A policy matching method and device, electronic equipment and storage medium
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NINGBO BIG DATA INVESTMENT DEVELOPMENT CO LTD
- Filing Date
- 2026-03-31
- Publication Date
- 2026-07-21
Smart Images
Figure CN121935634B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of government service technology, and more specifically, to a policy matching method, apparatus, electronic device, and storage medium. Background Technology
[0002] With policy resources experiencing massive growth and dynamic updates, and application requirements generally involving multi-dimensional rules and complex logical constraints, achieving a rapid and accurate match between a company's own conditions and applicable policies has become a key step in improving the success rate of applications.
[0003] However, current policy data is mostly scattered across heterogeneous data sources in unstructured text format. How enterprises can quickly and accurately extract suitable policies from massive amounts of information has become a pressing technical problem. Existing policy matching methods have significant limitations and struggle to provide enterprises with reasonable and reliable policy matching. Summary of the Invention
[0004] The problem addressed by this invention is how to provide a reasonable and reliable matching policy.
[0005] To address the above problems, this invention provides a policy matching method, comprising: The logical parameters in the pre-associated logical rules of each preset policy are clustered, and the demand parameters are determined based on the clustering results; wherein, each logical rule includes at least one logical parameter and the access attribute value corresponding to the logical parameter; the demand parameters include general parameters and special parameters; Information is extracted from the acquired basic enterprise information, and the actual attribute values corresponding to each of the aforementioned requirement parameters are determined based on the extraction results. When the actual attribute value of the demand parameter does not match the access attribute value of the corresponding logical parameter in the preset policy, the demand parameter is associated with the application obstacle parameter of the preset policy. Based on the application obstacle parameters, candidate policies are selected from the preset policies. When the number of candidate policies is greater than 1, a set of candidate policies that meet preset compatibility conditions is generated. The preset compatibility conditions include that the logical rules of all candidate policies in the candidate policy set are not mutually exclusive. When the application barrier parameter associated with the candidate policy in the candidate policy set is the general parameter, a temporary attribute value for the application barrier parameter is determined; When the temporary attribute value matches each corresponding attribute value to be verified, a policy matching result is generated based on the candidate policy set; wherein, the attribute value to be verified includes the admission attribute value of the logical parameter corresponding to the declaration barrier parameter, and the admission attribute value is located in the candidate policy of the candidate policy set.
[0006] Optionally, determining the demand parameters based on the clustering results includes: Determine the semantic vector corresponding to each of the logical parameters, and cluster the logical parameters with semantic similarity greater than a preset similarity threshold into a parameter cluster based on the semantic vector; When the number of logical parameters in the parameter cluster is greater than a preset number, each logical parameter in the parameter cluster is marked as the same general parameter; After traversing all the parameter clusters, the remaining unmarked logical parameters are marked as the respective dedicated parameters.
[0007] Optionally, the extraction result includes the extraction attribute value corresponding to each of the requirement parameters and / or extraction failure prompt information; determining the actual attribute value corresponding to each of the requirement parameters based on the extraction result includes: When the extraction result is the extracted attribute value, the corresponding actual attribute value is determined based on the extracted attribute value; When the extraction result is the extraction failure prompt message, supplementary prompt message is generated based on the requirement parameters corresponding to the extraction failure prompt message and sent to the preset interactive device; In response to the supplementary attribute value sent by the preset interactive device, the corresponding actual attribute value is determined based on the supplementary attribute value.
[0008] Optionally, the step of selecting candidate policies from the preset policies based on the application obstacle parameters includes: Obtain the weight coefficient corresponding to each of the application obstacle parameters, and determine the matching coefficient of the preset policy based on the weight coefficient corresponding to all the application obstacle parameters associated with the preset policy; The preset policies whose matching coefficient is greater than the preset matching threshold are selected as candidate policies; wherein the weighting coefficient is negatively correlated with the matching coefficient.
[0009] Optionally, determining the temporary attribute value of the declared obstacle parameter includes: Determine the overlapping range of attribute values corresponding to each attribute value to be verified, and select the attribute value with the smallest difference from the actual attribute value corresponding to the declared obstacle parameter within the overlapping range to obtain the temporary attribute value.
[0010] Optionally, the policy matching result includes application suggestion information; generating the policy matching result based on the candidate policy set includes: When the declared obstacle parameter is the general parameter, the suggested attribute value of the declared obstacle parameter is obtained based on the temporary attribute value; When the application obstacle parameter is the dedicated parameter, the suggested attribute value of the application obstacle parameter is determined according to the admission attribute value of the logical parameter corresponding to the application obstacle parameter; The application suggestion information is obtained based on the candidate policy set and the suggested attribute values corresponding to each of the application obstacle parameters.
[0011] Optionally, the policy matching result further includes a recommendation score; after obtaining the application suggestion information, it also includes: Obtain the actual attribute value of the demand parameter corresponding to the application obstacle parameter, determine the attribute difference information between the actual attribute value and the corresponding suggested attribute value, and determine the recommendation score based on the attribute difference information; wherein, the attribute difference information includes attribute difference values, and the attribute difference value is negatively correlated with the recommendation score.
