Data-Driven Evaluation and Recommendations for Regional Synergy Innovation Capability

Abstract

Regional synergy innovation capability is an important driving force in promoting the sustainable and high-quality development of the regional economy. Taking the regional innovation development panel data of the Yangtze River Delta integration region from 2010 to 2019 as a sample, this study constructs an evaluation index system of regional synergy innovation capability, weights the index using the entropy weight method, and measures the capability of the Yangtze River Delta integration region (three provinces and one city) using the composite system synergy degree model. The empirical results show that the synergy of regional synergy innovation in the Yangtze River Delta integration has increased steadily, but there is still much room for improvement. Anhui has great potential for synergy innovation with Jiangsu, Zhejiang, and Shanghai. Therefore, this study proposes countermeasures and suggestions for the high-quality development of Anhui’s synergy innovation capability under the integration of the Yangtze River Delta. This study provides theoretical and methodological support for enhancing regional synergy innovation capability and provides decision support for the sustainable and high-quality development of the regional economy.

1. Introduction

Synergy innovation refers to the organic coordination of innovation-related elements, resulting in overall synergistic effects that cannot be achieved by individual elements through complex interactions. With the continuous development of knowledge and technology, synergy innovation capability determines the level of influence and competitiveness of a country or region [1,2,3]. Therefore, accelerating the development of regional synergy innovation, narrowing the development gap between regions [4], and promoting cross-regional cooperation and innovation have become urgent issues that need to be addressed. The innovation capability of a single region cannot effectively deal with the rapidly changing competitive environment. Regional synergy innovation is conducive to the collaborative integration of innovation resource elements for all links between regions [5]. It promotes complementary advantages and win–win cooperation among regions [6], such as in China’s “one belt, one road” technological innovation action plan and the new Silk Road Economic Belt construction, Japan’s “intelligent manufacturing system (IMS)” international cooperation plan, the EU’s framework plan, and cross-regional developments such as the Beijing–Tianjin–Hebei integration development, the Guangdong–Hong Kong–Macao Greater Bay Area, and the Yangtze River Delta integration development. These scientific, technological, and economic development collaborations prove that regional synergy innovation is the major pillar in developing the regional integration and enhancing the overall regional advantages. This is inevitable at advanced stages of regional innovation and development. However, the issue of uneven and inconsistent regional development is still prominent [7], bringing problems and challenges to regional synergy innovation. For example, scholar Stojčić [8] pointed out that, due to the traditional idea of protecting local interests, regional segmentation occurred, and many innovative resources have not been circulated. Wang et al. [9] believed that there are varying degrees of difficulties in innovation synergy and communication, limited cooperation, and low efficiency in various regions. Lopez-Vega and Lakemond [10] pointed out that there are difficulties in the transformation of technological achievements and industrial transformation and upgrading. Yang et al. [11] pointed out that there is irrationality in the allocation of regional innovation resources, and the current situation of synergy innovation is not optimistic. The ability of regional synergy innovation reflects the degree of integration of various innovative elements among synergy innovation entities [12]. It plays an important role in improving and developing the regional innovation system [13] and reflects the contribution ability to the level of regional economic and technological development. Regional sustainable development requires synergy innovation, which is a prerequisite and an important driving force for achieving such development. Regional sustainable development and synergy innovative development are closely linked [14]. Accelerating the construction of the technological innovation community, realizing the circulation of innovation resources and synergy innovation, and achieving the region’s coordinated sustainable development are worthy initiatives. Therefore, it is particularly important to improve regional synergy innovation capability.

Regional synergy innovation capability is an essential guarantee for improving regional competitiveness [15], which is an important factor in world economic development. However, to improve regional collaborative innovation capability, we must first conduct a scientific, comprehensive, and systematic evaluation. Thus far, scholars have had many opinions on how to evaluate regional synergy innovation capabilities, and they have not reached an agreement. In the existing literature, regional synergy innovation capability evaluation is divided into two aspects: construction of an evaluation index system and evaluation methods.

Regarding the evaluation index system construction, scholars generally base it on the constituent elements of regional synergy innovation capability, namely, innovative resource, innovative output, and innovative milieu [16,17,18,19]. They actively explore diversified research perspectives such as the university–industry perspective [20,21,22], input–output perspective [23], green low-carbon perspective [24], and technology-oriented perspective [25]. These perspectives help to construct an evaluation index system. In terms of innovative resources, R&D personnel [26,27] and internal expenditure [28] are common indicators. In terms of innovation output, patent output [19,29] and output value of new products of industrial enterprises [30,31] are common indicators. In terms of innovation environment, most consider infrastructure [32], market environment [33], and pollutant emissions [34]. Ai et al. [35] believed that air pollution impacts regional innovation capabilities and has an inhibitory effect on them. Lanchun et al. [36] constructed a county-level innovation capability evaluation index system based on four aspects: innovation investment, innovation environment, enterprise innovation, and innovation performance. Zhang and Li [37] constructed an indicator system for regional innovation capability based on three aspects: technological benefits, economic benefits, and ecological benefits of innovation activities, and then used the entropy weight method to comprehensively evaluate regional innovation capability.

Evaluation methods are divided into evaluation index weight determination methods and regional synergy innovation capability evaluation methods. The entropy weight method [38], AHP [39], and anti-entropy weight method [40] determine the weight of evaluation indicators. The DANP can be used to confirm the evaluation index weight of regional innovation capability, along with a maldistributed decision-making method to assess regional innovation capability [41]. In terms of evaluation methods of regional synergy innovation capability, the PCA method [42], the DEA model [43,44], and factor analysis are common methods. In addition, Zhao et al. [45] constructed an evaluation index system based on four aspects: government innovation activities, university innovation activities, innovation activities of scientific research institutions, and enterprise innovation activities. Next, they used AHP and cluster analysis methods to assess China’s regional synergy innovation capability from various viewpoints of innovation subjects. Fan et al. [32] constructed evaluation indicators from five different types of innovation: knowledge innovation, technology innovation, industrial innovation, service innovation, and innovation environment. They used the capability structure relationship model to evaluate this standard of synergy innovation capability among regions. Chen et al. [46] established an index system from three aspects, innovation investment, innovation delivery, and innovation environment, and used this TOPSIS-based order relation method to evaluate the regional innovation capability of Liaoning Province. Yuan and Zheng [47] explored the application of improved intuitionistic fuzzy entropy in the evaluation of regional collaborative innovation capability. Dai et al. [48] used the mixed CFPR–VIKOR method to collect empirical data to evaluate Taiwan’s regional innovation capability.

