Service configuration method, electronic device, storage medium, and program product

Abstract

The application provides a service configuration method, an electronic device, a storage medium and a program product. The service configuration method comprises the following steps: obtaining a recommendation request of a user by using a terminal device, wherein the recommendation request comprises identification information and input information of the user; obtaining an intermediate object from a plurality of candidate objects according to the identification information and the candidate objects; obtaining a recommended object according to the intermediate object and the input information, and recommending the recommended object to the user by using the terminal device; the recommended object is used for indicating one or more service items of the user; receiving a selection operation of the user on the recommended object by using the terminal device; and associating the one or more service items with the identification information of the user according to the selection operation of the user, so as to realize service configuration of the user. The identification information of the user is used to screen the intermediate object, and then the input information is analyzed and matched to obtain the recommended object and push the recommended object to the user, so that the demand of the user for personalized service configuration is met.

Description

Service configuration methods, electronic devices, storage media and program products Technical Field

[0001] This application relates to the technical field of computer applications, and more particularly to service configuration methods, electronic devices, computer-readable storage media, and computer program products. Background Technology

[0002] With the continuous maturation of streaming media technology and the continuous improvement of the network environment, online live streaming platforms are becoming more and more widespread. Users can join and use these platforms to conduct various live streams, including games, entertainment programs, audio and video.

[0003] The platform needs to provide different services to users with different live streaming needs through service configuration. Existing service configuration methods for users are only applicable to traditional fields and do not consider the increasing demand for personalized service configurations as streaming media technology matures and network environments improve. Therefore, this application provides a service configuration method, electronic device, computer-readable storage medium, and computer program product to improve upon existing technologies. Summary of the Invention

[0004] The purpose of this application is to provide a service configuration method, electronic device, computer-readable storage medium, and computer program product. First, it uses the user's identification information to filter intermediate objects. Then, it analyzes and matches the input information to obtain recommended objects and pushes them to the user. It further refines the intermediate objects to obtain recommended objects and pushes them to the user. Finally, it configures the service based on the user's selection of recommended objects, thus meeting the user's need for personalized service configuration.

[0005] The objective of this application is achieved through the following technical solution:

[0006] Firstly, this application provides a service configuration method, the method comprising:

[0007] The user's recommendation request is obtained using a terminal device, and the recommendation request includes the user's identification information and input information;

[0008] Based on the identification information and the candidate objects, an intermediate object is obtained from a plurality of candidate objects;

[0009] Based on the intermediate object and the input information, a recommended object is obtained, and the recommended object is recommended to the user using the terminal device; the recommended object is used to indicate one or more service items for the user;

[0010] The terminal device is used to receive the user's selection of the recommended object;

[0011] Based on the user's selected action, one or more of the service items are associated with the user's identification information to achieve service configuration for the user.

[0012] The beneficial effects of this technical solution are as follows: The service configuration method provided in this application obtains a user's recommendation request through a terminal device, and then obtains an intermediate object from multiple candidate objects based on identification information. Next, a recommended object is obtained based on the intermediate object and input information, and the recommended object is recommended to the user using the terminal device to indicate one or more service items the user can select. After the user makes a selection, the one or more service items selected by the user are associated with the user's identification information to achieve personalized service configuration for the user. It can be understood that using intermediate objects and input information to obtain recommended objects greatly improves the accuracy of recommendations, allowing users to obtain a more customized service experience. On the one hand, the terminal device automatically completes service recommendation, selection, and configuration without manual intervention, greatly improving efficiency and achieving a high level of automation. On the other hand, user preferences can be quickly obtained based on the user's identification information and input information, thereby achieving personalized service configuration for the user. Furthermore, the method can respond to user recommendation requests in real time and adjust service configuration promptly based on user selection operations, greatly improving service real-time performance.

[0013] Compared to the selection of recommended objects in related service configuration methods, which directly chooses recommended objects from all candidate objects based on user input information—a approach that only considers the user's subjective needs (the input information is highly subjective)—this embodiment first selects intermediate objects based on the user's identification information (identification information reflects the user's objective attributes better than input information), and then obtains recommended objects from the intermediate objects based on the input information. Compared to directly selecting recommended objects from candidate objects, this method improves efficiency. Selecting recommended objects from candidate objects requires traversing all candidate objects, which is time-consuming. Selecting intermediate objects first narrows the selection range, thereby reducing search time and improving the efficiency of obtaining recommended objects. Furthermore, when there are too many candidate objects, directly selecting recommended objects from candidate objects results in low recommendation accuracy. By selecting intermediate objects and further filtering them based on the input information, more suitable recommended objects can be obtained, improving recommendation accuracy. Moreover, intermediate objects can be selected based on user information, user permissions, or levels, thus supporting personalized services. Compared to directly selecting recommended objects from candidate objects, this method better meets the needs of users for personalized services. On the other hand, when there are a large number of candidate items, directly selecting a recommended item from these candidates would lead to a large amount of computation, thus increasing computational costs. Selecting an intermediate item, however, can reduce the amount of computation and lower computational costs. Furthermore, since an intermediate item corresponding to the user's identification information is determined beforehand, selecting a recommended item from the product library of that intermediate item is more in line with the user's needs, improving the accuracy of the recommendation.

