Power grid professional category intelligent customer service system based on middle platform technology and question and answer method

Abstract

The invention provides a power grid professional category intelligent customer service system based on a middle platform technology and a question and answer method, and relates to the technical field of intelligent customer service. The method comprises the steps of obtaining power grid professional category product data and historical use scene data, performing classification analysis of response demand characteristics, and establishing a power grid professional category knowledge graph; obtaining historical user customer service data, extracting corresponding portrait information, and labeling the power grid professional category knowledge graph to form a power grid professional category portrait knowledge graph; initial demand information of a target user is obtained, dialogue analysis for demand category positioning is carried out, and demand dialogue information is formed; and obtaining demand feedback dialogue information formed based on the demand dialogue information, and performing directional analysis of professional categories according to the target portrait information of the target user to form recommended professional category data. According to the method, more intelligent and accurate product positioning and recommendation are realized by systematically associating detailed parameter performance information of power grid professional categories with user characteristics.

Description

Technical Field

[0001] This invention relates to the field of intelligent customer service technology, and more specifically, to an intelligent customer service system and question-and-answer method for power grid professional products based on middleware technology. Background Technology

[0002] The middle platform, as part of a platform-based organization, is an organizational module that connects the front-end operational units and the back-end resource departments. The usage requirements for power grid specialized equipment are numerous, ranging from the front-end submitting relatively technical needs to the back-end conducting equipment procurement analysis. Directly obtaining the requirements from the front-end would present significant challenges in requirement alignment.

[0003] Currently, some services based on middleware technology for converting demand for power grid-specific product categories have gradually emerged. These include internal customer service systems that move from front-end to back-end, using customer service Q&A dialogues to translate front-end demands in detail and then pinpoint the required product categories. However, current customer service Q&A is largely based on standard question-and-answer formats and lacks a systematic association between specific equipment parameters and user characteristics, making it impossible to provide intelligent and precise recommendations for specialized product categories.

[0004] Therefore, designing an intelligent customer service system and question-and-answer method for power grid professional product categories based on middleware technology, and achieving more intelligent and accurate product positioning and recommendation by systematically associating detailed parameter performance information of power grid professional product categories with user characteristics, is an urgent problem to be solved. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent customer service Q&A method for power grid professional product categories based on middleware technology. By acquiring power grid professional product category data and historical usage scenario data, a classification of product category demand characteristics with application scenario attributes is established. A professional knowledge graph suitable for demand decomposition and selection is created. Simultaneously, by combining historical user customer service data, user profile features of product categories are labeled. This further marks product categories under the professional knowledge graph data with user characteristic tendencies, providing a clearer and more structured customer service Q&A reference for subsequent demand conversion analysis targeting target users. This efficiently achieves the completion and confirmation of demand information during the intelligent Q&A process, and accurately locates the professional categories suitable for target users based on customer service Q&A data, making the products that meet the needs more reasonable and precise.

[0006] The present invention also aims to provide an intelligent customer service system for power grid professional product categories based on middleware technology. This system collects intelligent customer service Q&A data through a data acquisition unit and establishes a professional knowledge graph using a graph analysis unit, while simultaneously labeling product categories to enhance data personalization. The Q&A analysis unit processes the Q&A dialogue using the target user's needs information and obtains necessary demand information, thereby enabling more accurate and reasonable selection and positioning of product categories. The interconnectedness of different functional units forms an organic whole for intelligent customer Q&A, which is a crucial material foundation for realizing intelligent customer service Q&A based on middleware technology.

[0007] Firstly, this invention provides an intelligent customer service Q&A method for power grid professional product categories based on middleware technology, comprising: acquiring power grid professional product category data and historical usage scenario data, performing classification analysis based on the characteristics of the reflected needs, and establishing a power grid professional product category knowledge graph; acquiring historical user customer service data to extract corresponding profile information, forming user profile information data corresponding to historical users, and labeling the power grid professional product category knowledge graph to form a power grid professional product category profile knowledge graph; acquiring the initial demand information of the target user, and performing dialogue analysis based on the power grid professional product category profile knowledge graph to form demand dialogue information; acquiring demand feedback dialogue information formed based on the demand dialogue information, and performing targeted analysis of professional categories based on the target user's target profile information to form recommended professional category data.

[0008] In this invention, the method establishes a classification of product demand characteristics with application scenario attributes by acquiring power grid professional product category data and historical usage scenario data. It also creates a professional knowledge graph suitable for demand decomposition and selection. Simultaneously, it combines historical customer service data to label user profile features of product categories, thereby giving product categories under the professional knowledge graph data further characteristic markings of user tendencies. This provides a clearer and more structured customer service Q&A reference for subsequent demand conversion analysis targeting target users. Furthermore, it efficiently completes and confirms demand information during intelligent Q&A, and accurately locates suitable professional categories for target users based on customer service Q&A data, making the products that meet the needs more reasonable and precise.