In summary, the research status and limitations of this field are as follows: first, considering regional heterogeneity [49], the evaluation index system constructed is different. Moreover, there are subjective errors in quantifying qualitative indicators, a common phenomenon among existing evaluation indices. Therefore, we need to pay attention to its integrity and operability. Second, scholars mostly use qualitative evaluation methods, and the data selection in the existing quantitative evaluation mostly focuses on cross-sectional data, thus lacking dynamics. Regional synergy innovation capability formation is a process; hence, increasing the time dimension is more accurate. Therefore, to meet the above challenges, the study seeks to establish a data-driven dynamic and synthetical evaluation method to dynamically evaluate the regional synergy innovation capability. This was achieved by collecting panel data to clearly understand the development trend and dynamic law of synergy innovation capability. We performed horizontal and vertical comparative analysis, followed by better pinpointing of the location and measures in enhancing regional synergy innovation capability.

There is important theoretical and practical value to studying how to improve regional synergy innovation capability and finally realizing regional coordinated and sustainable development. The theoretical value is as follows: first, considering the regional characteristics, we construct a relatively complete evaluation index system, providing a new research vision for researchers. Second, on the basis of the data-driven synergy degree model of the composite system, we dynamically evaluate and compare the regional synergy innovation capability, which enriches the evaluation method. The practical value is as follows: first, it offers an important basis and means for the government to monitor and evaluate synergy innovation capability. Second, this study reveals the characteristics and influencing factors of regional synergy innovation capability and proposes targeted countermeasures and suggestions. It offers an important decision-making foundation for improving regional synergy innovation capability and building an integrated regional synergy innovation community.

To achieve the aforementioned research objectives, the research article is structured as follows: Section 2 explains the proposed methods of the article; Section 3 contains a case study that tests the proposed methods; Section 4 presents the conclusion, which summarizes the innovations and shortcomings.

2. Methods

Our data-driven approach to evaluating regional synergy innovation capability has five steps: method framework, data collection, data processing, data modeling, and data application.

2.1. Method Framework

Regional sustainable development emphasizes the goals and processes of regional development, while synergy innovation emphasizes the driving forces and mechanisms of regional development. This study offers guidance for constructing an analytical framework for regional synergy innovation capability of sustainable development. To improve the capability of regional synergy innovation, we need to build an evaluation framework or an evaluation system from the system theory perspective and coordinate the relevant interregional policies from a holistic optimization perspective. This is an urgent need for regional synergy innovation development. However, faced with multidimensional and complex regional collaborative innovation indicators, it is a challenge to determine effective methods to measure, evaluate, and optimize regional synergy innovation capability.

To cope with the challenge and improve the level of regional synergy innovation capability, we construct a data-driven dynamic and synthetical evaluation method for measuring, evaluating, and improving regional synergy innovation capability. First, we collect data on regional innovation input, economic spillover, knowledge creation, and environmental support. Next, we calculate the index weight using the entropy weight method in the data processing link. We then build a composite system synergy degree model to achieve the measurement and estimation of regional synergy innovation capability. Lastly, we apply the method to the case of Anhui’s integration in the Yangtze River Delta, verify this model, and obtain evaluation results. On the basis of this result, we provide policy recommendations to accelerate its improvement. The flowchart of the method is presented in Figure 1.

2.2. Data Collection

The evaluation criterion is a critical element that measures regional synergy innovation capability. This study follows rules for the scientific, systematic, operable, dynamic, and comparable establishment of an index system. Referring to relevant research [6,15], and considering pertinent influencing factors [50,51], this study establishes an evaluation index system including innovation input capability [52], economic spillover capability [33], knowledge creation capability [53,54], and environmental support capability [55] to measure and evaluate regional synergy innovation capability. The core element of synergy innovation activities is innovation input [56], which is the core foundation of synergy innovation development. The final operational outcome of synergy innovation activities includes knowledge creation and economic spillovers, which are the target elements for synergy innovation development [57]. Environmental support capacity guarantees the smooth progress of coordinated innovation activities [58] and synergy innovation development [35]. They are interrelated and mutually influencing, organically unified in the design of synergy innovation capability indicators. Therefore, this article divides regional synergy innovation capabilities into four aspects: innovation input capability, economic spillover capability, knowledge creation capability, and environmental support capability.

Innovation input capacity reflects the willingness and intensity of regional innovation activities, mainly including the input of financial resources [59] and human resources [60]. In this study, internal expenditure of R&D funds is used as an index of financial resources input, and the full-time equivalent of R&D personnel and their input are used as indices of human resources input. Economic spillover capability and knowledge creation capability are two kinds of results stemming from the operation of regional innovation activities [46]. Economic spillover capability directly produces economic value [61]. This study also uses GDP, new product sales revenue of industrial enterprises above the designated size, and turnover of the technology market to reflect economic spillover capability. Scientific papers and patents [29] are the main achievements of knowledge creation capability. Three indices are used in this study to reflect knowledge creation capability, namely, the number of scientific papers published, the authorized number of invention patents, and the number of patent applications authorized. Environmental support capability reflects the carrying capacity of the natural ecological environment for innovation and development [52,62]. This study uses total industrial wastewater discharge, total industrial sulfur dioxide emission, and industrial smoke (powder) dust emission to reflect the environmental support capability. In summary, this study outlines an evaluation index system of regional synergy innovation capability with four order parameters and 12 basic indicators, as listed in

Table 1. Construction of an Index system for regional synergy innovation capability.

