Electricity price and electricity charge policy knowledge base searching system and method considering user types

Abstract

The invention discloses an electricity price and electricity charge policy knowledge base search system considering user types, and the system comprises a user type classification module which is used for collecting user information and dividing users into different types of users according to the user information; the electricity price and electricity charge keyword generation and optimization module is used for determining basic keywords according to user types, performing semantic extension and adding associated vocabularies; the search execution module is used for constructing an index structure in the electricity price and electricity charge policy knowledge base, selecting a proper search algorithm according to the user type, and searching in the knowledge base based on the optimized keyword; and the search result processing module is used for sorting and screening the search results according to the user types so as to output accurate and personalized search results. The invention further discloses a corresponding method. By implementing the invention, the search efficiency and the search precision can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electricity price and electricity charge policy knowledge base, and in particular to an electricity price and electricity charge policy knowledge base search system and method that considers user types. Background Art

[0002] In current knowledge base systems, keyword search is a common way for users to obtain the knowledge they need. Usually, users enter keywords in the search box, and the system searches for documents, entries, or data records containing these keywords in the knowledge base based on a simple text matching algorithm, and presents the matching results to the user.

[0003] Existing keyword search methods are often based only on literal keyword matching, and it is difficult to accurately identify situations with similar semantics but different expressions. For example, when a user searches for knowledge about "industrial and commercial electricity prices", if there is relevant content in the knowledge base expressed as "general industrial and commercial electricity prices", it may not be accurately matched and returned to the user, resulting in incomplete search results and the user may miss some truly useful information. The differences in knowledge needs of different user types are not taken into account. When different users (such as residential users, industrial users, commercial users, ordinary business personnel, etc.) use knowledge bases, their search purposes, depth of understanding of knowledge, and the degree of detail of required knowledge are different, but the existing search methods provide unified search results for all users and cannot meet the personalized needs of different user types. As the scale of the knowledge base continues to expand, the efficiency of simple keyword matching search methods gradually decreases when processing large amounts of data. In particular, when users enter complex keyword combinations or perform fuzzy searches, the system needs to traverse a large number of data records, resulting in a long search time and affecting user experience. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a system and method for searching an electricity price and electricity fee policy knowledge base taking into account user types, which can improve search efficiency and search accuracy.

[0005] In order to solve the above technical problems, as one aspect of the present invention, a system for searching an electricity price and electricity fee policy knowledge base taking into account user types is provided, which comprises:

[0006] A user type classification module, used to collect user information and classify users into different types of users according to the user information;

[0007] The electricity price and electricity charge keyword generation and optimization module is used to determine the basic keywords according to the user type, and to perform semantic expansion and add related words to the basic keywords to generate optimized keywords;

[0008] A search execution module is used to construct an index structure in the electricity price and electricity fee policy knowledge base, select an appropriate search algorithm according to the user type, and search in the knowledge base based on the optimized keywords;

[0009] The search result processing module is used to sort and filter the search results according to the user type to output accurate and personalized search results.

[0010] Optionally, the user type classification module further includes:

[0011] The user information collection submodule is used to collect user information including but not limited to enterprise size, industry, electricity usage pattern, historical electricity fee payment records, and past query records on electricity price and electricity fee policies;

[0012] The user type determination submodule is used to analyze and process the collected user information using machine learning algorithms, and to divide users into types such as large industrial enterprise users, small industrial enterprise users, commercial users, and individual industrial and commercial households.

[0013] Optionally, the electricity price and electricity fee keyword generation and optimization module further includes:

[0014] A basic keyword determination unit, used to determine corresponding basic keywords according to the characteristics and needs of different user types;

[0015] The keyword optimization unit is used to semantically expand the basic keywords and add related words to generate more targeted and clear optimized keywords.

[0016] Optionally, the search execution module determines the search algorithm in the following manner:

[0017] For large industrial enterprise users, a search algorithm based on a combination of semantic understanding and rule matching is used;

[0018] For small industrial enterprise users, a relatively simple and direct keyword matching search algorithm is used;

[0019] For commercial users, a search algorithm combining time period analysis and keyword matching is used;

[0020] For individual businesses, choose a simple keyword matching search algorithm.