[0014] In summary, the technical solution of this application first uses the user's identification information (objective attributes such as user information, user permissions, or level) to filter intermediate objects. Then, through analysis and matching of input information, it further refines the intermediate objects to obtain recommended objects and pushes them to the user. Finally, based on the user's selection of recommended objects, one or more service items are configured for the user, meeting the user's needs for personalized service configuration.

[0015] In some possible implementations, the process of obtaining the recommendation object includes:

[0016] Using the semantic extraction model corresponding to the input information, semantic information is extracted from the input information;

[0017] The semantic information is clustered to obtain cluster information, which is used to indicate the service items required by the user.

[0018] Obtain the similarity between the clustering information and each of the intermediate objects;

[0019] Based on the similarity between the clustering information and each of the intermediate objects, at least one of the intermediate objects is selected as the recommended object.

[0020] The beneficial effects of this technical solution are as follows: By extracting semantic information from the input information and then clustering the extracted semantic information, clustering information is obtained to indicate the user's needs. Then, the similarity between the intermediate object and the clustering information is calculated, and the most matching intermediate object is selected as the recommendation object. That is, this application embodiment obtains recommendation objects based on semantic information extraction, clustering, and similarity calculation. On the one hand, by using semantic information extraction and clustering techniques, the type of service requested by the user can be more accurately indicated, which is beneficial for selecting intermediate objects with higher matching degrees for recommendation. Compared to performing similarity calculation through only semantic information extraction, this improves the accuracy of the recommendation service. On the other hand, although different users may put forward the same service needs, their expressions are different. This application's technical solution can classify the service requests put forward by different users through semantic information extraction and clustering techniques, making the service requests submitted by different users more universal, thereby providing more suitable and comprehensive recommendation services and improving the universality of recommendation object acquisition. Furthermore, the use of semantic information extraction and clustering techniques in this application embodiment can reduce redundant recommendation objects and save system resources. On the other hand, it can provide more accurate and comprehensive recommendation services, which can help users find the services they need more quickly and easily, thereby enhancing users' trust and satisfaction with the platform.

[0021] Compared to simply using a semantic extraction model corresponding to the input information, extracting semantic information from the input information, obtaining the similarity between the semantic information and the intermediate object corresponding to each service item, and selecting at least one intermediate object as the recommended object based on the similarity of the intermediate object corresponding to each service item, this application embodiment not only extracts semantic information from the input information and calculates the similarity with the intermediate object of the service item, but also cleverly introduces a process of clustering semantic information, and then calculates the similarity based on the intermediate object to select the recommended object. From this perspective, after clustering, similar service items are classified into the same cluster, and only need to be considered once in the recommendation process, thus reducing and optimizing the number of recommended objects. This reduces the burden on users when reading recommended objects, improving user satisfaction and experience. At the same time, because the recommended objects more accurately match the required service items, it also reduces the need for users to repeatedly select services later, lowering user churn and enhancing the platform's commercial competitiveness.

[0022] In summary, the technical solution of this application first uses a semantic extraction model corresponding to the input information to extract semantic information from the input information. Then, this semantic information is clustered to obtain cluster information, which can be used to indicate the type of service requested by the user and reduce redundant recommendation objects. Next, the similarity between intermediate objects and the cluster information is calculated. Finally, at least one intermediate object with a high similarity match is selected as a recommendation object, reducing the burden on the user when reading recommendation objects and improving user satisfaction and experience.

[0023] In some possible implementations, selecting at least one of the intermediate objects as the recommended object based on the similarity between the clustering information and each of the intermediate objects includes:

[0024] When the highest similarity between any of the intermediate objects and the clustering information is greater than a preset similarity, the intermediate object corresponding to the highest similarity is taken as the recommended object;

[0025] When the highest similarity between any of the intermediate objects and the clustering information is not greater than a preset similarity, one or more associated users of the user are obtained based on the identification information;

[0026] For each associated user, the object corresponding to the configured service item of the associated user is used as the recommended object.

[0027] The beneficial effects of this technical solution are as follows: In this application's technical solution, when the highest similarity between an intermediate object and the cluster information is greater than a preset similarity, the intermediate object is used as a recommended object. If the highest similarity between any intermediate object and the cluster information does not exceed the preset similarity, one or more associated users will be obtained based on the user's identification information, and the objects corresponding to the service items configured by these associated users will be used as recommended objects for the user to choose from. On the one hand, by clustering user needs and matching intermediate objects, the user's real needs can be better reflected, that is, more personalized and accurate service recommendations are provided. On the other hand, when the similarity between an intermediate object and the cluster information is not high, recommendations can still be provided through the configuration information of associated users, increasing the reliability and diversity of recommendations and improving user satisfaction and service experience.