Composite System	Subsystem	Order Parameter	Basic Index	Anno.	Ref.
Regional synergy innovation capability	Individual provinces and cities in the region	Innovation input	Internal expenditure of R&D funds (104 CNY)	A11	[18,41]
			Full-time equivalent of R&D personnel (person-year)	A12	[18,41]
			R&D personnel input (persons)	A13	[18,24]
		Economic spillover	GDP (109 CNY)	A21	[41]
			New product sales revenue of industrial enterprises above designated size (104 CNY)	A22	[36,51]
			Turnover of technology market (104 CNY)	A23	[41,51]
		Knowledge creation	Number of scientific papers published (pieces)	A31	[24,51]
			Authorized number of invention patents (pieces)	A32	[41,51]
			Number of patent applications authorized (pieces)	A33	[16,41]
		Environmental support	Total industrial wastewater discharge (104 tons)	A41	[41,51]
			Total industrial sulfur dioxide emission (104 tons)	A42	[41,51]
			Industrial smoke (powder) dust emission (104 tons)	A43	[41,51]

Anno. = annotations; Ref. = reference.

.

2.3. Data Processing

Through our analysis and comparison of objective weighting methods, we found that the entropy weight method [38] can fully mine the whole information included in statistical data and evaluate the conclusion objectively. Therefore, we use it to determine the index weight, improve the reliability and objectivity of the results of index weight, and lay the foundation for follow-up research to this study.

First, the data are standardized as follows:

$$x_{ij}^{\prime }=\left\{\begin{array}{c}\frac{x_{ij}-{\beta }_j}{{\alpha }_j-{\beta }_j}\times 0.99+0.01 x_j \mathrm{is} \mathrm{a} \mathrm{positive} \mathrm{index}\\ \frac{{\alpha }_j-x_{ij}}{{\alpha }_j-{\beta }_j}\times 0.99+0.01 x_j\mathrm{is} \mathrm{a} \mathrm{negative} \mathrm{index}\end{array}\right.,$$

(1)

where $x_{ij}$ represents the raw value, $x_{ij}^{\mathrm{\prime }}$ represents the standardized value, and ${\alpha }_j$ and ${\beta }_j$ are the maxima and minima of parameters of the index $j$ at its tipping point of the system stability. As the critical value of each subsystem evaluation index at the stable point cannot be determined, the maxima and minima of the index in the research period are used instead. To avoid the meaningless logarithm, we set 0.99 and 0.01 in the formula, such that the standardized value does not become 0. The setting of 0.99 and 0.01 only affects the size of the numerical value itself but does not affect the final result sorting.

The index weight ${ P}_{ij}$ is calculated using standardized data:

$$P_{\mathit{ij}}=\frac{x_{\mathit{ij}}^{\prime }}{\sum _{i=1}^t{x}_{\mathit{ij}}^{\prime }} i=1,2,3,\dots t;j=1,2,3,\dots n.$$

(2)

Make $m=1/ln\left(t\right)>0$ be a regulative factor and compute the index information entropy $e_j$:

$$e_j=-m\sum _{i=1}^t{P}_{\mathit{ij}}\ln P_{\mathit{ij}} i=1,2,3,\dots t;j=1,2,3,\dots n.$$

(3)

Calculate the index weight:

$$W_j=\frac{1-e_j}{n-{\sum }_{j=1}^{\mathrm{n}}{e}_j}\sum _{j=1}^{\mathrm{n}}{W}_j=1;j=1,2,3,\dots n,$$

(4)

where n is the total quantity of indices, $W_j$ is the weight of index j, and its value range is ${0<W}_j<1$.

2.4. Data Modeling

The regional synergy innovation is a compound dynamic system formed through this interaction between various innovation subsystems [63,64]. In this study, we use the composite system synergy degree model to measure the synergy between subsystems or elements in the regional synergy innovation capability. Compared with other methods [32,43], this model can dynamically, intuitively, and comprehensively reflect the synergistic effect of each subsystem and constituent elements within each subsystem of the regional synergy innovation capability under the nonlinear interaction. This model overcomes the disadvantage of studying only a single region, estimates the synergy innovation degree of a single subsystem in the region, and measures the degree of overall synergy innovation in the region [65].

Taking four subsystems as examples, this study establishes a composite system of regional synergy innovation capability $U=\left\{U_1,U_2,U_3,U_4\right\}$, where $U_i$ is the subsystem $i$ of the composite system $U$ ($i=1,2,3,4)$. $U_i=\left\{U_{i1},U_{i2},U_{i3},\dots U_{in}\right\}$, i.e., $U_i$ is made up of several order parameters.

2.4.1. Subsystem Order Degree

Suppose $e_{\mathit{ij}}=\left(e_{i1},e_{i2},e_{i3},\dots ,e_{\mathit{in}}\right)$ are the factor variables in the development of subsystem $i$, and ${\alpha }_{\mathit{ij}}\le e_{\mathit{ij}}\le {\beta }_{\mathit{ij}}$,${\alpha }_{\mathit{ij}}$,${\beta }_{\mathit{ij}}$ are the minimum and maximum values of the factor variables. If the factor variable has a positive impact on subsystem development, its order degree is

$$U_i\left(e_{\mathit{ij}}\right)=\left(e_{\mathit{ij}}-{\alpha }_{\mathit{ij}}\right)/\left({\beta }_{\mathit{ij}}-{\alpha }_{\mathit{ij}}\right)j\in \left[1,r\right].$$

(5)

If the factor variable negatively affects subsystem development, its order degree is

$$U_i\left(e_{\mathit{ij}}\right)=\left({\beta }_{\mathit{ij}}-e_{\mathit{ij}}\right)/\left({\beta }_{\mathit{ij}}-{\alpha }_{\mathit{ij}}\right) j\in \left[r+1,n\right].$$

(6)

According to the above formula, $U_i\left(e_{\mathit{ij}}\right)$ is the order degree of factor variables. $U_i\left(e_{\mathit{ij}}\right)\in \left[0,1\right]$, whereby a larger value of $U_i\left(e_{\mathit{ij}}\right)$ denotes a stronger influence on the subsystem, and a smaller value of $U_i\left(e_{\mathit{ij}}\right)$ denotes a weaker influence on the subsystem. The order degree of all factor variables in the subsystem is weighted and summed to obtain the order degree formula of the subsystem:

$$U_i\left(e_i\right)={\sum }_{j=1}^n{W}_{\mathit{ij}}{U}_i\left(e_{\mathit{ij}}\right)W_j\ge 0;{\sum }_{j=1}^n{W}_j=1;j=1,2,3,\dots n,$$

(7)

where $U_i\left(e_i\right)$ represents the order degree of subsystem $i$, $U_i\left(e_i\right)\in \left[0,1\right]$. With the increasing value of $U_i\left(e_i\right)$, the order degree of the subsystem $U_i$ increases, and vice versa. $W_{\mathit{ij}}$ is the weight of factor variable $j$ in subsystem $i$.

