Localized service recommendation system and method based on hotel guest room service robot

Abstract

The invention discloses a localized service recommendation system based on a hotel guest room service robot, and the system comprises a geographic position recognition module which is used for obtaining the information of the current position of a customer, and comprises a GPS module and a Wi-Fi module; the localized service database module is used for storing local scenic spots, food, specialty products, shopping information, local characteristic activities, recommended scenic spots and hot restaurant content; the personalized preference analysis module is used for analyzing personalized preferences of clients; the intelligent recommendation algorithm module is used for generating recommendation content meeting customer requirements by adopting an intelligent recommendation algorithm on the basis of customer positions, personalized preferences and a localized service database; the real-time interaction and feedback module performs real-time interaction with the client through the robot, adjusts recommendation content according to feedback and selection of the client, and optimizes a recommendation result; according to the localized service recommendation system based on the hotel guest room service robot, preferences of customers can be known, so that more accurate localized service recommendation is provided, and the experience of the customers during hotel accommodation is greatly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to a hotel room service robot-based localized service recommendation system and method. BACKGROUND

[0002] A hotel room service robot is an intelligent device with advanced artificial intelligence technology. Its original design is to provide comprehensive, efficient and convenient services in hotel rooms. Through a precise navigation system, this robot can autonomously move in the hotel room, accurately reach the designated location of the customer, and complete various tasks such as food delivery and item distribution.

[0003] With the development of technology, the functions of hotel room service robots are becoming increasingly rich. In addition to basic movement and positioning functions, some robots also have hotel booking, renewal and cancellation services. However, there is a shortcoming in the hotel room service robots currently on the market, which is the lack of localized service recommendation function. This means that when customers need to know and choose local food, scenic spots, entertainment and other activities, the robot cannot provide targeted recommendations.

[0004] Although some hotel room service robots have achieved localized service recommendations, they still need to improve in personalized recommendations. Due to the lack of in-depth understanding of customers' living habits and preferences, these robots cannot accurately recommend local services that meet customers' needs. This undoubtedly reduces the customer experience and limits the development space of hotel room service robots. SUMMARY

[0005] To overcome the shortcomings of the prior art, the present application aims to provide a hotel room service robot-based localized service recommendation system and method that can understand customers' preferences and provide more accurate localized service recommendations, greatly improving customers' experience during their stay at the hotel.

[0006] The technical solution adopted by the present application to solve its technical problems is: A hotel room service robot-based localized service recommendation system, comprising: a geographic position recognition module for obtaining information about the current location of the customer, including a GPS module and a Wi-Fi module; a localized service database module for storing local scenic spots, food, specialties, shopping information, and local characteristic activities, recommended scenic spots, and popular restaurants; a personalized preference analysis module for analyzing customers' personalized preferences; an intelligent recommendation algorithm module that generates recommended content that meets customers' needs based on their location, personalized preferences and localized service database using an intelligent recommendation algorithm; Real-time interaction and feedback module: real-time interaction between the robot and the customer, adjusting the recommended content according to the customer's feedback and selection, optimizing the recommended results.

[0007] Another technical problem to be solved by the present application is to provide a localized service intelligent recommendation method based on a hotel room service robot, comprising the following steps: When the customer interacts with the robot, the customer's location is obtained through the geographic position recognition module; According to the customer's location and the local service database, the information of the nearby scenic spots, food, specialties and shopping is filtered out; Combined with the personalized preference analysis module, the content that meets the customer's preferences is filtered out; Using the intelligent recommendation algorithm module, the recommended content that best meets the customer's needs is generated and displayed to the customer; According to the customer's feedback and selection, the recommended content is adjusted for secondary recommendation.

[0008] As a preferred method for obtaining the customer's location through the geographic position recognition module: Connect the GPS module to the main control board or processor of the robot; Write a program to communicate with the GPS module through a serial port or other communication interface; Receive the location information sent by the GPS module and parse the geographic position data such as latitude and longitude; Connect the Wi-Fi module to the main control board or processor of the robot; Write a program to scan the surrounding Wi-Fi signals and obtain relevant information such as signal strength and MAC address; Analyze the Wi-Fi signal data to determine the customer's current location information; Use data fusion algorithm to integrate and process GPS and Wi-Fi data; According to the location information obtained by GPS and Wi-Fi, determine the customer's current location.