[0028] In some possible implementations, when the highest similarity between any of the intermediate objects and the clustering information is no greater than a preset similarity, the method further includes:

[0029] Start the statistics and increment the count by one;

[0030] The system checks whether the number of statistical counts is greater than a preset number of statistical counts. If the number of statistical counts is greater than the preset number of statistical counts, the number of statistical counts is cleared to zero, and a recommendation prompt message is sent to the terminal device of the configuration personnel. The recommendation prompt message is used to remind the configuration personnel to pay attention to the user's input information.

[0031] This application does not limit the content and form of the recommendation prompts. For example, the prompts may be displayed as pop-up windows on the terminal configuration device, with the text "Please note that user A's input information is abnormal." Alternatively, the prompts may be displayed as voice messages on the terminal configuration device, with the voice message "Please note that user A's input information is abnormal."

[0032] The beneficial effects of this technical solution are as follows: When the highest similarity between any intermediate object and the cluster information is no greater than a preset similarity, the count begins and is incremented by 1. Simultaneously, it checks if the count exceeds the preset count; if so, the count is reset to zero, and a recommendation prompt is sent to the configuration personnel's terminal device (i.e., the terminal configuration device). Configuration personnel can use this recommendation prompt to pay attention to user input, avoiding situations where user input does not receive positive or effective feedback, thus improving recommendation accuracy. On one hand, when existing intermediate objects or cluster information cannot meet user needs, recommendation prompts are sent to configuration personnel, prompting them to pay attention to user input, thereby improving the accuracy and adaptability of recommendations and enhancing the adaptability of the service configuration method. On the other hand, by setting and pre-setting the count to detect the accuracy of intermediate objects and cluster information, the false positive rate can be reduced, improving recommendation accuracy. Furthermore, configuration personnel can adjust intermediate objects and cluster information promptly based on the recommendation prompts to update service options, thereby improving work efficiency and recommendation accuracy, and reducing unnecessary communication and adjustment costs when users do not receive the services they need.

[0033] In some possible implementations, associating one or more service items with the user's identification information based on the user's selection operation to configure services for the user includes:

[0034] When one or more of the recommended objects are selected by the user within a preset time interval, the service items corresponding to the selected recommended objects are associated with the user.

[0035] When no recommended object is selected by the user within a preset time interval, the associated recommended object of the user is obtained according to the identification information, and the associated recommended object is recommended to the user using the terminal device.

[0036] The associated recommendation object is used to indicate one or more configured service items of the user's associated users.

[0037] The beneficial effects of this technical solution are as follows: it can associate one or more service items with the user's identification information based on the user's selection, thereby enabling service configuration for the user. If no recommended item is selected by the user within a preset time interval, the system can retrieve the user's associated recommended items based on the user's identification information and recommend these associated recommended items to the user using the terminal device. This allows users to receive helpful suggestions when they are unable to make a choice, helping them to better configure their services, thereby improving service quality and efficiency.

[0038] On the one hand, by associating with user identification information, user needs can be accurately determined and identified, and services can be recommended and configured in a timely manner based on user selections and preset time intervals, improving the efficiency of service configuration. On the other hand, by setting preset time intervals, user selection behavior can be observed and understood over a certain period, providing recommendations for services that better meet user needs and preferences, thereby improving the user experience. Furthermore, users can select the services they need based on their own requirements and associate them with identification information, enabling more accurate service configuration, enhancing user initiative and accuracy in service configuration, and improving user understanding and awareness of the services. Moreover, when a user selects a recommended service, the service corresponding to the selected service is automatically associated with the user, saving configuration personnel time and effort.

[0039] In some possible implementations, the step of obtaining the user's associated recommended objects based on the identification information and recommending the associated recommended objects to the user using the terminal device when no recommended object is selected by the user within a preset time interval includes:

[0040] Obtain the identifier similarity between the identifier information and the identifier information of multiple historical users, and identify one or more of the historical users with the highest identifier similarity as the associated users;

[0041] Based on the historical recommendation data of the associated users, the service items of the associated users are obtained, and the objects corresponding to the service items of the associated users are used as the associated recommendation objects of the users.

[0042] The historical recommendation data includes one or more service items associated with the associated user, and recommendation feedback for each service item, including the associated user's rating and / or clicks on the service item.