[0009] One possible approach involves acquiring power grid product category data and historical usage scenario data, performing classification analysis to reflect demand characteristics, and establishing a power grid product category knowledge graph. This includes: extracting product parameter knowledge level information corresponding to different product categories based on the power grid product category data; clustering the product parameter knowledge level information corresponding to different product categories to form different product parameter knowledge level clustered category sets; extracting product scenario knowledge level information corresponding to different product categories based on historical usage scenario data; clustering different product categories in different product parameter knowledge level clustered category sets based on product scenario knowledge level information to form different product parameter scenario knowledge graph clustered category groups in the corresponding product parameter knowledge level clustered category sets; and forming a power grid product category knowledge graph containing all product parameter scenario knowledge graph clustered category groups based on the different product parameter scenario knowledge graph clustered category groups in all different product parameter knowledge level clustered category sets, using the product parameter knowledge level information and product scenario knowledge level information as references.

[0010] In this invention, the establishment of a knowledge graph for power grid professional categories mainly considers two aspects: firstly, how to define the classification hierarchy of the knowledge graph; and secondly, how the established knowledge graph can better facilitate the positioning of professional category products based on user needs. These two aspects are essentially complementary. The definition of the classification hierarchy, combined with demand conditions and characteristics, can be more direct and accurate in terms of information. Typically, for users, the demand for professional category products comes from the performance parameter data of the professional category products themselves, while also considering the application scenarios they should use. This allows for an accurate grasp of user needs and the formation of a more realistic classification hierarchy information for the professional category knowledge graph. Therefore, this application establishes a knowledge graph that both meets needs and enables efficient product positioning by including product data information of the professional category products themselves and historical information on specific scenarios in which the corresponding professional category products were used. It's important to note that for usage scenarios, information can be extracted based on the specific needs of each product category. For example, for insulating boots, based on product parameters and actual user requirements, the scenario information can be determined as 10KV live-line work. More specifically, it could be 10KV line emergency repair work. The level of detail can be adjusted as needed through a modular approach, such as providing a fixed scenario description based on parameter conditions, job type, and work type. Then, the three modules can be further refined based on the required level of detail. Of course, there are various methods for generating these word-filling modules. These could be based on semantic analysis of historical customer service data, big data analysis combining product usage data, or standardized question-and-answer patterns from customer service data.

[0011] One possible implementation involves clustering the product parameter knowledge level information corresponding to different product categories to form different product parameter knowledge level clustered product category sets. This includes: arbitrarily selecting a product category from the different product categories and designating it as the baseline product category; using all product parameter knowledge level information corresponding to the baseline product category as a reference, traversing all different product categories; if all product parameter knowledge level information corresponding to a product category is the same as all product parameter knowledge level information corresponding to the baseline product category, then clustering the product category with the baseline product category; after traversing all product categories, extracting all clustered product categories; arbitrarily extracting one product category from the remaining un-clustered product categories and designating it as the baseline product category; repeating the clustering judgment for product categories to extract new clustered product categories; repeating the clustering analysis for the remaining un-clustered product categories until the clustering of all product categories is completed; and determining the different clustered product categories as the corresponding product parameter knowledge level clustered product category sets.

[0012] In this invention, it is understood that establishing a professional knowledge graph essentially involves clustering different product categories based on defined classification levels. A single product category may be applicable to multiple classification levels. Therefore, reasonable clustering of product categories during graph construction can provide recommended product information based on the knowledge graph's classification level positioning. Here, the clustering method requires that all classification level information be identical to cluster different product categories together. Product categories generally share similar performance parameters; therefore, each cluster will contain multiple product categories. The product categories referred to here are series of products under a specific power grid professional category, such as the insulating gloves category, which includes a series of products that meet different main technical parameters. This is because a product category encompasses many specific products and equipment.

[0013] As one possible implementation method, product parameter knowledge hierarchy information includes, but is not limited to: technical standards, product parameters, and compliance rules.

[0014] In this invention, it should be noted that the classification hierarchy is determined by fully considering user needs. Therefore, language features can be extracted from historical customer service Q&A data to obtain information related to the performance parameters of the product category as classification hierarchy information. Alternatively, a direct definition can be used. This application, taking into full account the characteristics of the products, defines the classification hierarchy as including at least the technical standards followed by the product category, such as various manufacturing standards, product usage standards, and product functional standards; product performance parameters, such as voltage levels, mechanical strength, measurement accuracy range, and quantified values ​​of anti-interference capabilities; and product compliance rules, such as standards that must be equipped during use, like Class II insulation tools. Furthermore, the classification hierarchy can be further refined based on different platform architectures to ensure the completeness and comprehensiveness of the knowledge graph system and improve the accuracy and rationality of product category recommendations.

[0015] One possible approach involves acquiring historical user customer service data to extract corresponding profile information, forming user profile data for historical users, and then tagging the power grid professional category knowledge graph to form a power grid professional category profile knowledge graph. This includes: setting profile parameters; extracting profile information corresponding to the parameters based on historical user customer service data; determining all profile information corresponding to different product categories selected by historical users based on the historical user customer service data; and tagging the profile information of different product categories in the power grid professional category knowledge graph based on all the profile information corresponding to different product categories, thus forming a power grid professional category profile knowledge graph.

[0016] In this invention, the tagging of product categories clustered in the knowledge graph based on user profiles primarily involves assigning user preference attributes to these products. This allows for further recommendations tailored to user needs and corresponding product category positioning, incorporating user characteristics to improve the accuracy of product recommendations that meet those needs. It should be noted that there are various methods for extracting feature information from user profiles. This application adopts a direct definition approach, which allows for accurate and comprehensive control. The defined profile information includes, but is not limited to, job type, length of service, purchasing preferences (such as brand preferences), project content, and current project information (such as equipment model and voltage level in work orders). Of course, the profile information can be further refined based on actual circumstances to improve the accuracy of product category recommendations.

