8; If 10% ≤ return on investment < 25%, the membership degree D 41 =0.5; If the rate of return on investment is less than 10%, the membership degree D 41 =0.0; F 42 If the rate of return on investment is ≥25%, the membership degree D 42 =0.2; If 10% ≤ return on investment < 25%, the membership degree D 42 =0.8; If the rate of return on investment is less than 10%, the membership degree D 42 =0.2; F 43 If the rate of return on investment is ≥25%, the membership degree D 43 =0.0; If 10% ≤ return on investment < 25%, the membership degree D 43 =0.5; If the rate of return on investment is less than 10%, the membership degree D 43 =0.8; For example, if the return on investment for a service to be added is 50% according to the fourth formula, then according to the membership function F... 41 Obtain the membership degree D 41 =0.8, according to the membership function F 42 Obtain the membership degree D 42 =0.2, according to the membership function F 43 Obtain the membership degree D 43 =0.0, then the membership array D4=(D 41 D 42 D 43 = (0.8, 0.2, 0.0).

[0060] In an exemplary embodiment, step S400 may include steps S410 - S440: S410: Input the fuzzy set groups G1, G2, G3, and G4 corresponding to the to - be - added service item into N fuzzy rule bases, and obtain suggestions corresponding one - to - one to the fuzzy rule bases, where 2 ≤ N ≤ 4; S420: Reason about each of the N suggestions respectively to obtain a fuzzy degree corresponding one - to - one to the suggestion. Perform comprehensive reasoning based on the N fuzzy degrees and a predetermined algorithm to obtain a total fuzzy degree, where the predetermined algorithm includes the maximum - value method, the minimum - value method, or the weighted - average method; S430: Perform defuzzification processing on the total fuzzy degree using the centroid method to generate an accurate result after defuzzification; S440: Generate the decision suggestion corresponding to the to - be - added service item according to the accurate result, the total fuzzy degree, and the fuzzy set groups G1, G2, G3, and G4.

[0061] In this embodiment, step S410 may be executed based on the fuzzy rule bases of the inference decision module. The number of fuzzy rule bases may be 2, 3, or 4. The input of the fuzzy rule base is a fuzzy set group, including a fuzzy variable corresponding to the fuzzy set group, multiple fuzzy sets under the fuzzy set group, and linguistic variables of each fuzzy set. Step S420 may be executed based on the inference module of the inference decision module, where 0 ≤ fuzzy degree ≤ 1 and 0 ≤ total fuzzy degree ≤ 1. Step S430 may be executed based on the defuzzification module of the inference decision module, and the accurate result represents a comprehensive suggestion degree. Step S440 may be executed based on the decision - suggestion generation module of the inference decision module.

[0062] In an exemplary embodiment, each of the fuzzy rule bases includes multiple rules, and each rule includes a judgment condition and the suggestion; The judgment condition includes at least one fuzzy variable and a linguistic variable corresponding to the fuzzy variable. Among them, the fuzzy set groups G1, G2, G3, and G4 respectively correspond to one fuzzy variable. Each of the fuzzy set groups includes multiple fuzzy sets, and the fuzzy sets correspond one - to - one to the linguistic variables.

[0063] In this embodiment, the fuzzy variable of the fuzzy set group G1 is "demand intensity", G1 includes fuzzy sets G 11 、G 12 、G 13 ,the linguistic variable of G 11 is "high", the linguistic variable of G 12 is "medium", and the linguistic variable of G 13 is "low".

[0064] In this embodiment, the fuzzy variable of the fuzzy set group G2 is "competition intensity", and G2 includes fuzzy sets G 21 , G 22 , G 23 . The linguistic variable of G 21 is "strong", the linguistic variable of G 22 is "medium", and the linguistic variable of G 23 is "weak".

[0065] In this embodiment, the fuzzy variable of the fuzzy set group G3 is "operation ability", and G3 includes fuzzy sets G 31 , G 32 , G 33 . The linguistic variable of G 31 is "sufficient", the linguistic variable of G 32 is "average", and the linguistic variable of G 33 is "scarce".