[0043] The beneficial effects of this technical solution are as follows: When a user does not select any recommended object within a preset time interval, the system obtains the user's associated recommended objects based on the user's identification information. Specifically, it obtains the similarity between the user's identification information and the identification information of historical users. By calculating the similarity, the historical users most similar to the current user can be identified, thus determining associated users. In other words, these associated users have similar identification information to the current user, and their service needs and purchasing behaviors may also be similar to the current user's. Based on the historical recommendation data of associated users, the system obtains their service items and uses their corresponding recommended objects as associated recommended objects for the current user. These recommended objects have been verified by historical users and can better meet the current user's needs. Finally, the associated recommended objects are recommended to the current user to help them make a selection and complete the service configuration. This technical solution can provide users with more personalized service recommendations based on user identification information and historical recommendation data. At the same time, it can also promote user participation and feedback on services, continuously improving service quality and user satisfaction.

[0044] In some possible implementations, the step of obtaining the service items of the associated user based on the historical recommendation data of the associated user, and using the objects corresponding to the service items of the associated user as the associated recommendation objects of the user, includes:

[0045] Based on the recommended feedback, obtain feedback ratings for one or more service items associated with the associated user;

[0046] The service item corresponding to the highest feedback score will be used as the associated recommendation object for the user.

[0047] The system detects whether the maximum feedback score is less than a preset score. When the maximum feedback score is less than the preset score, a score prompt message is generated and sent to the terminal device of the configuration personnel. The score prompt message is used to remind the configuration personnel to pay attention to the user's identification information.

[0048] The beneficial effects of this technical solution are as follows: When a user does not select a recommended service, similar historical users are identified based on the user's identifiers, and service items and their feedback ratings are obtained from their historical recommendation data. Then, the service item corresponding to the highest rating is used as the user's associated recommended service. Simultaneously, if the highest rating is lower than a preset rating, a rating prompt message is generated and sent to the configuration personnel, allowing them to provide better service recommendations for specific users. On the one hand, this helps users quickly obtain associated recommended services when they do not select a service, thereby improving user service experience and satisfaction. On the other hand, by utilizing historical recommendation data, users can obtain more personalized and accurate recommendations, which also helps improve service quality. Furthermore, even when the rating is lower than the preset value, recommended services are generated first, followed by the generation of a rating prompt message and its sending to the relevant configuration personnel, ensuring that customers receive better service and support. In summary, this improves the adaptability and intelligence of the service configuration method.

[0049] Secondly, this application also provides an electronic device, the electronic device including a memory and at least one processor, the memory storing a computer program, the at least one processor being configured to execute the computer program to perform the following steps:

[0050] The user's recommendation request is obtained using a terminal device, and the recommendation request includes the user's identification information and input information;

[0051] Based on the identification information and the candidate objects, an intermediate object is obtained from a plurality of candidate objects;

[0052] Based on the intermediate object and the input information, a recommended object is obtained, and the recommended object is recommended to the user using the terminal device; the recommended object is used to indicate one or more service items for the user;

[0053] The terminal device is used to receive the user's selection of the recommended object;

[0054] Based on the user's selected action, one or more of the service items are associated with the user's identification information to achieve service configuration for the user.

[0055] Thirdly, this application also provides a computer-readable storage medium storing a computer program that, when executed by at least one processor, implements the steps of any of the above methods or the functions of any of the above electronic devices.

[0056] Fourthly, this application also provides a computer program product comprising a computer program that, when executed by at least one processor, implements the steps of any of the methods described above or the functions of any of the electronic devices described above. Attached Figure Description

[0057] The present application will be further described below with reference to the accompanying drawings and embodiments.

[0058] Figure 1 is a flowchart illustrating a service configuration method provided in an embodiment of this application.

[0059] Figure 2 is a schematic diagram of a process for obtaining recommended objects provided in an embodiment of this application.

[0060] Figure 3 is a schematic diagram of a process for sending recommendation prompts provided in an embodiment of this application.

[0061] Figure 4 is a schematic diagram of a process for obtaining associated recommendation objects provided in an embodiment of this application.

[0062] Figure 5 is a schematic diagram of a process for obtaining service objects provided in an embodiment of this application.

[0063] Figure 6 is a structural block diagram of an electronic device provided in an embodiment of this application.

[0064] Figure 7 is a schematic diagram of the structure of a computer program product provided in an embodiment of this application. Detailed Implementation

[0065] The technical solutions in this application will be described below with reference to the accompanying drawings and specific embodiments. It should be noted that, without conflict, the various embodiments or technical features described below can be arbitrarily combined to form new embodiments.

[0066] In this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any implementation or design described as "exemplary" or "for example" in this application should not be construed as being better or more advantageous than other implementations or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0067] The technical field and related terms of the embodiments of this application are briefly described below.

[0068] Artificial Intelligence (AI) is the theory, methods, technology, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive technology within computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. AI studies the design principles and implementation methods of various intelligent machines, enabling them to possess perception, reasoning, and decision-making capabilities. AI technology is a comprehensive discipline involving a wide range of fields, encompassing both hardware and software technologies. Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly include computer vision, speech processing, natural language processing, as well as machine learning / deep learning, autonomous driving, and intelligent transportation.