[0021] Optionally, the search result processing module includes:

[0022] The result sorting submodule is used to sort the search results according to factors such as the matching degree between the policy and user needs, the timeliness and authority of the policy;

[0023] The result screening submodule is used to screen out policy contents that are irrelevant to user needs or are too complex and difficult for users to understand based on user types.

[0024] Accordingly, as another aspect of the present invention, a method for searching an electricity price and electricity charge policy knowledge base considering user types is also provided, which comprises the following steps:

[0025] Collecting user information and classifying users into different types of users based on the user information;

[0026] Determine basic keywords according to user type, and perform semantic expansion and add related words to the basic keywords to generate optimized keywords;

[0027] Construct an index structure in the electricity price policy knowledge base and select an appropriate search algorithm based on the user type;

[0028] Search the knowledge base based on the optimized keywords and the selected search algorithm to obtain search results;

[0029] Sort and filter search results according to user type to output accurate and personalized search results.

[0030] Optionally, the step of collecting user information and classifying user types specifically includes:

[0031] Collect user information including but not limited to enterprise size, industry, electricity usage pattern, historical electricity fee payment records, and past inquiry records on electricity price and electricity fee policies;

[0032] Machine learning algorithms are used to analyze and process the collected user information, and users are divided into types such as large industrial enterprise users, small industrial enterprise users, commercial users, and individual industrial and commercial households.

[0033] Optionally, the step of generating optimized keywords specifically includes:

[0034] Determine the corresponding basic keywords according to the characteristics and needs of different user types;

[0035] Semantically expand basic keywords and add related words to generate more targeted and clear optimized keywords.

[0036] Optionally, the step of selecting a search algorithm specifically includes:

[0037] For large industrial enterprise users, choose a search algorithm based on a combination of semantic understanding and rule matching;

[0038] For small industrial enterprise users, choose a relatively simple and direct keyword matching search algorithm;

[0039] For commercial users, choose a search algorithm that combines time period analysis and keyword matching;

[0040] For individual businesses, choose a simple keyword matching search algorithm.

[0041] Optionally, the step of sorting and filtering the search results specifically includes:

[0042] Sort search results based on factors such as the degree of match between policies and user needs, the timeliness and authority of policies, etc.

[0043] According to the user type, policy content that is irrelevant to user needs or is too complex and difficult for users to understand is filtered out to output search results that best meet user needs.

[0044] The implementation of the embodiments of the present invention has the following beneficial effects:

[0045] The present invention provides a system and method for searching an electricity price and electricity charge policy knowledge base taking user types into consideration.

[0046] Implementing the embodiments of the present invention can improve search accuracy: by accurately classifying user types, the system can more deeply understand the search intentions and needs of different users; generating and optimizing search keywords according to user types makes the search process more targeted and accurate; and sorting and filtering search results according to user types, further ensuring the accuracy and relevance of search results.

[0047] The implementation of the embodiment of the present invention can meet personalized needs: different user types (such as large industrial enterprise users, small industrial enterprise users, commercial users, individual business owners, etc.) have different needs and concerns about electricity price policies. This solution can meet the personalized needs of different users through user type classification and targeted search strategies, and provide search results that are more in line with their own needs.

[0048] The implementation of the present invention can improve search efficiency: by building an efficient index structure, the location of records containing specific keywords can be quickly found during search. The appropriate search algorithm is selected according to the user type, which avoids unnecessary traversal and calculation and improves the search speed.

[0049] The implementation of the embodiments of the present invention can improve the user experience: by providing accurate and personalized search results, users can find the required information more quickly, reducing search time and effort. The sorting and filtering of search results make it easier for users to understand and select the policy content that best meets their needs.

[0050] In summary, this solution significantly improves the search efficiency and accuracy of the electricity price and fee policy knowledge base through the design and implementation of modules such as user type classification, keyword generation and optimization, search execution, and search result processing, meets the personalized needs of different users, and improves the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For a person skilled in the art, other drawings obtained based on these drawings still belong to the scope of the present invention without creative labor.

[0052] Figure 1 A schematic diagram of the structure of an embodiment of a knowledge base search system for electricity price and electricity fee policies taking into account user types provided by the present invention;

[0053] Figure 2 A schematic diagram of the main process of an embodiment of a method for searching an electricity price and electricity fee policy knowledge base taking into account user types provided by the present invention. DETAILED DESCRIPTION

[0054] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail below with reference to the accompanying drawings.