[0017] One possible approach is to obtain the initial demand information of the target user and combine it with the power grid professional category profile knowledge graph to conduct dialogue analysis for demand category positioning, thereby forming demand dialogue information. This includes: extracting hierarchical information corresponding to product parameter knowledge level information and product scenario knowledge level information based on the initial demand information of the target user, and performing a correspondence check to form a hierarchical information correspondence check result; and conducting demand category positioning analysis based on the hierarchical information correspondence check result to form demand dialogue information.

[0018] In this invention, after the professional category profile knowledge graph is established, the hierarchical information of the knowledge graph can be used to supplement the necessary information for locating and recommending products that was not provided in the initial demand information. This makes the customer service Q&A in the middle platform more targeted, efficient, and accurate. By comparing and verifying the initial demand information with the hierarchical information in the knowledge graph, it is determined whether the necessary demand information has been obtained. Then, reasonable demand Q&A data is formed in a targeted manner, ensuring that customer service Q&A can obtain sufficient and necessary information.

[0019] As one possible implementation, based on the results of the hierarchical information correspondence check, a demand category positioning analysis is performed to form demand dialogue information, including: if the hierarchical information correspondence check result is an incomplete correspondence, then the hierarchical information not extracted from the initial demand information is identified, corresponding hierarchical information demand questions are formed, and all hierarchical information demand questions are combined to form demand dialogue information; if the hierarchical information correspondence check result is a complete correspondence, then all extracted hierarchical information is combined to form complete demand information data.

[0020] In this invention, the correspondence check of the initial requirement information mainly involves two scenarios. The first is where the initial requirement information does not fully contain the hierarchical information matching the knowledge graph, thus requiring completion. The second is where the initial information already contains complete hierarchical information matching the knowledge graph. For the first scenario, the hierarchical information requiring completion is determined through comparison and verification, forming the corresponding question-and-answer content. It should be noted that the question-and-answer content can be pre-screened with specific sentence structures and content, or guided with specific formats for filling in and answering, thereby making the obtained information more accurate and efficient. Alternatively, the hierarchical information requiring completion can be used with AI intelligence to interact with the user, improving the flexibility of question-and-answer interactions while enhancing customer service quality and information flexibility.

[0021] One possible implementation involves acquiring demand feedback dialogue information based on demand dialogue information, and conducting targeted analysis of professional categories based on the target user's target profile information to generate recommended professional category data. This includes: if the hierarchical information correspondence check result is an incomplete correspondence, extracting the hierarchical information not obtained from the initial demand information based on the demand feedback dialogue information, and determining different product parameter scenario knowledge graph clustering groups that match the product parameter knowledge hierarchical information and product scenario knowledge hierarchical information based on the power grid professional category knowledge graph; if the hierarchical information correspondence check result is a complete correspondence, combining the complete demand information data and the power grid professional category knowledge graph, determining different product parameter scenario knowledge graph clustering groups that match the product parameter knowledge hierarchical information and product scenario knowledge hierarchical information; and conducting targeted analysis based on the determined different product parameter scenario knowledge graph clustering groups and target profile information to generate recommended professional category data.

[0022] In this invention, after obtaining complete matching knowledge graph hierarchical information, matching can be performed based on this data to locate the product category cluster based on the hierarchical information of the knowledge graph, which can effectively ensure that the located product category meets the user's needs.

[0023] As one possible approach, product category groups are clustered based on the knowledge graph of different product parameter scenarios, and targeted analysis is performed in conjunction with target profile information to form recommended professional category data. This includes: extracting the target profile information corresponding to all existing profile parameters based on the target profile information; and determining the product category with the most matches to different target profile information based on the target profile information and in conjunction with the power grid professional category profile knowledge graph, and labeling it as recommended professional category data.

[0024] In this invention, while the product category set based on hierarchical data positioning basically meets user needs, different users also have requirements for the series within each product category. Filtering through user profiles can further improve the personalization of the recommended product categories. The matching method for profile information is to select the product category with the highest number of profile information matches as the best recommendation. Of course, considering that the recommendations are only for providing users with a selection reference, when the number of best recommendations is small, a certain number of product categories can be selected sequentially according to the number of profile information matches.

[0025] Secondly, this invention provides an intelligent customer service system for power grid professional categories based on middleware technology, comprising: a data acquisition unit for acquiring power grid professional category product data, historical usage scenario data, historical user customer service data, and initial demand information of target users; a graph analysis unit for classifying and analyzing the power grid professional category product data and historical usage scenario data acquired by the data acquisition unit to establish a power grid professional category knowledge graph, and combining it with historical user customer service data for labeling to form a power grid professional category profile knowledge graph; and a question-and-answer analysis unit for performing dialogue analysis based on the initial demand information of target users acquired by the data acquisition unit and the power grid professional category profile knowledge graph formed by the graph analysis unit, forming demand dialogue information, acquiring demand feedback dialogue information, and performing targeted analysis to form recommended professional category data.