2.4.2. Composite System Synergy Degree

The composite system synergy degree model is constructed on account of the subsystem order degree model. In the four subsystem models, the order degrees of the subsystems are $U_1\left(e_1\right)$, $U_2\left(e_2\right)$, $U_3\left(e_3\right)$, and $U_4\left(e_4\right)$, according to Equation (7). The order degree changes dynamically with time over the entire research interval. Assuming that the initial time is 0, the order degree of a subsystem at time 0 is $U_i^0\left(e_i\right)$, and the order degree at time t is $U_i^t\left(e_i\right)$; the synergy degree DGS is

$$\mathit{DGS}=\theta \sum _{i=1}^4{\mu }_i\left[\left|U_i^t\left(e_i\right)-U_i^0\left(e_i\right)\right|\right],$$

(8)

where $\theta =\frac{\underset{i}{\min }\left[U_i^t\left(e_i\right)-U_i^0\left(e_i\right)\ne 0\right]}{\left|\underset{i}{\min }\left[U_i^t\left(e_i\right)-U_i^0\left(e_i\right)\ne 0\right]\right|}$ $i=1,2,3,4;{\mu }_i\ge 0;{\sum }_{i=1}^4{\mu }_i=1.$

$DGS$ is a composite system synergy degree, and $DGS\in \left[-1,1\right]$. If its value is higher, this indicates that the overall synergy degree is larger, and vice versa. The function of parameter θ is to judge whether $DGS$ is a positive or negative synergy degree. ${\mu }_i$ represents the weight of subsystem $i$.

2.5. Data Application

This research aimed to measure and evaluate the regional synergy innovation capability using the data-driven method and propose policy recommendations on the basis of the quantitative evaluation results. These recommendations can serve as the policymaking basis for the initiators and managers of regional synergy innovation. Figure 2 shows the specific method of data application.

Constructing an index system of regional synergy innovation capability is the first step. With reference to the relevant literature and comprehensive consideration of innovation input, economic spillover, knowledge creation, and environmental support, we build an index system that comprehensively and accurately evaluates the regional synergy innovation capability. The second step determines the weights of the indices. We use the entropy weight method to determine the weights, which objectively reflect the proportional function and effect of each index. The determination of index weight paves the way for the follow-up quantitative evaluation. The third step is to build the evaluation model for estimation and appraisal of the regional synergy innovation capability by the composite system synergy degree model. The fourth step is model validation. Taking the integration of Anhui into Yangtze River Delta as this study case, we test this constructed model and discover the evolution trend and law of regional synergy innovation capability of Yangtze River Delta integration, to locate the key optimization direction for Anhui. The fifth step proposes policy recommendations. On the basis of the data analysis results, we propose policy recommendations to improve Anhui’s synergy innovation capability.

3. Case Study

This study employed Anhui under Yangtze River Delta integration as the research region to implement and verify the method. We selected the 2010–2019 innovation and development data of this integration region as the study sample. To ensure the authority and reliability of basic index data collection, the variables were taken from the Anhui Statistical Yearbook [66], Zhejiang Statistical Yearbook [67], Jiangsu Statistical Yearbook [68], Shanghai Statistical Yearbook [69], and China Science and Technology Statistical Yearbook [70]. Due to the inconsistency of statistical caliber in the data of various provinces, it is sometimes difficult to obtain these data. There were two missing data, the value of A22 in 2016 and the value of A31 in 2018. For certain years, we used the SPSS mean interpolation method to process and estimate the incomplete data as a function of the existing statistical data.

3.1. Background

A government work report released on 5 March 2019 proposed upgrading the regional integration development of the Yangtze River Delta into a “national strategy”. On 1 December 2019, its development planning outline was promulgated. The integrated region of the Yangtze River Delta is shown in Figure 3. Its land covers 358,000 square kilometers. Shanghai, Jiangsu, Zhejiang, and Anhui were included in the scope of integration. The development of an integrated region has become a national strategy, and synergy innovation has become the focus of three provinces and one city to promote “integration” and “innovation-driven growth”. Anhui’s accession to the scope of integration is a requirement to advance higher-level reform and opening up, which shows that the region’s position in the national development pattern has greatly improved. However, for a long time, there was a chasm in innovation resources between Anhui and the other two provinces and cities. There is a certain cliff phenomenon that affects the improvement of the overall synergy innovation capability of the integration region up to a point. Thus, at present, there are important questions that need to be answered: Does this integration region have a close relationship with synergy innovation? What about Anhui’s regional synergy innovation capability under the integration? How can Anhui’s regional synergy innovation capability be effectively improved by integrating the Yangtze River Delta? This study constructs an evaluation index system of regional synergy innovation capability and measures the synergy innovation capability of three provinces and one city by using the composite system synergy degree model. We provide insight into the gap in Anhui synergy innovation capability to supply the practical basis for policy formulation and adjustment of Anhui synergy innovation development.

3.2. Results

We used three provinces and one city (Anhui, Zhejiang, Jiangsu, and Shanghai) as four subsystems, and the Yangtze River Delta integration region as the composite system. Using this latter method, we calculated the order degree of subsystem order parameters, order degree of the subsystems, and composite system synergy degree. On this basis, we analyzed and evaluated the synergy innovation capability from the two aspects of the regional whole and within the region to determine the development orientation of Anhui and realize the synergy innovation development.

3.2.1. Test Results of Index Data

For the collected indicator data, this article used SPSS 12.0 software to conduct descriptive statistics, as shown in

Table 2. Descriptive statistics of variables.