[0012] This invention clusters the logical parameters in the pre-associated logical rules of each preset policy to obtain demand parameters including general and specific parameters. It then extracts basic enterprise information to determine the actual attribute values of each demand parameter. This facilitates efficient, accurate, and comprehensive extraction of key information from multiple preset policies, avoiding the inefficiencies and omissions of crucial information that often occur when relying on manual policy reading. It also helps build a unified data foundation, ensuring that subsequent policy matching judgments follow the same reference criteria, thereby guaranteeing the accuracy and reliability of policy matching results. Furthermore, each preset policy's logical rules include at least one logical parameter and its corresponding access attribute value. The actual attribute value of the demand parameter can be compared with the corresponding access attribute value of the logical parameter. When they do not match, the demand parameter is associated as an application obstacle parameter for that preset policy, which helps to specifically identify the obstacles faced by enterprises when applying for different preset policies. After associating the application obstacle parameters corresponding to the preset policies, this invention filters candidate policies from the preset policies based on these parameters, ensuring the rationality of the candidate policy selection. When the number of candidate policies is greater than one, this invention generates a set of candidate policies that meet preset compatibility conditions, which is beneficial for providing enterprises with policy application combinations that can be submitted simultaneously. The preset compatibility conditions include that the logical rules of all candidate policies in the candidate policy set are not mutually exclusive, ensuring the feasibility of simultaneously submitting all candidate policies in the candidate policy set from the outset, and avoiding policy conflicts that may occur when enterprises apply for multiple candidate policies. Furthermore, when the application barrier parameter associated with a candidate policy in the candidate policy set is a general parameter, it indicates that adjusting the corresponding actual attribute value of the application barrier parameter will affect the matching results of the corresponding access attribute values in multiple candidate policies. In this case, a temporary attribute value for the application barrier parameter is determined, and it is judged whether the temporary attribute value matches each attribute value to be verified (i.e., the access attribute value of the logical parameter corresponding to the application barrier parameter in the candidate policy set). This is beneficial for verifying whether changes in the actual attribute value of the requirement parameter can meet the relevant requirements of all candidate policies in the candidate policy set. When the temporary attribute value matches each corresponding attribute value to be verified, it indicates that if the actual attribute value of the requirement parameter corresponding to each application barrier parameter changes to the corresponding temporary attribute value, the requirements of all candidate policies in the candidate policy set can be met simultaneously. Compared to methods that rely solely on current enterprise attribute values for single policy matching verification, this invention allows enterprises to address some application obstacles related to candidate policies. Based on this, a set of candidate policies that meet preset compatibility conditions is generated, providing a fundamental guarantee for the feasibility of enterprises simultaneously meeting the requirements of multiple candidate policies even after subsequent changes in actual attribute values.In this way, when the temporary attribute value matches each corresponding attribute value to be verified, a policy matching result is generated based on the candidate policy set. This not only provides enterprises with reasonable and reliable policy matching results, but also helps them to identify the current obstacles to their applications.
[0013] The present invention also provides a policy matching device, comprising: A clustering module is used to cluster the logical parameters in the logical rules pre-associated with each preset policy, and to determine the requirement parameters based on the clustering results; wherein, a logical rule includes at least one logical parameter and an access attribute value corresponding to the logical parameter; the requirement parameters include general parameters and specific parameters; The extraction module is used to extract information from the acquired basic enterprise information and determine the actual attribute values corresponding to each of the required parameters based on the extraction results. The association module is used to associate the demand parameter as an application obstacle parameter of the preset policy when the actual attribute value of the demand parameter does not match the access attribute value of the corresponding logical parameter in the preset policy. A filtering module is used to filter candidate policies from the preset policies based on the application obstacle parameters. When the number of candidate policies is greater than 1, a set of candidate policies that meet preset compatibility conditions is generated. The preset compatibility conditions include that the logical rules of all candidate policies in the candidate policy set are not mutually exclusive. A determination module is used to determine a temporary attribute value of the declaration barrier parameter when the declaration barrier parameter associated with the candidate policy in the candidate policy set is the general parameter; A matching module is used to generate a policy matching result based on the candidate policy set when the temporary attribute value matches each corresponding attribute value to be verified; wherein the attribute value to be verified includes the admission attribute value of the logical parameter corresponding to the declaration barrier parameter, and the admission attribute value is located in the candidate policy of the candidate policy set.
[0014] The policy matching device and the policy matching method provided by this invention have essentially the same advantages over the prior art, and will not be repeated here.
[0015] The present invention also provides an electronic device, including a memory and a processor; The memory is used to store computer programs; The processor is used to implement the policy matching method described above when executing the computer program.
[0016] The electronic device and policy matching method provided by this invention have essentially the same advantages as the prior art, and will not be elaborated further here.
[0017] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the policy matching method described above.
[0018] The computer-readable storage medium provided by this invention has essentially the same advantages as the policy matching method compared to the prior art, and will not be repeated here. Attached Figure Description
[0019] Figure 1 This is a flowchart illustrating the policy matching method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the policy matching device according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation
[0020] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the accompanying drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.
[0021] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.
[0022] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optionally" means "optional embodiments". Definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc., mentioned in this invention are used only to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.
[0023] It should be noted that the terms "a" and "a plurality of" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".
[0024] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, data stored, data displayed, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties. The collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.
[0025] like Figure 1 As shown in the figure, an embodiment of the present invention provides a policy matching method, which includes the following steps: S1: Cluster the logical parameters in the logical rules pre-associated with each preset policy, and determine the demand parameters based on the clustering results; wherein, a logical rule includes at least one logical parameter and the admission attribute value corresponding to the logical parameter; the demand parameters include general parameters and special parameters.
[0026] Specifically, in this embodiment, the "preset policy" refers to various policy documents acquired in advance, such as tax incentive policies and industry support policies. Each policy has its applicable conditions and regulations. Policy documents are usually stored in a database as unstructured text data. The text data can be read first using methods such as Optical Character Recognition (OCR) or document parsing interfaces, and then converted into a digital text stream that can be processed by a computer. The "logical rule" in this embodiment refers to the conditional rules specified in the preset policy for determining whether a company meets the policy's requirements. Each logical rule contains at least one logical parameter and the corresponding admission attribute value. The logical parameters and corresponding admission attribute values in the preset policy can be extracted in advance using a large language model to obtain the logical rules in each preset policy. For example, a logical rule could be that a company's annual turnover is greater than 10 million yuan and the number of employees is less than 500, where the company's annual turnover and number of employees are logical parameters, and greater than 10 million yuan and less than 500 employees are the corresponding admission attribute values. By automating the identification and structured extraction of massive amounts of pre-defined policies, it is beneficial to transform the originally discrete and heterogeneous policy texts into standardized logical rule data. This helps to avoid the inefficiencies and omissions that easily occur when manually reading policies. The requirement parameters referred to in this embodiment represent the parameters needed to determine whether an enterprise matches a pre-defined policy. These parameters can be determined based on the results of logical parameter clustering and include general parameters and specific parameters. General parameters represent logical parameters common to at least some pre-defined policies (such as the number of years an enterprise has been established), while specific parameters represent logical parameters unique to a specific policy (such as the technology innovation indicators for a particular industry in a specific industry support policy).