[0026] In this invention, the system collects intelligent customer service Q&A data through a data acquisition unit and establishes a professional knowledge graph using a graph analysis unit, while simultaneously labeling product categories to enhance data personalization. The Q&A analysis unit processes the question-and-answer dialogue using target user needs information and obtains necessary demand information, thereby enabling more accurate and reasonable selection and positioning of product categories. The different functional units are interconnected, forming an organic whole for intelligent customer Q&A, which is a crucial material foundation for realizing intelligent customer service Q&A based on middleware technology.

[0027] The beneficial effects of the intelligent customer service system and question-and-answer method for power grid professional categories based on middleware technology provided by this invention are as follows:

[0028] This method establishes a classification of product demand characteristics with application scenario attributes by acquiring power grid professional product category data and historical usage scenario data. It also creates a professional knowledge graph suitable for demand decomposition and selection. At the same time, it combines historical user customer service data to label the user profile characteristics of product categories. This gives product categories under the professional knowledge graph data further characteristic markings of user tendencies, providing a clearer and more structured customer service Q&A reference for subsequent demand conversion analysis targeting target users. This enables efficient completion and confirmation of demand information during intelligent Q&A, and also allows for accurate positioning of professional categories suitable for target users based on customer service Q&A data, making the products that meet the needs more reasonable and precise.

[0029] This system collects intelligent customer service Q&A data through a data acquisition unit and establishes a professional knowledge graph using a graph analysis unit, while also labeling product categories to enhance data personalization. The Q&A analysis unit processes the Q&A dialogue appropriately using target user needs information and obtains necessary demand information, thereby enabling more accurate and reasonable selection and positioning of product categories. The different functional units are interconnected, forming an organic whole for intelligent customer Q&A, which is a crucial material foundation for realizing intelligent customer service Q&A based on middleware technology. Attached Figure Description

[0030] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments of the present invention will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 A flowchart illustrating the steps of an intelligent customer service Q&A method for power grid professional categories based on middleware technology, provided in an embodiment of the present invention;

[0032] Figure 2 This is a schematic diagram of the structure of an intelligent customer service system for power grid professional categories based on middleware technology, provided as an embodiment of the present invention. Detailed Implementation

[0033] The technical solutions of the present invention will now be described with reference to the accompanying drawings in the embodiments of the present invention.

[0034] The middle platform, as part of a platform-based organization, is an organizational module that connects the front-end operational units and the back-end resource departments. The usage requirements for power grid specialized equipment are numerous, ranging from the front-end submitting relatively technical needs to the back-end conducting equipment procurement analysis. Directly obtaining the requirements from the front-end would present significant challenges in requirement alignment.

[0035] Currently, some services based on middleware technology for converting demand for power grid-specific product categories have gradually emerged. These include internal customer service systems that move from front-end to back-end, using customer service Q&A dialogues to translate front-end demands in detail and then pinpoint the required product categories. However, current customer service Q&A is largely based on standard question-and-answer formats and lacks a systematic association between specific equipment parameters and user characteristics, making it impossible to provide intelligent and precise recommendations for specialized product categories.

[0036] refer to Figures 1-2This invention provides an intelligent customer service Q&A method for power grid professional product categories based on middleware technology. This method establishes a category product demand characteristic classification with application scenario attributes by acquiring power grid professional product category data and historical usage scenario data. It also creates a professional knowledge graph suitable for demand decomposition and selection. Simultaneously, it labels user profile features of product categories based on historical user customer service data. This further marks product categories under the professional knowledge graph data with user characteristic tendencies, providing a clearer and more structured customer service Q&A reference for subsequent demand conversion analysis targeting target users. This efficiently completes and confirms demand information during the intelligent Q&A process, and accurately locates suitable professional categories for target users based on customer service Q&A data, making the products that meet the needs more reasonable and precise.

[0037] A smart customer service Q&A method for power grid professional categories based on middleware technology specifically includes the following steps:

[0038] S1: Obtain product data and historical usage scenario data for power grid professional categories, conduct classification analysis reflecting demand characteristics, and establish a knowledge graph for power grid professional categories.

[0039] This process involves acquiring product data and historical usage scenario data for power grid special categories, conducting classification analysis to reflect demand characteristics, and establishing a knowledge graph for power grid special categories. This includes: extracting product parameter knowledge level information for different product categories based on the product data; clustering the product parameter knowledge level information for different product categories to form different product parameter knowledge level clusters; extracting product scenario knowledge level information for different product categories based on historical usage scenario data; clustering different product categories within the different product parameter knowledge level clusters based on product scenario knowledge level information to form different product parameter scenario knowledge graph clusters within those clusters; and, based on these clusters and the product parameter knowledge level information, forming a power grid special category knowledge graph encompassing all product parameter scenario knowledge graph clusters.

[0040] Establishing a knowledge graph for power grid product categories primarily considers two aspects: firstly, how to define the classification hierarchy within the knowledge graph; and secondly, whether the established knowledge graph can better facilitate the positioning of product categories based on user needs. These two aspects are essentially complementary. The definition of the classification hierarchy, combined with demand conditions and characteristics, allows for more direct and precise information. Typically, users' needs for product categories stem from the performance parameters of the products themselves, while also considering the application scenarios they should use. This approach accurately grasps user needs and generates a more realistic classification hierarchy within the product category knowledge graph. Therefore, this application establishes a knowledge graph that both meets demand and enables efficient product category positioning by incorporating product data and historical usage scenarios for each product category. It's important to note that for usage scenarios, information can be extracted based on the specific needs of each product category. For example, for insulating boots, based on product parameters and actual user requirements, the scenario information can be determined as 10KV live-line work. More specifically, it could be 10KV line emergency repair work. The level of detail can be adjusted as needed through a modular approach, such as providing a fixed scenario description based on parameter conditions, job type, and work type. Then, the three modules can be further refined based on the required level of detail. Of course, there are various methods for generating these word-filling modules. These could be based on semantic analysis of historical customer service data, big data analysis combining product usage data, or standardized question-and-answer patterns from customer service data.