[0009] As a preferred method for filtering out the information of scenic spots, food, specialties and shopping near the customer's location: Query the location data and detailed description of each scenic spot, food, specialty and shopping information stored in the local service database; Compare the customer's location with the location of each scenic spot, food, specialty and shopping information, and calculate the distance between them; Set a range or radius r to filter out the scenic spots, food, specialties and shopping information within this range from the customer's location.

[0010] As a preferred, in combination with the personalized preference analysis module, the method of filtering out the content meeting the customer's preference is: According to the customer's needs and preferences, the filtered scenic spots, food, specialties, shopping information are classified and filtered, and only specific types of scenic spots, food, specialties, shopping information are displayed; According to the distance from the customer's location or the score, the filtered information is sorted; The nearby scenic spots, food, specialties, shopping information at the back of the sorting are filtered out.

[0011] As a preferred, the method of using intelligent recommendation algorithm module to generate the recommended content most meeting the customer's needs and display it to the customer is: Collect the content attribute information of the item; Collect the customer's preference information; Extract the features of the content attributes of the item, and use natural language processing technology to extract keywords and topics; According to the customer's preference information, calculate the weight of each feature for the customer; For each item j, multiply the content attribute features of the item with the customer's preference weight to get the recommendation score of the item for the customer ; According to the formula , calculate the recommendation score of each item for the customer .

[0012] According to the recommendation score of the item , sort the recommendation results from high to low; Display the generated recommended content to the customer.

[0013] The localization service intelligent recommendation method based on the hotel room service robot according to any one of claims 2-5, characterized in that the method of using intelligent recommendation algorithm module to generate the recommended content most meeting the customer's needs and display it to the customer is: According to the customer's individual preference information and current location information, calculate the user feature vector ; Traverse the localization service database to calculate the feature vector of each scenic spot, food, specialty, etc. ; Use the algorithm to calculate the rating prediction value of user u for each item i ; According to the rating prediction value , sort the items, and take the top 5-10 items with the highest scores as the recommendation list; Display the recommendation list to the customer; Adjust the recommended content and update the user feature vector according to the feedback and selection of the customer to optimize the recommendation results in the next round.

[0014] Another technical problem to be solved by the present application is to provide an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the localization service intelligent recommendation method based on the hotel room service robot according to any one of the above.

[0015] Another technical problem to be solved by the present application is to provide a computer-readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the localization service intelligent recommendation method based on the hotel room service robot according to any one of the above.

[0016] The beneficial effects of the present application are: By analyzing the personalized preferences of customers, the system can provide customized localization service recommendations for each customer, making the customer experience more personalized and comfortable. Combined with the geographic location recognition module and the localization service database module, the system can accurately obtain the location information of the customer and recommend scenic spots, food, specialties, shopping, and other service content that meet the needs of the customer according to the characteristics and needs of the customer's location. The intelligent recommendation algorithm module can generate real-time recommendations that best meet the needs of the customer based on the customer's location, personalized preferences, and information in the localization service database, improving the accuracy and quality of the recommendations.

[0017] Through the real-time interaction and feedback module, customers can communicate with the robot in real time and provide feedback or suggestions. The system can adjust the recommended content in real time according to the feedback and selection of the customer, thereby optimizing the recommendation results and improving customer satisfaction. The system integrates geographic location recognition, personalized preference analysis, and intelligent recommendation algorithms to provide customers with more convenient and thoughtful service experiences, helping customers better understand local culture and characteristics, and enhancing customer impressions and loyalty to the hotel. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 A principle block diagram of a localization service recommendation system based on a hotel room service robot according to the present application; Figure 2 A flowchart of a localization service recommendation method based on a hotel room service robot according to the present application. DETAILED DESCRIPTION

[0019] The principles and features of the present application are described below, and the examples are used only to explain the present application and are not intended to limit the scope of the present application. The present application is described in more detail in the following paragraphs by way of example. The advantages and features of the present application will be more apparent from the following description and claims.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items. Embodiments

[0021] Referring to Figure 1 As shown, a local service recommendation system based on a hotel room service robot includes: A geographic location identification module: for obtaining information about the current location of the customer, including a GPS module and a Wi-Fi module; A local service database module: for storing local attractions, food, specialties, shopping information, and local characteristic activities, recommended attractions, and popular restaurant content; A personalized preference analysis module: for analyzing the personalized preferences of the customer; An intelligent recommendation algorithm module: based on the customer's location, personalized preferences, and local service database, an intelligent recommendation algorithm is used to generate recommended content that meets the customer's needs; A real-time interaction and feedback module: through real-time interaction between the robot and the customer, the recommended content is adjusted according to the customer's feedback and selection, and the recommended results are optimized.