[0027] In one embodiment, various existing policies targeting enterprises can be pre-obtained as preset policies, and these preset policies can be logically parsed (e.g., using a large language model) to obtain logical rules consisting of logical parameters and corresponding access attribute values. Based on this, the logical parameters can be clustered, and the required parameters, including general and specific parameters, can be determined based on the clustering results.
[0028] Optionally, before clustering the logical parameters in the logical rules pre-associated with each of the acquired preset policies, the process further includes: filtering out initial policies from the initial policy pool that match the acquired enterprise type and current time, thus obtaining each preset policy. This facilitates the initial cleaning of the initial policy pool using enterprise type and time characteristics, eliminating initial policies that are clearly inconsistent with the enterprise type and time characteristics, and improving processing efficiency.
[0029] S2: Extract information from the acquired basic enterprise information and determine the actual attribute values corresponding to each requirement parameter based on the extraction results.
[0030] Specifically, in this embodiment, "basic enterprise information" refers to various basic data about the enterprise, such as enterprise registration information, operating data, and personnel information. Basic enterprise information can originate from heterogeneous data from multiple sources, including financial statement images and text files uploaded by the enterprise. Named entity recognition in natural language processing can be used to parse unstructured text, and regular expression matching algorithms can be combined to extract key values from structured databases, unifying data from different sources into a standardized data format. Information extraction in this embodiment refers to the process of extracting data related to requirement parameters from basic enterprise information. Actual attribute values in this embodiment refer to the actual values of each requirement parameter determined based on the results of basic enterprise information extraction. These actual attribute values can be extracted by semantically parsing the basic enterprise information using entity matching, regular expression methods, or by directly utilizing a large language model.
[0031] S3: When the actual attribute value of the demand parameter does not match the access attribute value of the corresponding logical parameter in the preset policy, the demand parameter is associated with the application obstacle parameter of the preset policy.
[0032] Specifically, in this embodiment, the "application obstacle parameter" refers to a parameter that may become an obstacle for an enterprise to apply for the policy. After obtaining the actual attribute values corresponding to each requirement parameter, a unified benchmark information for assessing whether each preset policy matches the enterprise's basic situation (i.e., the requirement parameters and their corresponding actual attribute values) has been determined. At this point, the admission attribute values of each logical parameter in the preset policy can be compared one by one with the actual attribute values of the corresponding requirement parameters to determine whether they match (e.g., a large language model can be used to set up an intelligent agent for logical judgment, specifically for judging whether the two match). When the actual attribute value of a requirement parameter does not match the admission attribute value of the corresponding logical parameter in the preset policy, the requirement parameter is associated as an application obstacle parameter of the preset policy. For example, a logical parameter of a preset policy includes the enterprise's annual turnover, whose corresponding admission attribute value is greater than 10 million yuan. The requirement parameter corresponding to this logical parameter is the enterprise's annual turnover, whose actual attribute value is 3 million yuan. Then, the requirement parameter of the enterprise's annual turnover can be associated as an application obstacle parameter of the policy.
[0033] S4: Based on the application obstacle parameter, select candidate policies from the preset policies. When the number of candidate policies is greater than 1, generate a set of candidate policies that meet the preset compatibility conditions. The preset compatibility conditions include that the logical rules of all candidate policies in the candidate policy set are not mutually exclusive.
[0034] Specifically, in this embodiment, the candidate policy refers to the policy that an enterprise may meet, selected from preset policies based on the application obstacle parameter. The candidate policy set in this embodiment refers to the set of candidate policies that meet preset compatibility conditions. These preset compatibility conditions include that the logical rules of all candidate policies in the candidate policy set are not mutually exclusive, meaning that the logical rules of different candidate policies in the candidate policy set are not contradictory.
[0035] In one embodiment, candidate policies can be selected from preset policies based on declaration obstacle parameters. For example, preset policies with fewer than three declaration obstacle parameters can be used as candidate policies, indicating that the company's current situation basically meets the requirements of the preset policies. When the number of candidate policies is greater than one, it is possible to check whether all logical rules in each candidate policy are mutually exclusive, and combine multiple candidate policies with non-mutually exclusive logical rules into a candidate policy set. For example, each logical rule in the candidate policies can be traversed, and the logical rules of different candidate policies can be compared one by one to identify whether there are semantically opposite or conditionally exclusive rule items. When mutually exclusive logical rules are detected, the corresponding conflicting candidate policies can be removed from the matching candidate policy list, and only logically compatible policy combinations can be retained, thereby generating a candidate policy set that meets the preset compatibility conditions. This embodiment takes the selection of three candidate policies as an example (for ease of understanding and description, the three candidate policies are referred to as policy A, policy B, and policy C, respectively). The logical rules corresponding to the three candidate policies can be obtained respectively, and mutual exclusion analysis can be performed on the logical rules in every two different candidate policies. Assuming that only policies A and B have mutually exclusive logical rules, we can obtain a first set of candidate policies including policies A and C, and a second set of candidate policies including policies B and C.
[0036] S5: When the declaration barrier parameter associated with the candidate policy in the candidate policy set is a general parameter, determine the temporary attribute value of the declaration barrier parameter.
[0037] In one embodiment, when the application barrier parameter is a general parameter, a temporary attribute value can be reasonably determined based on the company's actual situation (such as actual attribute values) and policy requirements (i.e., the access attribute value of the corresponding logical parameter). For example, assuming the application barrier parameter is the number of employees in the company, the actual attribute value of its corresponding demand parameter is 498 people, and the access attribute value of its corresponding logical parameter is greater than or equal to 500 people, then the attribute value with the smallest difference between the access attribute value and the actual attribute value (i.e., 500 people) can be used as the temporary attribute value of the application barrier parameter.
[0038] S6: When the temporary attribute value matches each corresponding attribute value to be verified, a policy matching result is generated based on the candidate policy set; wherein, the attribute value to be verified includes the admission attribute value of the logical parameter corresponding to the declaration barrier parameter, and the admission attribute value is located in the candidate policy of the candidate policy set.
[0039] Specifically, in this embodiment, the attribute value to be verified refers to the admission attribute value of the logical parameter corresponding to the declaration barrier parameter, selected from each candidate policy in the candidate policy set. After setting the temporary attribute value of the declaration barrier parameter, it is necessary to determine whether the temporary attribute value matches each corresponding attribute value to be verified.
