Policy relevance analysis method and system

Abstract

The present application is applicable to the field of data analysis technology, and in particular, relates to a policy relevance analysis method and system. The policy relevance analysis method includes: comprehensively grasping the basic situation of the target population and the historical background of the policy by obtaining the target population information and the policy information of multiple policies; determining the policy description mark of each policy based on the policy information of multiple policies to reflect the impact of the policy on different populations in the past, so as to accurately evaluate the potential impact of the policy on the target population in subsequent analysis; generating multi-dimensional matching analysis data based on the policy description mark and the target population information, and comprehensively evaluating the relevance between the policy and the target population from multiple dimensions; finally, determining the optimal matching policy for the target population information based on the multi-dimensional matching analysis data of the policy description mark and the target population information, so that the enterprise can effectively grasp the policy direction, optimize resource allocation, and enhance the competitiveness of the enterprise.

Description

Technical Field

[0001] The present application belongs to the field of data analysis technology, and in particular, relates to a policy relevance analysis method and system. Background Art

[0002] Policies have many impacts on corporate development, including positive promotion and negative challenges. Different types of policies, such as tax policies, financing policies, and innovation policies, have different impacts on corporate financial status, innovation capabilities, and market competitiveness.

[0003] In the information and intelligent era, the acquisition and use of policy information is crucial to the development of enterprises. However, faced with massive amounts of policy information and complex application processes, enterprises lack effective feedback mechanisms and data analysis tools, which makes it impossible for enterprises to effectively grasp the policy direction, increases the cost of survival of enterprises, and generates waste of resources. Summary of the invention

[0004] The embodiments of the present application provide a policy relevance analysis method and system, which can improve the problem that due to the lack of effective feedback mechanism and data analysis tools, enterprises are unable to effectively grasp the policy direction, increase the survival cost of enterprises and generate waste of resources.

[0005] In a first aspect, an embodiment of the present application provides a policy relevance analysis method, including:

[0006] Obtain target population information and policy information for multiple policies;

[0007] Determine a policy description mark for each policy based on the policy information of the plurality of policies; wherein the policy description mark is used to reflect the impact of the policy on different groups of people in the past;

[0008] Based on the policy description mark and the target population information, obtaining multi-dimensional matching analysis data of the policy description mark and the target population information;

[0009] An optimal matching policy for the target population information is determined based on the policy description mark and the multi-dimensional matching analysis data of the target population information.

[0010] The policy relevance analysis method provided in the embodiment of the present application obtains the target population information and the policy information of multiple policies to comprehensively grasp the basic situation of the target population and the historical background of the policy, thereby providing a reliable data basis for subsequent analysis. Based on the policy information of multiple policies, the policy description mark of each policy is determined to reflect the impact of the policy on different populations in the past, so as to accurately evaluate the potential impact of the policy on the target population in subsequent analysis. Based on the policy description mark and the target population information, multi-dimensional matching analysis data is generated, and the relevance of the policy and the target population is comprehensively evaluated from multiple dimensions, thereby improving the accuracy and depth of the analysis. Finally, based on the multi-dimensional matching analysis data of the policy description mark and the target population information, the optimal matching policy for the target population information is determined, so that the enterprise can effectively grasp the policy direction, optimize resource allocation, and enhance the competitiveness of the enterprise.

[0011] In a second aspect, the embodiment of the present application provides a policy relevance analysis system, including:

[0012] An acquisition unit, used to acquire target population information and policy information of multiple policies;

[0013] A marking unit, used to determine a policy description mark of each policy based on the policy information of the plurality of policies; wherein the policy description mark is used to reflect the impact of the policy on different groups of people in the past;

[0014] An analysis unit, configured to obtain multi-dimensional matching analysis data of the policy description mark and the target population information based on the policy description mark and the target population information;

[0015] A determination unit is used to determine the optimal matching policy for the target population information according to the policy description mark and the multi-dimensional matching analysis data of the target population information.

[0016] In a third aspect, an embodiment of the present application provides a policy relevance analysis device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described in any one of the first aspects above is implemented.

[0017] In a fourth aspect, an embodiment of the present application provides a computer program product, which, when executed on a terminal device, enables the terminal device to execute any one of the methods described in the first aspect.

