Automobile maintenance industry business index construction method based on multi-source data fusion

Abstract

The invention discloses an automobile maintenance industry prosperity index construction method based on multi-source data fusion. The method comprises the following steps: collecting monthly index data of an automobile maintenance industry; screening the monthly index data to obtain screened monthly index data; converting the screened monthly index data into index diffusion indexes of five dimensions; carrying out weight distribution on the indexes of the five dimensions based on an improved Delphi method, and calculating the business index of the automobile maintenance industry according to the distributed weight and the corresponding index diffusion index; according to the method, related data are collected in combination with five dimensions, the automobile maintenance industry condition index capable of dynamically monitoring industry condition changes is constructed, and a quantitative basis is provided for automobile maintenance enterprise operation decision making, investment planning and government policy making.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of transportation economy, and particularly relates to a method for constructing an automobile repair industry prosperity index based on multi-source data fusion. BACKGROUND

[0002] At present, the automobile repair industry in China is in a critical period of scale expansion and structural transformation. With the continuous and rapid rise of the number of motor vehicles in society, the market foundation is expanding, but contrary to the macro trend, the actual business volume of a large number of automobile repair enterprises is generally lower than their market expectations. The entire industry is seriously lagging in operation monitoring, trend analysis and scientific decision support capability. Due to the lack of accurate grasp of market micro fluctuations and macro cycles, repair enterprises are difficult to make scientific production plans and marketing strategies, and industry management departments are also difficult to introduce forward-looking guiding policies, which to some extent leads to inefficient allocation of market resources and blind competition.

[0003] In the field of economics and management, constructing an industry prosperity index is an effective tool for monitoring market dynamics and warning periodic fluctuations. A scientific prosperity index should be able to comprehensively reflect changes in multiple dimensions such as business size, operational efficiency, economic benefit, personnel status and market expectations. Although the logistics industry has successfully established a prosperity index system based on multi-source data fusion and realized regular publication, in the traditional service industry of automobile repair, the corresponding technical development is significantly lagging behind, and there is still no widely recognized, scientific and sensitive prosperity monitoring methodology and practice system.

[0004] Currently, in the technical practice of constructing the automobile repair industry prosperity index, there are mainly the following key technical problems and defects: 1. In the aspect of index design and system construction, the existing technology has the problems of fragmentation of index system and single dimension: Some existing attempts rely mainly on single and result-oriented financial indicators (such as operating income), and lack systematic dimension division. The existing technology fails to construct a multi-dimensional and multi-granularity composite index system, resulting in a superficial depiction of the industry prosperity situation and an inability to reveal the underlying causes, and the scientificity and explanatory power of the index are insufficient.

[0005] 2. In the aspect of data collection and source, the existing method has the problems of single data source, limited coverage and weak representativeness: The construction of the reliability index relies on a wide and representative data base. At present, the data sources of most researches or reports mainly rely on limited administrative records or small-scale sampling surveys, and fail to effectively integrate the multi-source data mastered by key data holders such as industry regulators, scientific research institutions of colleges and universities, local industry associations, large chain maintenance platforms and enterprise ERP (Enterprise Resource Planning) systems. Such narrow data channels lead to large sample bias and cannot comprehensively and unbiasedly reflect the real operating conditions of maintenance enterprises of different regions and different scales (especially a large number of small and medium-sized enterprises) in the country, so that the final index has systematic bias and is difficult to obtain industry-wide recognition.

[0006] 3. In terms of data fusion and processing technology, the existing method lacks efficient and standardized data integration and processing capability, resulting in poor index precision and timeliness: Even if multi-source data can be obtained, the existing technology faces great challenges in data fusion. The data from different sources differ greatly in format, standard, and update frequency (time frequency), and lack a unified data collection, cleaning, verification and fusion mechanism centered on a digital platform. There is no unified multi-scale data specification, making the data integration process tedious, inefficient, and prone to errors. This directly leads to obvious timeliness of the constructed prosperity index, which cannot achieve near real-time monitoring; at the same time, the index sequence contains too much noise and fluctuates sharply, with low predictive accuracy and reliability, making it difficult to play its due role in early warning and guidance.