Variable	Minimum	Maximum	Mean Value	Standard Deviation
A11	1,637,219.000	27,795,165.000	10,385,008.325	6,272,314.665
A12	64,169.000	635,279.000	282,689.500	162,470.043
A13	94,610.000	897,701.000	391,076.100	218,407.716
A21	12,359.000	99,632.000	40,458.291	22,225.041
A22	19,971,178.000	301,019,390.000	134,556,847.050	82,233,186.447
A23	461,470.000	14,715,193.000	4,592,696.325	3,700,696.698
A31	32,551.000	127,371.000	69,999.600	28,763.270
A32	1111.000	42,019.000	17,609.675	11,581.672
A33	16,012.000	314,395.000	140,235.525	92,491.966
A41	29,144.000	263,760.000	112,610.575	71,733.349
A42	1.080	105.380	42.430	29.433
A43	1.620	76.370	34.136	19.640

. There were no outliers in the current panel data, which were combined with the subsequent empirical requirements.

Reliability and validity testing is a necessary guarantee for ensuring the effectiveness of subsequent data analysis. Therefore, this study used SPSS software to test the reliability and validity of the panel data. The results are shown in

Table 3. Reliability and validity test results.

Reliability Test
Cronbach’s Alpha based on standardized terms		N of items
0.924		12
KMO and Bartlett’s test
KMO measure of sampling adequacy		0.749
Bartlett’s test	Approx. chi-square	1097.785
	df	66
	p-value	0.000

.

Cronbach’s alpha coefficient was used to evaluate the reliability of the data. It is generally believed that a Cronbach’s alpha greater than 0.6 indicates appropriate reliability, and the reliability of this sample data was very good, reaching 0.924. Therefore, this indicates that the data collected in this study had high internal consistency and strong reliability. Meanwhile, from Table 1, it can be seen that the KMO value of the measurement scale was 0.749, and Bartlett’s spherical test was significant (χ²/df = 1097.785, df = 66, p < 0.001), indicating that the data collected in this study had good validity. On the whole, the panel data showed good reliability and validity.

3.2.2. Order Degree of Subsystem Order Parameters

Taking 2010 as this base year, the order parameters’ order degree of each subsystem in this integration region was calculated using Equations (1)–(4) of the entropy weight method and Equations (5)–(7) of the composite system synergy degree model, as shown in

Table 4. Order degree of four order parameters of Anhui.

Order Parameter	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019
Innovation input	0.0100	0.1376	0.2993	0.4326	0.5226	0.5667	0.6138	0.7181	0.8021	1.0000
Economic spillover	0.0100	0.0949	0.1759	0.2685	0.3609	0.4183	0.5264	0.6524	0.8337	1.0000
Knowledge creation	0.0100	0.1784	0.3053	0.4344	0.4882	0.7595	0.8693	0.7811	0.9688	0.9697
Environmental support	0.1258	0.0877	0.1562	0.1260	0.0782	0.0965	0.7401	0.9117	0.9408	0.8563

,

Table 5. Order degree of four order parameters of Zhejiang.

Order Parameter	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019
Innovation input	0.0100	0.1002	0.2019	0.2932	0.3699	0.4614	0.5287	0.6222	0.7892	1.0000
Economic spillover	0.0100	0.0753	0.1072	0.1537	0.1869	0.2344	0.3527	0.4764	0.7275	1.0000
Knowledge creation	0.0871	0.1361	0.2866	0.2721	0.2069	0.4352	0.5912	0.7045	0.8853	1.0000
Environmental support	0.1232	0.1649	0.2689	0.2716	0.2704	0.3496	0.7700	0.8843	0.9126	0.7438

,

Table 6. Order degree of four order parameters of Jiangsu.

Order Parameter	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019
Innovation input	0.0100	0.1067	0.2670	0.4178	0.5128	0.5767	0.6809	0.7368	0.8079	1.0000
Economic spillover	0.0100	0.1407	0.2246	0.3220	0.3995	0.4563	0.5520	0.6566	0.7730	1.0000
Knowledge creation	0.0100	0.1927	0.3700	0.3539	0.3581	0.6494	0.6813	0.7385	0.9163	0.9729
Environmental support	0.2006	0.1676	0.2737	0.3137	0.2420	0.3392	0.6670	0.8752	0.9193	0.8323

and

Table 7. Order degree of four order parameters of Shanghai.

Order Parameter	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019
Innovation input	0.0100	0.1706	0.2504	0.3903	0.4601	0.5204	0.6498	0.7277	0.8315	1.0000
Economic spillover	0.0100	0.1480	0.1618	0.2081	0.3037	0.3103	0.4858	0.5902	0.8065	1.0000
Knowledge creation	0.0122	0.0582	0.1224	0.0886	0.1429	0.3370	0.3865	0.5159	0.7982	1.0000
Environmental support	0.3953	0.1471	0.1134	0.1916	0.1837	0.1889	0.6384	0.8918	1.0000	0.7941

.

According to Table 4, Table 5, Table 6 and Table 7 and Figure 4, in the three provinces and one city of the integration region, in addition to the order parameter of environmental support, the order degrees of innovation input, economic spillover, and knowledge creation maintained stable growth. Among the four order parameters, environmental support showed the lowest order degree in the four subsystems. This shows that environmental support had little contribution to the order of the four subsystems and the improvement of the overall synergy of the integration region. Moreover, the order parameter values of environmental support fluctuated before 2016, rather than the expected upward trend. The year 2016 saw several environmental protection policies, including legislative work in major fields such as the 10 articles of soil, new list of hazardous wastes, reform of emission rights. promotion of environmental protection tax, and launch of central environmental protection inspector. This, on the one hand, shows that the sustainable development level of the integration region needs to be improved and further strengthened. On the other hand, environmental protection policies can significantly improve the order of environmental support order parameters and improve the capability of regional synergy innovation.

3.2.3. Order Degree of the Subsystems

According to the order degree of order parameters of each subsystem in Anhui, Zhejiang, Jiangsu, and Shanghai, the order degree of synergy innovation of each subsystem was further calculated using Equations (1)–(4) of the entropy weight method and Equations (5)–(7) of the composite system synergy degree model. The calculation results are illustrated in

Table 8. Order degree of three provinces and one city in the integration region.