[0055] like Figure 1 As shown, a schematic diagram of the structure of an embodiment of a system for searching a knowledge base of electricity price and electricity charge policy considering user types provided by the present invention is shown; in this embodiment, the system for searching a knowledge base of electricity price and electricity charge policy considering user types 1 at least includes:

[0056] A user type classification module 10, used to collect user information and classify users into different types of users according to the user information;

[0057] In a specific example, the user type classification module 10 further includes:

[0058] The user information collection submodule is used to collect user information including but not limited to enterprise scale, industry, electricity usage pattern, historical electricity fee payment records, and past inquiry records of electricity price and electricity fee policies; the enterprise scale may include data such as the number of employees, annual turnover, transformer capacity, etc.; the electricity usage pattern may include information such as business hours, production shifts, etc.; the historical electricity fee payment records may include information such as payment amount, payment time, etc.;

[0059] The user type determination submodule is used to analyze and process the collected user information using machine learning algorithms (such as decision tree algorithms, clustering algorithms, etc.), and divide users into types such as large industrial enterprise users, small industrial enterprise users, commercial users (such as shopping malls, office buildings, etc.), and individual industrial and commercial users (such as small shops, small workshops, etc.).

[0060] For example, large industrial enterprises may have a large number of employees, a high annual turnover, and a transformer capacity of 315 kVA or above. Their electricity consumption patterns may have obvious seasonal or periodic fluctuations (such as peak production seasons for some industrial production). Individual industrial and commercial households may have a small number of employees, a relatively low annual turnover, a small scale of electricity consumption, and a relatively simple electricity consumption pattern.

[0061] In this embodiment, the collected user information is analyzed and processed using a machine learning algorithm. Users are divided into different types according to different feature combinations, specifically large industrial enterprise users, small industrial enterprise users, commercial users, and individual business types.

[0062] The electricity price and electricity charge keyword generation and optimization module 11 is used to determine the basic keywords according to the user type, and to perform semantic expansion and add related words to the basic keywords to generate optimized keywords;

[0063] In a specific example, the electricity price and electricity fee keyword generation and optimization module 11 further includes:

[0064] The basic keyword determination unit is used to determine the corresponding basic keywords according to the characteristics and needs of different user types; specifically, for large industrial enterprise users: according to their focus on the composition of electricity prices and adjustment policies, the basic keywords determined include "large industrial electricity prices", "basic electricity prices", "kilowatt-hour electricity prices", "power factor adjustment electricity charges", "seasonal electricity price fluctuations", "capacity-related electricity price policies", etc. For small industrial enterprise users: based on their needs for cost control and preferential policies, the basic keywords are set as "general industrial and commercial electricity prices", "cost control electricity price policies", "energy conservation and emission reduction subsidies", "simplified electricity fee calculation", "small and micro enterprise electricity price discounts", etc. For commercial users: considering their electricity consumption characteristics related to business hours and their attention to peak and valley time-of-use electricity price policies, the basic keywords include "commercial electricity", "peak and valley time-of-use electricity prices", "electricity consumption during business hours", "reduced electricity cost", "commercial electricity preferential policies", etc. For individual industrial and commercial households: in view of their attention to the basic composition of electricity prices, preferential policies and convenience of payment, the basic keywords are "individual industrial and commercial electricity", "basic composition of electricity prices", "small and micro enterprise electricity price discounts", "convenient electricity payment", etc.

[0065] The keyword optimization unit is used to semantically expand the basic keywords and add related words to generate more targeted and clear optimized keywords.

[0066] In this embodiment, keyword optimization includes:

[0067] Semantic expansion: semantic expansion of basic keywords for different user types. For example, for commercial users, "peak and valley time-of-use electricity prices" can be expanded to more targeted words such as "peak and valley time-of-use electricity prices for shopping malls" and "peak and valley time-of-use electricity prices for office buildings"; for individual industrial and commercial households, "small and micro enterprise electricity price discounts" can be expanded to "small shop electricity price discounts" and "small workshop electricity price discounts".

