Policy information automatic recommendation method and device, electronic equipment and storage medium

Abstract

The application discloses a policy information automatic recommendation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring policy data and enterprise data; performing word segmentation processing on the policy data and the enterprise data respectively, and determining policy label metadata and enterprise label metadata; establishing a standard word library according to the policy label metadata and the enterprise label metadata, wherein at least one enterprise label metadata corresponds to the policy label metadata; acquiring new policy label metadata of new policy information, and recommending the new policy information to a target enterprise matched with the new policy label metadata according to the standard word library. Through processing of the existing policy data and the enterprise data, the standard word library is established, and then the new policy label metadata is automatically matched based on the standard word library, so that the efficiency of recommending the new policy to the target enterprise is effectively improved.

Description

Technical Field

[0001] This invention relates to the field of data analysis technology, and in particular to a method, apparatus, electronic device, and storage medium for automated policy information recommendation. Background Technology

[0002] With the deepening of the national reform of streamlining administration, delegating power, and improving services, the service concept in the field of government services has begun to shift from "enterprises seeking policies" to "policies seeking enterprises." In other words, in order to provide more precise policy support and better services to enterprises, higher policy management requirements have been placed on government departments.

[0003] However, existing policies still rely on manual data entry and traditional time-series display methods. These methods suffer from issues such as manual intervention and passive service, failing to meet current government management principles. In other words, the current policy management model cannot quickly and accurately recommend optimal policies to businesses, thus failing to adequately meet the needs of the nation.

[0004] Therefore, in the existing technology, government management departments face the problem of low efficiency when recommending policies to enterprises. Summary of the Invention

[0005] In view of this, it is necessary to provide a method, device, electronic device and storage medium for automated policy information recommendation, in order to solve the problem of low recommendation efficiency in the existing technology when government management departments recommend policies to enterprises.

[0006] To address the above problems, this invention provides an automated policy information recommendation method, comprising:

[0007] Obtain policy data and enterprise data;

[0008] The policy data and enterprise data are segmented into words to determine the policy tag metadata and the enterprise tag metadata.

[0009] A standard thesaurus is established based on policy tag metadata and enterprise tag metadata, wherein at least one enterprise tag metadata corresponds to policy tag metadata;

[0010] Obtain new policy tag metadata for new policy information, and recommend the new policy information to target enterprises that match the new policy tag metadata based on a standard thesaurus.

[0011] Furthermore, based on policy tag metadata and enterprise tag metadata, a standard thesaurus is established, including:

[0012] The policy tag metadata and enterprise tag metadata were simplified respectively to determine the policy keywords and enterprise keywords;

[0013] Establish a standard thesaurus based on policy keywords and enterprise keywords.

[0014] Furthermore, new policy tag metadata is obtained from new policy information. Based on a standard thesaurus, the new policy information is recommended to target enterprises that match the new policy tag metadata, including:

[0015] The new policy information is segmented into words to determine the new policy tag metadata;

[0016] Based on the new policy tag metadata and a standard thesaurus, the target enterprise tag metadata corresponding to the new policy tag metadata is determined.

[0017] Based on the target company's tag metadata, new policy information will be recommended to the target company that corresponds to the target company's tag metadata.

[0018] Furthermore, based on the new policy tag metadata and a standard thesaurus, the target enterprise tag metadata corresponding to the new policy tag metadata is determined, including:

[0019] Based on the standard thesaurus, determine whether there exists a policy tag metadata sample that is completely identical to the new policy tag metadata;

[0020] If so, determine the corresponding enterprise tag metadata sample based on the policy tag metadata sample, and identify the enterprise tag metadata sample as the target enterprise tag metadata.

[0021] If not, based on the thesaurus, the new policy tag metadata is compared with the policy tag metadata samples in the standard thesaurus to determine the preferred policy tag metadata samples and their corresponding homogeneous enterprise tag metadata samples, and the homogeneous enterprise tag metadata samples are determined as the target enterprise tag metadata.

[0022] Furthermore, based on the target enterprise's tag metadata, new policy information is recommended to the target enterprise corresponding to the target enterprise's tag metadata, including:

[0023] Match the corresponding enterprise data based on the target enterprise's tag metadata;

[0024] Identify the target company based on the corresponding enterprise data;

[0025] The new policy information will be recommended to the target companies.