Year	Anhui Subsystem	Zhejiang Subsystem	Jiangsu Subsystem	Shanghai Subsystem
2010	0.0540	0.0471	0.0508	0.0959
2011	0.1154	0.1106	0.1502	0.1197
2012	0.2149	0.1974	0.2817	0.1527
2013	0.2750	0.2338	0.3533	0.1940
2014	0.3066	0.2505	0.3856	0.2475
2015	0.3863	0.3522	0.5100	0.3303
2016	0.6870	0.5223	0.6421	0.5131
2017	0.7868	0.6348	0.7445	0.6546
2018	0.8937	0.8096	0.8484	0.8507
2019	0.9398	0.9524	0.9575	0.9545

and Figure 5.

Table 8 and Figure 5 show that the order of each subsystem of synergy innovation in the integration region is increasing. The order degree of synergy innovation systems in Zhejiang, Jiangsu, and Shanghai increased steadily. Since 2016, the order degree of the Anhui synergy innovation system greatly improved, and it was at its highest level in three provinces and one city from 2016 to 2018. This is highly consistent with the actual status of synergy innovation development in Anhui. In 2016, Anhui officially participated in the construction of a world-class city group, and the development of synergy innovation began to accelerate gradually. This further verifies the correctness of the national decision to integrate Anhui into the integration development, bringing significant strategic development opportunities to Anhui Province. In 2019, the order of synergy innovation subsystems in the three provinces and one city tended to be consistent, exceeding 0.9.

3.2.4. Composite System Synergy Degree

The composite system synergy degree formula was used for measuring the overall synergy degree of the integration region. First, the weight coefficients of the subsystems in the integration region were determined. When calculating the weight coefficient, this study took the regional GDP index as a variable and calculated it using ${\mu }_i=\frac{{GDP}_i}{\sum _{i=1}^4{GDP}_i}$ ($i=$ Anhui, Zhejiang, Jiangsu, and Shanghai). The weights of each subsystem in the integration region are listed in

Table 9. Weights of four subsystems.

Year	Anhui	Zhejiang	Jiangsu	Shanghai
2010	0.1254	0.2779	0.4198	0.1769
2011	0.1324	0.2757	0.4227	0.1691
2012	0.1368	0.2732	0.4267	0.1634
2013	0.1392	0.2702	0.4295	0.1611
2014	0.1392	0.2672	0.4329	0.1607
2015	0.1355	0.2679	0.4387	0.1580
2016	0.1363	0.2671	0.4372	0.1593
2017	0.1379	0.2675	0.4383	0.1564
2018	0.1561	0.2662	0.4278	0.1500
2019	0.1564	0.2628	0.4199	0.1608

.

The overall synergy degree of the integration region was calculated using Equation (8). The formula for the internal regional synergy degree was the same. The research findings are presented below.

As shown in

Table 10. The overall synergy of the Yangtze River Delta integration region and internal region.

Region	2011	2012	2013	2014	2015	2016	2017	2018	2019
Yangtze River Delta integration	0.0717	0.1709	0.2269	0.2588	0.3652	0.5382	0.6496	0.7884	0.8953
Anhui–Zhejiang	0.0628	0.1538	0.1981	0.2201	0.3144	0.5282	0.6367	0.7888	0.8981
Anhui–Jiangsu	0.0906	0.2142	0.2827	0.3147	0.4283	0.6011	0.7030	0.8077	0.9011
Anhui–Shanghai	0.0394	0.1026	0.1542	0.1984	0.2798	0.5169	0.6390	0.7946	0.8725
Zhejiang–Jiangsu	0.0851	0.1991	0.2573	0.2841	0.4004	0.5473	0.6535	0.7843	0.9062
Zhejiang–Shanghai	0.0481	0.1148	0.1536	0.1840	0.2786	0.4537	0.5769	0.7597	0.8885
Jiangsu–Shanghai	0.0770	0.1812	0.2459	0.2848	0.3983	0.5452	0.6576	0.7864	0.8942

and Figure 6, the synergy degree in the integration region steadily improved. The regional synergy innovation relationship between the integration region and the regional synergy innovation capability was continuously enhanced. However, the overall synergy degree was relatively small. By 2019, the overall synergy degree did not exceed 0.900, which shows that there is still more room to improve the synergy innovation capability of the integration region. In 2018, the Yangtze River Delta regional integration became a national strategy, the regional synergy innovation capability rapidly improved, and the difference in the degree of synergy between regions was reduced. Although Anhui Province was officially integrated in 2018, the process of integration is ongoing.

The synergy degree of synergy innovation between Anhui and Jiangsu was highest during the research period. This is because geographical advantages make Anhui and Jiangsu have high docking and synergy innovation and development. Anhui borders Jiangsu the most, especially Nanjing, Xuzhou, and other important cities in Jiangsu. It maintains close contact and a strong willingness for synergy innovation in economic and social areas. The synergy among Anhui, Zhejiang, and Shanghai increased rapidly during the study period. The year 2016 was a watershed moment, consistent with the signing of the cooperation framework agreement involving Shanghai, Jiangsu, Zhejiang, and Anhui on jointly promoting a synergy innovation network in the integrated region.

At the same time, this study found that the synergy between Zhejiang and Shanghai was at its lowest level during the study period. Zhejiang and Shanghai’s regional innovation level was high because the innovation gap between the two was small, and there was a competitive relationship to a certain extent, which may have affected regional integration and coordinated development. In addition, both regions had a good ecological environment for innovation result conversion, and the willingness for synergy innovation may not have been strong enough.

3.3. Policy Recommendations

High-quality regional synergy innovation can have the effect of 1 + 1 > 2. Anhui’s accession to the integration region can create conditions for synergy and help form a “chess game” for synergy innovation and development. As a rising star, most of its innovation indicators are backward, but the significance of synergy lies in differentiation and complementarity. Anhui Province has many traditional, advantageous industries, which are indispensable as a link in the synergy innovation chain. Considering its resource endowment and location advantages, Anhui Province should constantly improve its competitive ability in this innovation chain, value chain, and supply chain.