[0069] Machine learning (ML) is a multidisciplinary field involving probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory, among others. A computer program can learn experience E given a certain type of task T and a performance metric P. If its performance on task T can be precisely measured by P, then it improves with experience E. Machine learning specifically studies how computers can simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to endow computers with intelligence; its applications span all areas of artificial intelligence.

[0070] Deep learning is a special type of machine learning that learns to represent the world using nested hierarchical concepts, achieving tremendous functionality and flexibility. Each concept is defined as being associated with a simpler one, while more abstract representations are computed in a less abstract manner. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and learning by demonstration.

[0071] Clustering is an unsupervised learning method that aims to group similar objects together and separate unrelated objects into different groups. The basic idea of ​​clustering algorithms is: given a set of unlabeled samples, similar samples are grouped into one class by calculating the distance or similarity between them.

[0072] Clustering algorithms can be divided into two types: prototype-based clustering and hierarchical clustering. Prototype-based clustering (such as the K-Means algorithm) clusters data by selecting prototype points in the dataset and dividing the space into k regions centered on core samples. Hierarchical clustering algorithms (such as the AGNES algorithm), on the other hand, achieve clustering by progressively merging or dividing clusters, thus forming a hierarchical clustering structure.

[0073] Semantic extraction refers to the automatic extraction of semantic information from input information, which can be text, speech, or images. Semantic extraction facilitates the understanding and processing of text, speech, or image information by computers. When the input information is text, the process may include the following steps: First, the text is segmented into words to obtain a series of words. Then, entities such as names of people, places, and organizations are identified and labeled. Relationships between entities are searched and extracted from the text. Finally, event types, participants, time, and location information are searched and extracted. In other words, semantic extraction technology can be applied to fields such as natural language processing, text mining, and knowledge graphs, improving computers' ability to understand and analyze text semantically, and supporting tasks such as information retrieval, intelligent question answering, and machine translation.

[0074] Existing service configurations are mostly applicable to traditional fields and do not consider the increasing demand for personalized service configurations from users as streaming media technology matures and network environments improve. With technological advancements, the increasing maturity of streaming media technology, and the continuous improvement of network environments, users have greater needs for personalized service configurations. Based on this, this application provides a service configuration method, electronic device, computer-readable storage medium, and computer program product to improve upon existing technologies.

[0075] The solutions provided in this application involve technologies such as interaction design and artificial intelligence, and are specifically illustrated through the following embodiments. It should be noted that the order of description of the following embodiments is not intended to limit the preferred order of the embodiments.

[0076] Method Implementation Examples

[0077] Referring to Figure 1, Figure 1 is a flowchart illustrating a service configuration method provided in an embodiment of this application.

[0078] This application provides a service configuration method, the method including:

[0079] Step S101: Obtain the user's recommendation request using the terminal device, wherein the recommendation request includes the user's identification information and input information;

[0080] Step S102: Based on the identification information and candidate objects, obtain an intermediate object from a plurality of candidate objects;

[0081] Step S103: Based on the intermediate object and the input information, obtain a recommended object, and use the terminal device to recommend the recommended object to the user; the recommended object is used to indicate one or more service items for the user;

[0082] Step S104: Receive the user's selection of the recommended object using the terminal device;

[0083] Step S105: Based on the user's selection operation, associate one or more of the service items with the user's identification information to configure the service for the user.

[0084] The service configuration method can run on an electronic device. The electronic device and the (user-used) terminal device can be independent of each other, or the electronic device and the terminal device can be integrated. When the electronic device and the terminal device are independent, the electronic device can be a computer, server (including cloud server), or other device with computing capabilities. This application does not limit the terminal device; it can be, for example, a mobile phone, tablet computer, laptop computer, desktop computer, smart wearable device, or other smart terminal device with a display screen, microphone, and speaker. Alternatively, the terminal device can be a workstation or console with a display screen, microphone, and speaker. The display screen can be a touch screen or a non-touch screen. The terminal device mentioned in this application generally refers to the terminal device used by the user, while the terminal device of the configuration personnel mentioned below can be described as a terminal configuration device in the examples.

[0085] A platform refers to a platform used by users to share content. When the platform is a live streaming platform, it provides online live streaming services to users through live streaming rooms, allowing users to broadcast their own content and activities. The name of a live streaming platform can be something like "Early Childhood Craft Teaching," "Middle-Aged People's Fitness Live Stream," "Seafood Product Mega Sale," or "Insurance Business Promotion." In other words, the aforementioned platform combines live streaming technology with social networks, video sharing, and real-time interaction, enabling users to broadcast anytime, anywhere using various terminal devices (such as smartphones, tablets, and computers). A platform can also be a knowledge-paying platform, an e-commerce platform, or other non-live streaming platform. The following mainly uses live streaming platforms as examples to facilitate understanding of the technical solution, but this application does not limit the type of platform.

