Intelligent recommendation system based on big data in city-wide life service system

Abstract

The invention provides an intelligent recommendation system based on big data in a city-wide life service system, which is characterized by comprising a data information storage module, a service classification management module, an application recommendation matching module and a service feedback scoring module, the data information storage module comprises a client information storage unit, a server information storage unit and an information registration management unit, the client information storage unit is used for storing buyer user information requiring life service, and the server information storage unit is used for storing seller user information providing life service; the information registration management unit is used for registering user information; according to the system, historical data of the user can be analyzed, hidden preference features irrelevant to service items can be mined, appropriate recommendation information can be given, and the user can be helped to obtain good service experience more quickly.

Description

Technical Field

[0001] The present invention relates to the field of electric digital data processing, and more particularly to an intelligent recommendation system based on big data in an urban life service system. Background Art

[0002] With the popularization of Internet technology and mobile devices, the urban life service industry has developed rapidly. Users' demand for personalized, efficient and convenient services has increased day by day. Most traditional urban life service platforms adopt keyword search or simple classification-based recommendations, which are difficult to meet the diverse needs of users. Therefore, an intelligent recommendation system is needed that can accurately identify users' needs and improve the accuracy and efficiency of service matching.

[0003] The foregoing discussion of the background art is only intended to facilitate an understanding of the present invention. This discussion does not recognize or admit that any of the materials mentioned is part of the common general knowledge.

[0004] Many service recommendation systems have now been developed. After a large amount of retrieval and reference, it is found that existing service recommendation systems are like the system disclosed in Publication No. CN113392291B. These systems generally include obtaining employee behavior data in a project center; obtaining an employee behavior map based on the behavior data, establishing a connection between the constructed structured behavior map and each service project, and performing user preference clustering; obtaining service recommendation results according to the clustering results and a preset random forest regression model; however, this system only analyzes the service project preferences of users and cannot recommend more appropriate object information when determining service projects, and the service experience obtained requires multiple attempts. Summary of the Invention

[0005] The object of the present invention is to propose an intelligent recommendation system based on big data in an urban life service system for the existing deficiencies.

[0006] The present invention adopts the following technical solutions:

[0007] An intelligent recommendation system based on big data in an urban life service system includes a data information storage module, a service classification management module, an application recommendation matching module, and a service feedback scoring module;

[0008] The data information storage module includes a client information storage unit, a server information storage unit, and an information registration management unit. The client information storage unit is used to store the information of buyer users who need life services, the server information storage unit is used to store the information of seller users who provide life services, and the information registration management unit is used to register user information;

[0009] The service classification management module includes a service classification engine unit, a user classification execution unit, and a same-category sorting and output unit. The service classification engine unit is used to build classification rules. The user classification execution unit classifies server users based on the classification rules. The same-category sorting and output unit is used to output the sorting information of users of the same service type.

[0010] The application recommendation and matching module includes an application selection interaction unit, a personal feature analysis unit, and a service-user matching unit. The application selection interaction unit is used to select application services. The personal feature analysis unit is used to extract features from the historical information of buyer users. The service-user matching unit matches seller users based on the feature information.

[0011] The service feedback and scoring module includes a feedback information interaction unit, a feedback information analysis unit, and a seller information correction unit. The feedback information interaction unit is used to submit service feedback information from buyer users. The feedback information analysis unit is used to analyze the reliability of the feedback information. The seller information correction unit is used to adjust the scoring information in the seller information.

[0012] Furthermore, the personal feature analysis unit includes a data extraction processor, a portrait modeling processor, and a weight output processor. The data extraction processor is used to extract features from the historical behavior data of users. The portrait modeling processor is used to build user portraits. The weight output processor is used to output the preference weights of users.

[0013] Furthermore, the portrait modeling processor generates behavior tags based on the extracted behavior data, sorts the behavior tags from the highest to the lowest frequency of occurrence, and retains the tags with the highest ranking as portrait tags. The portrait tags form the user portrait. The weight output processor calculates the weight coefficient of each portrait tag according to the following formula:

[0014]

[0015] where F is the frequency of occurrence of the portrait tag, S is the sorting serial number of the portrait tag, λ is the attenuation rate, t is the most recent occurrence time of the portrait tag, and e is the natural constant.