[0040] In one embodiment, after determining the temporary attribute value of the application barrier parameter, for each temporary attribute value, it can be determined whether the temporary attribute value matches each corresponding attribute value to be verified (e.g., whether the temporary attribute value is within the range of the attribute value to be verified). If yes, it means that after adjusting the actual attribute value of the requirement parameter corresponding to the application barrier parameter (i.e., the current actual value reflecting the enterprise's situation) to the temporary attribute value (i.e., the target value that the enterprise needs to achieve to meet the application conditions), each candidate policy in the candidate policy set can be applied for simultaneously. At this time, a policy matching result can be generated based on the candidate policy set (e.g., it can include the candidate policy set and the temporary attribute value corresponding to the application barrier parameter). If no, it means that the currently adjusted temporary attribute value cannot meet the requirements of the relevant candidate policies in the candidate policy set (i.e., including the candidate policies of the logical parameters corresponding to the application barrier parameter). At this time, it is possible to return to step S5 to redetermine the temporary attribute value and re-perform the matching verification. This helps to avoid unreliable policy matching results caused by occasional errors such as incorrect matching verification results or incorrect candidate policy set selection (e.g., the large language model mistakenly determines two mutually exclusive logical rules as compatible logical rules).
[0041] In this embodiment, by clustering the logical parameters in the pre-associated logical rules of each preset policy, demand parameters including general and specific parameters are obtained. Enterprise basic information is extracted to determine the actual attribute values of each demand parameter. This facilitates efficient, accurate, and comprehensive extraction of key information from multiple preset policies, avoiding the inefficiencies and omissions of key information that often occur when relying on manual policy reading. It also helps build a unified data foundation, ensuring that subsequent policy matching judgments follow the same reference criteria, thereby guaranteeing the accuracy and reliability of policy matching results. Furthermore, each preset policy's logical rules include at least one logical parameter and its corresponding access attribute value. The actual attribute value of the demand parameter can be compared with the corresponding access attribute value of the logical parameter. When they do not match, the demand parameter is associated as an application obstacle parameter for that preset policy. This achieves precise location and association of policy matching obstacles, enabling targeted identification of the obstacles faced by enterprises when applying for different preset policies. This provides a clear targeting basis for subsequent candidate policy screening and temporary parameter value matching verification. After associating the application barrier parameters corresponding to the preset policies, this embodiment selects candidate policies from the preset policies based on the application barrier parameters to ensure the rationality of the candidate policy selection. When the number of candidate policies is greater than 1, this embodiment generates a set of candidate policies that meet the preset compatibility conditions, which is beneficial for providing enterprises with policy application combinations that can be submitted simultaneously. Among them, the preset compatibility conditions include that the logical rules of all candidate policies in the candidate policy set are not mutually exclusive, which ensures the feasibility of submitting all candidate policies in the candidate policy set at the root and avoids policy conflict problems that may occur when enterprises apply for multiple candidate policies. Furthermore, when the application barrier parameter associated with the candidate policy in the candidate policy set is a general parameter, it means that the adjustment of the corresponding actual attribute value of the application barrier parameter will affect the matching result of the corresponding access attribute value in multiple candidate policies. At this time, a temporary attribute value of the application barrier parameter is determined, and it is judged whether the temporary attribute value matches each attribute value to be verified (i.e., the access attribute value of the logical parameter corresponding to the application barrier parameter in the candidate policy set). This is beneficial for verifying whether the relevant requirements of all candidate policies in the candidate policy set can be met after the actual attribute value of the requirement parameter changes. Unlike the approach of verifying policy matching based solely on the current information provided by the enterprise, this embodiment determines the temporary attribute value of the application obstacle parameter. This allows for the pre-simulation of scenarios where the enterprise adjusts the relevant parameters to better meet the policy application requirements and then performs policy matching again. This avoids the situation where rigid matching based solely on the enterprise's current static parameters fails to accommodate the dynamic development of enterprise information, thus causing the enterprise to miss out on potential future policy candidates.When the temporary attribute value matches each corresponding attribute value to be verified, it indicates that if the actual attribute value of the requirement parameter corresponding to each declaration obstacle parameter changes to the corresponding temporary attribute value, the requirements of all candidate policies in the candidate policy set can be met simultaneously. Compared to methods that rely solely on the current actual attribute value of the enterprise for single policy matching verification, this embodiment allows enterprises to currently have some declaration obstacle parameters for candidate policies. Based on this, a candidate policy set that meets preset compatibility conditions is generated, which provides a basic guarantee for the feasibility of enterprises simultaneously meeting the requirements of multiple candidate policies after subsequent changes in actual attribute values. Thus, when the temporary attribute value matches each corresponding attribute value to be verified, policy matching results are generated based on the candidate policy set. This not only provides enterprises with reasonable and reliable policy matching results but also helps them to specifically identify current declaration obstacles.
[0042] It should be understood that when enterprises need to apply for policies and undergo policy matching, the first step is to comprehensively collect all current enterprise information. To ensure the authenticity and reliability of this information, significant human and material resources are often required. The policy matching results output at this time are usually used as the basis for future application work, affecting the enterprise's work arrangements throughout the entire application cycle (such as collecting relevant materials and preparing application documents). However, policy matching methods typically only output a one-time matching result, making it difficult to dynamically monitor policies that are excluded due to the actual attribute values of the demand parameters not meeting the corresponding access attributes of the logical parameters. Even if some enterprise information (such as the number of employees, qualifications, etc.) changes during the application cycle, enterprises usually do not collect information again for policy matching, which can easily lead to enterprises missing out on potentially eligible candidate policies. This embodiment, on the one hand, allows enterprises to have some application obstacles for candidate policies at present, and is compatible with the possibility that some data in the enterprise's basic information may be dynamically updated in the future (such as the number of patents, the number of employees, etc.). This avoids relying solely on the current enterprise information as the only matching basis and only outputting policy matching results under the current information, which could lead to missing out on future eligible policies. On the other hand, in this embodiment, when the declaration obstacle parameter is a general parameter, determining its corresponding temporary attribute value is beneficial for providing enterprises with optimization directions for policy declaration and future matching possibility analysis. When the temporary attribute value matches each attribute value to be verified, it can also provide enterprises with feasible improvement directions to meet the declaration requirements of the candidate policy set. It has strong practicality and guidance, and fully breaks through the technical bottleneck of existing policy matching methods that can only achieve static matching and rigid matching at present.