[0041] Clustering of product parameter knowledge level information corresponding to different product categories forms different product parameter knowledge level clustered category sets. This includes: arbitrarily selecting one product category from different product categories and designating it as the baseline product category; using all product parameter knowledge level information corresponding to the baseline product category as a reference, traversing all different product categories; if all product parameter knowledge level information corresponding to a product category is identical to that corresponding to the baseline product category, then clustering the product category with the baseline product category; after traversing all product categories, extracting all clustered product categories; arbitrarily extracting one product category from the remaining un-clustered product categories and designating it as the baseline product category, repeating the clustering judgment for product categories to extract new clustered product categories; repeating the clustering analysis for the remaining un-clustered product categories until clustering of all product categories is completed; and determining the resulting different clustered product categories as the corresponding product parameter knowledge level clustered category sets.

[0042] Understandably, building a professional knowledge graph essentially involves clustering different product categories based on defined classification levels. A single product category may be applicable to multiple classification levels. Therefore, reasonable clustering of product categories during graph construction provides recommended product information based on the knowledge graph's classification levels. Here, the clustering method requires all classification levels to be identical to group different product categories together. Product categories generally share similar performance parameters, resulting in multiple product categories within each cluster. The product categories referred to here are series of products under a specific power grid professional category, such as insulating gloves, which includes a series of products meeting different key technical parameters. This is because a product category encompasses many specific products and equipment.

[0043] Product parameter knowledge level information includes, but is not limited to, technical standards, product parameters, and compliance rules. It should be noted that the classification level is determined by fully considering user needs; therefore, it can be based on extracting language features from historical customer service Q&A data to obtain information related to the performance parameters of the product category as classification level information. Alternatively, a direct definition can be used. This application, taking into full account the characteristics of the products, defines the classification level as including at least the technical standards followed by the product category, such as various manufacturing standards, product usage standards, and product functional standards; product performance parameters, such as voltage levels, mechanical strength, measurement accuracy range, and quantified values ​​of anti-interference capabilities; and product compliance rules, such as standards that must be equipped during use, such as Class II insulation tools. Furthermore, the classification level can be further refined based on different middleware platforms to ensure the completeness and comprehensiveness of the knowledge graph system and improve the accuracy and rationality of product category recommendations.

[0044] S2: Obtain historical user customer service data, extract corresponding profile information, form user profile information data corresponding to historical users, and label the power grid professional category knowledge graph to form a power grid professional category profile knowledge graph.

[0045] The process involves: acquiring historical user customer service data to extract corresponding profile information, forming user profile data for historical users, and then tagging the power grid professional category knowledge graph to form a power grid professional category profile knowledge graph. This includes: setting profile parameters and extracting profile information corresponding to the parameters based on historical user customer service data; determining all profile information corresponding to different product categories selected by historical users based on historical user customer service data; and tagging the profile information of different product categories in the power grid professional category knowledge graph based on all profile information corresponding to different product categories to form a power grid professional category profile knowledge graph.

[0046] The user profile-based tagging process for clustered product categories in a knowledge graph primarily involves assigning user preference attributes to these categories. This allows for further recommendations tailored to user needs and product category positioning, enhancing the accuracy of recommendations that meet those needs. It's important to note that user profiles can be extracted in various ways; this application employs a direct definition approach for precise and comprehensive control. The defined profile information includes, but is not limited to, job type, length of service, purchasing preferences (such as brand preferences), project content, and current project information (such as equipment model and voltage level in work orders). Of course, the profile information can be further refined based on specific circumstances to improve the accuracy of product category recommendations.

[0047] S3: Obtain the initial demand information of the target users, and combine it with the power grid professional category profile knowledge graph to conduct dialogue analysis for demand category positioning, and form demand dialogue information.

[0048] Obtain initial demand information from target users and combine it with the power grid professional category profile knowledge graph to conduct dialogue analysis targeting demand category positioning, forming demand dialogue information, including: extracting hierarchical information corresponding to product parameter knowledge level information and product scenario knowledge level information based on the initial demand information of target users, and conducting a correspondence check to form hierarchical information correspondence check results; and conducting demand category positioning analysis based on the hierarchical information correspondence check results to form demand dialogue information.

[0049] Once a professional category profile knowledge graph is established, the hierarchical information of the knowledge graph can be used to supplement the necessary information for product positioning and recommendation that was not provided in the initial demand information. This makes the customer service Q&A in the middle platform more targeted, efficient, and accurate. By comparing and verifying the initial demand information with the hierarchical information in the knowledge graph, it is determined whether the necessary demand information has been obtained. Then, reasonable demand Q&A data is formed in a targeted manner, ensuring that customer service Q&A obtains sufficient and necessary information.