[0026] Furthermore, automated policy information recommendation methods also include:

[0027] Obtain the new enterprise tag metadata, and determine the target policy tag metadata corresponding to the new enterprise tag metadata based on the standard thesaurus;

[0028] Based on the target policy tag metadata, match the target policy information corresponding to the target policy tag metadata for new enterprises.

[0029] Furthermore, automated policy information recommendation methods also include:

[0030] Acquire behavioral data of new enterprises, and use collaborative filtering to identify homogeneous enterprises with similar behavioral data to the new enterprises;

[0031] Obtain the metadata of homogeneous enterprise tags, and determine the metadata of homogeneous enterprise policy tags based on the standard thesaurus;

[0032] Based on the policy tag metadata of homogeneous enterprises, the target policy information corresponding to the policy tag metadata of homogeneous enterprises is matched for new enterprises.

[0033] To address the above problems, the present invention also provides an automated policy information recommendation device, comprising:

[0034] The data acquisition module is used to acquire policy data and enterprise data;

[0035] The tag metadata acquisition module is used to perform word segmentation on policy data and enterprise data respectively, and determine policy tag metadata and enterprise tag metadata.

[0036] The standard thesaurus creation module is used to create a standard thesaurus based on policy tag metadata and enterprise tag metadata, wherein at least one enterprise tag metadata corresponds to the policy tag metadata;

[0037] The policy information automated recommendation module is used to obtain new policy tag metadata for new policy information and recommend the new policy information to target enterprises that match the new policy tag metadata based on a standard thesaurus.

[0038] To address the aforementioned problems, the present invention also provides an electronic device, including a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, it implements the policy information automated recommendation method as described above.

[0039] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing computer program instructions that, when executed by a computer, cause the computer to perform the policy information automated recommendation method described above.

[0040] The beneficial effects of adopting the above technical solution are as follows: This invention provides a method, apparatus, electronic device, and storage medium for automated policy information recommendation. The method includes: acquiring policy data and enterprise data; performing word segmentation processing on the policy data and enterprise data respectively to determine policy tag metadata and enterprise tag metadata; establishing a standard thesaurus based on the policy tag metadata and enterprise tag metadata, wherein at least one enterprise tag metadata corresponds to the policy tag metadata; acquiring new policy tag metadata for new policy information; and recommending the new policy information to target enterprises that match the new policy tag metadata based on the standard thesaurus. By processing existing policy data and enterprise data to establish a standard thesaurus, and then automatically matching new policy tag metadata based on the standard thesaurus, the efficiency of recommending new policies to target enterprises is effectively improved. Attached Figure Description

[0041] Figure 1 A flowchart illustrating an embodiment of the policy information automated recommendation method provided by the present invention;

[0042] Figure 2 This is a flowchart illustrating an embodiment of the present invention for establishing a standard thesaurus;

[0043] Figure 3 This is a schematic diagram of the process for recommending new policy information to target enterprises according to the first embodiment of the present invention;

[0044] Figure 4 This is a flowchart illustrating an embodiment of the target enterprise tag metadata provided by the present invention;

[0045] Figure 5 This is a schematic diagram of the second embodiment of the present invention for recommending new policy information to target enterprises;

[0046] Figure 6 This is a flowchart illustrating an embodiment of the present invention for automatically recommending policy information to new enterprises;

[0047] Figure 7 This is a schematic diagram of the process for recommending new policy information to target enterprises in the third embodiment of the present invention;

[0048] Figure 8 A schematic diagram of an embodiment of the policy information automated recommendation device provided by the present invention;

[0049] Figure 9 A structural block diagram of an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0050] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0051] Before presenting the implementation examples, let's first explain web crawling, collaborative filtering, and word forests:

[0052] A web crawler, also known as a web spider or web robot, is a program or script that automatically retrieves information from the World Wide Web according to certain rules.

[0053] Collaborative filtering refers to recommending information that a user might be interested in by leveraging the preferences of a group of like-minded individuals with shared experiences. Individuals respond to the information (such as rating) through a collaborative mechanism, and this feedback is recorded to achieve the filtering purpose, thereby helping others to select information. Notably, responses are not limited to information that is of particular interest; recording information that is of particular disinterest is also quite important.

