Policy data acquisition and analysis method and system

Abstract

The invention aims to provide a policy data acquisition and analysis method and system. The method comprises the following steps: acquiring policy information by adopting a crawler technology; preprocessing the acquired policy information to obtain a relationship among a policy field, a policy object and a policy, and calculating policy driving force according to the relationship among the policy field, the policy object and the policy; and predicting a policy evolution result according to the policy driving force. The policy information can be acquired through a crawler technology, and the target keyword in the policy information is extracted, so that the content of the policy information can be more conveniently compressed and analyzed, the correlation between policies can be analyzed, the general evolution direction of the policies can be finally predicted, and a guidance direction is provided for enterprises and industries.

Description

Technical Field

[0001] The present invention relates to the field of data analysis, and in particular to a policy data collection and analysis method and system. Background Art

[0002] Policy data refers to the various forms of data generated, collected, stored, and used by governments during the process of policy formulation and implementation. This data includes not only text but also multimedia information such as images, audio, and video, and may even include complex data types generated by emerging technologies such as big data and cloud computing. Policy data is a resource accumulated by governments during the exercise of their functions, the provision of public services, and the processing of data. These data resources play a vital role in government decision-making, helping them better understand social needs, evaluate policy effectiveness, and make informed decisions. Policy data has a wide range of applications in government affairs. For example, government data is a crucial foundation for building a digital government. Through data sharing and analysis, the scientific nature and accuracy of government decision-making can be improved. Furthermore, government data plays a vital role in typical government service scenarios, such as public services and economic operations, helping governments better serve the public and businesses. Policy data is primarily acquired through the generation, collection, storage, and use of data by government departments in their daily work. Utilization methods include data sharing, data analysis, and policy evaluation. By establishing an integrated government data sharing hub, it is possible to share and access various data resources, improving the efficiency and value of data use.

[0003] The content of policy data is very large and the information is very complex, which leads to low efficiency of policy analysis and inaccurate analysis results. Therefore, it is difficult for enterprises to obtain information beneficial to their own development from different policies. This has led to many enterprises being unable to use policy benefits to promote their own development. Even if the government issues policies, the relevant industries and related fields still have low benefits. In addition, the policies issued by the country, provinces, cities and districts are related, and it is difficult for enterprises and entrepreneurs themselves to make correct judgments on the direction of development based solely on the issued policy texts. Summary of the Invention

[0004] The purpose of the present invention is to provide a policy data collection and analysis method and system, which can obtain policy information through crawler technology and extract target keywords in the policy information, making it more convenient to compress and analyze the content of the policy information. It can also analyze the correlation between policies and ultimately predict the general direction of policy evolution, providing guidance for enterprises and industries.

[0005] A policy data collection and analysis method, comprising: Use crawler technology to obtain policy information; Pre-process the acquired policy information to obtain the relationship between policy areas, policy objects and policies; Calculate policy drivers based on the relationships between the policy areas, policy objects and policies; Predict policy evolution outcomes based on the stated policy drivers.

[0006] Preferably, the pre-processing of the acquired policy information to obtain the relationship between the policy field, policy object and policy includes: Convert policy text information into input vectors; Construct an information extraction layer to obtain policy areas and policy objects in policy information; Calculate the relationship between policies based on the policy areas and policy objects.

[0007] Preferably, converting the policy text information into an input vector comprises: Convert the vocabulary and the frequency of each vocabulary in the policy text information into input vectors.

[0008] Preferably, the step of constructing the information extraction layer to obtain policy fields and policy objects in the policy information includes: Construct an information extraction layer to obtain the policy fields and policy objects in the input vector; Input the policy areas and policy objects as target keywords into the information extraction layer; The information extraction layer extracts policy areas and policy objects based on the frequency of target keywords.

[0009] Preferably, the calculating the relationship between policies according to the policy fields and policy objects includes: Calculate the similarity between the i-th policy and the k-th policy; If the similarity is less than the threshold, it means that there is no correlation between the two policies; If the similarity is greater than the threshold, the correlation between the i-th policy and the k-th policy is calculated.