[0007] In summary, the existing technology in constructing the automobile maintenance industry prosperity index has the core defect that it fails to achieve effective coordination and deep integration of the three of "multi-dimensional index system", "wide coverage of multi-source data" and "standardized digital processing platform". This directly restricts the scientificity, representativeness and practicality of the index. Therefore, there is an urgent need for a prosperity index system that can truly, sensitively and prospectively reflect the operating conditions of the automobile maintenance industry. SUMMARY

[0008] The present application provides a kind of automobile maintenance industry prosperity index construction method based on multi-source data fusion to overcome the above technical problems.

[0009] In order to achieve the above purpose, the technical scheme of the present application is: A kind of automobile maintenance industry prosperity index construction method based on multi-source data fusion, comprising: S1: collecting monthly index data of the automobile maintenance industry; S2: screening the monthly index data to obtain screened monthly index data; S3: converting the screened monthly index data into five-dimensional index diffusion index; S4: Based on the improved Delphi method, the indicators of the five dimensions are weighted and distributed, and the automobile repair industry prosperity index is calculated according to the distributed weight and the corresponding index diffusion index.

[0010] Further, the monthly index data is converted into five-dimensional index diffusion index, including: The single index diffusion index is constructed, as shown in formula (1), (1) Wherein, represents the diffusion index, represents the five-dimensional tertiary index, represents the proportion of enterprise samples with upward index change, represents the proportion of enterprise samples with flat index change.

[0011] Further, the five-dimensional index diffusion index is respectively the business index diffusion index, the efficiency index diffusion index, the benefit index diffusion index, the employee index diffusion index and the expectation index diffusion index; The tertiary index of the business index diffusion index is respectively the business volume index, the automobile maintenance business volume index, the automobile repair business volume index, the accident vehicle repair business volume index and the new energy vehicle business volume index; The tertiary index of the efficiency index diffusion index is the repair station utilization rate index; The tertiary index of the benefit index diffusion index is respectively the operating income index, the automobile repair service price index and the operating profit index; The tertiary index of the employee index diffusion index is respectively the employee cost index and the employee number index; The tertiary index of the expectation index diffusion index is the operation situation expectation index.

[0012] Further, based on the improved Delphi method, the five-dimensional index diffusion index is weighted and distributed, including: Step 1: Invite experts to allocate initial weights to the five dimensions, forming an initial weight vector , satisfying ; wherein represents the expert; Step 2: Calculate the weight vector between experts using the cosine of the included angle, i.e. the consistency coefficient, as shown in formula (2), (2) Wherein, represents the cosine of the included angle between the initial weight vectors of experts a and b, and respectively represent the initial weight vector of expert a and expert b; Step three: calculate the average consistency of each expert, as shown in formula (3), (3) wherein, represents the average value of the consistency of the a-th expert with all other experts; represents the projection of the weight vector on . Step four: synthesize the final weight vector according to the standardized average consistency, as shown in formula (5), (4) wherein, represents the standardized average consistency; Step four: according to the standardized average consistency, synthesize the final weight vector, as shown in formula (5), (5) wherein, is the final weight vector of the single index; Step five: according to steps two-four, the final weight vector of the business index diffusion index is , the final weight vector of the efficiency index diffusion index is , the final weight vector of the benefit index diffusion index is , the final weight vector of the employee index diffusion index is , and the final weight vector of the expectation index diffusion index is .

[0013] Further, according to the assigned weight and the corresponding index diffusion index, the automobile repair industry prosperity index is calculated, including: The automobile repair industry prosperity index synthesis formula is shown in formula (6), (6) wherein, represents the total business index selected from the three-level index of the business index diffusion index, represents the repair station utilization rate index in the three-level index of the efficiency index diffusion index, represents the operating income index selected from the three-level index of the benefit index diffusion index, represents the employee cost index selected from the three-level index of the employee index diffusion index, represents the operation situation expectation index in the three-level index of the expectation index diffusion index.