[0054] Word segmentation is a technique used by search engines to segment user-submitted query metadata strings using various matching methods. This segmentation is performed on the user's metadata strings after the search engine has processed them. When mining text, segmenting the entire sentence can reduce the difficulty of automated text processing.

[0055] In this application, "thesaurus" refers to the "Extended Version of the Thesaurus of Synonyms from the Information Retrieval Laboratory of Harbin Institute of Technology." The "Thesaurus of Synonyms" is a computational Chinese lexicon compiled by Mei Jiaju et al. in 1983, initially intended to aid in creative and translation work. Due to the lexicon's age, the Information Retrieval Laboratory of Harbin Institute of Technology invested significant human and material resources to complete the "Extended Version of the Thesaurus of Synonyms from the Information Retrieval Laboratory of Harbin Institute of Technology." Based on this extended version, the similarity between words is primarily calculated through the hierarchical structural relationships between concepts. For example, methods using word distance as the main factor and the number of branch nodes and branch intervals as fine-tuning parameters; or assigning different edge weights to edges between different layers, calculating word similarity based on the interval between concepts and the number of direct subordinate nodes of the nearest common superordinate node.

[0056] Currently, based on the ability of government management departments to accurately interpret policies, the state has put forward higher policy management requirements for these departments in order to better provide more precise policy support to enterprises and reduce their operational pressure.

[0057] However, existing policies are still entered manually and displayed using traditional time-series methods, which is insufficient to meet the requirements of today's government administration and cannot quickly and accurately recommend the best policies to enterprises. In other words, current technology suffers from low efficiency in recommending policies to enterprises.

[0058] To address the aforementioned problems, this invention provides a method, apparatus, electronic device, and storage medium for automated policy information recommendation, which will be described in detail below.

[0059] like Figure 1 As shown, Figure 1 A flowchart illustrating an embodiment of the policy information automated recommendation method provided by the present invention includes:

[0060] Step S101: Obtain policy data and enterprise data.

[0061] Step S102: Perform word segmentation on the policy data and enterprise data respectively to determine the policy tag metadata and enterprise tag metadata.

[0062] Step S103: Establish a standard thesaurus based on policy tag metadata and enterprise tag metadata, wherein at least one enterprise tag metadata corresponds to the policy tag metadata.

[0063] Step S104: Obtain the new policy tag metadata of the new policy information, and recommend the new policy information to the target enterprises that match the new policy tag metadata according to the standard thesaurus.

[0064] In this embodiment, firstly, the policy data and enterprise data are segmented into words to determine the policy tag metadata and enterprise tag metadata. Then, a standard thesaurus is established based on the policy tag metadata and enterprise tag metadata, wherein at least one enterprise tag metadata corresponds to the policy tag metadata to meet the needs of subsequent automatic matching. Finally, the new policy tag metadata of the new policy information is obtained, and adaptive matching is performed based on the data in the standard thesaurus, thereby recommending the new policy information to the target enterprise that matches the new policy tag metadata.

[0065] It is understandable that the above embodiments, by processing existing policy data and enterprise data, establish a standard thesaurus, organically integrate policy data and enterprise data, and clarify the relationship between policy data and enterprise data; by automatically matching new policy tag metadata, the efficiency of recommending new policy information to target enterprises is greatly improved, and the tag metadata reflects the content of the policy information and the key points of the policy information. Recommendation through tag metadata can ensure the accuracy of the recommendation.

[0066] As a preferred embodiment, in step S101, in order to obtain more comprehensive policy data and enterprise data, data can also be collected from publicly available government policies, enterprise business registration information, news information, etc., to improve the policy data and enterprise data.

[0067] In one specific embodiment, in order to improve the efficiency of acquiring policy data and enterprise data, the policy data and enterprise data are processed according to the crawling algorithm. The crawling algorithm can also be used to process publicly available government policies, enterprise business registration information, news information and other information.

[0068] In another specific embodiment, policy data and enterprise data can also be obtained through manual input, which can better ensure the accuracy of policy data and enterprise data acquisition.