[0016] Furthermore, the service-user matching unit includes a matching information receiving processor, a merchant matching calculation processor, and a service contract docking processor. The matching information receiving processor is used to receive data information related to matching calculations. The merchant matching calculation processor is used to calculate the matching degree of merchants. The service contract docking processor is used to select merchants and generate service contracts.

[0017] Furthermore, the merchant matching calculation processor calculates the adaptability P between the merchant and the portrait tag according to the following formula:

[0018]

[0019] Among them, m is the number of merchant sorting items, and k i is the correlation coefficient between the i-th sorting item and the portrait label, N is the number of valid merchants of the i-th sorting item, and n(i) is the serial number of the merchant in the i-th sorting item;

[0020] The merchant matching calculation processor calculates the matching degree Q between the merchant and the user according to the following formula:

[0021]

[0022] Among them, M is the number of portrait labels, W(i) is the weight coefficient of the i-th portrait label, and P(i) is the adaptation degree between the merchant and the i-th portrait label.

[0023] The beneficial effects achieved by the present invention are:

[0024] Through user portrait modeling and behavioral data analysis, this system accurately identifies user needs and realizes personalized recommendation. By adopting a multi-dimensional weighted matching algorithm and comprehensively considering factors such as user preferences, historical behaviors, merchant ratings, and service types, the accuracy of matching is improved. It can effectively enhance the intelligence, accuracy, and user experience of local life services, realize personalized recommendation, dynamic optimization, and intelligent management, provide more convenient and efficient local services for users, and at the same time improve the operation efficiency and competitiveness of the platform.

[0025] To further understand the features and technical content of the present invention, please refer to the following detailed description and drawings of the present invention. However, the provided drawings are only for reference and illustration, and are not used to limit the present invention. Description of the Drawings

[0026] Figure 1 is a schematic diagram of the overall structural framework of the present invention;

[0027] Figure 2 is a schematic diagram of the composition of the service classification management module of the present invention;

[0028] Figure 3 is a schematic diagram of the composition of the application recommendation matching module of the present invention;

[0029] Figure 4 is a schematic diagram of the composition of the service feedback scoring module of the present invention;

[0030] Figure 5 is a schematic diagram of the composition of the service user matching unit of the present invention;

[0031] Figure 6 is a comparison diagram of the usage effects of the present invention system and a general system. Detailed Implementation Modes

[0032] The following are specific embodiments to illustrate the implementation modes of the present invention. Those skilled in the art can understand the advantages and effects of the present invention from the content disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and various details in this specification can also be modified and changed based on different viewpoints and applications without departing from the spirit of the present invention. Additionally, the drawings of the present invention are only for simple schematic illustration and are not drawn according to actual dimensions. This is stated in advance. The following implementation modes will further detail the relevant technical content of the present invention, but the disclosed content is not used to limit the protection scope of the present invention.

[0033] Embodiment 1.

[0034] This embodiment provides an intelligent recommendation system based on big data in an urban life service system, combined with Figure 1 , including a data information storage module, a service classification management module, an application recommendation matching module, and a service feedback scoring module;

[0035] The data information storage module includes a client information storage unit, a server information storage unit, and an information registration management unit. The client information storage unit is used to store the information of buyer users who need life services. The server information storage unit is used to store the information of seller users who provide life services. The information registration management unit is used to register user information;

[0036] The service classification management module includes a service classification engine unit, a user classification execution unit, and a same-category sorting output unit. The service classification engine unit is used to build classification rules. The user classification execution unit classifies server users based on the classification rules. The same-category sorting output unit is used to output the sorting information of users of the same type of service;

[0037] The application recommendation matching module includes an application selection interaction unit, a personal feature analysis unit, and a service-user matching unit. The application selection interaction unit is used to select application services. The personal feature analysis unit is used to extract features from the historical information of buyer users. The service-user matching unit matches seller users based on the feature information;

[0038] The service feedback scoring module includes a feedback information interaction unit, a feedback information analysis unit, and a seller information correction unit. The feedback information interaction unit is used to submit the service feedback information of buyer users. The feedback information analysis unit is used to analyze the reliability of the feedback information. The seller information correction unit is used to adjust the scoring information in the seller information.