[0018] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 It is a flowchart of a policy relevance analysis method provided in an embodiment of the present application;

[0021] Figure 2 It is a flowchart of step S200 in the policy relevance analysis method provided in one embodiment of the present application;

[0022] Figure 3 It is a flowchart of step S220 of the policy relevance analysis method provided in one embodiment of the present application;

[0023] Figure 4 It is a flowchart of step S223 of the policy relevance analysis method provided in one embodiment of the present application;

[0024] Figure 5 It is a flowchart of step S300 of the policy relevance analysis method provided in one embodiment of the present application;

[0025] Figure 6 It is a flowchart of step S310 of the policy relevance analysis method provided in one embodiment of the present application;

[0026] Figure 7 It is a flowchart of step S400 of the policy relevance analysis method provided in one embodiment of the present application;

[0027] Figure 8 It is a flowchart of step S420 of the policy relevance analysis method provided in one embodiment of the present application;

[0028] Fig. 9 It is a structural diagram of a policy relevance analysis system provided by an embodiment of the present application;

[0029] Fig.10 It is a structural diagram of a policy relevance analysis device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0030] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0031] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0032] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0033] As used in the specification of this application and the appended claims, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "if it is determined" or "if the described condition or event is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce the described condition or event is detected" or "in response to detecting the described condition or event" depending on the context.

[0034] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0035] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0036] In the information and intelligent era, the acquisition and use of policy information is crucial to the development of enterprises. However, faced with massive amounts of policy information and complex application processes, enterprises lack effective feedback mechanisms and data analysis tools, which makes it impossible for enterprises to effectively grasp the policy direction, increases the cost of survival of enterprises, and generates waste of resources.

[0037] To solve the above problems, the embodiments of the present application provide a policy relevance analysis method and system. In this method, by obtaining the target population information and the policy information of multiple policies, the basic situation of the target population and the historical background of the policy are fully grasped, thereby providing a reliable data basis for subsequent analysis. Based on the policy information of multiple policies, the policy description mark of each policy is determined to reflect the impact of the policy on different populations in the past, so as to accurately evaluate the potential impact of the policy on the target population in subsequent analysis. Based on the policy description mark and the target population information, multi-dimensional matching analysis data is generated, and the relevance of the policy and the target population is comprehensively evaluated from multiple dimensions to improve the accuracy and depth of the analysis. Finally, according to the multi-dimensional matching analysis data of the policy description mark and the target population information, the optimal matching policy for the target population information is determined, so that the enterprise can effectively grasp the policy direction, optimize resource allocation, and enhance the competitiveness of the enterprise.

[0038] The policy relevance analysis method provided in the embodiment of the present application can be applied to a terminal device. In this case, the terminal device is the executor of the policy relevance analysis method provided in the embodiment of the present application. The embodiment of the present application does not impose any restrictions on the specific type of the terminal device.

[0039] For example, the terminal device can be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a desktop computer, a smart large screen, a smart TV and other terminal devices, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, an Internet of Vehicles terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, etc.

[0040] In order to better understand the policy relevance analysis method provided in the embodiment of the present application, the specific implementation process of the policy relevance analysis method provided in the embodiment of the present application is exemplarily introduced below.

[0041] Figure 1A schematic flow chart of a policy relevance analysis method provided in an embodiment of the present application is shown, and the policy relevance analysis method includes:

[0042] S100, obtaining target population information and policy information of multiple policies.

[0043] It can be understood that the collected and collated information of the target population and the policy information of multiple policies related to it can be obtained. The information of the target population can be multiple dimensions, such as demographic information, socioeconomic status, educational background, health status, occupational information, etc. This information can be obtained through various channels, including government databases, social surveys, public data sets, etc. Policy-related information, policies can include various laws and regulations issued by the government, economic stimulus plans, social security measures, etc. The acquisition of policy information is not limited to the policy text itself, but can also include the background information of the policy, the implementation time, the interest groups involved, the expected effects, the adjustment during the policy implementation process, etc. Policy information can be extracted from official documents issued by the government, policy databases, research reports and other sources or extracted by manually uploading materials, and the policy text is parsed using natural language processing technology (NLP) to extract key policy clauses, goals, audiences and other contents. By combining the information of the target population with the information of multiple policies, comprehensive data support can be provided for subsequent analysis to ensure the accuracy and pertinence of policy analysis. The acquisition process of target population information can use data mining technology and information integration technology.

[0044] S200, determining a policy description mark for each policy based on policy information of multiple policies; wherein the policy description mark is used to reflect the impact of the policy on different groups of people in the past.

[0045] It can be understood that by analyzing the policy information of multiple policies, the policy description tag of each policy is determined. The policy description tag is a label used to summarize and reflect the historical impact of a policy, which can identify the impact of a policy on a specific population in different historical periods. The process of determining the policy description tag can conduct a detailed analysis of the policy text and the historical implementation effect, and combine the information of the target population to extract a tag that can represent the characteristics of the policy impact. The generation of policy description tags is a multi-dimensional data integration and analysis. Methods such as weighted average, fuzzy logic, and cluster analysis can be used to integrate data from various dimensions into a comprehensive policy description tag. The policy description tag not only reflects the effect of the policy, but also takes into account factors such as the duration and breadth of the policy. For example, assuming that a policy A is mainly targeted at low-income people in a certain period of time and has significantly improved the quality of life of such people, then the description tag of the policy may include a combination of "low-income people + improved quality of life + implementation period". The policy description tag provides accurate data support for subsequent matching analysis.