[0086] Platform administrators refer to the platform's staff, specifically those who configure the services needed by users of the live streaming room. Platform administrators manage and supervise aspects of the platform (live streaming room) including technology, user experience, and content security. Generally, they oversee the technical operation and stability of the live streaming room, ensuring smooth streaming, high audio and video quality, and a good user experience. Platform administrators can also formulate and enforce user management policies, including registration and verification, account management, and handling of violations. Furthermore, they can collect and analyze user data or user-viewer data to understand user needs and market changes, and adjust platform strategies accordingly.

[0087] Users refer to individuals who utilize the services provided by the platform to share knowledge, teach, and interact with audiences. For example, they can log in and use the platform by registering an account, and showcase their talents or skills, or provide information needed by the audience, through interaction. When users use the platform for education and training, the user might be a receptionist (or account manager), and the audience might be learners (or students) acquiring skills or knowledge. In some specific applications, users can utilize the content provided by the platform to offer services to the audience using virtual objects.

[0088] Virtual objects include virtual humans, virtual animals, and virtual cartoon characters. Virtual humans, in particular, are anthropomorphic figures constructed using CG technology and operating in code form, possessing various interactive capabilities such as language communication, facial expressions, and action demonstrations. Virtual human technology has rapidly developed in the field of artificial intelligence and has been applied in many technological areas, such as virtual live streaming rooms, film and television, media, games, finance, cultural tourism, education, and healthcare. It can not only customize virtual hosts, virtual anchors, virtual idols, virtual customer service representatives, virtual lawyers, virtual training instructors, virtual doctors, virtual guides, and virtual assistants, but also generate videos with a single click from text or audio. Among virtual humans, service-oriented virtual humans primarily function to replace real-life services and provide daily companionship; they are virtualizations of real-world service roles. Their industrial value mainly lies in reducing costs in existing service industries, improving efficiency and reducing costs in the existing market.

[0089] The application embodiments do not limit the services provided by virtual objects. Virtual objects can provide users with various types of services through interactive videos, such as programming teaching, foreign language teaching, insurance consultation, shopping consultation, travel services, etc., covering the needs of various users.

[0090] Therefore, the service configuration method provided in this application obtains the user's recommendation request through a terminal device, and then obtains an intermediate object from multiple candidate objects based on the identification information. Next, it obtains a recommended object based on the intermediate object and input information, and uses the terminal device to recommend the recommended object to the user, indicating one or more service items the user can select. After the user makes a selection, the one or more service items selected by the user are associated with the user's identification information to achieve personalized service configuration for the user. It can be understood that using intermediate objects and input information to obtain recommended objects greatly improves the accuracy of recommendations, allowing users to obtain a more customized service experience. On the one hand, the terminal device automatically completes service recommendation, selection, and configuration without manual intervention, greatly improving efficiency and achieving a high level of automation. On the other hand, it can quickly obtain the user's preferences based on the user's identification information and input information, thereby achieving personalized service configuration for the user. Furthermore, it can respond to the user's recommendation request in real time and adjust the service configuration promptly based on the user's selection operation, greatly improving the real-time performance of the service.

[0091] Compared to the selection of recommended objects in related service configuration methods, which directly chooses recommended objects from all candidate objects based on user input information—a approach that only considers the user's subjective needs (the input information is highly subjective)—this embodiment first selects intermediate objects based on the user's identification information (identification information reflects the user's objective attributes better than input information), and then obtains recommended objects from the intermediate objects based on the input information. Compared to directly selecting recommended objects from candidate objects, this method improves efficiency. Selecting recommended objects from candidate objects requires traversing all candidate objects, which is time-consuming. Selecting intermediate objects first narrows the selection range, thereby reducing search time and improving the efficiency of obtaining recommended objects. Furthermore, when there are too many candidate objects, directly selecting recommended objects from candidate objects results in low recommendation accuracy. By selecting intermediate objects and further filtering them based on input information, more suitable recommended objects can be obtained, improving recommendation accuracy. Moreover, intermediate objects can be selected based on user information, user permissions, or levels, thus supporting personalized services. Compared to directly selecting recommended objects from candidate objects, this method better meets the needs of users for personalized services. On the other hand, when there are a large number of candidate items, directly selecting a recommended item from these candidates would lead to a large amount of computation, thus increasing computational costs. Selecting an intermediate item, however, can reduce the amount of computation and lower computational costs. Furthermore, since an intermediate item corresponding to the user's identification information is determined beforehand, selecting a recommended item from the product library of that intermediate item is more in line with the user's needs, improving the accuracy of the recommendation.

[0092] In summary, the technical solution of this application first uses the user's identification information (objective attributes such as user information, user permissions, or level) to filter intermediate objects. Then, through analysis and matching of input information, it further refines the intermediate objects to obtain recommended objects and pushes them to the user. Finally, based on the user's selection of recommended objects, one or more service items are configured for the user, meeting the user's needs for personalized service configuration.