[0014] Beneficial effects: This invention provides a method for constructing a business climate index for the automotive repair industry based on multi-source data fusion. By combining relevant data collected from five dimensions, a business climate index for the automotive repair industry can be constructed that can dynamically monitor changes in the industry's business climate, providing quantitative basis for business decision-making, investment planning, and government policy formulation for automotive repair enterprises. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart illustrating a method for constructing a business climate index for the automotive repair industry based on multi-source data fusion, provided by this invention; Figure 2 A line graph of the national automobile repair industry prosperity index in 2024, provided as an embodiment of the present invention, illustrates a method for constructing an automobile repair industry prosperity index based on multi-source data fusion. Figure 3 A line graph showing the 2024 automotive repair industry prosperity index for Class I, Class II, and Class III automotive repair enterprises, based on a method for constructing an automotive repair industry prosperity index based on multi-source data fusion, provided as an embodiment of the present invention. Figure 4 A line graph of the 2024 new energy vehicle repair industry prosperity index, provided as an embodiment of the present invention, is a method for constructing a prosperity index of the automotive repair industry based on multi-source data fusion. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] This embodiment provides a method for constructing a business climate index for the automotive repair industry based on multi-source data fusion, such as... Figure 1 As shown, it includes: S1: Collect monthly indicator data for the auto repair industry; S2: Filter the monthly indicator data to obtain the filtered monthly indicator data; S3: converting the screened monthly index data into five-dimensional index diffusion indexes; S4: distributing weights to the five-dimensional indexes based on the improved Delphi method, and calculating the automobile repair industry prosperity index according to the distributed weights and the corresponding index diffusion indexes.

[0019] Specifically, first, monthly index data of the automobile repair industry are collected, the data collection range involves three types of automobile repair enterprises in the standard (GB / T 16739.1-3-1997) issued by the former Ministry of Transport, and the data are divided into five dimensions, i.e., business, efficiency, benefit, employee, and expectation, and the specific data of the automobile repair in a single month and the basic information of the repair enterprises are collected through a qualitative collection method. The monthly index data are screened to obtain screened monthly index data, and the data are screened to remove noise data in the monthly index data to obtain screened data. Secondly, the screened monthly index data are converted into five-dimensional index diffusion indexes, and the diffusion indexes of each index in the five dimensions are obtained by defining the proportion of the enterprise samples with upward and flat trends in each index. The diffusion index method is applied to construct the index, which can comprehensively evaluate the overall development trend of the automobile repair industry. Finally, the five-dimensional indexes are distributed weights based on the improved Delphi method, and the automobile repair industry prosperity index is calculated according to the distributed weights and the corresponding index diffusion indexes, and the final automobile repair industry prosperity index is obtained to measure the overall change of the automobile repair industry in China. The problems of imperfect traditional industry monitoring index system, insufficient data representativeness, and low prediction accuracy are solved, which can accurately capture the structural changes and seasonal fluctuations of the industry and provide scientific decision-making basis for enterprises and government departments.

[0020] In specific embodiments, the scheme for collecting monthly index data of the automobile repair industry is as follows: In this embodiment, based on the comprehensive analysis of automobile repair business and process, the development points, key features, and front trends of the domestic and foreign automobile repair industry are comprehensively analyzed, the automobile repair industry prosperity index system is established, the overall change of the automobile repair industry in China is measured from the business, efficiency, benefit, employee, and expectation dimensions, and the index data of the five dimensions are selected. The business dimension reflects the total amount and structure of market demand, which is the original driving force of the industry operation. The efficiency dimension and the employee dimension together constitute the supply capacity system, which respectively reflects the utilization efficiency of capital factors (equipment) and the configuration state of labor factors (personnel). The benefit dimension measures the operating performance and reflects the economic return of factor input. The expectation dimension captures the market participants' prediction of the supply and demand relationship and forms the leading signal of the prosperity fluctuation. The five dimensions cover the demand, supply, value, and expectation of the automobile repair industry, ensuring the theoretical completeness of the dimension division. The collected five-dimensional indicator data is subdivided into 12 tertiary indicators, and the "1+5+N" indicator system is constructed.