[0039] The personal feature analysis unit includes a data extraction processor, a portrait modeling processor, and a weight output processor. The data extraction processor is used to extract features from the historical behavior data of the user. The portrait modeling processor is used to establish a user portrait. The weight output processor is used to output the preference weights of the user.

[0040] The portrait modeling processor generates behavior labels based on the extracted behavior data, sorts the behavior labels in descending order according to the occurrence frequency, and retains the labels with higher rankings as portrait labels. The portrait labels constitute the user portrait. The weight output processor calculates the weight coefficient of each portrait label according to the following formula:

[0041]

[0042] where F is the occurrence frequency of the portrait label, S is the sorting serial number of the portrait label, λ is the attenuation rate, t is the most recent occurrence time of the portrait label, and e is the natural constant.

[0043] The service user matching unit includes a matching information receiving processor, a merchant matching calculation processor, and a service contract docking processor. The matching information receiving processor is used to receive data information related to matching calculations. The merchant matching calculation processor is used to calculate the matching degree of the merchant. The service contract docking processor is used to select a merchant and generate a service contract.

[0044] The merchant matching calculation processor calculates the adaptability P between the merchant and the portrait label according to the following formula:

[0045]

[0046] where m is the number of merchant sorting items, k i is the correlation coefficient between the i-th sorting item and the portrait label, N is the number of valid merchants for the i-th sorting item, and n(i) is the serial number of the merchant in the i-th sorting item;

[0047] The merchant matching calculation processor calculates the matching degree Q between the merchant and the user according to the following formula:

[0048]

[0049] where M is the number of portrait labels, W(i) is the weight coefficient of the i-th portrait label, and P(i) is the adaptability between the merchant and the i-th portrait label.

[0050] Embodiment 2.

[0051] This embodiment includes all the content of Embodiment 1 and provides an intelligent recommendation system based on big data in an urban life service system, which includes a data information storage module, a service classification management module, an application recommendation matching module, and a service feedback scoring module;

[0052] The data information storage module includes a client information storage unit, a server information storage unit, and an information registration management unit. The client information storage unit is used to store the information of buyer users who need life services. The server information storage unit is used to store the information of seller users who provide life services. The information registration management unit is used to register user information;

[0053] Combined with Figure 2 , the service classification management module includes a service classification engine unit, a user classification execution unit, and a same-category sorting output unit. The service classification engine unit is used to build-in classification rules. The user classification execution unit is used to classify server users based on the classification rules. The same-category sorting output unit is used to output the sorting information of users of the same type of service;

[0054] Combined with Figure 3 , the application recommendation matching module includes an application selection interaction unit, a personal feature analysis unit, and a service-user matching unit. The application selection interaction unit is used to select application services. The personal feature analysis unit is used to extract features from the historical information of buyer users. The service-user matching unit matches seller users based on the feature information;

[0055] Combined with Figure 4 , the service feedback scoring module includes a feedback information interaction unit, a feedback information analysis unit, and a seller information correction unit. The feedback information interaction unit is used to submit the service feedback information of buyer users. The feedback information analysis unit is used to analyze the reliability of the feedback information. The seller information correction unit is used to adjust the scoring information in the seller information;

[0056] The client information storage unit includes a user information register, a behavior record processor, and a privacy protection processor. The user information register is used to store the basic information of buyer users. The behavior record processor is used to collect the operation information of buyer users on this system. The privacy protection processor is used to encrypt and store the sensitive information of buyer users;

[0057] The server information storage unit includes a merchant information register, a service record processor, and a qualification review processor. The merchant information register is used to store the basic information of seller users. The service record processor is used to collect the service information of seller users on this system. The qualification review processor is used to review the certificates of merchants;

[0058] The information registration and management unit includes a registration interaction processor, an identity authentication processor, and a storage space application processor. The registration interaction processor is used to provide a registration interface and collect registration information. The identity authentication processor is used to perform real-name authentication on users. The storage space application processor applies for storage space in the corresponding register based on the user type;

[0059] The service classification engine unit includes a service definition processor, a feature setting processor, and a rule mapping processor. The service definition processor is used to define each service item. The feature setting processor is used to set feature items. The rule mapping processor is used to set the mapping rules between feature items and service items;