[0069] In other embodiments, policy data and enterprise data may be obtained through other means, which are not limited here.

[0070] In a preferred embodiment, in step S102, in order to improve the efficiency of word segmentation processing of policy data and enterprise data, jieba word segmentation technology is used to segment policy data and enterprise data respectively to determine the corresponding policy tag metadata and enterprise tag metadata.

[0071] In a preferred embodiment, in step S103, in order to establish a standard lexicon, such as... Figure 2 As shown, Figure 2 A flowchart illustrating an embodiment of establishing a standard thesaurus provided by the present invention includes:

[0072] Step S131: Simplify the policy tag metadata and enterprise tag metadata respectively, and determine the policy keywords and enterprise keywords.

[0073] Step S132: Establish a standard thesaurus based on policy keywords and enterprise keywords.

[0074] In this embodiment, firstly, the policy tag metadata and enterprise tag metadata are simplified to determine policy keywords and enterprise keywords. This process removes duplicate and meaningless metadata, improving data validity. Then, a standard thesaurus is established based on the policy keywords and enterprise keywords, integrating all policy keywords and enterprise keywords together. Each policy keyword has one or more corresponding enterprise keywords, and each enterprise keyword also has one or more corresponding policy keywords, thus providing a solid foundation for the matching work.

[0075] In a preferred embodiment, in step S104, in order to recommend the new policy information to target enterprises that match the new policy tag metadata, such as... Figure 3 As shown, Figure 3 The flowchart illustrating the first embodiment of recommending new policy information to target enterprises provided by the present invention includes:

[0076] Step S141: Perform word segmentation on the new policy information to determine the new policy tag metadata.

[0077] Step S142: Based on the new policy tag metadata and the standard thesaurus, determine the target enterprise tag metadata corresponding to the new policy tag metadata.

[0078] Step S143: Based on the target enterprise's tag metadata, recommend the new policy information to the target enterprise corresponding to the target enterprise's tag metadata.

[0079] In this embodiment, for new policy information that needs to be automatically recommended to target enterprises, firstly, the new policy information is segmented to obtain new policy tag metadata; then, based on a standard thesaurus, the target enterprise tag metadata corresponding to the new policy tag metadata is determined; finally, based on the target enterprise tag metadata, the new policy information is recommended to the target enterprise corresponding to the target enterprise tag metadata.

[0080] In this embodiment, firstly, the new policy tag metadata of the new policy information is extracted, which enables the connection between the new policy information and the standard thesaurus. Then, based on the relationship between the policy tag metadata and enterprise tag metadata in the standard thesaurus, a more comprehensive target enterprise tag metadata can be obtained, thereby identifying the target enterprise that matches the new policy information. This not only achieves automatic matching, but also ensures the integrity of the target enterprise based on the data in the standard thesaurus.

[0081] In a preferred embodiment, in step S142, in order to determine the target enterprise tag metadata, such as... Figure 4 As shown, Figure 4 A flowchart illustrating an embodiment of the target enterprise tag metadata provided by the present invention includes:

[0082] Step S1421: Based on the standard thesaurus, determine whether there exists a policy tag metadata sample that is completely identical to the new policy tag metadata.

[0083] Step S1422: If yes, then determine the corresponding enterprise tag metadata sample based on the policy tag metadata sample, and determine the enterprise tag metadata sample as the target enterprise tag metadata.

[0084] Step S1423: If not, based on the thesaurus, perform a synonym comparison between the new policy tag metadata and the policy tag metadata samples in the standard thesaurus, determine the preferred policy tag metadata samples and their corresponding homogeneous enterprise tag metadata samples, and determine the homogeneous enterprise tag metadata samples as the target enterprise tag metadata.

[0085] In this embodiment, firstly, the new policy tag metadata is traversed and matched with the policy tag metadata in the standard thesaurus to determine whether there is a policy tag metadata sample that is completely identical to the new policy tag metadata. Then, the target enterprise tag metadata is determined according to the determination result. Specifically, when there is a policy tag metadata sample in the standard thesaurus that is completely identical to the new policy tag metadata, the corresponding enterprise tag metadata sample is determined based on the policy tag metadata sample, and the enterprise tag metadata sample is determined as the target enterprise tag metadata. When there is no policy tag metadata sample in the standard thesaurus that is completely identical to the new policy tag metadata, based on the thesaurus, the new policy tag metadata is compared with the policy tag metadata samples in the standard thesaurus to determine the preferred policy tag metadata sample and its corresponding homogeneous enterprise tag metadata sample, and the homogeneous enterprise tag metadata sample is determined as the target enterprise tag metadata.