[0066] In this embodiment, the fuzzy variable of the fuzzy set group G4 is "revenue", and G4 includes fuzzy sets G 41 , G 42 , G 43 . The linguistic variable of G 41 is "high", the linguistic variable of G 42 is "medium", and the linguistic variable of G 43 is "low".

[0067] To illustrate steps S410 - S440 of the embodiment of the present application in detail, the following uses a specific example one to elaborate: In this specific example, the fuzzy rule base in step S410 includes 3 fuzzy rule bases: the first rule base, the second rule base, and the third rule base, and the service item to be added is the car wash service.

[0068] The judgment condition of each rule in the first rule base can include the fuzzy variables "demand intensity + linguistic variable" and "competition intensity + linguistic variable", and the suggestion of each rule includes the degree of suggesting to add the car wash service, that is, taking the fuzzy set groups G1 (including fuzzy sets G 11 , G 12 , G 13 ) and G2 (including fuzzy sets G 21 , G 22 , G 23 ) as the input of the first rule base, and obtaining a corresponding suggestion for the car wash service; The first rule base can include rules R 11 , R 12 , R 13 : "R 11If demand is high and competition is weak, it is recommended to add car wash services. R 12 If demand is high and competition is moderate, it is advisable to add car wash services. R 13 "If demand is high and competition is fierce, it is not recommended to add a car wash service."

[0069] The judgment conditions for each rule in the second rule base can include fuzzy variables "demand intensity + linguistic variable" and "operational capability + linguistic variable". Each rule's suggestion includes the degree to which it recommends adding car wash services, i.e., the degree of suggestion from the fuzzy set group G1 (including fuzzy set G...). 11 G 12 G 13 ) and G3 (including fuzzy set G) 31 G 32 G 33 As input to the second rule base, a corresponding suggestion is obtained for the car wash service; The second rule base can include rule R 21 R 22 R 23 : “R 21 If demand is high and operational capacity is sufficient, it is recommended to add car wash services. R 22 If demand is high and operational capacity is average, it is recommended to add car wash service. R 23 "If demand is low and operational capacity is insufficient, it is not recommended to add car wash services."

[0070] The judgment conditions for each rule in the third rule base can include the fuzzy variable "benefit + linguistic variable". Each rule's suggestion includes the degree to which it recommends adding a car wash service, i.e., the fuzzy set group G4 (including the fuzzy set G...). 41 G 42 G 43 As input to the third rule base, a corresponding suggestion is obtained for the car wash service; The third rule base can include rule R 31 R 32 R 33 : “R 31 If the revenue is high, it is recommended to add car wash service; R 32 If the business is profitable, it would be advisable to add a car wash service. R 33 "If the revenue is low, it is not recommended to add a car wash service."

[0071] For example, during step S410, three suggestions are obtained at once based on the first, second, and third rule bases: not recommending adding a car wash service, recommending adding a car wash service, and recommending adding a car wash service. During step S420, reasoning is performed based on these three suggestions. The reasoning module pre-stores the fuzziness corresponding to each suggestion. For example, "recommend adding a car wash service—fuzziness 0.8, compare recommendations to add a car wash service—fuzziness 0.4, not recommending adding a car wash service—fuzziness 0," then the fuzzinesses obtained based on the above three suggestions are 0, 0.8, and 0.8 respectively. During the comprehensive reasoning in step S420, when the predetermined algorithm is maximum... If the algorithm is the minimum value method, the total ambiguity is max(0, 0.8, 0.8) = 0.8; if the algorithm is the minimum value method, the total ambiguity is min(0, 0.8, 0.8) = 0; if the algorithm is the weighted average method, the total ambiguity is calculated according to the weighted average formula, which is: total ambiguity = weight1 × ambiguity1 + weight2 × ambiguity2 + weight3 × ambiguity3 (weight1 + weight2 + weight3 = 1). The inference module has pre-stored weight1 = 0.2, weight2 = 0.4, and weight3 = 0.4, so the total ambiguity is 0.2 × 0 + 0.4 × 0.8 + 0.4 × 0.8 = 0.64.