[0043] Optionally, the demand parameters are determined based on the clustering results, including: Determine the semantic vector corresponding to each logical parameter, and cluster logical parameters with semantic similarity greater than a preset similarity threshold into a parameter cluster based on the semantic vector; When the number of logical parameters in a parameter cluster exceeds the preset number, all logical parameters in the parameter cluster are marked as the same general parameter. After traversing all parameter clusters, the remaining unmarked logical parameters are marked as dedicated parameters.
[0044] Specifically, in this embodiment, the semantic vector refers to the representation of logical parameters in a vector space through natural language processing. The dimension and value of the vector reflect the semantic features of the parameters. The preset similarity threshold in this embodiment refers to a pre-set boundary value used to judge the semantic similarity between two logical parameters, which can be determined in advance (e.g., 95%). The parameter cluster in this embodiment refers to a set formed by clustering logical parameters whose semantic similarity is greater than the preset similarity threshold.
[0045] In one embodiment, a word vector model from natural language processing can be used to generate a semantic vector corresponding to each logical parameter. Based on this, the similarity between the semantic vectors of any two logical parameters (e.g., cosine similarity, Euclidean distance, etc.) can be determined, and logical parameters with a similarity greater than a preset similarity threshold are grouped into a parameter cluster. For each parameter cluster, the number of logical parameters within it can be counted. If the number is greater than a preset number (e.g., 2, meaning logical parameters shared by at least 2 preset policies are marked as general parameters), it indicates that these logical parameters are general parameters that multiple preset policies may involve, and each logical parameter in that parameter cluster can be marked as the same general parameter. For example, if a parameter cluster contains "number of employees," "number of staff," and "total number of employees," and the number is 3, which is greater than the preset number of 2, then all three logical parameters can be marked as the general parameter "number of employees." After traversing all parameter clusters and marking all general parameters, the remaining unmarked logical parameters can be considered as dedicated parameters unique to a specific preset policy, and these unmarked logical parameters can be marked as their respective dedicated parameters. For example, after traversing all parameter clusters and marking all general parameters, if the logical parameter in a certain independent parameter cluster is the R&D investment ratio (unmarked), it can be marked as a special parameter - R&D investment ratio.
[0046] In this embodiment, the same logical parameter (such as revenue within a year) may correspond to different statistical calibers (such as annual revenue or current year revenue) in different preset policies. This embodiment identifies general and specific parameters by clustering the logical parameters in all preset policies, which helps to provide a unified data foundation for subsequent matching judgments and ensures the consistency of the data source. It avoids the situation that the same indicator may correspond to different actual attribute values when the actual attribute values are extracted independently for each preset policy, thus ensuring the reliability of policy matching.
[0047] Optionally, the extraction results include the extracted attribute values corresponding to each requirement parameter and / or extraction failure prompts; based on the extraction results, the actual attribute values corresponding to each requirement parameter are determined, including: When the extraction result is an extracted attribute value, the corresponding actual attribute value is determined based on the extracted attribute value; When the extraction result is an extraction failure message, supplementary prompt information is generated based on the requirement parameters corresponding to the extraction failure message and sent to the preset interactive device; In response to the supplementary attribute value sent by the preset interactive device, the corresponding actual attribute value is determined based on the supplementary attribute value.
[0048] Specifically, the extraction result referred to in this embodiment refers to the information obtained after extracting information from the enterprise's basic information, which may include the extraction attribute values corresponding to each requirement parameter and / or extraction failure prompts. The extraction attribute value referred to in this embodiment refers to the specific numerical value or description successfully extracted from the enterprise's basic information that corresponds to the requirement parameter. For example, if the value of the enterprise's annual turnover extracted from the financial statements in the enterprise's basic information is 15 million yuan, then 15 million yuan is the extraction attribute value of the requirement parameter "enterprise annual turnover". The supplementary prompt information referred to in this embodiment refers to the prompt content generated based on the requirement parameter corresponding to the extraction failure prompt information, used to guide relevant personnel to supplement the required information. For example, assuming the extraction result corresponding to the requirement information of R&D investment amount is an extraction failure prompt information, the prompt information could be "please supplement the enterprise's R&D investment amount for this year". The preset interactive device referred to in this embodiment refers to a device or platform used for information interaction with relevant personnel, who can use this interactive device to upload enterprise basic information, receive supplementary prompt information, send supplementary attribute values, and view policy matching results, etc. In this embodiment, the supplementary attribute value refers to the attribute value of the required parameters input by relevant personnel through a preset interactive device based on supplementary prompts.
[0049] Optionally, in this embodiment, all the required parameters corresponding to the extraction failure prompt information can be uniformly integrated to obtain a table of information to be supplemented, and sent to a preset interactive device so that relevant personnel can uniformly supplement the missing information and improve the interaction efficiency.
[0050] In this embodiment, when the extraction result is an extracted attribute value, the extracted attribute value can be directly used as the corresponding actual attribute value. When the extraction result is an extraction failure message, targeted supplementary prompts can be generated based on the corresponding requirement parameters and sent to the preset interactive device. In response to relevant personnel viewing the supplementary prompts and inputting and sending supplementary attribute values in the preset interactive device, the received supplementary attribute values can be used as the actual attribute values corresponding to the requirement parameters. This helps ensure the completeness and reliability of the actual attribute values corresponding to each requirement parameter, avoiding unreliable policy matching results due to missing partial actual attribute values.
[0051] Optionally, candidate policies can be selected from preset policies based on application barrier parameters, including: Determine the weight coefficient corresponding to each application obstacle parameter, and determine the matching coefficient of the preset policy based on the weight coefficient corresponding to all application obstacle parameters associated with the preset policy; Preset policies with matching coefficients greater than a preset matching threshold are selected as candidate policies; among them, the weight coefficient is negatively correlated with the matching coefficient.