[0050] Based on the results of the hierarchical information correspondence check, a demand category positioning analysis is performed to form demand dialogue information, including: if the hierarchical information correspondence check result is incomplete correspondence, the hierarchical information not extracted from the initial demand information is identified, the corresponding hierarchical information demand questions are formed, and all hierarchical information demand questions are combined to form demand dialogue information; if the hierarchical information correspondence check result is complete correspondence, all extracted hierarchical information is combined to form complete demand information data.

[0051] There are two main scenarios for checking the correspondence of initial request information. The first is where the initial request information does not fully match the hierarchical information of the knowledge graph, thus requiring completion. The second is where the initial information already contains complete hierarchical information matching the knowledge graph. For the first scenario, the required hierarchical information is determined through comparison and verification, forming the corresponding question-and-answer content. It's worth noting that the question-and-answer content can be pre-screened with specific sentence structures and content, or guided with specific formats for filling out and answering, thereby making the obtained information more accurate and efficient. Alternatively, the required hierarchical information can be used with AI to interact with users, improving the flexibility of question-and-answer interactions while enhancing customer service quality and information flexibility.

[0052] S4: Obtain demand feedback dialogue information based on demand dialogue information, and conduct targeted analysis of professional categories based on the target user's target profile information to form recommended professional category data.

[0053] The process involves acquiring demand feedback dialogue information based on demand dialogue information, and conducting targeted analysis of professional categories based on the target user's target profile information to generate recommended professional category data. This includes: if the hierarchical information correspondence check result is incomplete, extracting the hierarchical information not obtained from the initial demand information based on the demand feedback dialogue information, and determining different product parameter scenario knowledge graph clustering groups that match the product parameter knowledge hierarchical information and product scenario knowledge hierarchical information based on the power grid professional category knowledge graph; if the hierarchical information correspondence check result is complete, combining the complete demand information data and the power grid professional category knowledge graph, determining different product parameter scenario knowledge graph clustering groups that match the product parameter knowledge hierarchical information and product scenario knowledge hierarchical information. Based on the determined different product parameter scenario knowledge graph clustering groups, and combined with the target profile information, conducting targeted analysis to generate recommended professional category data.

[0054] After obtaining complete matching knowledge graph hierarchical information, matching can be performed based on this data to locate the product category clustered by the hierarchical information of the knowledge graph, which can effectively ensure that the located product category meets the user's needs.

[0055] Based on the determined product parameter scenario knowledge graph, product categories are clustered and targeted analysis is performed in conjunction with target profile information to form recommended professional category data. This includes: extracting the target profile information corresponding to all existing profile parameters based on the target profile information; and determining the product category with the most matches to different target profile information based on the target profile information and in conjunction with the power grid professional category profile knowledge graph, and labeling it as recommended professional category data.

[0056] While product category sets based on hierarchical data positioning generally meet user needs, different users also have specific requirements for product series within those categories. Filtering through user profiles can further enhance the personalization of recommended product categories. The matching method for user profile information prioritizes product categories with the highest number of matching profile information entries. However, these recommendations are only intended to provide users with a selection reference. When the number of optimal recommendations is limited, a certain number of product categories can be selected sequentially based on the number of matching profile information entries.

[0057] This invention also provides an intelligent customer service system for power grid professional categories based on middleware technology. The system includes: a data acquisition unit for acquiring power grid professional category product data, historical usage scenario data, historical user customer service data, and initial demand information of target users; a graph analysis unit for classifying and analyzing the power grid professional category product data and historical usage scenario data acquired by the data acquisition unit to establish a power grid professional category knowledge graph, and combining it with historical user customer service data for labeling to form a power grid professional category profile knowledge graph; and a question-and-answer analysis unit for performing dialogue analysis based on the initial demand information of target users acquired by the data acquisition unit and the power grid professional category profile knowledge graph formed by the graph analysis unit, forming demand dialogue information, acquiring demand feedback dialogue information, and performing targeted analysis to generate recommended professional category data.

[0058] This system collects intelligent customer service Q&A data through a data acquisition unit and establishes a professional knowledge graph using a graph analysis unit, while also labeling product categories to enhance data personalization. The Q&A analysis unit processes the Q&A dialogue appropriately using target user needs information and obtains necessary demand information, thereby enabling more accurate and reasonable selection and positioning of product categories. The different functional units are interconnected, forming an organic whole for intelligent customer Q&A, which is a crucial material foundation for realizing intelligent customer service Q&A based on middleware technology.

[0059] In summary, the beneficial effects of the intelligent customer service system and question-and-answer method for power grid professional categories based on middleware technology provided by the embodiments of the present invention are as follows:

[0060] This method establishes a classification of product demand characteristics with application scenario attributes by acquiring power grid professional product category data and historical usage scenario data. It also creates a professional knowledge graph suitable for demand decomposition and selection. At the same time, it combines historical user customer service data to label the user profile characteristics of product categories. This gives product categories under the professional knowledge graph data further characteristic markings of user tendencies, providing a clearer and more structured customer service Q&A reference for subsequent demand conversion analysis targeting target users. This enables efficient completion and confirmation of demand information during intelligent Q&A, and also allows for accurate positioning of professional categories suitable for target users based on customer service Q&A data, making the products that meet the needs more reasonable and precise.