3.3.1. Realize the Linkage Development of Innovation and Reform

The three provinces and one city have completed the full coverage of the free trade zone, and regional linkage and coordinated development are expected to reach a new level. Shanghai, Jiangsu, and Zhejiang have higher economic development levels. If the newly joined Anhui wants to integrate into this region and connect with the other provinces, it is necessary to realize the reform and linkage development from the institutional level to further promote the synergy innovation capability of the integrated region and form a “chess game”. First, policy support for opening up and connecting with the new Silk Road Economic Belt should be increased, and regional innovation cooperation and trade exchanges among Anhui and the other provinces and city should be actively promoted. Second, the connection with the system and mechanism of the integrated region should be strengthened, and a package of reform and innovation in management, taxation, laws, and regulations should be carried out to accelerate the circulation of logistics, people flow, information flow, and science and technology flow among the integrated regions, to enhance the synergy innovation and development of one city and three provinces. Lastly, the regional cooperation mechanism should be innovated, the reform of the commercial system should be deepened [71], efficient government affairs should be actively promoted, along with the “digital government” and the standardization of government services, a better investment environment should be created, and institutional guarantees should be provided for undertaking the transfer of industries and innovative achievements.

3.3.2. Strive to Build a Synergy Innovation Hinterland

First, the opening and development of Wanjiang and Northern Anhui should be vigorously promoted, along with the establishment of the industrial transferring demonstration area in the Wanjiang urban belt and the industrial transfer cluster area. Anhui should play a role as a function of its comprehensive district competitive advantages including good industrial foundation, low factor cost, and strong supporting capacity; it should scientifically undertake industrial transfer, reasonably divide labor with the one city and two provinces, and guide the optimal allocation of resource factors. At the same time, Anhui should bring into play its comparative advantages and characteristics, drive the dynamic flow of innovation elements among regions [72], guide the adjustment of regional economic layout, seek differentiated development, and play a breakthrough and leading role in certain fields. This will create greater development space for upgrading the industrial structure of Jiangsu, Zhejiang, and Shanghai, improve its development quality, and better radiate and drive the rise of Anhui and the central region. It will also form a new pattern of benign interaction, complementary advantages, mutual promotion, and coordinated development.

Second, according to the characteristics of provinces and cities, full play should be given to Anhui’s advantages in terms of location, resources, and labor force, and the horizontal economic alliance and cooperation with the integrated region should be strengthened. Authorities should make full use of the physical industry advantages of Jiangsu Province, actively connect, fully support, and actively strengthen the synergy innovation with neighboring cities (Nanjing and Xuzhou), become the development hinterland of Nanjing and Xuzhou, and further integrate, support, and serve Jiangsu. They should also make full use of Shanghai’s advantages in innovation capability and service industry, actively promote the cooperation between Hefei and Shanghai comprehensive national science centers, and carry out interregional coordinated development and innovation resource sharing. With complimentary advantages and collaborative linkages, Anhui should strive to become the input of Shanghai’s intellectual resources and innovation outcome. Meanwhile, Shanghai has become the export destination of Anhui’s natural and labor resources, winning a broader docking space for Anhui’s deep integration. It is, thus, crucial to promote the “two hearts to create together” between Hefei and Shanghai, jointly build a synergy innovation platform, and accelerate the building of an innovation community in the Yangtze River Delta. Authorities should fully utilize the advantages of Zhejiang’s digital and circulation economy and developed private economy ecology. They should seize the opportunity for Huangshan and other cities to be included in the Hangzhou metropolitan area and strengthen the synergy innovation capability in the fields of e-commerce, free trade zone, tourism industry, and manufacturing value chain. They should learn from the experience of pilot reform in the Zhejiang Free Trade Zone to set the basis for the innovation and development of the Anhui free trade zone. In addition, Anhui should carry out exchanges, cooperation, and in-depth integration with Zhejiang in digital innovation, emerging industries and large enterprises, innovative talent training, and strategic decision-making consultation, to realize synergy innovation and development.

Third, Anhui Province should optimize the competitive relationship between Zhejiang and Shanghai in innovation. Zhejiang and Shanghai’s regional innovation development levels are high, the innovation gap is small, and there is a robust competitive relationship. However, the transformation of innovation achievements and innovation spillover between the two places are inevitable, and Anhui Province should make good use of the gap between itself and the two places. Anhui can become a common transfer and transformation destination between Shanghai and Zhejiang to undertake industrial transfer and transformation of innovation achievements. In this way, the coordination between Anhui and the two provinces and one city can be further strengthened, and the rapid economic and social development of the province can be greatly promoted.

Moreover, Anhui has the advantage of rich innovative resources. Anhui should take “the birthplace of technological innovation” as the starting point, through the development orientation of “two places and one area”, and rely on the talent and scientific and technological advantages of key universities to strengthen scientific and technological research.

3.3.3. Introduce Cross-Regional Synergy Innovation and Development Policies

To accelerate the all-round, deep-seated, and wide-ranging integration of Anhui into the integrated region, the capability of cross-regional synergy innovation development from the perspective of policy guarantee [73] should be continuously deepened and improved. First, an efficient, comprehensive intellectual property management platform should be built to promote intellectual property creation, application, protection, management, and service chain. At the same time, professional service talents should be introduced, such as patent agents and technology brokers, who can play a “threading” role in the co-construction and sharing of intellectual property rights to promote cross-regional collaborative service efficiency. Second, full play should be given to finance leverage, strengthen the orientation of financial resource allocation, and provide precise support for synergy innovation and development projects between Anhui and the Yangtze River Delta, especially core technology joint development projects. Lastly, authorities should take multiple measures to promote cross-regional cooperation and the exchange of advanced talent, actively explore the “Yangtze River Delta integrated regional public talent service system”, connect with the labor and employment service management center of brother provinces in the Yangtze River Delta, realize in-depth cooperation in human resources services, and build a human resources information sharing and advanced talent exchange platform with the cooperating region to maximize the talent resource effect.

3.3.4. Establish Coordination Mechanisms for Environmental Carrying

The goal of high-level synergy innovation is still green, low-carbon, and sustainable development [74]. As things stand, the order parameter of environmental support capability in Anhui Province has the highest order and strong environmental carrying capacity. However, the order parameter of environmental support capability in the integrated region is not high. With the further promotion of industrial transfer, the three kinds of industrial waste discharge in Jiangsu, Zhejiang, and Shanghai should be significantly improved. However, Anhui Province can increase three kinds of industrial waste discharge in undertaking industrial transfer. Therefore, Anhui should actively cooperate with the other two provinces and one city to jointly formulate the regional environmental carrying integration coordination mechanism, reach a consensus according to the overall interests of the region, and comprehensively plan industrial transfer projects, environmental capacity and carrying capacity, and the direction of industrial transformation and upgrading in the integration region. In the process of industrial transfer, environmental support and compensation [75] should be increased for Anhui Province to carry out industrial technology-upgrading iterations and realize high-quality development of synergy innovation. Additionally, Anhui should selectively undertake the industries transferred from Zhejiang, Jiangsu, and Shanghai in combination with its own situation, do a good job in the protection and restoration of the ecological environment, and build a regional innovative industrial structure compatible with the environment that is well coordinated with available resources.