[0093] As an example, user Xiaojia creates a "children's crafts" livestream room on the platform. Xiaojia finds that the page displayed in his livestream room is too monotonous and fails to engage young viewers. Xiaojia uses his computer to input the text message, "The colors of the page displayed during my livestream are too monotonous; I need more template options." The platform retrieves Xiaojia's recommendation request using a terminal device. The identifiers could include Xiaojia's ID, registration date, usage duration, and user level (e.g., Gold Member). The input message is the text "The colors of the page displayed during my livestream are too monotonous; I need more template options."

[0094] Based on the identification information, an intermediate object is obtained from multiple candidate objects. The candidate information may include "Platinum Member," "Gold Member," "Solar Member," "Template Member," and "Diamond Member." Since Xiaojia's identification information indicates that he is already a Gold Member, the intermediate object can be "Platinum Member," "Solar Member," "Template Member," and "Diamond Template Member." At this point, based on the input information, "Template Member" and "Diamond Template Member" are selected as recommended objects from the above intermediate objects, and recommended to Xiaojia using Xiaojia's computer. The recommendation method can be in the form of checkboxes or option buttons; this embodiment does not limit the method.

[0095] Xiaojia selected "Template Member" as the recommended option. The "Template Member" service is linked to Xiaojia's identification information, allowing Xiaojia to choose the template he needs from a wider selection, making the live stream more attractive to young viewers.

[0096] In this example, users only need to input their needs to receive multiple recommendations related to those needs, which can provide a better user experience and improve user satisfaction and loyalty.

[0097] As another example, the difference from the previous example is that the host in the live broadcast room is a virtual host (i.e., a virtual object), and the alternative information can include decorations, effects, hairstyles, makeup, etc. for the virtual host.

[0098] This application does not limit the type of service provided. Examples include increasing bandwidth support for more viewers, providing marketing support (i.e., assisting users in developing marketing plans and providing tools for promotional activities and advertising), providing data analysis support (i.e., providing users with data analysis tools to help them understand their audience and their performance), and providing financial settlement support (i.e., providing users with financial settlement support).

[0099] In some embodiments, obtaining an intermediate object from a plurality of candidate objects based on the identification information and candidate objects may be selecting an object corresponding to a service item that the user does not have, as indicated by the identification information, or an object with higher permissions than the user's current (service) permissions.

[0100] As an example, on a platform, users with service privilege level 3 can enjoy more discounts than users with service privilege levels 1 or 2, and also receive extra points rewards when purchasing platform services. Meanwhile, users with service privilege level 5 can enjoy more exclusive services, such as dedicated customer service. Such service offerings can improve member satisfaction, promote user loyalty, and thus increase the platform's revenue.

[0101] Referring to Figure 2, Figure 2 is a schematic diagram of a process for obtaining recommended objects provided in an embodiment of this application.

[0102] In some embodiments, the process of obtaining the recommended object includes:

[0103] Step S201: Use the semantic extraction model corresponding to the input information to extract semantic information from the input information;

[0104] Step S202: Cluster the semantic information to obtain cluster information, which is used to indicate the service items required by the user;

[0105] Step S203: Obtain the similarity between the clustering information and each of the intermediate objects;

[0106] Step S204: Based on the similarity between the clustering information and each of the intermediate objects, select at least one of the intermediate objects as the recommended object.

[0107] Therefore, by extracting semantic information from the input information and then clustering the extracted semantic information, clustering information is obtained to indicate the user's needs. The similarity between intermediate objects and the clustering information is then calculated, and the most matching intermediate object is selected as the recommendation object. In other words, this application embodiment obtains recommendation objects based on semantic information extraction, clustering, and similarity calculation. On the one hand, by using semantic information extraction and clustering techniques, the type of service requested by the user can be more accurately indicated, thus facilitating the selection of intermediate objects with higher matching degrees for recommendation. Compared to performing similarity calculation through only semantic information extraction, this improves the accuracy of the recommendation service. On the other hand, although different users may submit the same service request, their expressions may differ. This application's technical solution can classify the service requests submitted by different users through semantic information extraction and clustering techniques, making the service requests submitted by different users more universal, thereby providing more suitable and comprehensive recommendation services and improving the universality of recommendation object acquisition. Furthermore, the use of semantic information extraction and clustering techniques in this application embodiment can reduce redundant recommendation objects and save system resources. On the other hand, it can provide more accurate and comprehensive recommendation services, which can help users find the services they need more quickly and easily, thereby enhancing users' trust and satisfaction with the platform.