[0046] In one possible implementation, see Figure 2 , S200, based on the policy information of multiple policies, determine the policy description tag of each policy, including:

[0047] S210, based on the policy information of the plurality of policies, determine the affected population and the time information of the affected population when each policy was implemented in the past.

[0048] It can be understood that according to the policies of multiple policies, the affected population and the time information of the impact of each policy in the past implementation are determined, and the specific impact scope and time span of each policy in the historical implementation process are analyzed in detail. The policy text and related data can be analyzed to identify the specific audience group of each policy. The audience group can be classified by different characteristics, such as age, income, occupation, geographical location, etc. Classification algorithms and cluster analysis methods can be used to segment the policy audience and identify the impact scope of each policy. Combined with historical data, the specific time information of policy implementation is determined. Time information usually includes the effective time of the policy, the duration of implementation, the end time of the policy, etc. This time information can be matched with the data of the audience group to ensure that the impact scope and time span of each policy can be accurately recorded. For example, a policy B may be implemented between 2010 and 2015 and mainly affects the middle-aged population in a specific city. The time information of the policy can be integrated with the distribution data of the middle-aged population to generate the specific impact data of the policy on the middle-aged population at different time points. These data will provide key support for the subsequent generation of policy description tags.

[0049] S220, based on the information about the affected population and the time of impact of each policy when it was implemented in the past, obtain a policy description tag for each policy.

[0050] It can be understood that a policy description tag can be generated for each policy based on the determined affected population and its time information, and complex impact data can be converted into tags that can reflect the historical effects of the policy. The affected population data and time information of each policy can be comprehensively analyzed. By analyzing the degree of impact of the policy on various populations in different time periods, the main impact objects of the policy and the distribution of these impacts in time can be identified. Using time series analysis methods and weighted average methods, these data are integrated into a comprehensive tag. In order to describe the impact of the policy more specifically, multiple description tags can be generated for each policy. For example, a policy C may have different impacts on different populations in different time periods. The description tags of these time periods and populations are generated separately and integrated into a complete policy description tag. Assume that policy C has a significant impact on the employment rate of low-income people from 2010 to 2012, and plays an important role in improving the educational opportunities of middle-income people from 2013 to 2015. The generated policy description tags can include a combination of "low-income people + employment improvement + 2010-2012" and "middle-income people + education improvement + 2013-2015". The policy description marks will serve as the basic data for subsequent analysis.

[0051] Optionally, see Figure 3 , S220, based on the information of the affected population and the time of impact of each policy when it was implemented in the past, obtain the policy description tag of each policy, including:

[0052] S221, based on the information of the affected population and the time of impact of each policy when it was implemented in the past, determine the impact weight parameter corresponding to each affected population of the policy.

[0053] It can be understood that an impact weight parameter can be determined for each policy's different impact groups. These weight parameters are used to quantify the actual impact of policies on different groups. The determination of impact weight parameters depends on the impact analysis of each group during the policy implementation process, including the policy implementation effect, the breadth and depth of the impact. Based on the specific effects of the policy on each group in different time periods, the basis for determining the impact weight can be the substantial changes in the policy on the target group, the intensity of policy measures, and the degree of achievement of policy goals. The calculation of impact weight parameters can be combined with actual historical data, such as survey results, statistical analysis, and feedback information. By comprehensively analyzing these data, the weight parameters of each impact group are determined. Further refine the analysis of the impact group and time information of each policy, and determine the corresponding impact weight parameters for each impact group. The determination of impact weight parameters is to quantify the specific impact of different policies on different groups. The main groups affected by the policy can be identified, and the impact of each policy on these groups in different time periods can be determined. A weight parameter is assigned to each group based on these impact levels. The determination of weight parameters may involve multiple factors, including the intensity of policy implementation, the characteristics of the group, the duration of policy impact, etc.

[0054] The impact weight parameter can be calculated by a formula. For example, assuming that the impact of a policy D on low-income people in a specific period of time is I1, and the impact on middle-income people is I2, then the weighted formula can be used: ,in, represents the weight parameter of the i-th influencing group, is the policy impact value of the ith affected population, and n is the total number of affected populations. Through the above calculation, we can get the weight parameters of each policy for different populations in each time period, which will be used to generate more accurate policy description tags.

[0055] S222, based on the impact weight parameter corresponding to each affected group of the policy, weighted processing is performed on each affected group respectively to obtain the historical weighted data corresponding to each policy; wherein the weight parameter corresponding to the affected group with earlier impact time information is smaller than the weight parameter corresponding to the affected group with later impact time information.