[0072] When performing deblurring in step S430, a total ambiguity of 0.64 obtained based on the weighted average method is selected, and the centroid method is used for deblurring. The deblurring module pre-stores four suggestion intervals: "Strongly recommended [0.7, 1.0]; Recommended [0.4, 0.7]; Neutral [0.3, 0.4]; Not recommended [0, 0.3]". Each suggestion interval corresponds to an isosceles triangle membership function X=(a+b+c) / 3, where a represents the left endpoint of the isosceles triangle (corresponding to the left endpoint of the suggestion interval), c represents the left endpoint of the isosceles triangle, and c represents the right endpoint of the isosceles triangle. The right endpoint of the isosceles triangle (corresponding to the right endpoint of the suggested interval), b represents the vertex of the isosceles triangle, and X represents the precise result; since the total ambiguity of 0.64 falls within the interval range of "suggested [0.4, 0.7)", a=0.4, c=0.7, b=0.55, when using the centroid method for defuzzification, the precise result is obtained according to the formula X=(a+b+c) / 3=(0.4+0.55+0.7) / 3=0.55, that is, the precise result obtained in step S430 is 0.55, which represents the comprehensive suggestion degree of adding car wash service is 0.55.

[0073] When executing step S440, the exact result is 0.55, the total ambiguity is 0.64, and the fuzzy set group G1(G 11 G 12 G 13 ), Fuzzy set group G2=(G 21 G 22 G 23), Fuzzy set group G3=(G 31 G 32 G 33 ), Fuzzy set group G4=(G 41 G 42 G 43 The above parameters are input into the decision suggestion generation module to generate decision suggestions corresponding to the car wash service. The decision suggestions include the following aspects: 1. Based on the total ambiguity of 0.64 and the precise result of 0.55, it is generally recommended to add car wash services. 2. Opportunities and Challenges: Opportunity: High demand intensity (D) 21 =0.8), sufficient operational capacity (D 31 =1.0) and high returns (D 41 =0.8), strongly support adding car wash service; Challenge: High level of competition (D) 21 =0.8), which is the only risk factor; 3. Strategy Recommendations: Offer differentiated car wash services: Develop unique or high-quality car wash services to stand out in a highly competitive market; Marketing strategy: Develop promotional strategies to attract customers and increase service awareness; Financial control: Although the expected returns are high, it is still necessary to closely monitor costs and revenues to ensure that the actual return on investment meets or exceeds expectations; Market monitoring: Regularly obtain the latest car wash-related demands and competitive information, and adjust business strategies accordingly. Rapid implementation: With most indicators favorable, implementation can be considered as soon as possible; 4. Risk Management: Continuously monitor market changes and maintain strategic flexibility; Develop specific strategies to cope with fierce competition, such as providing excellent customer service and membership benefit programs; 5. Follow-up actions: Conduct detailed market research to gain a deep understanding of customer needs and competitors; Develop a detailed implementation plan, including equipment procurement, personnel training, and marketing strategies; Set key performance indicators (KPIs) and regularly evaluate the performance of new services; Consider synergies with existing gas station operations, such as joint promotional activities.

[0074] This application embodiment also provides a decision suggestion generation device for adding site services, including a memory and a processor, such as... Figure 2 As shown, The memory is used to store the decision suggestion generation program for adding site services; The processor is configured to read the decision suggestion generation program for adding site services and perform the decision suggestion generation method for adding site services as described in any one of claims 1-9.

[0075] It will be understood by those skilled in the art that all or some of the steps, systems, or apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term "computer storage medium" includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

Claims

1. A method for generating decision suggestions for adding site services, characterized in that, include: Obtain a set of candidate services for a target site, wherein the set of candidate services includes multiple service items to be added to the target site; For each of the service items to be added, perform the following steps: Obtain the quantitative data corresponding to the service item to be added, including demand data, competitive data, target site capability data, and cost-benefit data; The quantitative data corresponding to the service item to be added is fuzzified to obtain the membership array D1 and fuzzy set group G1 corresponding to the demand data; the membership array D2 and fuzzy set group G2 corresponding to the competitive data; the membership array D3 and fuzzy set group G3 corresponding to the target site capability data; and the membership array D4 and fuzzy set group G4 corresponding to the cost and benefit data. Fuzzy logic reasoning is performed on the fuzzy set group G1, G2, G3, and G4 corresponding to the service item to be added to generate decision suggestions corresponding to the service item to be added.