[0010] Preferably, the calculating of the policy driving force according to the relationship between the policy field, policy object and policy comprises: The driving force of a policy is expressed based on its impact on industries and enterprises.

[0011] Preferably, predicting the policy evolution result according to the policy driving force includes: The policy evolution factor is calculated based on environmental constraints, industry revenue growth after the policy is introduced, and public support.

[0012] A policy data collection and analysis system, comprising: Data acquisition module, used to obtain policy information using crawler technology; The data processing module is used to pre-process the acquired policy information to obtain the relationship between policy areas, policy objects and policies; a data analysis module for calculating policy drivers based on the relationships among the policy areas, policy objects, and policies; The policy prediction module is used to predict the policy evolution results based on the policy driving forces.

[0013] An electronic device includes: a chip, a processor and a memory, wherein the memory is used to store computer program code, and the computer program code includes computer instructions. When the chip executes the computer instructions, the electronic device executes a policy data collection and analysis method.

[0014] A computer-readable storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor is caused to execute a policy data collection and analysis method.

[0015] The beneficial effects of the present invention are: 1. The present invention can convert a large amount of policy information into a simple text vector form, which can facilitate the computer to quickly process policy information and accelerate the efficiency of policy analysis; 2. The present invention performs targeted information extraction on policy information, selects the most judgmental words as target keywords, and thus analyzes the main information of long-term and difficult policies; 3. The present invention can predict the general direction of future policy evolution based on the correlation between national policies, provincial and municipal policies, and county policies and the effects of policy issuance, and provide decision-making guidance for industries and enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0018] Figure 1 This is a flow chart of a policy data collection and analysis method of the present invention; Figure 2 Schematic diagram of the information extraction layer structure of the present invention; Figure 3 The figure is a schematic diagram of the hardware structure of an electronic device of the present invention. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0020] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0021] In addition, the descriptions of "first", "second", etc. in the present invention are for descriptive purposes only and should not be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but this must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0022] The content of policy data is very large and the information is very complex, which leads to low efficiency of policy analysis and inaccurate analysis results. Therefore, it is difficult for enterprises to obtain information beneficial to their own development from different policies. This has led to many enterprises being unable to use policy benefits to promote their own development. Even if the government issues policies, the relevant industries and related fields still have low benefits. In addition, the policies issued by the country, provinces, cities and districts are related, and it is difficult for enterprises and entrepreneurs themselves to make correct judgments on the direction of development based solely on the issued policy texts.

[0023] The present invention can convert a large amount of policy information into a simple text vector form, which can facilitate computers to quickly process policy information and accelerate policy analysis efficiency; the present invention performs targeted information extraction on policy information, selects the most judgmental words as target keywords, and thus analyzes the main information of long-term and difficult policies; the present invention can predict the general direction of future policy evolution based on the correlation between national policies, provincial and municipal policies, and county policies, as well as the effects of policy issuance, and provide decision-making guidance for industries and enterprises.

[0024] Example 1 A policy data collection and analysis method, reference Figure 1,include: S100, uses crawler technology to obtain policy information; Policy texts primarily come from the official websites of relevant government departments and professional websites focused on policy research. National, provincial, and municipal policies are the three main levels of the policy system, with clear divisions of power and responsibilities, as well as close coordination and linkage. National policies are macro-strategies and regulations covering the entire country. Provincial policies are formulated by provincial governments, which implement national policies and refine measures tailored to the specific characteristics of their respective provinces. Municipal policies are formulated by city, district, and county governments, focusing on specific local implementation details, including household registration reform (residence permit system), allocation of education and medical resources, issuance of consumer vouchers, enterprise subsidies, shantytown redevelopment, and the planning of characteristic towns.