[0056] It can be understood that each affected group can be weighted using a determined impact weight parameter to obtain historical weighted data for each policy. The impact data in different time periods can be weighted based on the policy implementation time information. Specifically, the specific impact of the policy at different time points is calculated based on the weight parameters of each affected group, and the impact data is summarized. For impact data at different time points, the impact weight at earlier times should be relatively low, while the impact weight at later times should be relatively high. When performing weighted processing, that is, as time goes by, the impact of a policy may gradually weaken, so the impact weight can be adjusted based on time information. Time decay can be achieved through an exponential decay function, for example: W t =W0*e −λ⋅t , where W t represents the weight parameter at time point t, W0 is the initial weight, λ is the time decay coefficient, and t is the time difference. Through the above calculation, the historical weighted data of each policy can be accurately weighted. These weighted data not only consider the impact of the policy in different time periods, but also reflect the changes in the impact of the policy over time. These historical weighted data will serve as an important basis for the subsequent generation of policy description tags.

[0057] S223, sorting the historical weighted data corresponding to each affected group of people according to the chronological relationship between the corresponding time information to obtain a policy description mark for each policy.

[0058] It can be understood that the historical weighted data of each affected population can be sorted in the order of time information to generate a policy description mark for each policy. This process involves the collation and analysis of historical data to ensure that the generated mark can accurately reflect the impact of the policy at different time points. The historical weighted data of the affected population of each policy can be sorted in time, and the corresponding historical weighted data can be arranged in time order according to the policy implementation time information of each affected population. The sorting result can show the weighted impact of the policy on different populations in different time periods. For example, assuming that policy E has different impacts on low-income populations and middle-income populations in 2015 and 2016 respectively, the impact data on low-income populations in 2015 and the impact data on middle-income populations in 2016 can be sorted separately. After time sorting, these data are integrated to generate a comprehensive historical weighted data sequence. These sorted historical weighted data are used to generate policy description marks. The sorted data are integrated in time series to obtain a complete description mark for each policy. This mark not only contains the weighted data at each time point, but also can reflect the actual impact on different populations during the implementation of the policy. For example, if the weighted data of policy E is high in 2015 and low in 2016, the generated policy description tag may contain the information of "high impact in 2015" and "low impact in 2016". In this way, the policy description tag can fully reflect the actual effect of the policy in different time periods, providing key data for subsequent analysis.

[0059] For example, see Figure 4 , S233, sort the historical weighted data corresponding to each affected group according to the order of the corresponding time information, and obtain the policy description mark of each policy, including:

[0060] S2231, sort the historical weighted data corresponding to each affected group of people according to the chronological relationship between the corresponding time information, and obtain a list of historical weighted data corresponding to each policy.

[0061] It can be understood that the historical weighted data of each affected population can be sorted to generate a historical weighted data list for each policy, and the weighted data at each time point can be arranged in chronological order to generate a time series data list. The sorted data list can clearly show the actual impact of the policy on each affected population in different time periods. This list not only helps to understand the historical effect of the policy, but also provides useful information for further analysis. By arranging the data in this way, a more detailed and structured basis can be provided for the generation of policy description tags. For example, assuming that the historical weighted data of policy F includes the data of low-income population in 2010 and the data of middle-income population in 2012, these data are arranged in chronological order to generate a weighted data list for 2010 and 2012. This list will show the impact intensity of policy F on various populations at different time points, thereby providing detailed time series data for generating policy description tags.

[0062] S2232: Matching is performed according to the historical weighted data list corresponding to each policy to obtain at least one policy description mark for each policy.

[0063] It can be understood that by matching the historical weighted data list corresponding to each policy, at least one policy description tag can be generated for each policy. This tag is used to summarize and describe the historical effect of the policy and provide support for subsequent matching analysis. According to the sorted historical weighted data list, a comprehensive analysis is performed to generate a policy description tag. The matching process includes comparison of historical data, weighted calculation, and tag generation. For example, one or more policy description tags can be generated based on the change trend of weighted data, the impact intensity within a time period, etc., to describe the main impact characteristics of the policy. If the impact of policy G on different groups of people in different time periods is different, multiple policy description tags can be generated. For example, one description tag of policy G may be "employment improvement of low-income groups from 2010 to 2012", while another description tag may be "education improvement of middle-income groups from 2013 to 2015". These tags can fully reflect the impact of policy G in different time periods and provide a detailed description for subsequent matching analysis.

[0064] S300, based on the policy description mark and the target population information, obtaining multi-dimensional matching analysis data of the policy description mark and the target population information.