[0021] When selecting the indicators of the business index, comprehensive consideration should be given from multiple angles, not only to ensure the comprehensiveness of the indicators, but also to ensure the independence and complementarity between the indicators. Based on the following principles, the indicator system of the business index of the automobile repair industry is constructed: The principle of clarity and clarity. The indicators in the indicator system have clear definitions to ensure that their meanings and calculation methods are clearly understood; The principle of relevance and correlation. Select indicators related to the automobile repair industry to ensure that the indicators can measure the current situation of the automobile repair industry in China to some extent; The principle of comprehensiveness and effectiveness. Select indicators that can capture different levels and types of data to ensure that the indicator system effectively assesses the automobile repair industry.

[0022] Based on the above principles, the tertiary indicators of each dimension are as follows: The tertiary indicators of the business indicators are business volume, automobile maintenance business volume, automobile repair business volume, accident vehicle repair business volume, and new energy vehicle business volume; The tertiary indicator of the efficiency indicator diffusion is the repair station utilization rate; The tertiary indicators of the benefit indicator diffusion are operating income, automobile repair service price, and operating profit index; The tertiary indicators of the employee indicator diffusion index are employee cost index and number of employees; The tertiary indicator of the expected indicator diffusion index is the operation situation expectation; The data collection work of the business index adopts a qualitative collection method. For each indicator, the enterprise selects one from the three choices of rising, flat, and falling, and fills in the specific data of the number of entries this month. In addition, in order to comprehensively analyze the changes of automobile repair enterprises from multiple angles and multiple levels, the basic information of repair enterprises is collected, including enterprise name, business address, enterprise type, business qualification, main repair vehicle type, business scope, number of workstations, and factory area. The data collection scope involves three types of automobile repair enterprises in the original standard (GB / T 16739.1-3-1997) issued by the former Ministry of Transport: (1) Class I enterprises: engaged in automobile overhaul and assembly repair, and can also engage in automobile maintenance, minor repair and special repair. (2) Class II enterprises: engaged in automobile maintenance and minor repair. (3) Class III enterprises: specialized in automobile special repair and maintenance, mainly including body, painting, decorative seat cushion, water tank, tire, crankshaft grinding, cylinder boring, electrical and other special repairs; In this embodiment, the data collection work is collected online through the official release platform, "Che Sharp" applet; The data collection adopts a PPS sample method, i.e., a proportional probability sampling according to the size, and the sample number of each type of automobile repair enterprise is determined according to the contribution of each type of automobile repair enterprise to the main business income of the automobile repair industry, while the regional distribution, enterprise type distribution and scale distribution of the sample are taken into account. The PPS sample method is a commonly used technical means in data collection and is known to those skilled in the art, and therefore will not be described in detail.

[0023] In specific embodiments, the scheme for screening the monthly index data to obtain screened monthly index data is as follows: In this embodiment, the index data is removed from the noise data, specifically including: (1) Remove missing values: when the business qualification is missing, it should be supplemented as "three types"; when the answer of the subdivided index is missing, it should be supplemented as "none"; (2) Remove outliers: some indicators have "0%, -100%, 100%" abnormal data, which are treated as missing values and removed; Consistency processing of index data: there are two types of data samples, text and numbers, and all numerical data need to be converted to text. "Rising" is defined as more than 5% higher than the same enterprise's monthly index, and "flat" is defined as the same enterprise's monthly data compared to the previous month's data within ±5%.