2. The method for generating decision suggestions for adding site services as described in claim 1, characterized in that, The process of obtaining the set of candidate services for the target site includes: Obtain the existing service set of all stations within the target area and the service demand set of the customer group within the target area, wherein the target station is located within the target area, the existing service set includes the existing service items of all stations within the target area, and the service demand set includes the service items demanded by the customer group within the target area. Calculate the union of the existing service set and the service demand set, and remove the existing service items of the target site from the service items contained in the union, then form the candidate service set from the remaining service items.

3. The method for generating decision suggestions for adding site services as described in claim 1, characterized in that, The step of obtaining the quantitative data corresponding to the service item to be added includes demand data, competition data, target site capability data, and cost-benefit data, including: Obtain the demand parameters of the service item to be added, input the demand parameters into the first formula for calculation, and use the calculated value as the demand data corresponding to the service item to be added. The demand parameters include the total demand frequency of the service item to be added, the demand frequency corresponding to each season, and the economic prosperity value. Obtain the competitive parameters of the service item to be added, input the competitive parameters into the second formula for calculation, and use the calculated value as the competitive data corresponding to the service item to be added. The competitive parameters include the market share of the service item to be added, the service quality data of competitors, the service pricing data, and the customer satisfaction data. Obtain the target site parameters for the service item to be added, input the target site parameters into the third formula for calculation, and use the calculated value as the target site capability data corresponding to the service item to be added. The target site parameters include target site area data, human resources data, and current facility data. Obtain the cost-benefit parameters of the service item to be added, input the cost-benefit parameters into the fourth formula for calculation, and use the calculated value as the cost-benefit data corresponding to the service item to be added. The cost-benefit parameters include the initial investment cost, annual operating cost, and expected annual revenue.

4. The method for generating decision suggestions for adding site services as described in claim 1, characterized in that, The step of fuzzifying the quantified data corresponding to the service item to be added, to obtain the membership array D1 and fuzzy set group G1 corresponding to the demand data, includes: The required data corresponding to the service item to be added is respectively input into the preset membership function F. 11 F 12 F 13 Obtain the corresponding membership degree D 11 D 12 D 13 ; If D 11 ≠0, the service item to be added is related to D 11 The correspondence is set in the preset fuzzy set G. 11 Inside; if D 12 ≠0, the service item to be added is related to D 12 The correspondence is set in the preset fuzzy set G. 12 Inside; if D 13 ≠0, the service item to be added is related to D 13 The correspondence is set in the preset fuzzy set G. 13 Inside; Wherein, the membership array D1 includes D 11 D 12 and D 13 The fuzzy set group G1 includes the fuzzy set G 11 G 12 and G 13 The fuzzy set G 11 The membership function is F 11 The fuzzy set G 12 The membership function is F 12 The fuzzy set G 13 The membership function is F 13 ; The membership function F 11 For example: If the required data is greater than or equal to X1, the membership degree D is... 11 =A1; If X2 ≤ required data < X1, membership degree D 11 =A2; If the required data < X2, the membership degree D 11 =A3; where 1≥A1>A2>A3≥0; The membership function F 12 For example: If the required data is greater than or equal to X1, the membership degree D is... 12 =A4; If X2 ≤ required data < X1, the membership degree D 12 =A5; If the required data < X2, the membership degree D 12 =A6; where 1≥A5>A4≥0, 1≥A5>A6≥0; The membership function F 13 For example: If the required data is greater than or equal to X1, the membership degree D is... 13 =A7; If X2 ≤ required data < X1, membership degree D 13 =A8; If the required data < X2, the membership degree D 13 =A9; where 1≥A9>A8>A7≥0; X1 and X2 are both preset demand thresholds, and X1 > X2.