[0086] In step S1423, "the thesaurus" refers to the existing "Extended Version of the Thesaurus of Synonyms from the Information Retrieval Research Lab of Harbin Institute of Technology".

[0087] By identifying optimal policy tag metadata samples through the thesaurus, adaptive matching based on word meaning can be performed when no identical new policy tag metadata exists in the standard thesaurus. This expands the scope of recognition for new tag metadata, avoids recognition problems caused by different word choices, and improves the recommendation efficiency when government departments recommend policy information to enterprises.

[0088] In a preferred embodiment, in step S143, in order to recommend the new policy information to the target enterprise, such as... Figure 5 As shown, Figure 5 The flowchart illustrating the second embodiment of recommending new policy information to target enterprises provided by the present invention includes:

[0089] Step S1431: Match the corresponding enterprise data based on the target enterprise tag metadata.

[0090] Step S1432: Determine the target company based on the corresponding company data.

[0091] Step S1433: Recommend the new policy information to the target companies.

[0092] In this embodiment, firstly, based on the correspondence between enterprise tag metadata and enterprise data, the enterprise data corresponding to the target enterprise tag metadata is automatically obtained according to the target enterprise tag metadata; then, the target enterprise is determined according to the corresponding enterprise data; finally, the new policy information is recommended to the target enterprise.

[0093] In this embodiment, based on the relationship between enterprise tag metadata and enterprise data, the target enterprise can be automatically located through the target enterprise tag metadata, thereby effectively improving the efficiency of recommending new policy information to the target enterprise.

[0094] In this embodiment, in step S1432, after obtaining the enterprise data, new restrictions can be added according to actual needs, thereby adaptively narrowing the scope of enterprise data so that the final target enterprise can better meet actual needs.

[0095] Furthermore, when new enterprises emerge, government departments also need to provide them with relevant support policy information. Similar to the methods described above, to automatically recommend policy information to new enterprises, such as... Figure 6 As shown, Figure 6 This is a flowchart illustrating an embodiment of the present invention for automatically recommending policy information to new enterprises, including:

[0096] Step S161: Obtain the new enterprise tag metadata and determine the target policy tag metadata corresponding to the new enterprise tag metadata based on the standard thesaurus.

[0097] Step S162: Match the target policy information corresponding to the target policy tag metadata for the new enterprise.

[0098] In this embodiment, by effectively utilizing the relationship between enterprise tag metadata and policy tag metadata in the standard thesaurus, after extracting the new enterprise tag metadata, the system can automatically recommend target policy information to the new enterprise through effective matching, thereby effectively improving the efficiency of recommending support policy information to the new enterprise.

[0099] Furthermore, to broaden the scope of new policy information recommendations to target enterprises and ensure the completeness of the target enterprises, data on enterprises' browsing, application, and search behaviors related to policies can be collected. This allows for collaborative filtering to mutually recommend applicable policies to similar enterprises, avoiding omissions. For example... Figure 7 As shown, Figure 7 The flowchart of the third embodiment of the present invention, which recommends new policy information to target enterprises, includes:

[0100] Step S171: Obtain the behavioral data of the new enterprise, and identify homogeneous enterprises with similar behavioral data to the new enterprise through collaborative filtering.

[0101] Step S172: Obtain the metadata of homogeneous enterprise tags and determine the metadata of homogeneous enterprise policy tags based on the standard thesaurus.

[0102] Step S173: Based on the policy tag metadata of homogeneous enterprises, match the target policy information corresponding to the policy tag metadata of homogeneous enterprises for the new enterprise.