[0065] It can be understood that multidimensional matching analysis data can be generated by combining policy description tags with target population information. Through multidimensional analysis, the relationship between policy description tags and target population information can be deeply understood, so as to evaluate the adaptability and effectiveness of the policy. The description tags of each policy can be matched with the information of the target population to obtain a set of multidimensional data. These data can include the correlation between the policy description tags and the target population in various dimensions, such as income level, educational background, geographical location, etc. Through this multidimensional analysis, the response patterns and preferences of the target population to different policies can be identified, revealing the applicability of policies to different populations. It is possible to process high-dimensional data and extract meaningful patterns through data processing and statistical analysis techniques, such as principal component analysis (PCA) and factor analysis. The data of multidimensional matching analysis can provide a scientific basis for policy adjustment and optimization, ensuring that policies can more accurately meet the needs of the target population.

[0066] In one possible implementation, see Figure 5 , S300, based on the policy description mark and the target population information, obtain the multi-dimensional matching analysis data of the policy description mark and the target population information, including:

[0067] S310, based on the policy description mark and the target population information, obtaining a policy description mark distribution parameter corresponding to the target population information.

[0068] It can be understood that by analyzing the policy description mark and the target population information, the policy description mark distribution parameters corresponding to the target population information are obtained. By determining the distribution of the target population under different policy description marks, further analysis and matching can be facilitated. The distribution characteristics of the target population under different policy description marks can be analyzed. By statistics and classification of the target population information, the distribution of various policy description marks in the target population can be obtained. For example, some policy description marks may occupy a higher proportion in a specific population, while other marks may appear in different populations. The policy description mark distribution parameters can understand which policy description marks have a higher degree of match with the characteristics of the target population, thereby providing a basis for policy selection and adjustment. The calculation of distribution parameters can provide detailed reference data for subsequent matching analysis through statistical analysis techniques, such as frequency distribution analysis, probability distribution model, etc., making policy matching more accurate and effective.

[0069] Optionally, the target population information includes the average change trend of the target population under the policy implementation corresponding to different policy description tags, see Figure 6 , S310, based on the policy description mark and the target population information, obtain the policy description mark distribution parameters corresponding to the target population information, including:

[0070] S311, based on the policy description mark and the average change trend of the target population under the policy implementation corresponding to different policy description marks, obtain the correlation coefficient between the target population and each policy description mark.

[0071] It can be understood that based on the average change trend of the policy description marker and the target population under the policy implementation corresponding to different policy description markers, the correlation coefficient between the target population and each policy description marker is calculated. The correlation coefficient is used to quantify the strength of the relationship between the target population information and the policy description marker. Statistical analysis methods, such as the Pearson correlation coefficient, the Spearman rank correlation coefficient, etc., can be used to calculate the correlation coefficient between the target population and each policy description marker. The average changes in various indicators of the target population after the implementation of the policy description marker can be analyzed, and the calculation formula can be expressed as: , is the change value of the ith data point, and n is the total number of data points. The Pearson correlation coefficient calculation formula is: in, and are the trend data of policy description markers and target populations, respectively, and n is the number of data points. By calculating the correlation coefficient, we can evaluate the strength of the relationship between the target population information and each policy description marker, thereby identifying the most relevant policy description marker. These correlation coefficients will provide a quantitative basis for subsequent analysis.

[0072] S312, obtaining the mean value of the correlation coefficient between the target population and the policy description mark according to the correlation coefficient between the target population and each policy description mark.

[0073] It can be understood that based on the correlation coefficient between the target population and each policy description marker, the mean of the correlation coefficient between the target population and the policy description marker can be calculated. The mean is used to summarize the overall correlation between the target population and all policy description markers. The correlation coefficient of each policy description marker can be averaged to obtain the mean. The calculation formula is: , where R is the mean of the correlation coefficient, m is the total number of policy description tags, and r i is the correlation coefficient of the i-th policy statement label. In this way, the correlation coefficient (r) will help us understand the policy statement label (X i ) and target population response (Y i This information is crucial for subsequent matching analysis to identify policy statement markers that best meet the needs of the target population.

[0074] S313, selecting all correlation coefficients greater than the mean of the correlation coefficients to obtain the policy description label distribution parameters corresponding to the target population information.

[0075] It can be understood that all correlation coefficients greater than the mean of the correlation coefficients can be selected to generate the distribution parameters of the policy description markers corresponding to the target population information, and screen out the policy description markers that are highly correlated with the target population information. The calculated correlation coefficient can be compared with the mean, and those correlation coefficients greater than the mean can be selected. These higher correlation coefficients indicate that there is a strong correlation between the target population information and the corresponding policy description markers. These highly correlated policy description markers are used to generate the distribution parameters of the target population information. For example, assuming that the correlation coefficient of policy description marker A is 0.8 and the mean is 0.6, then the marker will be selected to generate the policy description marker distribution parameters. The policy description marker distribution parameters will reflect the distribution of the target population information under these highly correlated policy description markers, providing data support for subsequent matching analysis.