5. The method for generating decision suggestions for adding site services as described in claim 1, characterized in that, The step of fuzzifying the quantized data corresponding to the service item to be added, to obtain the membership array D2 and fuzzy set group G2 corresponding to the competing data, includes: The competitive data corresponding to the service item to be added is respectively input into the preset membership function F. 21 F 22 F 23 Obtain the corresponding membership degree D 21 D 22 D 23 ; If D 21 ≠0, the service item to be added is related to D 21 The correspondence is set in the preset fuzzy set G. 21 Inside; if D 22 ≠0, the service item to be added is related to D 22 The correspondence is set in the preset fuzzy set G. 22 Inside; if D 23 ≠0, the service item to be added is related to D 23 The correspondence is set in the preset fuzzy set G. 23 Inside; Wherein, the membership array D2 includes D 21 D 22 and D 23 The fuzzy set group G2 includes the fuzzy set G. 21 G 22 and G 23 The fuzzy set G 21 The membership function is F 21 The fuzzy set G 22 The membership function is F 22 The fuzzy set G 23 The membership function is F 23 ; The membership function F 21 For example: if the number of competing data is greater than or equal to X3, the membership degree D is... 21 =B1; If X4 ≤ competitive data < X3, membership degree D 21 =B2; If the competing data < X4, the membership degree D 21 =B3; where 1≥B1>B2>B3≥0; The membership function F 22 For example: if the number of competing data is greater than or equal to X3, the membership degree D is... 22 =B4; If X4 ≤ competitive data < X3, membership degree D 22 =B5; If the competing data < X4, the membership degree D 22 =B6; where 1≥B5>B4≥0, 1≥B5>B6≥0; The membership function F 23 For example: if the number of competing data is greater than or equal to X3, the membership degree D is... 23 =B7; If X4 ≤ competitive data < X3, membership degree D 23 =B8; If the competing data < X4, the membership degree D 23 =B9; where 1≥B9>B8>B7≥0; X3 and X4 are both preset competitive thresholds, and X3 > X4.

6. The method for generating decision suggestions for adding site services as described in claim 1, characterized in that, The step of fuzzifying the quantized data corresponding to the service item to be added, to obtain the membership array D3 and fuzzy set group G3 corresponding to the target site capability data, includes: The target site capability data corresponding to the service item to be added is respectively input into the preset membership function F. 31 F 32 F 33 Obtain the corresponding membership degree D 31 D 32 D 33 ; If D 31 ≠0, the service item to be added is related to D 31 The correspondence is set in the preset fuzzy set G. 31 Inside; if D 32 ≠0, the service item to be added is related to D 32 The correspondence is set in the preset fuzzy set G. 32 Inside; if D 33 ≠0, the service item to be added is related to D 33 The correspondence is set in the preset fuzzy set G 33 Inside; Wherein, the membership array D3 includes D 31 D 32 and D 33 The fuzzy set group G3 includes the fuzzy set G. 31 G 32 and G 33 The fuzzy set G 31 The membership function is F 31 The fuzzy set G 32 The membership function is F 32 The fuzzy set G 33 The membership function is F 33 ; The membership function F 31 For example: If the target site's capability data is ≥ X5, the membership degree D is... 31 =C1; If X6 ≤ target site capability data < X5, membership degree D 31 =C2; If the target site capability data < X6, the membership degree D 31 =C3; where 1≥C1>C2>C3≥0; The membership function F 32 For example: If the target site's capability data is ≥ X5, the membership degree D is... 32 =C4; If X6 ≤ target site capability data < X5, membership degree D 32 =C5; If the target site capability data < X6, the membership degree D 32 =C6; where 1≥C5>C4≥0, 1≥C5>C6≥0; The membership function F 33 For example: If the target site's capability data is ≥ X5, the membership degree D is... 33 =C7; If X6 ≤ target site capability data < X5, membership degree D 33 =C8; If the target site capability data < X6, the membership degree D 33 =C9; where 1≥C9>C8>C7≥0; Both X5 and X6 are preset target site capability thresholds, and X5 > X6.