[0103] In this embodiment, firstly, behavioral data of the new enterprise is acquired, and homogeneous enterprises with similar behavioral data are identified through collaborative filtering; then, the homogeneous enterprise tag metadata is acquired, and the policy tag metadata of the homogeneous enterprises is determined according to a standard thesaurus; finally, based on the policy tag metadata of the homogeneous enterprises, target policies corresponding to the policy tag metadata of the homogeneous enterprises are automatically recommended to the new enterprise.

[0104] In this embodiment, behavioral data of new enterprises is effectively utilized to identify similar enterprises of the same type through collaborative filtering. Policies applicable to these similar enterprises are then recommended to the new enterprise in the same way. This not only effectively avoids situations where new enterprises, in their early stages of operation, might miss out on support policies due to a lack of business familiarity, but also significantly improves the efficiency of policy recommendations for new enterprises based on collaborative filtering.

[0105] Through the above methods, a standard thesaurus is used to specifically integrate and match policy data and enterprise data. After obtaining new policy tag metadata, the system can automatically match this metadata, significantly improving the efficiency of recommending new policies to target enterprises. Similarly, after obtaining new enterprise tag metadata, the system can also automatically match it. Furthermore, collaborative filtering is used to collect and analyze the behavioral data of new enterprises, automatically matching relevant policies and effectively improving the efficiency of policy recommendation.

[0106] To address the aforementioned problems, the present invention also provides an automated policy information recommendation device, such as... Figure 8 As shown, Figure 8 This is a schematic diagram of an embodiment of the automated policy information recommendation device provided by the present invention. The automated policy information recommendation device 800 includes:

[0107] Data acquisition module 801 is used to acquire policy data and enterprise data;

[0108] The tag metadata acquisition module 802 is used to perform word segmentation on policy data and enterprise data respectively, and determine policy tag metadata and enterprise tag metadata.

[0109] The standard thesaurus creation module 803 is used to create a standard thesaurus based on policy tag metadata and enterprise tag metadata, wherein at least one enterprise tag metadata corresponds to the policy tag metadata;

[0110] The policy information automated recommendation module 804 is used to obtain new policy tag metadata for new policy information and recommend the new policy information to target enterprises that match the new policy tag metadata according to the standard thesaurus.

[0111] The present invention also provides an electronic device, such as... Figure 9 As shown, Figure 9 This is a structural block diagram of an embodiment of the electronic device provided by the present invention. The electronic device 900 can be a computing device such as a mobile terminal, desktop computer, laptop, handheld computer, and server. The electronic device 900 includes a processor 901 and a memory 902, wherein the memory 902 stores a policy information automated recommendation program 903.

[0112] In some embodiments, memory 902 may be an internal storage unit of a computer device, such as a hard disk or memory. In other embodiments, memory 902 may be an external storage device of a computer device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc. Further, memory 902 may include both internal and external storage units of the computer device. Memory 902 is used to store application software and various types of data installed on the computer device, such as program code for installing the computer device. Memory 902 can also be used to temporarily store data that has been output or will be output. In one embodiment, the automated policy information recommendation program 903 may be executed by processor 901 to implement the automated policy information recommendation method of the various embodiments of the present invention.

[0113] In some embodiments, processor 901 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 902 or process data, such as executing an automated policy information recommendation program.

[0114] This embodiment also provides a computer-readable storage medium storing an automated policy information recommendation program thereon. When the program is executed by a processor, it implements the automated policy information recommendation method as described in any of the above technical solutions.

[0115] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0116] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for automated recommendation of policy information, characterized by, The method comprises the following steps: acquiring policy data and enterprise data; performing word segmentation processing on the policy data and the enterprise data respectively to determine policy label metadata and enterprise label metadata; establishing a standard vocabulary according to the policy label metadata and the enterprise label metadata, wherein at least one of the enterprise label metadata corresponds to the policy label metadata; acquiring new policy label metadata of new policy information, and recommending the new policy information to target enterprises corresponding to the new policy label metadata according to the standard vocabulary, which comprises the following steps: performing word segmentation processing on the new policy information to determine new policy label metadata; determining target enterprise label metadata corresponding to the new policy label metadata based on the standard vocabulary according to the new policy label metadata; and recommending the new policy information to target enterprises corresponding to the target enterprise label metadata according to the target enterprise label metadata; wherein determining target enterprise label metadata corresponding to the new policy label metadata based on the standard vocabulary according to the new policy label metadata comprises the following steps: determining whether there is a policy label metadata sample identical to the new policy label metadata according to the standard vocabulary; if yes, determining the enterprise label metadata sample corresponding to the policy label metadata sample, and determining the enterprise label metadata sample as the target enterprise label metadata; if no, performing synonymous comparison between the new policy label metadata and the policy label metadata sample in the standard vocabulary based on a word forest to determine an optimal policy label metadata sample and the homogenous enterprise label metadata sample corresponding thereto, and determining the homogenous enterprise label metadata sample as the target enterprise label metadata.