[0060] The user classification execution unit includes a label generation processor, a category division processor, and a centralized management processor. The label generation processor is used to generate feature labels included in a merchant. The category division processor divides the merchant into corresponding service categories based on the mapping rules. The centralized management processor is used to centrally manage the storage addresses of merchants in the same category;

[0061] The same-category sorting and output unit includes a task receiving processor, a merchant retrieval processor, and a sorting and output processor. The task receiving processor is used to accept an output task. The merchant retrieval processor retrieves corresponding merchant information based on the output task. The sorting and output processor outputs sorting information based on the output task and the merchant information;

[0062] The application selection and interaction unit includes an interface interaction processor, a detailed information display processor, and a confirmation output processor. The interface interaction processor is used to display an interaction interface and process interaction information. The detailed information display processor is used to display the detailed information of a merchant. The confirmation output processor is used to output task information after confirming the service content;

[0063] The personal feature analysis unit includes a data extraction processor, a portrait modeling processor, and a weight output processor. The data extraction processor is used to extract features from the historical behavior data of a user. The portrait modeling processor is used to build a user portrait. The weight output processor is used to output the preference weight of the user;

[0064] The portrait modeling processor generates behavior labels based on the extracted behavior data, sorts the behavior labels from largest to smallest according to the occurrence frequency, and retains the top-ranked labels as portrait labels. The portrait labels constitute the user portrait. The weight output processor calculates the weight coefficient of each portrait label according to the following formula:

[0065]

[0066] Wherein, F is the occurrence frequency of the image label, S is the sorting serial number of the image label, λ is the attenuation rate, t is the most recent occurrence time of the image label, and e is the natural constant;

[0067] The occurrence of the image label means that the user has performed an act containing the image label;

[0068] Combined with Figure 5 , the service user matching unit includes a matching information receiving processor, a merchant matching calculation processor, and a service contract docking processor. The matching information receiving processor is used to receive data information related to matching calculation, the merchant matching calculation processor is used to calculate the matching degree of the merchant, and the service contract docking processor is used to select the merchant and generate a service contract;

[0069] The matching information received by the matching information receiving processor is the sorting information output by the same type sorting output unit and the weight coefficient information of the image label;

[0070] The merchant matching calculation processor calculates the adaptation degree P between the merchant and the image label according to the following formula:

[0071]

[0072] Wherein, m is the number of merchant sorting items, k i is the correlation coefficient between the i-th sorting item and the image label, N is the number of valid merchants of the i-th sorting item, and n(i) is the serial number of the merchant in the i-th sorting item;

[0073] The merchant matching calculation processor calculates the matching degree Q between the merchant and the user according to the following formula:

[0074]

[0075] Wherein, M is the number of image labels, W(i) is the weight coefficient of the i-th image label, and P(i) is the adaptation degree between the merchant and the i-th image label;

[0076] The service contract processor sorts the merchants in descending order of the matching degree and displays them to the user for selection;

[0077] The feedback information interaction unit includes a service end monitoring processor, a feedback information collection processor, and a feedback packaging processor. The service end monitoring processor is used to monitor the service progress and open the feedback channel at the end. The feedback information collection processor is used to collect the user's feedback information in the feedback channel, and the feedback packaging processor is used to package the feedback information and send it to the feedback information analysis unit;

[0078] The feedback information analysis unit includes a basic sentiment analysis processor, a user feature correction processor, and an effective evaluation output processor. The basic sentiment analysis processor is used to analyze the basic score of the feedback information. The user feature correction processor performs correction analysis on the basic score based on the user's historical feedback features. The effective evaluation output processor is used to output effective evaluation information;

[0079] The user feature correction processor calculates the user's correction coefficient α according to the following formula:

[0080]

[0081] where b is the user's negative review rate, Bn is the number of the user's negative reviews, a(i) is the negative review rate of the i-th negative review object, c is the fluctuation range, and ε is a decimal to prevent zero;

[0082] When the correction coefficient is less than the threshold, the effective evaluation output processor determines that the feedback information is invalid information. Otherwise, it calculates the effective score value V according to the following formula:

[0083] V = V0·(2 - α·b);

[0084] where V0 is the basic score;

[0085] The seller information correction unit includes a score adjustment processor, a reputation management processor, and a malicious measure processor. The score adjustment processor is used to adjust the user's score information. The reputation management processor is used to manage the user's reputation status. The malicious measure processor is used to take trigger measures against merchants in a malicious state;

[0086] The i appearing in the above text is an ordinal number used to represent the serial number and has no actual meaning.