[0068] Add related words: According to the electricity consumption characteristics and concerns of the user type, add some related words to further clarify the search intent. For example, for large industrial enterprise users, "summer production electricity" and "winter production electricity" can be added on the basis of "seasonal electricity price fluctuations"; for commercial users, "daytime business electricity" and "nighttime business electricity" can be added on the basis of "business hours electricity".

[0069] A search execution module 12 is used to construct an index structure in the electricity price and electricity fee policy knowledge base, select a suitable search algorithm according to the user type, and search in the knowledge base based on the optimized keywords;

[0070] In a specific example, the search execution module 12 may further include: an index construction submodule and a search algorithm submodule.

[0071] Among them, the index construction submodule is used to build an efficient index structure in the electricity price and electricity fee policy knowledge base, and adopts common index construction methods such as inverted index to index the documents, terms, etc. in the knowledge base according to keywords, so that the location of records containing specific keywords can be quickly found during the search.

[0072] The search algorithm submodule is used to select an appropriate search algorithm according to the user type.

[0073] Specifically, for large industrial enterprise users, a search algorithm based on a combination of semantic understanding and rule matching is adopted; it is necessary to accurately understand the semantic content involving complex electricity price composition and adjustment mechanisms, and to match relevant policy rules and clauses to obtain accurate and comprehensive policy information.

[0074] For small industrial enterprise users, a relatively simple and direct keyword matching search algorithm is used, with the focus on quickly finding clear policy statements related to cost control, preferential policies, etc., because such users may need more concise and clear policy interpretations;

[0075] For commercial users, a search algorithm combining time period analysis and keyword matching is used. In addition to matching keywords such as "peak and valley time-of-use electricity prices", it can also analyze the applicability of electricity prices in different time periods in the policy according to the characteristics of the commercial users' business time periods, so as to accurately find the policy content related to reducing electricity costs;

[0076] For individual industrial and commercial households, a simple keyword matching search algorithm is selected to give priority to searching for policy information directly related to the basic structure of electricity prices, preferential policies for small and micro enterprises, and convenient methods of paying electricity bills, so as to meet their needs for understanding basic policies and practical operational convenience.

[0077] The search result processing module 13 is used to sort and filter the search results according to the user type to output accurate and personalized search results.

[0078] In a specific example, the search result processing module 13 further includes:

[0079] The result sorting submodule is used to sort the search results according to factors such as the matching degree between policies and user needs, the timeliness and authority of policies; specifically, for large industrial enterprise users: the sorting basis may include the matching degree between policies and the scale and characteristics of user electricity consumption (such as whether they are formulated for the characteristics of large industrial electricity consumption), the timeliness of policies (the latest policies are given priority), the authority of policies (policies issued by authoritative departments are given priority), etc., and the policy information that best meets user needs is placed in the front. For small industrial enterprise users: the matching degree between policies and user cost control and preferential acquisition needs, the degree of policy understanding (easy for such users to understand), and the timeliness of policies are used as sorting basis, and the policy content that is most helpful to user cost control and preferential acquisition is presented first. For commercial users: the sorting basis mainly includes the matching degree between policies and commercial users' business hours and electricity cost control needs, the timeliness of policies, and the operability of policies (such as whether they can directly guide commercial users to reasonably arrange electricity time to reduce costs), etc., and the policies that can best help commercial users reduce electricity costs are placed in the front. For individual industrial and commercial households: Sort the policies based on their matching degree with their basic electricity consumption and preferential treatment needs, their ease of understanding, their timeliness, etc., so that the policy information that best meets the needs of individual industrial and commercial households is placed at the front.

[0080] The result screening submodule is used to screen out policy contents that are irrelevant to user needs or are too complex and difficult for users to understand according to user types. Specifically, for large industrial enterprise users: some policy contents that are too simple and do not involve the complex mechanism of large industrial electricity consumption, as well as policies that are not very relevant to the user's industry or electricity consumption characteristics, can be screened out, and only the contents that are of substantial help to users and can deeply interpret the large industrial electricity price and electricity fee policies are retained. For small industrial enterprise users: some policy contents that are too professional, complex and difficult for users to understand are screened out, and only simple and clear policy contents that are directly related to user cost control and preferential acquisition needs are retained. For commercial users: some policy contents that are irrelevant to commercial users' business hours and electricity cost control needs are screened out, and only policy contents that can effectively guide commercial users to reduce electricity costs are retained. For individual industrial and commercial households: some policy contents that are too complex and not easy for individual industrial and commercial households to understand and operate are filtered out, and only policy contents that are helpful for the basic composition of electricity prices, preferential acquisition and convenient electricity fee payment for individual industrial and commercial households are retained.