[0022] Referring to Figure 2 As shown, a local service intelligent recommendation method based on a hotel room service robot includes the following steps: When the customer interacts with the robot, the customer's location is obtained through the geographic location identification module; According to the customer's location and the local service database, attractions, food, specialties, and shopping information near the customer's location are filtered out; Combined with the personalized preference analysis module, the content that meets the customer's preferences is filtered out; Using the intelligent recommendation algorithm module, the recommended content that best meets the customer's needs is generated and displayed to the customer; According to the customer's feedback and selection, the recommended content is adjusted for secondary recommendation.

[0023] To ensure the security and privacy of sensitive data such as customer location information and personalized preferences, necessary data encryption and access control measures must be taken, including but not limited to data encryption technology, user authentication, access log recording and auditing, etc. To provide customers with the latest localized service recommendations, the information in the localized service database will be updated in real time every 24 hours to ensure the accuracy and completeness of information such as tourist attractions, food, specialties, shopping, etc. It is worth noting that the specialty refers to famous and unique products, including customized products, personalized products and segmented products.

[0024] To improve the accuracy of recommendations, the scheme uses a highly accurate personalized preference analysis algorithm that accurately analyzes customers' interests based on their historical behavior and preference data. In combination with factors such as customer location and personalized preferences, the scheme can provide customers with more relevant recommendations.

[0025] The method for obtaining the location of the customer through the geographic location recognition module is as follows: Connect the GPS module to the main control board or processor of the robot; Write a program to communicate with the GPS module through a serial port or other communication interface; Receive the location information sent by the GPS module and parse the geographic location data such as latitude and longitude; Connect the Wi-Fi module to the main control board or processor of the robot; Write a program to scan for Wi-Fi signals around and obtain relevant information such as signal strength and MAC address; Analyze Wi-Fi signal data to determine the customer's current location information; Use a data fusion algorithm to integrate and process GPS and Wi-Fi data; Determine the customer's current location based on the location information obtained by GPS and Wi-Fi.

[0026] Combining GPS and Wi-Fi technologies can more accurately obtain the customer's current location information and improve the accuracy of location recognition. GPS and Wi-Fi modules can obtain real-time location information of customers and quickly transmit it to the system for processing, making the feedback of customer location identification more timely.

[0027] GPS and Wi-Fi technologies are mature and stable, and can reliably obtain customer location information in different environments, ensuring the stability and reliability of the system. Compared with other positioning technologies, the hardware and software costs of GPS and Wi-Fi modules are relatively low, which can reduce the implementation and operation costs of the system to a certain extent.

[0028] The GPS and Wi-Fi modules usually have standard interfaces and communication protocols, facilitating connection and communication with the main control board or processor of the robot, and facilitating integration into the system; using data fusion algorithms to integrate GPS and Wi-Fi data can further improve the accuracy and stability of position recognition, thereby better meeting customer needs.

[0029] The method for screening out attractions, food, specialties, and shopping information near the customer's location is as follows: Query the location data and detailed description of each attraction, food, specialty, and shopping information stored in the localized service database; Compare the customer's location with the location of each attraction, food, specialty, and shopping information, and calculate the distance between them; Set a range or radius r to screen out attractions, food, specialties, and shopping information within a certain range from the customer's location.

[0030] According to the actual location and distance of the customer, personalized recommendation services that are closer to the customer's needs can be provided, enhancing the customer experience; through specific distance calculations, the location of attractions, food, specialties, and shopping information near the customer's location can be relatively accurately determined, avoiding the recommendation of too far or irrelevant content.

[0031] The range or radius r setting method can flexibly adjust the breadth of the recommendation results, allowing for personalized settings based on actual conditions and customer needs, increasing the flexibility of the recommendation results; through precise screening, the recommendation of too far or irrelevant content can be avoided, saving system resources and customer time, and improving recommendation efficiency; customers can clearly understand the attractions, food, specialties, and shopping information that are relatively close to them, increasing their trust and satisfaction with the recommended content.

[0032] In combination with the personalized preference analysis module, the method for filtering out content that meets the customer's preferences is as follows: According to the customer's needs and preferences, classify and filter the screened attractions, food, specialties, and shopping information, and only display specific types of attractions, food, specialties, and shopping information; Sort the screened information according to its distance from the customer's location or its rating; Screen out nearby attractions, food, specialties, and shopping information that are ranked last.