2. The policy information automated recommendation method of claim 1, wherein, establishing a standard vocabulary according to the policy label metadata and the enterprise label metadata comprises the following steps: performing simplification processing on the policy label metadata and the enterprise label metadata respectively to determine policy keywords and enterprise keywords; establishing a standard vocabulary according to the policy keywords and the enterprise keywords.

3. The policy information automated recommendation method of claim 1, wherein, recommending the new policy information to target enterprises corresponding to the target enterprise label metadata according to the target enterprise label metadata comprises the following steps: matching the corresponding enterprise data according to the target enterprise label metadata; determining the target enterprises according to the corresponding enterprise data; recommending the new policy information to the target enterprises.

4. The policy information automated recommendation method of claim 1, wherein, The method further comprises the following steps: acquiring new enterprise label metadata of a new enterprise, and determining target policy label metadata corresponding to the new enterprise label metadata according to the standard vocabulary; matching target policy information corresponding to the target policy label metadata for the new enterprise according to the target policy label metadata.

5. The policy information automated recommendation method of claim 1, wherein, The method further comprises the following steps: acquiring behavior data of the new enterprise, and determining homogenous enterprises similar to the behavior data of the new enterprise through collaborative filtering; acquiring homogenous enterprise label metadata of the homogenous enterprises, and determining policy label metadata of the homogenous enterprises according to the standard vocabulary; According to the policy tag metadata of the homogeneous enterprise, the new enterprise is matched with target policy information corresponding to the policy tag metadata of the homogeneous enterprise.

6. A policy information automated recommendation apparatus characterized by comprising: The method comprises the following steps: a data acquisition module is configured to acquire policy data and enterprise data; a tag metadata acquisition module is configured to perform word segmentation on the policy data and the enterprise data respectively, and determine policy tag metadata and enterprise tag metadata; a standard vocabulary establishment module is configured to establish a standard vocabulary according to the policy tag metadata and the enterprise tag metadata, wherein at least one of the enterprise tag metadata corresponds to the policy tag metadata; a policy information automatic recommendation module is configured to acquire new policy tag metadata of new policy information, and recommend the new policy information to a target enterprise corresponding to the new policy tag metadata according to the standard vocabulary, comprising the following steps: performing word segmentation on the new policy information to determine new policy tag metadata; determining target enterprise tag metadata corresponding to the new policy tag metadata based on the standard vocabulary; and recommending the new policy information to a target enterprise corresponding to the target enterprise tag metadata according to the target enterprise tag metadata. According to the new policy tag metadata, the target enterprise tag metadata corresponding to the new policy tag metadata is determined based on the standard vocabulary, comprising the following steps: determining whether there is a policy tag metadata sample identical to the new policy tag metadata according to the standard vocabulary; if yes, determining the enterprise tag metadata sample corresponding to the policy tag metadata sample, and determining the enterprise tag metadata sample as the target enterprise tag metadata; if no, performing synonymous comparison between the new policy tag metadata and the policy tag metadata sample in the standard vocabulary based on a word forest, determining an optimal policy tag metadata sample and the homogeneous enterprise tag metadata sample corresponding thereto, and determining the homogeneous enterprise tag metadata sample as the target enterprise tag metadata.

7. An electronic device, comprising: The method comprises a processor and a memory, and the memory stores a computer program which, when executed by the processor, implements the policy information automatic recommendation method of any one of claims 1-5.

8. A storage medium, characterized by The storage medium stores computer program instructions, which, when executed by a computer, cause the computer to perform the policy information automatic recommendation method of any one of claims 1-5.

Images