3.4. Discussion and Implications

The outline of the national innovation-driven development strategy proposed optimizing the allocation of regional innovation resources and building a regional economic growth pole by “building a regional synergy innovation community and coordinating and leading the development of regional integration”. Subsequently, the outline of the Yangtze Delta Regional Integration Development Plan was issued, which raised the regional integration development to a national strategy. Building an integrated regional synergy innovation community has important practical and far-reaching strategic significance for the Yangtze River Delta region, and even the national and regional economic development pattern. As a new member, Anhui can enhance the regional synergy innovation capability. Therefore, it is crucial to conduct a comprehensive and systematic evaluation of Anhui’s synergy innovation capability and reveal the existing gaps, explore the sustainable development layout, and design a path for it to build an innovation community, thus upgrading the synergy innovation capability of the integrated region.

Compared to the previous literature [20,21,22], this paper has the following unique advantages: (1) formulation of a much more scientific and reasonable index system of regional synergy innovation capability on the basis of the status of four variables of innovation input, economic spillover, knowledge creation, and environmental support; (2) construction of a data-driven evaluation model to measure and dynamically and quantitatively evaluate the regional synergy innovation capability; (3) proposal of policy recommendations to the government regarding the top-level design for promoting Anhui’s integration into the integrated region. Promoting regional synergy innovation capability is strategically important to advance regional integration and sustainable development. On the basis of the above research results, we obtain three important insights for management:

• Regional synergy innovation capability is a complex system. Considering system theory and global optimum, we should synergistically develop various innovation subsystems of regional synergy innovation for realizing regional sustainable development.
• With the close connection of science and technology and regional economic development, supported by regional innovation data, the construction of data-driven measurement, evaluation, and optimization methods of regional synergy innovation capability can more effectively supplement the government decision making of regional synergy innovation development.
• Innovation-driven development is a significant part of the regional development challenge. To pursue regional innovation-driven growth, the bottom line is to enhance regional synergy innovation capability. Therefore, exploring the mechanism and mode of this development and constructing an effective quantitative evaluation method of regional synergy innovation capability are worthy undertakings for research.

4. Conclusions

Regional synergy innovation capability is an important part of regional sustainable development capability, which is indispensable for improving resource utilization and saving nonrenewable resources and energy. Relying on synergy innovation to reduce and control environmental pollution is the key to implementing sustainable development. This study proposes a comprehensive evaluation method for data-driven regional synergy innovation capability. It is necessary to apply this method to measure, evaluate, and optimize the synergy innovation capability of the Yangtze River Delta integration (three provinces and one city). The below-described research results were obtained.

(1)

In addition to environmental support capability, innovation input capability, economic spillover capability, and knowledge creation capability all maintained stable improvement. It can be seen that the innovation input–output of the research area is increasing day by day, and the innovation performance is becoming increasingly significant. The environmental support capability has contributed only a little to the overall synergy innovation capability improvement of the Yangtze River Delta integrated region.

(2)

During the research period, the synergy innovation capability within the regions of Zhejiang, Jiangsu, and Shanghai steadily improved. Anhui significantly improved its synergy innovation capabilities within the region since 2016. From 2016 to 2018, the synergy innovation capability within the Anhui region was at the highest level among the three provinces and one city.

(3)

The overall synergy innovation capability of the Yangtze River Delta integrated region continues to increase but the overall synergy degree value is relatively small, and there is significant room for improvement. The synergy innovation capability between Anhui and Jiangsu has consistently stayed at the highest level during the research period. The synergy innovation capability between Zhejiang and Shanghai has been at its lowest level during the research period. Thus, we propose policy recommendations from the system, location, policy, and environment levels.

In this study, we propose a data-driven method for measuring, evaluating, and optimizing regional synergy innovation, which provides content and methodological references for studying regional synergy innovation capability in other world regions. This study provides both theoretical and methodological support for the evaluation and optimization of synergy innovation capability and decision-making support for the sustainable and high-quality development of economies, in other regions of the world. The following innovations are completed at present:

(1)

Constructing the regional synergy innovation capability evaluation index system. The scientific and reasonable evaluation index system is constructed from four aspects: innovation input, economic spillover, knowledge creation, and environmental support.

(2)

Building the data-driven synergy degree model of the composite system, carrying out a dynamic estimation and contrast analysis of the regional synergy innovation capability of the integrated region from the horizontal and vertical levels, the overall level, and the provincial level, revealing the characteristics and existing problems of Anhui’s synergy innovation capability, and providing quantitative academic support for the framing and adjusting of follow-up countermeasures.

(3)

By building the Yangtze River Delta integrated regional synergy innovation community, high-quality development countermeasures can be formulated to improve Anhui’s synergy innovation capability at the four levels of system, location, policy, and environment.

The improvement of regional synergy innovation capability plays a vital role in realizing high-quality and sustainable development of the regional economy and optimizing industrial structures. However, researching the comprehensive regional synergy innovation capability evaluation is complicated systematical engineering. Considering the high complexity and unbalanced characteristics of regional synergy innovation systems, the integrity of the construction of the regional synergy innovation capability evaluation index system requires further study. For example, future studies should focus on further characterizing the indicators of industrial structure coupling, innovation factor flow, and collaborative organization guarantee to enrich the evaluation index system of regional synergy innovation capability. Moreover, the study uses a singular research method; therefore, the analysis may not be sufficiently comprehensive. Future research could enhance the application of integrated model methods, such as using regression models and new learning algorithms [76] with better accuracy and dynamic system recognition characteristics to evaluate and optimize regional synergy innovation systems. They could also actively explore the combination of quantitative and qualitative research methods.