[0033] According to the customer's preferences and needs, classify and filter attractions, food, specialties, and shopping information, which can provide personalized recommendation results that better meet the customer's tastes, enhancing user experience; by filtering according to customer preferences, the amount of information the customer needs to browse can be reduced, saving time, and providing recommendation content that better meets the customer's tastes, further improving customer satisfaction.

[0034] According to the high-low or distance sorting display information, customers can more easily find the desired content, enhance customer participation and trust in the recommended results; by filtering the nearby scenic spots, food, specialty, shopping information at the end of the ranking, it can ensure that the recommended content seen by customers is more relevant and high-quality, improve user experience and satisfaction; combined with the method of personalized preference analysis module, it can more accurately match the customer's preferences and needs, improve the accuracy and precision of the recommendation system.

[0035] The method of using the intelligent recommendation algorithm module to generate the most suitable recommendation content for the customer and display it to the customer is: Collecting the content attribute information of the item; Collecting customer preference information; Extracting features of the content attributes of the item, using natural language processing technology to extract keywords and topics; According to the customer's preference information, calculate the customer's weight for each feature; For each item j, multiply the content attribute features of the item with the customer's preference weight to get the recommendation score of the item to the customer ; According to the formula , calculate the recommendation score of each item to the customer .

[0036] According to the recommendation score of the item , sort the recommended results from high to low; Display the generated recommendation content to the customer.

[0037] By collecting customer preference information and extracting features of the content attributes of the item, personalized recommendation can be achieved to ensure that the recommended results are more in line with the customer's taste and needs; according to the customer's preference weight and the content attribute of the item, the recommendation score is calculated, which can quantify the customer's love for the item, thereby improving the accuracy of the recommended results; by sorting and filtering the recommended content with higher scores, customers can see the most relevant and interesting items, improving user satisfaction and experience.

[0038] When displaying the recommended content, personalized display and interaction can be performed according to customer preferences and interface design, improving user participation and experience; collecting customer feedback in a timely manner and optimizing according to feedback can continuously improve the recommendation algorithm and results, making the recommendation system more intelligent and effective; through feature extraction and weight calculation, it can more quickly and accurately recommend and sort a large number of items, improving system recommendation efficiency and user experience.

[0039] The method of using the intelligent recommendation algorithm module to generate the most suitable recommendation content for the customer and display it to the customer is: According to the personalized preference information and current location information of the customer, calculate the user feature vector ; Traverse the localized service database, calculate the feature vector of each scenic spot, delicacy, specialty, etc. ; Use algorithm Calculate the rating prediction value of user u for each item i ; According to the rating prediction value , sort the items, and take the top 5-10 rated items as the recommendation list; Show the recommendation list to the customer; According to the customer's feedback and selection, adjust the recommended content and update the user feature vector to optimize the next round of recommendation results.

[0040] By obtaining the personalized preference information and current location information of the customer, the user feature vector can be generated, thereby realizing personalized recommendation results. Customers can see more recommended content that meets their interests and location, improving satisfaction; by calculating the similarity between the user feature vector and the item feature vector, using the algorithm for rating prediction, the user's preference for each item can be more accurately predicted. This can ensure that the recommended items meet the customer's expectations.

[0041] According to the rating prediction value, sort the items, and place the items with higher ratings at the front of the recommendation list. This allows customers to see the items they are most interested in first, improving the quality and effectiveness of the recommendation results; through real-time interaction with customers, such as collecting feedback and choices, the recommended content can be continuously adjusted and the user feature vector can be updated, further optimizing the next round of recommendation results. This feedback loop can continuously improve the accuracy and personalization of the recommendation system; by calculating the feature vector and performing rating prediction, a large number of items can be quickly sorted for recommendation. This can improve the efficiency of the system and provide customers with a smoother, real-time recommendation experience.

[0042] The embodiment also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the localized service intelligent recommendation method based on the hotel room service robot as described above.

[0043] The embodiment also provides a computer storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement the steps of the localized service intelligent recommendation method based on the hotel room service robot as described above.

[0044] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, storage, database or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0045] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of functional units and modules is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the system is divided into different functional units or modules to complete all or part of the above-mentioned functions.

[0046] The above-mentioned embodiments of the present application are not a limitation on the protection scope of the present application, and the embodiments of the present application are not limited thereto. According to the above-mentioned content of the present application, other various forms of modifications, replacements or changes of the above-mentioned structure of the present application can be made according to ordinary technical knowledge and conventional means in the art without departing from the above-mentioned basic technical idea of the present application, which should fall within the protection scope of the present application.