[0024] In specific embodiments, the scheme for converting the screened monthly index data into index diffusion indexes of five dimensions is as follows: The single index diffusion index is constructed, as shown in formula (7), (7) Wherein, represents the diffusion index, represents the five dimensions of the three-level index, represents the proportion of enterprise samples with an upward index change, represents the proportion of enterprise samples with a flat index change; this formula assigns half the weight to the "flat" state, converts the discrete qualitative judgment into a continuous numerical value, and smooths the index fluctuations.

[0025] In this scheme, the fluctuation characteristics of the economic cycle are captured through statistical analysis of different index states, thereby providing a basis for judging the development trend of the industry. This method has strong sensitivity to trend inflection points and can comprehensively reflect the overall operation situation of the industry.

[0026] In specific embodiments, the scheme for distributing weights to the five dimensions of the index based on the improved Delphi method, and calculating the automobile repair industry sentiment index according to the allocated weights and the corresponding index diffusion index is as follows: Step 1: Invitation The experts assigned initial weights to the five dimensions, forming an initial weight vector. ,satisfy ;in Indicates the first One expert; Step 2: Calculate the weight vector among experts, i.e., the consensus coefficient, using the cosine of the included angle, as shown in formula (8). (8) in, This represents the cosine of the angle between the initial weight vectors of expert a and expert b. and Let represent the initial weight vectors of expert a and expert b, respectively; Step 3: Calculate the average consensus of each expert, as shown in formula (9). (9) in, This represents the average degree of agreement between the a-th expert and all other experts. Represents the weight vector exist Projection on; The average consistency is standardized as shown in formula (10). (10) in, This represents the average consistency after standardization. Step 4: Synthesize the final weight vector based on the standardized average consistency, as shown in formula (11). (11) in, The final weight vector for a single indicator; Step 5: Based on Steps 2-4, determine the final weight vector of the business indicator diffusion index. The final weight vector of the efficiency index diffusion index is: The final weight vector of the diffusion index of the benefit indicator is: The final weight vector of the diffusion index of practitioners is: The final weight vector of the expected diffusion index is: ; In this embodiment, the business indicator diffusion index directly reflects the scale of market demand, therefore It is given the highest weight of 45%; the benefit diffusion index, as the core representation of the benefit dimension, is therefore... The weighting is 25%; the efficiency index, employment index, and expectation index diffusion index are less sensitive to the dynamics of industry prosperity, therefore... , Enter Each is assigned a weight of 10%. The automotive repair industry prosperity index is calculated based on the assigned weights and the corresponding indicator diffusion index, including: The formula for synthesizing the prosperity index of the automobile repair industry is shown in formula (6). (6) in, This represents the total business volume index selected from the three levels of the business indicator diffusion index. The maintenance workstation utilization rate index is a third-level indicator representing the efficiency index diffusion index. This represents the operating income index selected from the third-level indicators of the benefit index diffusion index. This represents the employee cost index, selected from the third-level indicators of the employee indicator diffusion index. This represents the operational expectation index, which is a third-level indicator within the expected indicator diffusion index.

[0027] The AMRPI ranges from 0% to 100%, and its economic significance is defined by the boom-bust line. Specifically, when the AMRPI is above 50%, it indicates that the economic activity in the auto repair industry is in an expansionary phase; conversely, if the AMRPI is below 50%, it reflects that the industry has entered a contractionary phase. Specifically, in this embodiment, representative third-level indicator indices under five dimensions are selected as the dimension results: 1) Business Dimension: This includes five tertiary indicators. Business is a direct indicator of market demand and business activity. In this embodiment... The value is the total business volume index, and the other indicators can be used to analyze the development trends of different automotive repair businesses. 2) Efficiency dimension: includes one tertiary indicator, namely The value is the maintenance bay utilization rate index; the maintenance bay utilization rate index measures the utilization efficiency of maintenance equipment and reflects the overall service capability of the industry. 3) Profitability Dimension: This includes three tertiary indicators, reflecting the profitability of the auto repair industry. The value is the operating income index, and the other indicators can be used to analyze the operating costs and profits of auto repair enterprises. 4) Practitioner Dimension: Includes two tertiary indicators. The value is the employee cost index; 5) Expected Dimension: Includes one tertiary indicator. The value of the operating situation expectation index reflects the judgment and confidence of the industry on future market trends.