[0061] This system collects intelligent customer service Q&A data through a data acquisition unit and establishes a professional knowledge graph using a graph analysis unit, while also labeling product categories to enhance data personalization. The Q&A analysis unit processes the Q&A dialogue appropriately using target user needs information and obtains necessary demand information, thereby enabling more accurate and reasonable selection and positioning of product categories. The different functional units are interconnected, forming an organic whole for intelligent customer Q&A, which is a crucial material foundation for realizing intelligent customer service Q&A based on middleware technology.

[0062] In the embodiments of this application, "instruction" can include direct and indirect instructions, as well as explicit and implicit instructions. The information indicated by a certain piece of information is called the information to be instructed. In the specific implementation process, there are many ways to instruct the information to be instructed, such as, but not limited to, directly instructing the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly instruct the information to be instructed by instructing other information, where there is a relationship between the other information and the information to be instructed. It can also instruct only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent. At the same time, common parts of various pieces of information can be identified and uniformly indicated to reduce the instruction overhead caused by individually indicating the same information.

[0063] Furthermore, the specific indication method can also be any existing indication method, such as, but not limited to, the above-mentioned indication methods and their various combinations. Specific details of various indication methods can be found in existing technologies, and will not be repeated here. As described above, for example, when multiple pieces of information of the same type need to be indicated, the indication methods for different pieces of information may differ. In the specific implementation process, the required indication method can be selected according to specific needs. This application embodiment does not limit the selected indication method; therefore, the indication methods involved in this application embodiment should be understood to cover various methods that enable the party to be indicated to obtain the information to be indicated.

[0064] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information messages sent separately, and the sending period and / or timing of these sub-information messages can be the same or different. The specific sending method is not limited in this application embodiment. The sending period and / or timing of these sub-information messages can be predefined, for example, according to a protocol, or configured by the sending device by sending configuration information to the receiving device.

[0065] "Predefined" or "pre-configured" can be achieved by pre-saving corresponding codes, tables, or other means that can be used to indicate relevant information in the device. This application does not limit the specific implementation method. "Saving" can refer to saving in one or more memories. These memories can be separate installations or integrated into the encoder, decoder, processor, or communication device. Alternatively, some memories can be separately installed, while others are integrated into the decoder, processor, or communication device. The type of memory can be any form of storage medium, and this application does not limit this.

[0066] The “protocol” mentioned in the embodiments of this application may refer to a protocol family in the field of communication, a standard protocol with a similar protocol family frame structure, or a related protocol applied to future communication systems. The embodiments of this application do not specifically limit this.

[0067] In the embodiments of this application, descriptions such as "when," "under the circumstances," "if," and "if" all refer to the device making corresponding processing under certain objective circumstances, and are not limited to a specific time. They do not require the device to make a judgment action during implementation, nor do they imply any other limitations.

[0068] In the description of the embodiments of this application, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can represent A or B. "And / or" in the embodiments of this application is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. Furthermore, in the description of the embodiments of this application, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple. Additionally, to facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first," "second," etc., do not limit the quantity or order of execution, and that "first," "second," etc., are not necessarily different. Furthermore, in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate that something is being used as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.

[0069] It should be understood that the processor in the embodiments of this application can be a central processing unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0070] It should also be understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0071] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0072] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0073] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0074] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0075] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0076] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0077] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0078] 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 this embodiment according to actual needs.

[0079] In addition, the functional units in the various embodiments of this application 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.

[0080] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0081] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A smart customer service question-and-answer method for power grid professional categories based on middleware technology, characterized in that, include: Acquire product data and historical usage scenario data for power grid professional categories, conduct classification analysis reflecting demand characteristics, and establish a knowledge graph for power grid professional categories; Historical user customer service data is obtained to extract corresponding profile information, forming user profile information data corresponding to historical users. The power grid professional category knowledge graph is then labeled to form a power grid professional category profile knowledge graph. Obtain the initial demand information of the target user, and combine it with the power grid professional category profile knowledge graph to conduct dialogue analysis based on the demand category positioning, and form demand dialogue information; Obtain demand feedback dialogue information based on the demand dialogue information, and perform targeted analysis of professional categories based on the target user's target profile information to generate recommended professional category data.

2. The intelligent customer service question-and-answer method for power grid professional categories based on middleware technology according to claim 1, characterized in that, The process of acquiring power grid professional product category data and historical usage scenario data, performing classification analysis reflecting demand characteristics, and establishing a power grid professional product category knowledge graph includes: Based on the power grid professional product data, extract the product parameter knowledge level information corresponding to different product categories; Cluster the product parameter knowledge hierarchy information corresponding to different product categories to form different product parameter knowledge hierarchy clustering category sets; Based on the historical usage scenario data, extract product scenario knowledge level information corresponding to different product categories; Clustering is performed on different product categories in different product parameter knowledge level clustering categories based on product scenario knowledge level information to form different product parameter scenario knowledge graph clustering categories in the corresponding product parameter knowledge level clustering categories; Based on the different product parameter scenario knowledge graph clustering categories in all the different product parameter knowledge level clustering categories, and with the product parameter knowledge level information and the product scenario knowledge level information as references, a power grid professional category knowledge graph containing all the product parameter scenario knowledge graph clustering categories is formed.