[0081] It can be understood that in the embodiment provided by the present invention, when searching the electricity price and electricity fee policy knowledge base, users are first classified by type, and then search keywords are generated and optimized in a targeted manner based on the characteristics and needs of different user types, and a suitable search algorithm is used to search the knowledge base. Finally, the search results are sorted and screened according to the user type, thereby achieving accurate and personalized search result output and improving search efficiency.

[0082] like Figure 2 FIG. 1 is a schematic diagram showing a main flow chart of an embodiment of a method for searching a knowledge base of electricity price and electricity fee policies taking into account user types provided by the present invention. In this embodiment, the method comprises the following steps:

[0083] Step S10, collecting user information, and dividing users into different types of users according to the user information;

[0084] In a specific example, in this step, the step of collecting user information and classifying user types specifically includes:

[0085] Collect user information including but not limited to enterprise size, industry, electricity usage pattern, historical electricity fee payment records, and past inquiry records on electricity price and electricity fee policies;

[0086] Machine learning algorithms are used to analyze and process the collected user information, and users are divided into types such as large industrial enterprise users, small industrial enterprise users, commercial users, and individual industrial and commercial households.

[0087] Step S11, determining basic keywords according to the user type, and semantically expanding the basic keywords and adding related words to generate optimized keywords;

[0088] In a specific example, in this step, the step of generating optimized keywords specifically includes:

[0089] Determine the corresponding basic keywords according to the characteristics and needs of different user types;

[0090] Semantically expand basic keywords and add related words to generate more targeted and clear optimized keywords.

[0091] Step S12, constructing an index structure in the electricity price and electricity fee policy knowledge base, and selecting a suitable search algorithm according to the user type;

[0092] In a specific example, in this step, the step of selecting a search algorithm specifically includes:

[0093] For large industrial enterprise users, choose a search algorithm based on a combination of semantic understanding and rule matching;

[0094] For small industrial enterprise users, choose a relatively simple and direct keyword matching search algorithm;

[0095] For commercial users, choose a search algorithm that combines time period analysis and keyword matching;

[0096] For individual businesses, choose a simple keyword matching search algorithm.

[0097] Step S13, searching in the knowledge base based on the optimized keywords and the selected search algorithm to obtain search results;

[0098] In a specific example, in this step, the step of sorting and screening the search results specifically includes:

[0099] Sort search results based on factors such as the degree of match between policies and user needs, the timeliness and authority of policies, etc.

[0100] According to the user type, policy content that is irrelevant to user needs or is too complex and difficult for users to understand is filtered out to output search results that best meet user needs.

[0101] Step S14, sorting and filtering the search results according to the user type to output accurate and personalized search results.

[0102] For more details, please refer to and combine the above Figure 1 The description is not repeated here.

[0103] The implementation of the embodiments of the present invention has the following beneficial effects:

[0104] The present invention provides a system and method for searching an electricity price and electricity charge policy knowledge base taking user types into consideration.

[0105] Implementing the embodiments of the present invention can improve search accuracy: by accurately classifying user types, the system can more deeply understand the search intentions and needs of different users; generating and optimizing search keywords according to user types makes the search process more targeted and accurate; and sorting and filtering search results according to user types, further ensuring the accuracy and relevance of search results.

[0106] The implementation of the embodiment of the present invention can meet personalized needs: different user types (such as large industrial enterprise users, small industrial enterprise users, commercial users, individual business owners, etc.) have different needs and concerns about electricity price policies. This solution can meet the personalized needs of different users through user type classification and targeted search strategies, and provide search results that are more in line with their own needs.

[0107] The implementation of the present invention can improve search efficiency: by building an efficient index structure, the location of records containing specific keywords can be quickly found during search. The appropriate search algorithm is selected according to the user type, which avoids unnecessary traversal and calculation and improves the search speed.

[0108] The implementation of the embodiments of the present invention can improve the user experience: by providing accurate and personalized search results, users can find the required information more quickly, reducing search time and effort. The sorting and filtering of search results make it easier for users to understand and select the policy content that best meets their needs.