[0052] Specifically, in this embodiment, the "application barrier parameter" refers to the parameter associated with the preset policy when the actual attribute value of the demand parameter does not match the access attribute value of the corresponding logical parameter in the preset policy. The weighting coefficient in this embodiment is used to measure the impact of the application barrier parameter on the degree of policy matching. The weighting coefficient for each application barrier parameter can be determined according to preset rules. For example, different parameter types can be pre-defined, and corresponding weighting coefficients can be set for different types of parameters. Assuming the application barrier parameter includes the number of personnel, semantic analysis can be used to determine that it belongs to a pre-defined enterprise structure class, and its weighting coefficient can be 0.05. Therefore, 0.05 can be used as the weighting coefficient corresponding to this application barrier parameter.
[0053] In this embodiment, for each preset policy, all associated application obstacle parameters can be obtained, and a corresponding weight coefficient can be assigned to each application obstacle parameter according to preset rules. Based on this, the matching coefficient of the preset policy can be determined based on the weight coefficients corresponding to all application obstacle parameters associated with the preset policy. For example, the weight coefficients corresponding to all application obstacle parameters associated with the preset policy can be summed, and the negative of the summation result can be used as the matching coefficient (i.e., the weight coefficient and the matching coefficient are negatively correlated). When the matching coefficient is greater than a preset matching threshold (e.g., greater than -0.2), the preset policy can be considered a candidate policy. This embodiment, by determining the preset weight coefficients corresponding to the application obstacle parameters and determining the matching coefficient of the preset policy based on this, helps to quantify the degree of matching between the preset policy and the actual situation of the enterprise, accurately reflecting the degree of adaptation between the enterprise's current situation and each preset policy, thereby ensuring the rationality and reliability of the candidate policy selection.
[0054] Optionally, determine temporary attribute values for the reporting obstacle parameters, including: Determine the overlapping range of attribute values corresponding to each attribute value to be verified, and select the attribute value with the smallest difference from the actual attribute value corresponding to the declared obstacle parameter within the overlapping range to obtain the temporary attribute value.
[0055] Specifically, the overlapping range of attribute values referred to in this embodiment indicates the overlapping portion between the attribute values to be verified. For example, the candidate policy set includes policy A requiring an enterprise's annual turnover to be greater than 9 million yuan, and policy B requiring an enterprise's annual turnover to be greater than 8.5 million yuan. For the attribute values to be verified regarding the enterprise's annual turnover in policies A and B, the overlapping range is greater than 9 million yuan.
[0056] In this embodiment, after determining the overlapping range of attribute values corresponding to each attribute value to be verified for the application obstacle parameter, a temporary attribute value is obtained by selecting the attribute value with the smallest difference from the actual attribute value corresponding to the application obstacle parameter within the overlapping range. For example, when the actual attribute value of the demand parameter corresponding to the application obstacle parameter is less than the minimum value of the overlapping range, the minimum value of the overlapping range is used as the temporary attribute value. When the actual attribute value of the demand parameter corresponding to the application obstacle parameter is greater than the maximum value of the overlapping range, the maximum value of the overlapping range is used as the temporary attribute value. In this way, while satisfying the admission attribute values of the logical parameters corresponding to the application obstacle parameters in each candidate policy, it can also be as close as possible to the actual situation of the enterprise. This ensures that the temporary attribute value not only meets the common requirements of the candidate policies but also minimizes the gap with the current situation of the enterprise, increasing the likelihood that the enterprise meets the requirements of the candidate policies.
[0057] Optionally, the policy matching results include application suggestion information; the policy matching results generated based on the candidate policy set include: When the obstacle parameter is a general parameter, the suggested attribute value of the obstacle parameter is obtained based on the temporary attribute value. When the declared obstacle parameter is a special parameter, the suggested attribute value of the declared obstacle parameter is determined based on the admission attribute value of the logical parameter corresponding to the declared obstacle parameter; Based on the candidate policy set and the suggested attribute values corresponding to each application obstacle parameter, application suggestion information is obtained.
[0058] Specifically, in this embodiment, the policy matching result includes application suggestion information, which represents the application suggestions obtained based on the enterprise's basic information and the matching of preset policies, tailored to the enterprise's current situation. This can include a candidate policy set consisting of multiple candidate policies that can be applied for simultaneously, and suggested attribute values corresponding to the application obstacle parameters associated with the candidate policies within the candidate policy set. In this embodiment, the suggested attribute values refer to recommended values for the application obstacle parameters provided by the enterprise's application policy.
[0059] In this embodiment, when the application barrier parameter is a general parameter, since a temporary attribute value matching all the attribute values to be verified has already been determined, this temporary attribute value can be directly used as the suggested attribute value for the application barrier parameter. When the application barrier parameter is a specific parameter, since it is unique to a particular candidate policy, its suggested attribute value can be directly determined based on the admission attribute value of the logical parameter corresponding to the application barrier parameter, which is beneficial for quickly meeting the application requirements of the candidate policy. Based on this, application suggestion information can be obtained according to the candidate policy set and the suggested attribute values corresponding to each application barrier parameter, thus providing targeted policy application guidance for enterprises.
[0060] Optionally, the policy matching results also include a recommendation score; after receiving the application recommendation information, the following steps are also included: Obtain the actual attribute values of the required parameters corresponding to the application obstacle parameters, determine the attribute difference information between the actual attribute values and the corresponding suggested attribute values, and determine the recommended score based on the attribute difference information; wherein, the attribute difference information includes attribute difference values, and the attribute difference value is negatively correlated with the recommended score.
[0061] Specifically, the attribute difference information referred to in this embodiment represents the difference between the actual attribute value of the requirement parameter corresponding to the application barrier parameter and the admission attribute value of the corresponding logical parameter. This can include attribute differences, type differences, etc. For example, assuming the application barrier parameter is the number of years the company has been established, its actual attribute value is 4 years, while the suggested attribute value is 5 years, then the attribute difference is 1 year. As another example, assuming the application barrier parameter is the industry category to which the company belongs, the actual attribute value is manufacturing, and the suggested attribute value is high-tech industry, the attribute difference information can be a type difference.
[0062] In one embodiment, after determining the attribute difference information between the suggested attribute values and actual attribute values corresponding to the application obstacle parameters, a recommended score for the candidate policy set can be determined based on the attribute difference information. The attribute difference information includes attribute differences, which are negatively correlated with the recommended score. For example, a weight coefficient corresponding to each application obstacle parameter can be determined (the determination method is as described above and will not be repeated here), and the corresponding attribute differences can be weighted based on the weight coefficient to obtain a weighted value. Based on this, the weighted values of all application obstacle parameters corresponding to the candidate policy set can be summed, and the recommended score can be determined according to the gradient range of the final summed value (e.g., pre-setting different gradient ranges and preset recommended scores corresponding to each gradient range).