[0025] S200, pre-processing the acquired policy information to obtain the relationship between policy areas, policy objects and policies; A policy domain refers to the range of social, economic, or political issues addressed by a policy, typically organized by industry, function, or societal need. A policy target refers to the individuals, groups, or organizations directly affected or impacted by the policy—that is, the entities the policy intends to mobilize or constrain. These can be individuals, businesses, social organizations, or natural systems. For example, the targets of education policy (domain) are primarily students, teachers, and schools, while the targets of industrial policy (domain) are businesses and industry associations.

[0026] S300, calculates policy drivers based on the relationship between policy areas, policy objects, and policies; Policy drivers refer to the power of the government to promote economic development and social progress through the formulation and implementation of various policies. Policy drivers can be exerted in many ways, including financial support, tax incentives, and the formulation of laws and regulations.

[0027] S400, predicting policy evolution outcomes based on policy drivers.

[0028] The results of these policy changes are primarily reflected in economic, social, and environmental aspects. The government has increased support for small and medium-sized enterprises through tax cuts and subsidies, helping them grow steadily and promoting economic recovery. The government has increased investment in research and development, optimized the innovation environment, encouraged businesses to engage in technological innovation and R&D, and promoted sustained and healthy economic development. The government has also increased investment in vocational education, increased demand for highly skilled personnel, guided changes in the job market, and created more employment opportunities.

[0029] Preferably, reference Figure 2 , S200, pre-process the obtained policy information to obtain the relationship between policy areas, policy objects and policies, including: S210, converting policy text information into an input vector; S220, constructing an information extraction layer to obtain policy fields and policy objects in policy information; S230, calculating the relationship between policies based on policy areas and policy objects.

[0030] In this embodiment of the present invention, policies can be categorized into three types based on the recipients of their release: national, provincial, and municipal policies. Within different recipients, policies exert macro-guidance and promotional influences on each other. Within the same recipient level, different policies can be further categorized based on their policy areas and recipients. These policies can also influence and promote each other, making studying the relationships between policies essential for predicting future policy evolution. Policies provide guidance and direction for the exercise of administrative power. When exercising power, administrative agencies must adhere to the objectives and principles of policies to ensure that their exercise aligns with the overall interests of the nation and the needs of social development. At the same time, administrative agencies can also, within the legal framework, adopt flexible and diverse measures and methods based on policy needs to achieve policy objectives. Overall policy arrangements and specific policies are interdependent and mutually dependent on each other's existence and development. When formulating and implementing specific policies, it is important to consider both their local characteristics and positive impacts while also prioritizing the overall system and striving for optimal results. Precision policy implementation requires balancing macro-guidance with micro-operations to ensure that all policies are effective at both the macro and micro levels. A systematic policy chain is a chain of related policies formed by technical connections, logical relationships, and spatial and temporal arrangements. Each policy link is interconnected and interactive, strengthening policy relevance analysis, paying attention to the interrelationships between policies within the same scope, ensuring the interaction between policy goals and measures and the external environment, and comprehensively considering the impact of various factors on policy implementation.

[0031] Preferably, converting the policy text information into an input vector includes: Convert the vocabulary and the frequency of each vocabulary in the policy text information into input vectors.

[0032] Converting policy information into input vectors improves the efficiency of computational processing and policy analysis. Vectorization converts text data into numerical form, enabling computers to process this data more efficiently. Vectorization allows text data to be directly fed into various efficient algorithms, improving processing speed and computational efficiency. Converting policy information into input vectors also enhances expressiveness: vector representations can capture deep relationships within text, such as the similarity between synonyms, which is crucial for many downstream tasks. High-quality text vectors improve model accuracy and efficiency.

[0033] Preferably, reference Figure 2 , constructing the information extraction layer to obtain policy areas and policy objects in policy information, including: Construct an information extraction layer to obtain the policy fields and policy objects in the input vector; The information extraction layer is a key component of natural language processing. Its primary task is to extract useful information from unstructured text data and transform it into a structured form. The information extraction layer identifies entities within text, such as names of people, places, and organizations. Named entity recognition is the foundation of information extraction and helps the system identify key information carriers within text.