[0076] S320, analyzing the distribution parameters of the policy description marks corresponding to the target population information to obtain multi-dimensional matching analysis data of the policy description marks and the target population information.

[0077] It can be understood that the policy description marker distribution parameters corresponding to the target population information can be analyzed to generate matching analysis data between the policy description marker and the target population information. This analysis is used to evaluate the matching degree between different policy description markers and the target population information. The policy description marker distribution parameters corresponding to the target population information can be analyzed in detail, and data mining and statistical analysis techniques can be used to evaluate the matching effect of different policy description markers. This can include calculating the similarity and correlation between the policy description marker and the target population information. For example, the distribution parameters of the policy description marker and the target population information can be reduced and visualized using methods such as multidimensional scaling analysis (MDS) and principal component analysis (PCA). Through these analyses, the policy description marker that best meets the needs of the target population is identified, thereby providing effective matching analysis data.

[0078] Optionally, S320, performing analysis based on distribution parameters of policy description marks corresponding to target population information to obtain matching analysis data of policy description marks and target population information includes:

[0079] S321, performing a multivariate linear regression analysis on the distribution parameters of the policy description marks corresponding to the target population information to obtain matching analysis data of the policy description marks and the target population information.

[0080] It can be understood that a multiple linear regression analysis is performed on the distribution parameters of the policy description markers corresponding to the target population information to generate matching analysis data of the policy description markers and the target population information. Multiple linear regression analysis is used to evaluate the degree of influence of multiple factors on the target population information and provide detailed data support for matching analysis. A multiple linear regression model can be constructed with the target population information as the dependent variable and the policy description marker distribution parameters as the independent variable. The formula of the regression model is: Y=β0+β1X1+β2X2+⋯+β n X n +ϵ, where Y is the target population information, X 1， X 2，... X n The distribution parameter X is the policy specification. n is the intercept, β1,β2,…,β n is the regression coefficient, and ϵ is the error term. Through regression analysis, we can obtain the degree of influence of each policy description mark on the target population information, thereby generating matching analysis data. These data are used to evaluate the matching effect between the policy description mark and the target population information, and provide a basis for selecting the optimal policy.

[0081] S400, determining the optimal matching policy for the target population information based on the multi-dimensional matching analysis data of the policy description mark and the target population information.

[0082] It can be understood that the optimal matching policy for the target population information can be determined based on the multidimensional matching analysis data of the policy description mark and the target population information, and the policy that best meets the needs of the target population can be found, thereby achieving the best match between the policy and the target population. The matching analysis data of the policy description mark and the target population information can be analyzed, and the optimal policy can be determined using methods such as matching degree calculation and optimization algorithm. It can be to compare all policies and select those policies that have the highest matching degree with the target population information. For example, the weighted comprehensive scoring method can be used to score the matching degree of each policy, and the policy with the highest score can be selected as the optimal matching policy. The score calculation can be based on multidimensional analysis data, such as correlation coefficients, regression analysis results, etc.

[0083] In one possible implementation, see Figure 7 , S400, determining the optimal matching policy for the target population information based on the multi-dimensional matching analysis data of the policy description mark and the target population information, including:

[0084] S410, determining relevant policy description tags corresponding to the target population information based on multi-dimensional matching analysis data of the policy description tags and the target population information.

[0085] It can be understood that policy description markers with high correlation with target population information can be identified to provide a basis for optimal policy selection. The matching analysis data can be used to determine which policy description markers have high correlation with target population information. The correlation coefficient between each policy description marker and the target population information is analyzed, and those policy description markers with high correlation coefficients are screened out. For example, if a policy description marker has a correlation coefficient of 0.8 with the target population information, which is higher than the correlation coefficients of other markers, then the marker will be considered a relevant policy description marker. These relevant markers will be used for subsequent policy comparisons and optimal matching.

[0086] S420, comparing the policy description mark of each policy according to the corresponding relevant policy description mark of the target population information, and determining the optimal matching policy for the target population information.

[0087] It can be understood that the policy that best meets the needs of the target population can be found through comparative analysis. Compare the relevant policy description tags of the target population information with the policy description tags of all policies to analyze the matching degree of these tags. You can use matching degree calculation, similarity measurement and other methods to compare the policy description tags of each policy to determine its fit with the relevant tags. For example, if the relevant policy description tag of the target population information is "low-income people + employment promotion", compare the description tags of all policies to see which policy tags have the highest fit with the relevant tag. The policy with a high degree of fit will be considered the best matching policy.