[0087] Part of the code information of this system is as follows:

[0088]

[0089]

[0090]

[0091]

[0092] Now, multiple users are selected to test 3 service items. The number of service times required for the users to repeatedly select merchants under the same service item is statistically obtained, and the mean values are statistically obtained and processed under this system and a general system respectively, obtaining Figure 6 the comparison chart shown.

[0093] The content disclosed above is only a preferred and feasible embodiment of the present invention, and does not limit the protection scope of the present invention. Therefore, all equivalent technical changes made by using the content of the specification and drawings of the present invention are included in the protection scope of the present invention. In addition, with the development of technology, the elements therein can be updated.

Claims

1. An intelligent recommendation system based on big data in a same-city life service system, characterized in that, It includes a data information storage module, a service classification management module, an application recommendation matching module, and a service feedback scoring module; The data information storage module includes a client information storage unit, a server information storage unit, and an information registration management unit. The client information storage unit is used to store the information of buyer users who need life services. The server information storage unit is used to store the information of seller users who provide life services. The information registration management unit is used to register user information; The service classification management module includes a service classification engine unit, a user classification execution unit, and a same-category sorting output unit. The service classification engine unit is used to build-in classification rules. The user classification execution unit classifies the server users based on the classification rules. The same-category sorting output unit is used to output the sorting information of users of the same type of service; The application recommendation matching module includes an application selection interaction unit, a personal feature analysis unit, and a service-user matching unit. The application selection interaction unit is used to select application services. The personal feature analysis unit is used to extract features from the historical information of buyer users. The service-user matching unit matches seller users based on the feature information; The service feedback scoring module includes a feedback information interaction unit, a feedback information analysis unit, and a seller information correction unit. The feedback information interaction unit is used to submit the service feedback information of buyer users. The feedback information analysis unit is used to analyze the reliability of the feedback information. The seller information correction unit is used to adjust the scoring information in the seller information.

2. The intelligent recommendation system based on big data in a same-city life service system according to claim 1, wherein The personal feature analysis unit includes a data extraction processor, a portrait modeling processor, and a weight output processor. The data extraction processor is used to extract features from the historical behavior data of users. The portrait modeling processor is used to build user portraits. The weight output processor is used to output the preference weights of users.

3. The intelligent recommendation system based on big data in a same-city life service system according to claim 2, wherein The portrait modeling processor generates behavior tags based on the extracted behavior data, sorts them from largest to smallest according to the occurrence frequency of the behavior tags, and retains the tags with the highest ranking as portrait tags. The portrait tags constitute the user portrait. The weight output processor calculates the weight coefficient of each portrait tag according to the following formula: Where F is the occurrence frequency of the portrait tag, S is the sorting serial number of the portrait tag, λ is the attenuation rate, t is the most recent occurrence time of the portrait tag, and e is the natural constant.

4. The intelligent recommendation system based on big data in a same-city life service system according to claim 1, characterized in that, The service-user matching unit includes a matching information receiving processor, a merchant matching calculation processor, and a service contract docking processor. The matching information receiving processor is used to receive data information related to matching calculations. The merchant matching calculation processor is used to calculate the matching degree of merchants. The service contract docking processor is used to select merchants and generate service contracts.

5. The intelligent recommendation system based on big data in a same-city life service system according to claim 4, wherein The merchant matching calculation processor calculates the adaptation degree P between the merchant and the portrait tag according to the following formula: where m is the number of merchant sorting items, and k i is the correlation coefficient between the i-th sorting item and the portrait label, N is the number of valid merchants for the i-th sorting item, and n(i) is the serial number of the merchant in the i-th sorting item; The merchant matching calculation processor calculates the matching degree Q between the merchant and the user according to the following formula: Where M is the number of portrait tags, W(i) is the weight coefficient of the i-th portrait tag, and P(i) is the adaptation degree between the merchant and the i-th portrait tag.

Images