[0034] Input policy areas and policy objects as target keywords into the information extraction layer; Converting policy fields into target keywords is an important step in policy analysis, information retrieval and intelligent recommendation. In an embodiment of the present invention, the policy fields converted into target keywords can be the names of various industries, various company names, etc.

[0035] In the embodiment of the present invention, the policy text is, for example: supporting the digital transformation of small and medium-sized enterprises, providing tax incentives and subsidies. Among them, the policy targets small and medium-sized enterprises; providing R&D funding subsidies to new energy vehicle companies, among which the policy targets are new energy vehicle companies; encouraging college graduates to return to their hometowns to start businesses, providing low-interest loans, among which the policy targets are college graduates.

[0036] The information extraction layer extracts policy areas and policy objects based on the frequency of target keywords.

[0037] Relationship extraction usually uses triples to identify the relationship between entities. The target keywords of the information extraction layer refer to the key terms or phrases identified and extracted from the text data during the information extraction process. These keywords are usually words in the text that have specific meanings or refer to specific entities, such as names of people, places, organizations, time, events, etc. In terms of technical implementation, information extraction usually uses natural language processing tools and models, such as large language models. For example, the target long text is input into the large language model, and the target keywords are extracted based on the output of the model. These keywords are then used to generate corresponding regular expressions, and the text is processed to extract entity relationships.

[0038] Preferably, calculating the relationship between policies based on policy areas and policy objects includes: Calculate the similarity between policies; ; in, is the input vector of the i-th policy, is the input vector of the k-th policy; In the embodiment of the present invention, the similarity between policies can also be reflected in the purpose and function of the policies, such as the social problems that the policies are to solve, the social fields in which the policies affect, etc.

[0039] If the similarity is less than the threshold, it means that there is no correlation between the two policies; If the similarity is greater than the threshold, the correlation between the two policies is calculated; The correlation between the i-th policy and the k-th policy is expressed as: ; in, is an adjustable parameter and T is the prior dataset.

[0040] The above formula can reflect the probability that the i-th policy and the k-th policy belong to the same category.

[0041] The relationship between economic and social policies: Economic policy promotes the rational allocation of social resources by regulating economic operations, providing a material foundation for social policy; social policy creates a stable environment for economic policy by improving people's livelihoods and ensuring social equity. The two policies share both synergies and tensions, requiring a dynamic balance between efficiency and equity for their mutual development. The relationship between fiscal and monetary policies: Fiscal policy directly influences aggregate demand (e.g., government spending and tax adjustments), while monetary policy indirectly influences investment and consumption through adjustments to interest rates and money supply. Their complementary nature allows for a more comprehensive coverage of the economy, and their coordination can shorten the overall regulatory cycle, avoid policy conflicts, and achieve a balance between multiple objectives.

[0042] Preferably, calculating the policy driving force based on the relationship between policy areas, policy objects and policies includes: The driving force of the policy is expressed according to the impact of the policy on the industry and enterprises, which can be expressed as: ; Among them, G is the impact of the policy on industries and enterprises, n is the number of policy areas, that is, industries; r is the number of policy targets, that is, enterprises or employees; is the growth proportion of r enterprises in industry c in year t, which is used to measure the increase in enterprises in a certain industry under the influence of policies. is the employment population density of industry c in year t, indicating the increase in the employed population in industry c in year t under the influence of policies.