3. The intelligent customer service question-and-answer method for power grid professional categories based on middleware technology according to claim 2, characterized in that, The process of clustering the product parameter knowledge hierarchy information corresponding to different product categories to form different product parameter knowledge hierarchy clustering category sets includes: Select any product category from the different product categories and designate it as the benchmark product category; Using the knowledge level information of all product parameters corresponding to the benchmark product category as a reference, all different product categories are traversed. If all the knowledge level information of all product parameters corresponding to a product category is the same as that of all product parameters corresponding to the benchmark product category, then the product category is clustered with the benchmark product category. After traversing all product categories, extract all clustered product categories. For the remaining un-clustered product categories, arbitrarily extract one product category and label it as the baseline product category. Repeat the clustering judgment for product categories to extract new clustered product categories. Repeat the cluster analysis on the remaining unclustered product categories until clustering of all product categories is completed; The different clustered product categories are identified as corresponding product parameter knowledge level clustered product category sets.

4. The intelligent customer service question-and-answer method for power grid professional categories based on middleware technology according to claim 2, characterized in that, The product parameter knowledge hierarchy information includes, but is not limited to: technical standards, product parameters, and compliance rules.

5. The intelligent customer service question-and-answer method for power grid professional categories based on middleware technology according to claim 4, characterized in that, The process of obtaining historical user customer service data to extract corresponding profile information, forming user profile information data corresponding to historical users, and then labeling the power grid professional category knowledge graph to form a power grid professional category profile knowledge graph includes: Set profile parameters, and extract profile information corresponding to the profile parameters based on the historical user customer service data; Based on the historical user customer service data, all the profile information corresponding to the different product categories selected by the historical users is determined; Based on all the profile information corresponding to different product categories, the profile information of different product categories in the power grid professional category knowledge graph is labeled to form the power grid professional category profile knowledge graph.

6. The intelligent customer service question-and-answer method for power grid professional categories based on middleware technology according to claim 5, characterized in that, The process involves obtaining the initial demand information of the target user and combining it with the power grid professional category profile knowledge graph to perform dialogue analysis targeting the demand category, thereby forming demand dialogue information, including: Based on the initial demand information of the target user, extract the hierarchical information corresponding to the product parameter knowledge hierarchy information and the product scenario knowledge hierarchy information, perform a correspondence check, and form a hierarchical information correspondence check result. Based on the results of the hierarchical information correspondence check, a demand category positioning analysis is performed to generate the demand dialogue information.

7. The intelligent customer service Q&A method for power grid professional categories based on middleware technology according to claim 6, characterized in that, The step of performing demand category positioning analysis based on the corresponding results of the hierarchical information to form the demand dialogue information includes: If the result of the hierarchical information correspondence check is an incomplete correspondence, then the hierarchical information that was not extracted from the initial requirement information is identified, the corresponding hierarchical information requirement question is formed, and all hierarchical information requirement questions are collected to form the requirement dialogue information. If the result of the hierarchical information correspondence check is a complete correspondence, then all extracted hierarchical information is collected to form the required complete information data.

8. The intelligent customer service question-and-answer method for power grid professional categories based on middleware technology according to claim 7, characterized in that, The process of acquiring demand feedback dialogue information based on the demand dialogue information, and performing targeted analysis of professional categories based on the target user's target profile information to form recommended professional category data, includes: If the result of the hierarchical information correspondence check is an incomplete correspondence, the hierarchical information not obtained from the initial demand information is extracted according to the demand feedback dialogue information, and the different product parameter scenario knowledge graph clustering category groups that correspond to and match the product parameter knowledge hierarchical information and the product scenario knowledge hierarchical information are determined according to the power grid professional category knowledge graph. If the correspondence check result of the hierarchical information is a complete correspondence, then, combining the complete information data of the requirements and the knowledge graph of the power grid professional categories, the different clustering categories of the product parameter scenario knowledge graph that correspond to and match the product parameter knowledge hierarchical information and the product scenario knowledge hierarchical information are determined. Based on the determined product parameter scenarios, the product categories are clustered using a knowledge graph, and targeted analysis is performed in conjunction with the target profile information to generate recommended professional category data.

9. The intelligent customer service question-and-answer method for power grid professional categories based on middleware technology according to claim 8, characterized in that, The process involves clustering product categories based on the determined product parameter scenarios using a knowledge graph, and then performing targeted analysis in conjunction with the target profile information to generate recommended professional category data, including: Based on the target profile information, extract the target profile information corresponding to all existing profile parameters; Based on the target profile information and combined with the power grid professional category profile knowledge graph, the product category that matches the most different target profile information is identified and marked as the recommended professional category data.

10. A smart customer service system for power grid professional categories based on middleware technology, employing the smart customer service question-and-answer method for power grid professional categories based on middleware technology as described in any one of claims 1-9, characterized in that, include: The data acquisition unit is used to acquire data on power grid professional product categories, historical usage scenario data, historical user customer service data, and initial demand information of target users. The graph analysis unit is used to classify and analyze the power grid professional category product data and historical usage scenario data obtained by the data acquisition unit to establish a power grid professional category knowledge graph, and to perform labeling processing in combination with historical user customer service data to form a power grid professional category profile knowledge graph. The question-and-answer analysis unit is used to perform dialogue analysis based on the initial demand information of the target user obtained by the data acquisition unit and the power grid professional category profile knowledge graph formed by the graph analysis unit, to form demand dialogue information, obtain demand feedback dialogue information, and perform targeted analysis to form recommended professional category data.

Images