[0109] In summary, this solution significantly improves the search efficiency and accuracy of the electricity price and fee policy knowledge base through the design and implementation of modules such as user type classification, keyword generation and optimization, search execution, and search result processing, meets the personalized needs of different users, and improves the user experience.

[0110] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] The above disclosure is only a preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A knowledge base search system for electricity price and electricity fee policy considering user types, characterized in that: include: A user type classification module, used to collect user information and classify users into different types of users according to the user information; The electricity price and electricity charge keyword generation and optimization module is used to determine the basic keywords according to the user type, and to perform semantic expansion and add related words to the basic keywords to generate optimized keywords; A search execution module is used to construct an index structure in the electricity price and electricity fee policy knowledge base, select an appropriate search algorithm according to the user type, and search in the knowledge base based on the optimized keywords; The search result processing module is used to sort and filter the search results according to the user type to output accurate and personalized search results.

2. The system according to claim 1, characterized in that The user type classification module further includes: The user information collection submodule is used to collect user information including but not limited to enterprise size, industry, electricity usage pattern, historical electricity fee payment records, and past query records on electricity price and electricity fee policies; The user type determination submodule is used to analyze and process the collected user information using machine learning algorithms, and to divide users into types such as large industrial enterprise users, small industrial enterprise users, commercial users, and individual industrial and commercial households.

3. The system according to claim 2, characterized in that The electricity price and electricity fee keyword generation and optimization module further includes: A basic keyword determination unit, used to determine corresponding basic keywords according to the characteristics and needs of different user types; The keyword optimization unit is used to semantically expand the basic keywords and add related words to generate more targeted and clear optimized keywords.

4. The system according to claim 3, characterized in that The search execution module determines the search algorithm in the following manner: For large industrial enterprise users, a search algorithm based on a combination of semantic understanding and rule matching is used; For small industrial enterprise users, a relatively simple and direct keyword matching search algorithm is used; For commercial users, a search algorithm combining time period analysis and keyword matching is used; For individual businesses, choose a simple keyword matching search algorithm.

5. The system according to claim 4, characterized in that The search result processing module includes: The result sorting submodule is used to sort the search results according to factors such as the matching degree between the policy and user needs, the timeliness and authority of the policy; The result screening submodule is used to screen out policy contents that are irrelevant to user needs or are too complex and difficult for users to understand based on user types.

6. A method for searching a knowledge base of electricity price and electricity charge policies considering user types, characterized in that: The following steps are involved: Collecting user information and classifying users into different types of users based on the user information; Determine basic keywords according to user type, and perform semantic expansion and add related words to the basic keywords to generate optimized keywords; Construct an index structure in the electricity price policy knowledge base and select an appropriate search algorithm based on the user type; Search the knowledge base based on the optimized keywords and the selected search algorithm to obtain search results; Sort and filter search results according to user type to output accurate and personalized search results.

7. The method according to claim 6, characterized in that The steps of collecting user information and classifying user types specifically include: Collect user information including but not limited to enterprise size, industry, electricity usage pattern, historical electricity fee payment records, and past inquiry records on electricity price and electricity fee policies; Machine learning algorithms are used to analyze and process the collected user information, and users are divided into types such as large industrial enterprise users, small industrial enterprise users, commercial users, and individual industrial and commercial households.

8. The method according to claim 7, characterized in that The step of generating optimized keywords specifically includes: Determine the corresponding basic keywords according to the characteristics and needs of different user types; Semantically expand basic keywords and add related words to generate more targeted and clear optimized keywords.

9. The method according to claim 8, characterized in that The step of selecting a search algorithm specifically includes: For large industrial enterprise users, choose a search algorithm based on a combination of semantic understanding and rule matching; For small industrial enterprise users, choose a relatively simple and direct keyword matching search algorithm; For commercial users, choose a search algorithm that combines time period analysis and keyword matching; For individual businesses, choose a simple keyword matching search algorithm.

10. The method according to claim 9, characterized in that The steps of sorting and screening the search results specifically include: Sort search results based on factors such as the degree of match between policies and user needs, the timeliness and authority of policies, etc. According to the user type, policy content that is irrelevant to user needs or is too complex and difficult for users to understand is filtered out to output search results that best meet user needs.

Images