[0043] Government macroeconomic policies, such as monetary and fiscal policies, directly impact the business environment. Loosening or tightening monetary policy can affect a company's financing costs, which in turn influences its investment plans and development direction. Adjustments to fiscal policy can also impact a company's tax burden and the level of government support, significantly impacting its production and operations. Government industrial policies directly influence a company's development direction and competitiveness. Industrial policies may include tax incentives, subsidies, and support for technological innovation. These measures can reduce operating costs, stimulate investment, and promote technological innovation and industrial upgrading. Industrial policies can also reduce operating costs and time costs for companies by optimizing the business environment, streamlining approval procedures, and lowering market entry barriers, thereby improving operational efficiency and market competitiveness. Government regional policies also influence the geographic distribution and production layout of companies. Government support policies for specific regions influence companies' investment and production decisions in those areas. For example, government tax incentives and fiscal subsidies can attract companies to establish production bases in certain areas, thereby promoting local economic development. Government foreign trade policies and opening-up policies influence companies' export and import operations. Tariff policies, exchange rate policies, and trade agreements all directly impact a company's international competitiveness and development direction. Adjustments to opening-up policies also influence companies' decisions on overseas cooperation and investment. Government social and environmental policies also impact businesses. Labor policies, social security policies, and environmental regulations influence a company's labor costs, social responsibility, and environmental investment. Companies need to adjust their employment practices, fulfill their social responsibilities, and implement environmental measures in accordance with government policies to meet government requirements for corporate social responsibility.

[0044] For example, policies related to large-scale equipment upgrades have driven profit growth in industries like specialized and general-purpose equipment. Consumer product trade-in policies have also significantly boosted profits in industries like wearable smart device manufacturing and household kitchen appliance manufacturing. Therefore, government policies can directly promote the development of specific industries and increase the profits of related companies.

[0045] The driving force of a policy represents the influence of the policy on industries and enterprises. It is reflected by promoting enterprise growth and promoting employment. The policy driving force can intuitively reflect the direct impact of a policy on the policy field and policy objects, and can be directly used to evaluate whether the current policy is suitable for the current policy field and policy objects. If the policy driving force is strong enough, then the current policy field and policy objects will continue to develop under the influence of the policy. If the policy driving force is relatively weak, then the policy still needs to be improved.

[0046] Preferably, predicting the policy evolution results based on the policy driving force includes: Calculate the policy evolution factor: ; Among them, H is the environmental constraint factor, Y is the industry revenue growth after the policy is introduced, is a random disturbance term, and I is the public support.

[0047] National policies determine the general evolution direction of local policies, and the evolution direction of local policies is usually affected by the feedback from policy issuance. If the policy issuance receives high support from the masses and produces good benefits, then the local policy will evolve in a good direction. If a local policy does not receive support from the masses and cannot produce good benefits, then the local policy will develop in the direction of improvement. However, policy evolution is also constrained by the environment. An industry always has a saturation value. When an industry reaches a saturated state, the policy will not continue to evolve in the original direction. Therefore, the environmental constraint factor is related to the saturation of the industry on which the current policy acts. If the industry supported by the current policy is relatively saturated, then the value of the environmental constraint factor will be relatively small, and the overall value of the policy evolution factor will be relatively small, reflecting that the current policy will not evolve in the original direction. If the industry supported by the current policy still has a lot of room for development, then the value of the environmental constraint factor will be relatively large, and the overall value of the policy evolution factor will be relatively large, reflecting that the current policy will evolve and develop rapidly in the original direction.

[0048] Example 2 A policy data collection and analysis system, comprising: Data acquisition module, used to obtain policy information using crawler technology; The data processing module is used to pre-process the acquired policy information to obtain the relationship between policy areas, policy objects and policies; A data analysis module to calculate policy drivers based on the relationships between policy areas, policy objects, and policies; The policy prediction module is used to predict the policy evolution results based on policy driving forces.

[0049] Example 3 An electronic device includes: a chip, a processor and a memory, the memory is used to store computer program code, the computer program code includes computer instructions, and when the chip executes the computer instructions, the electronic device executes a policy data collection and analysis method.

[0050] refer to Figure 3The electronic device 2 includes a processor 21, a memory 22, an input device 23, and an output device 24. The processor 21, the memory 22, the input device 23, and the output device 24 are coupled via a connector, which may include various interfaces, transmission lines, or buses, etc., but this is not limited in the present embodiment. It should be understood that in various embodiments of the present invention, coupling refers to mutual connection in a specific manner, including direct connection or indirect connection through other devices, such as connection via various interfaces, transmission lines, buses, etc.