[0028] The diffusion index of the five dimensions is represented by the corresponding three-level indicators, among which the business dimension is represented by the business volume index, the efficiency dimension is represented by the repair station utilization rate index, the benefit dimension is represented by the operating income index, the employee dimension is represented by the number of employees index, and the expectation dimension is represented by the operating situation expectation index. The above selection is made by industry experts based on comprehensive analysis of automobile repair business, process, etc., comprehensive automobile repair industry development points, key features and frontiers, in-depth analysis of the theoretical connotation, data availability, industry sensitivity and representation fit of each three-level indicator, and the decision is made to ensure that the index system is scientific, simple and can accurately reflect the industry prosperity.

[0029] A specific application example is used to further illustrate the technical solutions of the embodiments of the invention.

[0030] Taking the national data in 2024 as an example, an automobile repair industry prosperity index indicator system is constructed, mainly including business, efficiency, benefit, employee and expectation five dimensions of indicator data, following the principles of clarity, correlation and comprehensiveness to determine the specific indicator content and data statistical method, and the index evaluation system is shown in Table 1, Table 1: Automobile repair industry prosperity index evaluation system

[0031] In step one, monthly indicator data of the automobile repair industry is collected, and data is collected through the "Che Sharp" platform. The PPS sampling method is used, and the economic contribution of the main business income of the enterprise is used as the stratification variable to implement sample allocation.

[0032] In step two, the indicator data is screened and noise data is removed. The data is verified by the built-in logic verification and manual review mechanism of the "Che Sharp" platform, and the abnormal values and invalid data (such as repeated reporting, logical contradiction items) are removed to ensure data quality.

[0033] Taking the data in June 2024 as an example, a total of 3138 samples were collected, 2945 valid data, and the sample validity rate was 93.85%. Among them, the proportion of Class I enterprises was 6.59% (194), the proportion of Class II enterprises was 23.45% (690), and the proportion of Class III enterprises was 69.96% (2059), which conforms to the "pyramid type" structure characteristics of China's automobile repair industry. The sample composition and validity statistics in June 2024 are shown in Table 2, Table 2: Sample composition and validity statistics in June 2024

[0034] In 2024, the business scope of the first type of enterprise is comprehensive, and the scale is large. In the business, efficiency, benefit, and expected dimensions, the prosperity index remains at a low level of fluctuation. Only the employees fluctuate greatly due to the high demand for labor and high skill requirements. The second and third types of enterprises have single business and focus on low-end markets or special maintenance. Influenced by technology iteration, the efficiency and expectation dimensions fluctuate significantly. The third type of enterprise has low operating costs, high benefit index, but large fluctuations. In addition, the demand for labor is small, and the employee index is more stable.

[0035] In step three, the monthly index data after removing noise data is converted into an index diffusion index. Based on the effective sample data obtained each month, the diffusion index method is used to quantitatively analyze the 12 three-level indicators reported by enterprises each month (see Table 1 for details).

[0036] In step four, the index diffusion indexes of the five dimensions are weighted and allocated to synthesize the automobile repair industry prosperity index (AMRPI). The monthly prosperity index is calculated by comprehensively weighting the business, efficiency, benefit, employee, and expectation five-dimensional indexes. Specifically, the diffusion value of each index is calculated based on the "up" and "flat" proportions reported by enterprises. Then, the five-dimensional index weights are synthesized based on the improved Delphi method to obtain the prosperity index.