[0088] Optionally, see Figure 8 S420, comparing the policy description mark of each policy according to the corresponding relevant policy description mark of the target population information, and determining the optimal matching policy for the target population information, including:

[0089] S421, comparing the policy description mark of each policy according to the corresponding relevant policy description mark of the target population information, and calculating the mark fit between the policy description mark of each policy and the relevant policy description mark.

[0090] It can be understood that the tag fit between the policy description tag of each policy and the relevant policy description tag of the target population information is calculated to quantify the degree of match between the policy description tag of each policy and the needs of the target population. The tag fit can be evaluated using calculation formulas and matching algorithms. For example, the cosine similarity calculation formula can be used to measure the similarity between two tags: , where A and B are the vector representations of the policy description tag and the relevant policy description tag, respectively. and are the moduli of vectors A and B, respectively. By calculating the fit of the markers, it is possible to evaluate the degree of match between the policy description markers of each policy and the relevant markers of the target population information.

[0091] S422, selecting a policy with the highest degree of matching between the policy description mark and the related policy description mark as the optimal matching policy for the target population information.

[0092] It can be understood that after calculating the degree of fit between all policy description tags and related policy description tags, these fits can be sorted to determine which policy description tag is closest to the related policy description tag of the target population information. The sorting can be based on the size of the fit, and the higher the fit, the higher the degree of match between the two policy description tags. The policy corresponding to the policy description tag with the highest fit is selected as the optimal matching policy for the target population information. This means that in the historical data, the policy shows the strongest relevance under similar populations or conditions, so it is expected that it will also have the most significant impact on the current target population. For example, if the description tag of a certain policy A has the highest degree of fit with the related policy description tag, policy A can be selected as the optimal matching policy for the target population. Ultimately, it effectively helps enterprises grasp the direction of policy implementation, thereby providing important strategic support for enterprises in a rapidly changing environment.

[0093] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0094] Corresponding to the policy relevance analysis method described in the above embodiment, the embodiment of the present application also provides a policy relevance analysis system, and each unit of the system can implement each step of the policy relevance analysis method. Fig. 9 A structural block diagram of a policy relevance analysis system provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0095] Reference Fig. 9 , the policy relevance analysis system includes:

[0096] An acquisition unit, used to acquire target population information and policy information of multiple policies;

[0097] A marking unit, used to determine a policy description mark of each policy based on the policy information of the plurality of policies; wherein the policy description mark is used to reflect the impact of the policy on different groups of people in the past;

[0098] An analysis unit, configured to obtain multi-dimensional matching analysis data of the policy description mark and the target population information based on the policy description mark and the target population information;

[0099] A determination unit is used to determine the optimal matching policy for the target population information according to the policy description mark and the multi-dimensional matching analysis data of the target population information.

[0100] It should be noted that the information interaction, execution process, etc. between the above-mentioned systems / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0101] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit module can exist physically separately, or two or more unit modules can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0102] The present application also provides a policy relevance analysis device. Fig.10 This is a schematic diagram of the structure of a policy relevance analysis device provided in one embodiment of the present application. Fig.10 As shown, the policy relevance analysis device 6 of this embodiment includes: at least one processor 60 ( Fig.10 Only one is shown), at least one memory 61 ( Fig.10 Only one is shown in the figure) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, the policy relevance analysis device 6 implements the steps in any of the above-mentioned policy relevance analysis method embodiments, or implements the functions of the various units in the above-mentioned system embodiments.

[0103] Exemplarily, the computer program 62 may be divided into one or more units, which are stored in the memory 61 and executed by the processor 60 to complete the present application. The one or more units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 62 in the policy relevance analysis device 6.

[0104] The policy relevance analysis device 6 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The policy relevance analysis device may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will appreciate that Fig.10 It is only an example of the policy relevance analysis device 6 and does not constitute a limitation of the policy relevance analysis device 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, buses, etc.

[0105] The processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0106] In some embodiments, the memory 61 may be an internal storage unit of the policy relevance analysis device 6, such as a hard disk or memory of the policy relevance analysis device 6. In other embodiments, the memory 61 may also be an external storage device of the policy relevance analysis device 6, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the policy relevance analysis device 6. Further, the memory 61 may also include both an internal storage unit and an external storage device of the policy relevance analysis device 6. The memory 61 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 61 may also be used to temporarily store data that has been output or is to be output.

[0107] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0108] An embodiment of the present application provides a computer program product. When the computer program product runs on a policy relevance analysis device, the policy relevance analysis device implements the steps in any of the above method embodiments.

[0109] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the policy relevance analysis device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0110] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0111] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0112] In the embodiments provided in the present application, it should be understood that the disclosed policy relevance analysis system / policy relevance analysis device and method can be implemented in other ways. For example, the policy relevance analysis system / policy relevance analysis device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. There may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection of systems or units, which may be electrical, mechanical or other forms.