7. The method for generating decision suggestions for adding site services as described in claim 1, characterized in that, The step of fuzzifying the quantitative data corresponding to the service item to be added, to obtain the membership array D4 and fuzzy set group G4 corresponding to the cost-benefit data, includes: The cost and revenue data corresponding to the service item to be added are respectively input into the preset membership function F. 41 F 42 F 43 Obtain the corresponding membership degree D 41 D 42 D 43 ; If D 41 ≠0, the service item to be added is related to D 41 The correspondence is set in the preset fuzzy set G. 41 Inside; if D 42 ≠0, the service item to be added is related to D 42 The correspondence is set in the preset fuzzy set G. 42 Inside; if D 43 ≠0, the service item to be added is related to D 43 The correspondence is set in the preset fuzzy set G. 43 Inside; Wherein, the membership array D4 includes D 41 D 42 and D 43 The fuzzy set group G4 includes the fuzzy set G. 41 G 42 and G 43 The fuzzy set G 41 The membership function is F 41 The fuzzy set G 42 The membership function is F 42 The fuzzy set G 43 The membership function is F 43 ; The membership function F 41 For example: If the cost-benefit data is ≥ X7, the membership degree D is... 41 =E1; If X8 ≤ cost-benefit data < X7, membership degree D 41 =E2; If cost-benefit data <X8, membership degree D 41 =E3; where 1≥E1>E2>E3≥0; The membership function F 42 For example: If the cost-benefit data is ≥ X7, the membership degree D is... 42 =E4; If X8 ≤ cost-benefit data < X7, membership degree D 42 =E5; If cost-benefit data <X8, membership degree D 42 =E6; where 1≥E5>E4≥0, 1≥E5>E6≥0; The membership function F 43 For example: If the cost-benefit data is ≥ X7, the membership degree D is... 43 =E7; If X8 ≤ cost-benefit data < X7, membership degree D 43 =E8; If cost-benefit data <X8, membership degree D 43 =E9; where 1≥E9>E8>E7≥0; Both X7 and X8 are preset cost-benefit thresholds, and X7 > X8.

8. The method for generating decision suggestions for adding site services as described in claim 1, characterized in that, The step of performing fuzzy logic reasoning on the fuzzy set group G1, G2, G3, and G4 corresponding to the service item to be added, and generating decision suggestions corresponding to the service item to be added, includes: Input the fuzzy set groups G1, G2, G3 and G4 corresponding to the service item to be added into N fuzzy rule bases to obtain suggestions that correspond one-to-one with the fuzzy rule bases, where 2≤N≤4; Reasoning is performed on each of the N suggestions to obtain the ambiguity corresponding to each suggestion. Based on the N ambiguities and a predetermined algorithm, a comprehensive reasoning is performed to obtain the total ambiguity. The predetermined algorithm includes the maximum value method, the minimum value method, or the weighted average method. The total ambiguity is defuzzified using the centroid method to generate a precise defuzzified result; Based on the precise results, the total fuzziness, and the fuzzy set groups G1, G2, G3, and G4, a decision suggestion corresponding to the service item to be added is generated.

9. The method for generating decision suggestions for adding site services as described in claim 8, characterized in that: Each of the aforementioned fuzzy rule bases includes multiple rules, and each rule includes a judgment condition and the aforementioned suggestion; The judgment condition includes at least one fuzzy variable and a linguistic variable corresponding to the fuzzy variable. The fuzzy set groups G1, G2, G3 and G4 each correspond to one of the fuzzy variables. Each fuzzy set group includes multiple fuzzy sets, and the fuzzy sets correspond one-to-one with the linguistic variables.

10. A decision suggestion generation device for adding site services, comprising a memory and a processor, characterized in that: The memory is used to store the decision suggestion generation program for adding site services; The processor is configured to read the decision suggestion generation program for adding site services and perform the decision suggestion generation method for adding site services as described in any one of claims 1-9.

Images