[0037] The 2024 automobile repair industry prosperity index line chart drawn according to the results is shown in Figure 2 The 2024 automobile repair industry prosperity index line chart drawn according to the results is shown in Figure 3 The 2024 new energy automobile repair industry prosperity index line chart is shown in Figure 4

[0038] In summary, the present application analyzes the characteristics of the automobile repair industry, extracts the prosperity index system reflecting the development characteristics of the industry, collects monthly index data of the automobile repair industry, filters the index data, removes noise data, converts the monthly index data after removing noise data into an index diffusion index, and synthesizes the automobile repair industry prosperity index (AMRPI) by weighting the index diffusion indexes of the five dimensions, thereby achieving efficient application of big data.

[0039] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or make equivalent substitutions for part or all of the technical features; and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.​

Claims

1. A multi-source data fusion-based automobile maintenance industry prosperity index construction method, characterized in that, Comprise: S1: Collect monthly index data of the automobile repair industry; S2: Screen the monthly index data to obtain screened monthly index data; S3: Convert the screened monthly index data into five-dimensional index diffusion indexes; S4: Based on the improved Delphi method, the five-dimensional indexes are weighted and distributed, and the automobile repair industry prosperity index is calculated according to the allocated weight and the corresponding index diffusion index. 2.The method according to claim 1, characterized in that, The monthly index data is converted into five-dimensional index diffusion indexes, including: Constructing a single index diffusion index, as shown in formula (1), （1） wherein, represents the diffusion index, represents the three-level indicators of the five dimensions, represents the proportion of enterprise samples with the index change direction rising, represents the proportion of enterprise samples with the index change direction flat. 3.The method according to claim 2, characterized in that, The five-dimensional index diffusion indexes are business index diffusion index, efficiency index diffusion index, benefit index diffusion index, employee index diffusion index and expectation index diffusion index; The three-level indexes of the business index diffusion index are business volume index, automobile maintenance business volume index, automobile repair business volume index, accident vehicle repair business volume index and new energy vehicle business volume index; The three-level index of the efficiency index diffusion index is repair station utilization rate index; The three-level indexes of the benefit index diffusion index are operating income index, automobile repair service price index and operating profit index; The three-level indexes of the employee index diffusion index are employee cost index and employee number index; The three-level index of the expectation index diffusion index is operation situation expectation index. 4.The method according to claim 3, characterized in that, Based on the improved Delphi method, the five-dimensional index diffusion indexes are weighted and distributed, including: Step one: invitation The initial weight vector is formed by the fifth dimension of the five experts , meet ; Wherein The first expert is represented by the first expert ​ Step two: Calculate the weight vector between experts using the cosine of the included angle, that is, the consistency coefficient, as shown in formula (2), （2） wherein, denotes the cosine of the angle between the initial weight vectors of expert a and expert b, and denotes the initial weight vector of expert a and expert b, respectively; Step three: Calculate the average consistency degree of each expert, as shown in formula (3), （3） wherein, represents the average of the agreement of the a-th expert with all other experts; represents the weight vector the projection on the projection on Standardize the average consistency degree, as shown in formula (4), （4） wherein, represents the normalized average degree of identity; Step four: Synthesize the final weight vector according to the standardized average consistency degree, as shown in formula (5), （5） wherein, the final weight vector being a single index; Step five: according to step two-step four, the final weight vector of the business index diffusion index is , the final weight vector of the efficiency index diffusion index is , the final weight vector of the benefit index diffusion index is , the final weight vector of the employee index diffusion index is , and the final weight vector of the expectation index diffusion index is . 5.The method of claim 4, wherein, According to the allocated weight and the corresponding index diffusion index, the automobile repair industry prosperity index is calculated, including: The automobile repair industry prosperity index synthesis formula is shown in formula (6), （6） wherein, represents a business volume index selected from the three-level indices of the business index diffusion index, represents a maintenance work station utilization rate index in the three-level indices of the efficiency index diffusion index, represents an operating income index selected from the three-level indices of the benefit index diffusion index, represents an employee cost index selected from the three-level indices of the employee index diffusion index, represents an operation situation expectation index in the three-level indices of the expectation index diffusion index.

Images