[0063] In this embodiment, the types and numbers of application obstacle parameters are usually different for different candidate policy sets. This embodiment determines the attribute difference information between the actual attribute value and the corresponding suggested attribute value, and determines the recommendation score based on the attribute difference information. This helps to accurately quantify the matching degree between the current actual situation of the enterprise (i.e., the basic information of the enterprise) and different candidate policy sets, and helps to provide a reliable reference for enterprises to make reasonable application decisions.
[0064] like Figure 2 As shown, an embodiment of the present invention provides a policy matching device 200, comprising: Clustering module 210 is used to cluster the logical parameters in the logical rules pre-associated with each preset policy, and determine the demand parameters based on the clustering results; wherein, a logical rule includes at least one logical parameter and an admission attribute value corresponding to the logical parameter; the demand parameters include general parameters and special parameters; Extraction module 220 is used to extract information from the acquired basic enterprise information and determine the actual attribute values corresponding to each of the required parameters based on the extraction results. The association module 230 is used to associate the demand parameter as an application obstacle parameter of the preset policy when the actual attribute value of the demand parameter does not match the access attribute value of the logical parameter corresponding to the preset policy. The filtering module 240 is used to filter candidate policies from the preset policies based on the application obstacle parameters. When the number of candidate policies is greater than 1, a set of candidate policies that meet preset compatibility conditions is generated. The preset compatibility conditions include that the logical rules of all candidate policies in the candidate policy set are not mutually exclusive. The determination module 250 is used to determine a temporary attribute value of the declaration barrier parameter when the declaration barrier parameter associated with the candidate policy in the candidate policy set is the general parameter; The matching module 260 is used to generate a policy matching result based on the candidate policy set when the temporary attribute value matches each corresponding attribute value to be verified; wherein the attribute value to be verified includes the admission attribute value of the logical parameter corresponding to the declaration barrier parameter, and the admission attribute value is located in the candidate policy of the candidate policy set.
[0065] The policy matching device and policy matching method provided in this embodiment can produce basically the same technical effects, and will not be described again here.
[0066] like Figure 3 As shown, an electronic device 300 provided in this embodiment of the invention includes a memory 310 and a processor 320; the memory 310 is used to store a computer program; the processor 320 is used to implement the policy matching method as described above when the computer program is executed.
[0067] Alternatively, an electronic device 300 includes a memory 310 and a processor 320 coupled to the memory 310; the memory 310 is configured to store a computer program; and the processor 320 is configured to perform the following operations when the computer program is executed: The logical parameters in the pre-associated logical rules of each preset policy are clustered, and the demand parameters are determined based on the clustering results; wherein, each logical rule includes at least one logical parameter and the access attribute value corresponding to the logical parameter; the demand parameters include general parameters and special parameters; Information is extracted from the acquired basic enterprise information, and the actual attribute values corresponding to each of the aforementioned requirement parameters are determined based on the extraction results. When the actual attribute value of the demand parameter does not match the access attribute value of the corresponding logical parameter in the preset policy, the demand parameter is associated with the application obstacle parameter of the preset policy. Based on the application obstacle parameters, candidate policies are selected from the preset policies. When the number of candidate policies is greater than 1, a set of candidate policies that meet preset compatibility conditions is generated. The preset compatibility conditions include that the logical rules of all candidate policies in the candidate policy set are not mutually exclusive. When the application barrier parameter associated with the candidate policy in the candidate policy set is the general parameter, a temporary attribute value for the application barrier parameter is determined; When the temporary attribute value matches each corresponding attribute value to be verified, a policy matching result is generated based on the candidate policy set; wherein, the attribute value to be verified includes the admission attribute value of the logical parameter corresponding to the declaration barrier parameter, and the admission attribute value is located in the candidate policy of the candidate policy set.
[0068] The electronic devices and policy matching methods provided in this embodiment can produce essentially the same technical effects, which will not be repeated here.
[0069] This invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the policy matching method described above.
[0070] Alternatively, a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the following operations: The logical parameters in the pre-associated logical rules of each preset policy are clustered, and the demand parameters are determined based on the clustering results; wherein, each logical rule includes at least one logical parameter and the access attribute value corresponding to the logical parameter; the demand parameters include general parameters and special parameters; Information is extracted from the acquired basic enterprise information, and the actual attribute values corresponding to each of the aforementioned requirement parameters are determined based on the extraction results. When the actual attribute value of the demand parameter does not match the access attribute value of the corresponding logical parameter in the preset policy, the demand parameter is associated with the application obstacle parameter of the preset policy. Based on the application obstacle parameters, candidate policies are selected from the preset policies. When the number of candidate policies is greater than 1, a set of candidate policies that meet preset compatibility conditions is generated. The preset compatibility conditions include that the logical rules of all candidate policies in the candidate policy set are not mutually exclusive. When the application barrier parameter associated with the candidate policy in the candidate policy set is the general parameter, a temporary attribute value for the application barrier parameter is determined; When the temporary attribute value matches each corresponding attribute value to be verified, a policy matching result is generated based on the candidate policy set; wherein, the attribute value to be verified includes the admission attribute value of the logical parameter corresponding to the declaration barrier parameter, and the admission attribute value is located in the candidate policy of the candidate policy set.
[0071] The computer-readable storage medium and policy matching method provided in this embodiment can produce essentially the same technical effects, and will not be described again here.
[0072] The present invention will now be described an electronic device 300 that can serve as a server or client of the present invention, which is an example of a hardware device that can be applied to various aspects of the present invention. Electronic device 300 is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 300 can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.
[0073] Electronic device 300 includes a computing unit that can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) or a computer program loaded from a storage unit into random access memory (RAM). The RAM may also store various programs and data required for device operation. The computing unit, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.
[0074] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc. In this application, the units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention according to actual needs. Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units can be implemented in hardware or as software functional units.
[0075] While the present invention has been disclosed above, its scope of protection is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention, and all such changes and modifications will fall within the scope of protection of the present invention.