[0051] The processor 21 may be one or more graphics processing units (GPUs). If the processor 21 is a GPU, the GPU may be a single-core GPU or a multi-core GPU. Alternatively, the processor 21 may be a processor group consisting of multiple GPUs, with the multiple processors coupled to each other via one or more buses. Alternatively, the processor may be another type of processor, and this is not limited in this embodiment of the present invention.

[0052] The memory 22 can be used to store computer program instructions and various computer program codes, including program codes for executing the embodiments of the present invention. Optionally, the memory includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM), and is used for related instructions and data.

[0053] The input device 23 is used to input data and / or signals, and the output device 24 is used to output data and / or signals. The output device 24 and the input device 23 can be independent devices or an integrated device.

[0054] Example 4 A computer-readable storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a policy data collection and analysis method.

[0055] The present invention can convert a large amount of policy information into a simple text vector form, which can facilitate computers to quickly process policy information and accelerate policy analysis efficiency; the present invention performs targeted information extraction on policy information, selects the most judgmental words as target keywords, and thus analyzes the main information of long-term and difficult policies; the present invention can predict the general direction of future policy evolution based on the correlation between national policies, provincial and municipal policies, and county policies, as well as the effects of policy issuance, and provide decision-making guidance for industries and enterprises.

[0056] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is intended to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A policy data collection and analysis method, characterized in that: include: Use crawler technology to obtain policy information; Pre-process the acquired policy information to obtain the relationship between policy areas, policy objects and policies; Calculate policy drivers based on the relationships between the policy areas, policy objects and policies; Predict policy evolution outcomes based on the stated policy drivers.

2. A policy data collection and analysis method according to claim 1, characterized in that: The obtained policy information is pre-processed to obtain the relationship between policy areas, policy objects and policies, including: Convert policy text information into input vectors; Construct an information extraction layer to obtain policy areas and policy objects in policy information; Calculate the relationship between policies based on the policy areas and policy objects.

3. A policy data collection and analysis method according to claim 2, characterized in that: The converting of the policy text information into an input vector includes: Convert the vocabulary and the frequency of each vocabulary in the policy text information into input vectors.

4. A policy data collection and analysis method according to claim 3, characterized in that: The policy fields and policy objects in the policy information obtained by constructing the information extraction layer include: Construct an information extraction layer to obtain the policy fields and policy objects in the input vector; Input the policy areas and policy objects as target keywords into the information extraction layer; The information extraction layer extracts policy areas and policy objects based on the frequency of target keywords.

5. A policy data collection and analysis method according to claim 4, characterized in that: The relationship between the policies calculated based on the policy fields and policy objects includes: Calculate the similarity between the i-th policy and the k-th policy; If the similarity is less than the threshold, it means that there is no correlation between the two policies; If the similarity is greater than the threshold, the correlation between the i-th policy and the k-th policy is calculated.

6. A policy data collection and analysis method according to claim 1, characterized in that: The calculation of the policy driving force based on the relationship between the policy field, policy object and policy includes: The driving force of a policy is expressed based on its impact on industries and enterprises.

7. A policy data collection and analysis method according to claim 6, characterized in that: The prediction of policy evolution results based on the policy driving force includes: The policy evolution factor is calculated based on environmental constraints, industry revenue growth after the policy is introduced, and public support.

8. A policy data collection and analysis system, characterized in that: include: Data acquisition module, used to obtain policy information using crawler technology; The data processing module is used to pre-process the acquired policy information to obtain the relationship between policy areas, policy objects and policies; a data analysis module for calculating policy drivers based on the relationships among the policy areas, policy objects, and policies; The policy prediction module is used to predict the policy evolution results based on the policy driving forces.

9. An electronic device, characterized in that: include: A chip, a processor and a memory, wherein the memory is used to store computer program code, and the computer program code includes computer instructions. When the chip executes the computer instructions, the electronic device executes a policy data collection and analysis method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a policy data collection and analysis method according to any one of claims 1 to 7.

Images