Claims

1. A localized service recommendation system based on a hotel room service robot, characterized by, Comprising: Geolocation identification module: for obtaining the information of the current location of the customer, including GPS module, Wi-Fi module; Local service database module: for storing local scenic spots, food, specialty or shopping information, as well as local characteristic activities, recommended scenic spots or popular restaurant content; Personalized preference analysis module: for analyzing the personalized preferences of the customer; Intelligent recommendation algorithm module: based on the customer's location, personalized preferences and local service database, using intelligent recommendation algorithm to generate recommended content that meets the customer's needs; Real-time interaction and feedback module: through the robot and the customer to interact in real time, according to the customer's feedback and selection to adjust the recommended content, optimize the recommended results. 2.A method for intelligent recommendation of localized services based on a hotel room service robot, characterized in that, Comprising the following steps: When the customer interacts with the robot, the geolocation identification module is used to obtain the customer's location; According to the customer's location and the local service database, filter out the scenic spots, food, specialty, shopping information that meets the customer's location; Combined with the personalized preference analysis module, filter out the content that meets the customer's preferences; Use the intelligent recommendation algorithm module to generate the recommended content that meets the customer's needs and show it to the customer; According to the customer's feedback and selection, adjust the recommended content and make a second recommendation. 3.The method of claim 2, wherein, The method for obtaining the customer's location through the geolocation identification module is: Connect the GPS module to the main control board or processor of the robot; Write a program to communicate with the GPS module through the serial port or other communication interface; Receive the location information sent by the GPS module and parse the latitude and longitude and other geographic location data; Connect the Wi-Fi module to the main control board or processor of the robot; Write a program to scan the surrounding Wi-Fi signal and obtain relevant information such as signal strength, MAC address; Analyze the Wi-Fi signal data to determine the customer's current location information; Use data fusion algorithm to integrate and process GPS and Wi-Fi data; Determine the customer's current location based on the location information obtained by GPS and Wi-Fi. 4.The method of claim 3, wherein, The method for filtering out the scenic spots, food, specialty, shopping information that meets the customer's location is: Query the location data and detailed description of each scenic spot, food, specialty, shopping information stored in the local service database; Compare the customer's location with the location of each scenic spot, food, specialty, shopping information, and calculate the distance between them; Set a range or radius r, and filter out the scenic spots, food, specialty, shopping information within this range from the customer's location. 5.The method of claim 4, wherein, The method for filtering out the content that meets the customer's preferences combined with the personalized preference analysis module is: According to the customer's needs and preferences, classify and filter the filtered scenic spots, food, specialty, shopping information, and only display specific types of scenic spots, food, specialty, shopping information; Sort the filtered information according to the distance from the customer's location or the score; Filter out the nearby scenic spots, food, specialty, shopping information that ranks last. 6.The method of claim 2-5, wherein, The method for generating the recommended content that meets the customer's needs and showing it to the customer using the intelligent recommendation algorithm module is: Collect the content attribute information of the items; Collect the customer's preference information; Feature extraction is performed on the content attribute of the item, and a keyword and a theme are extracted using a natural language processing technique; According to the preference information of the customer, the weight of each feature of the customer is calculated; For each item j, multiply the item's content attribute features by the customer's preference weights to get the item's recommendation score for the customer ; The recommendation score of each item to the customer is calculated according to the formula .​ 7. The item's recommendation score The recommendation results are ranked from high to low. The generated recommended content is displayed to the customer. 8.The method of claim 2-5, wherein, The method for generating the recommended content most meeting the needs of the customer and displaying the recommended content to the customer by using the intelligent recommendation algorithm module is as follows: According to the personalized preference information and the current location information of the client, a user feature vector is calculated ; Traverse the localization service database, calculate the feature vector of each scenic spot, food, specialty, etc. ; Using an algorithm Computing a predicted rating value for each item i by the user u ; According to the score prediction value Rank the items and take the top 5-10 items with the highest scores as the recommendation list; The recommended list is displayed to the customer. Adjusting the recommended content and updating the user feature vector according to the feedback and selection of the customer to optimize the recommendation result of the next round.

9. An electronic device, comprising: The computer program is stored in the memory and can be run on the processor, and when the processor executes the program, the localization service intelligent recommendation method based on the hotel room service robot is realized.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to realize the localization service intelligent recommendation method based on the hotel room service robot as claimed in any one of claims 2-7.

Images