Claims
1. A policy matching method, characterized in that, include: The logical parameters in the pre-associated logical rules of each preset policy are clustered, and the demand parameters are determined based on the clustering results; wherein, each logical rule includes at least one logical parameter and the access attribute value corresponding to the logical parameter; the demand parameters include general parameters and special parameters; Information is extracted from the acquired basic enterprise information, and the actual attribute values corresponding to each of the aforementioned requirement parameters are determined based on the extraction results. When the actual attribute value of the demand parameter does not match the access attribute value of the corresponding logical parameter in the preset policy, the demand parameter is associated with the application obstacle parameter of the preset policy. Candidate policies are selected from the preset policies based on the application obstacle parameters. When the number of candidate policies is greater than 1, a set of candidate policies that meet preset compatibility conditions is generated. The preset compatibility conditions include that the logical rules of all candidate policies in the candidate policy set are not mutually exclusive. The process of selecting candidate policies from the preset policies based on the application obstacle parameters includes: obtaining the weight coefficient corresponding to each application obstacle parameter, and determining the matching coefficient of the preset policy based on the weight coefficients corresponding to all application obstacle parameters associated with the preset policy; selecting preset policies whose matching coefficients are greater than a preset matching threshold as candidate policies. The weight coefficients and the matching coefficients are negatively correlated. When the application barrier parameter associated with the candidate policy in the candidate policy set is the general parameter, a temporary attribute value for the application barrier parameter is determined; When the temporary attribute value matches each corresponding attribute value to be verified, a policy matching result is generated based on the candidate policy set; wherein, the attribute value to be verified includes the admission attribute value of the logical parameter corresponding to the declaration barrier parameter, and the admission attribute value is located in the candidate policy of the candidate policy set.
2. The policy matching method according to claim 1, characterized in that, The determination of demand parameters based on clustering results includes: Determine the semantic vector corresponding to each of the logical parameters, and cluster the logical parameters with semantic similarity greater than a preset similarity threshold into a parameter cluster based on the semantic vector; When the number of logical parameters in the parameter cluster is greater than a preset number, each logical parameter in the parameter cluster is marked as the same general parameter; After traversing all the parameter clusters, the remaining unmarked logical parameters are marked as the respective dedicated parameters.
3. The policy matching method according to claim 1, characterized in that, The extraction results include the extraction attribute values corresponding to each of the required parameters and / or extraction failure prompts; The process of determining the actual attribute values corresponding to each of the required parameters based on the extraction results includes: When the extraction result is the extracted attribute value, the corresponding actual attribute value is determined based on the extracted attribute value; When the extraction result is the extraction failure prompt message, supplementary prompt message is generated based on the requirement parameters corresponding to the extraction failure prompt message and sent to the preset interactive device; In response to the supplementary attribute value sent by the preset interactive device, the corresponding actual attribute value is determined based on the supplementary attribute value.
4. The policy matching method according to claim 1, characterized in that, The determination of the temporary attribute value of the reporting obstacle parameter includes: Determine the overlapping range of attribute values corresponding to each attribute value to be verified, and select the attribute value with the smallest difference from the actual attribute value corresponding to the declared obstacle parameter within the overlapping range to obtain the temporary attribute value.
5. The policy matching method according to claim 1, characterized in that, The policy matching result includes application suggestion information; the generation of policy matching result based on the candidate policy set includes: When the declared obstacle parameter is the general parameter, the suggested attribute value of the declared obstacle parameter is obtained based on the temporary attribute value; When the application obstacle parameter is the dedicated parameter, the suggested attribute value of the application obstacle parameter is determined according to the admission attribute value of the logical parameter corresponding to the application obstacle parameter; The application suggestion information is obtained based on the candidate policy set and the suggested attribute values corresponding to each of the application obstacle parameters.
6. The policy matching method according to claim 5, characterized in that, The policy matching result also includes a recommendation score; after obtaining the application suggestion information, it also includes: Obtain the actual attribute value of the demand parameter corresponding to the application obstacle parameter, determine the attribute difference information between the actual attribute value and the corresponding suggested attribute value, and determine the recommendation score based on the attribute difference information; wherein, the attribute difference information includes attribute difference values, and the attribute difference value is negatively correlated with the recommendation score.
7. A policy matching device, characterized in that, include: A clustering module is used to cluster the logical parameters in the logical rules pre-associated with each preset policy, and to determine the requirement parameters based on the clustering results; wherein, a logical rule includes at least one logical parameter and an access attribute value corresponding to the logical parameter; the requirement parameters include general parameters and specific parameters; The extraction module is used to extract information from the acquired basic enterprise information and determine the actual attribute values corresponding to each of the required parameters based on the extraction results. The association module is used to associate the demand parameter as an application obstacle parameter of the preset policy when the actual attribute value of the demand parameter does not match the access attribute value of the corresponding logical parameter in the preset policy. A filtering module is used to filter candidate policies from the preset policies based on the application obstacle parameters. When the number of candidate policies is greater than 1, a set of candidate policies that meet preset compatibility conditions is generated. The preset compatibility conditions include that the logical rules of all candidate policies in the candidate policy set are not mutually exclusive. The step of filtering candidate policies from the preset policies based on the application obstacle parameters includes: obtaining the weight coefficient corresponding to each application obstacle parameter, and determining the matching coefficient of the preset policy based on the weight coefficients corresponding to all application obstacle parameters associated with the preset policy; selecting preset policies whose matching coefficients are greater than a preset matching threshold as candidate policies. The weight coefficients and the matching coefficients are negatively correlated. A determination module is used to determine a temporary attribute value of the declaration barrier parameter when the declaration barrier parameter associated with the candidate policy in the candidate policy set is the general parameter; A matching module is used to generate a policy matching result based on the candidate policy set when the temporary attribute value matches each corresponding attribute value to be verified; wherein the attribute value to be verified includes the admission attribute value of the logical parameter corresponding to the declaration barrier parameter, and the admission attribute value is located in the candidate policy of the candidate policy set.
8. An electronic device, characterized in that, Including memory and processor; The memory is used to store computer programs; The processor is configured to implement the policy matching method as described in any one of claims 1 to 6 when executing the computer program.
9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, implements the policy matching method as described in any one of claims 1 to 6.