[0113] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0114] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A policy relevance analysis method, characterized in that: include: Obtain target population information and policy information for multiple policies; Determine a policy description mark for each policy based on the policy information of the plurality of policies; wherein the policy description mark is used to reflect the impact of the policy on different groups of people in the past; Based on the policy description mark and the target population information, obtaining multi-dimensional matching analysis data of the policy description mark and the target population information; Determining an optimal matching policy for the target population information based on the policy description mark and the multi-dimensional matching analysis data of the target population information; Wherein, determining the policy description mark of each policy based on the policy information of the plurality of policies includes: Determine, based on the policy information of the plurality of policies, the population affected by each policy when it was implemented in the past and the time information of its impact; Based on the affected population and the time information of the affected population when each policy was implemented in the past, obtain a policy description tag for each policy; The policy description mark of each policy is obtained based on the affected population and the time information of the affected population when each policy was implemented in the past, including: Based on the affected population and the time information of the affected population when each policy was implemented in the past, respectively determine the impact weight parameter corresponding to each affected population of the policy; Based on the impact weight parameter corresponding to each of the affected groups of the policy, weighted processing is performed on each of the affected groups to obtain historical weighted data corresponding to each of the policies; wherein the weight parameter corresponding to the affected group with earlier impact time information is smaller than the weight parameter corresponding to the affected group with later impact time information; Sort the historical weighted data corresponding to each affected group of people according to the order of the corresponding time information to obtain a policy description mark for each policy; The historical weighted data corresponding to each affected group is sorted according to the order of the corresponding time information to obtain a policy description mark for each policy, including: Sort the historical weighted data corresponding to each affected group of people according to the order of the corresponding time information to obtain a list of historical weighted data corresponding to each policy; Matching is performed according to the historical weighted data list corresponding to each of the policies to obtain at least one policy description mark for each of the policies; The step of obtaining multi-dimensional matching analysis data of the policy description mark and the target population information based on the policy description mark and the target population information includes: Based on the policy description mark and the target population information, obtaining a policy description mark distribution parameter corresponding to the target population information; Analyze the distribution parameters of the policy description marks corresponding to the target population information to obtain multi-dimensional matching analysis data between the policy description marks and the target population information; The target population information includes the average change trend of the target population under the implementation of policies corresponding to different policy description marks. Based on the policy description mark and the target population information, the policy description mark distribution parameter corresponding to the target population information is obtained, including: Based on the average change trend of the policy description mark and the target population under the implementation of policies corresponding to different policy description marks, the correlation coefficient between the target population and each policy description mark is obtained; According to the correlation coefficient between the target population and each policy description mark, obtain the mean value of the correlation coefficient between the target population and the policy description mark; All the correlation coefficients that are greater than the mean value of the correlation coefficients are selected to obtain the policy description mark distribution parameters corresponding to the target population information.

2. The policy relevance analysis method according to claim 1, characterized in that: The analyzing the distribution parameters of the policy description mark corresponding to the target population information to obtain the matching analysis data of the policy description mark and the target population information includes: A multivariate linear regression analysis is performed on the distribution parameters of the policy description marks corresponding to the target population information to obtain matching analysis data between the policy description marks and the target population information.

3. The policy relevance analysis method according to claim 1, characterized in that: Determining the optimal matching policy for the target population information based on the policy description mark and the multi-dimensional matching analysis data of the target population information includes: Determine the corresponding relevant policy description mark of the target population information according to the multi-dimensional matching analysis data of the policy description mark and the target population information; The policy description mark of each policy is compared according to the corresponding relevant policy description mark of the target population information to determine the optimal matching policy for the target population information.

4. The policy relevance analysis method according to claim 3, characterized in that: The step of comparing the policy description mark of each policy with the corresponding relevant policy description mark of the target population information to determine the optimal matching policy for the target population information includes: Compare the policy description mark of each policy according to the corresponding relevant policy description mark of the target population information, and calculate the mark fit between the policy description mark of each policy and the relevant policy description mark; The policy with the highest degree of fit between the policy description mark and the mark of the relevant policy description mark is selected as the optimal matching policy for the target population information.

5. A policy relevance analysis system, characterized in that: For implementing the method according to any one of claims 1 to 4, the policy relevance analysis system comprises: An acquisition unit, used to acquire target population information and policy information of multiple policies; A marking unit, used to determine a policy description mark of each policy based on the policy information of the plurality of policies; wherein the policy description mark is used to reflect the impact of the policy on different groups of people in the past; An analysis unit, configured to obtain multi-dimensional matching analysis data of the policy description mark and the target population information based on the policy description mark and the target population information; A determination unit is used to determine the optimal matching policy for the target population information according to the policy description mark and the multi-dimensional matching analysis data of the target population information.

Images