[0108] Compared to simply using a semantic extraction model corresponding to the input information, extracting semantic information from the input information, obtaining the similarity between the semantic information and the intermediate object corresponding to each service item, and selecting at least one intermediate object as the recommended object based on the similarity of the intermediate object corresponding to each service item, this application embodiment not only extracts semantic information from the input information and calculates the similarity with the intermediate object of the service item, but also cleverly introduces a process of clustering semantic information, and then calculates the similarity based on the intermediate object to select the recommended object. From this perspective, after clustering, similar service items are classified into the same cluster, and only need to be considered once in the recommendation process, thus reducing and optimizing the number of recommended objects. This reduces the burden on users when reading recommended objects, improving user satisfaction and experience. At the same time, because the recommended objects more accurately match the required service items, it also reduces the need for users to repeatedly select services later, lowering user churn and enhancing the platform's commercial competitiveness.

[0109] In summary, the technical solution of this application first uses a semantic extraction model corresponding to the input information to extract semantic information from the input information. Then, this semantic information is clustered to obtain cluster information, which can be used to indicate the type of service requested by the user and reduce redundant recommendation objects. Next, the similarity between intermediate objects and the cluster information is calculated. Finally, at least one intermediate object with a high similarity match is selected as a recommendation object, reducing the burden on the user when reading recommendation objects and improving user satisfaction and experience.

[0110] This application does not limit the type of input information, which may include text, voice, or image information. When the input information is text, a touchscreen, keyboard, or similar device can be used for input. When the input information is voice, a microphone can be used for input. When the input information is image, a camera, mouse, or similar device can be used for input.

[0111] In some embodiments, when the input information is text information, the semantic extraction model corresponding to the input information is a pre-trained language model based on deep learning; when the input information is speech information, the semantic extraction model corresponding to the input information includes a speech-to-text model based on deep learning and a pre-trained language model based on deep learning; when the input information is image information, the semantic extraction model corresponding to the input information is a semantic segmentation model based on deep learning.

[0112] Therefore, deep learning-based models can be used to extract semantic features from input information. Different deep learning models are used for semantic extraction for different types of input information, including pre-trained language models, speech-to-text models, and semantic segmentation models.

[0113] For textual information, pre-trained language models, such as BERT and RoBERTa, are used to extract semantic features from the input text. These models, through pre-training on a large amount of text, can learn the structure and semantic information of the language, thus effectively extracting the semantic information of the input text.

[0114] For speech information, deep learning-based speech-to-text models, such as CTC and Transformer, are used to convert speech information into text information, and pre-trained language models are used to extract semantic features from the text information. In this way, semantic information related to the input information can be extracted from the speech information.

[0115] For image information, deep learning-based semantic segmentation models, such as UNet and DeepLab, are used to segment the image and extract the semantic information corresponding to each pixel. This allows for the accurate extraction of semantic information related to the input information from the image.

[0116] The advantages of this approach are that using deep learning-based semantic extraction models can more accurately extract the semantic features of input information, thereby improving the accuracy and efficiency of semantic understanding; using pre-trained language models can improve the capabilities of natural language processing, including text classification, sentiment analysis, and machine translation; and employing different deep learning models can enable the processing of multimodal information, including text, speech, and image information, thus achieving more comprehensive information processing.

[0117] As an example, when a user inputs the text "I am a teacher, I like to teach children, and I want to open an educational live stream with 100 students," a pre-trained language model can be used for semantic extraction and understanding. Through text processing techniques, the input text "I am a teacher, I like to teach children, and I want to open an educational live stream with 100 students" can be segmented, word-vectorized, and encoded into sentences. Then, a pre-trained model can be used to perform semantic understanding to obtain the corresponding semantic information.

[0118] Specifically, a semantic understander based on the BERT model can be used to convert the input text into corresponding representation vectors. These vectors are then calculated and compared to obtain the final semantic information. For the input information "I am a teacher, I like to teach children, and I want to open an educational live-streaming room with one hundred students," semantic understanding is performed as follows: First, the text is segmented into words and converted into corresponding word vector representations; then, the word vectors are input into the BERT model to obtain the representation vector at each position (including the outputs of all layers); then, the representation vectors at each position are weighted and summed to obtain the representation vector of the entire sentence; finally, the sentence representation vector is input into a classification model to obtain the final semantic classification result such as "education" or "one hundred students."

[0119] Furthermore, if a deep learning-based keyword extractor is used for semantic processing, keywords are first extracted from the input text, and then a prediction model is used to classify and summarize the keywords to obtain the corresponding semantic information. For example, for the input information "My live stream template is too simple," a deep learning-based keyword extractor can be used to process it, obtaining keywords such as "lacking template" and "simple template." These keywords are then input into the prediction model to obtain the semantic classification results.

[0120] The similarity between the clustering information and each of the intermediate objects can be calculated using a similarity model.

[0121] In one embodiment, calculating the similarity between the clustering information and any of the intermediate objects may include: inputting the clustering information and the intermediate objects into a similarity model to obtain the similarity between the clustering information and the intermediate objects.

[0122] In one embodiment, the training process of the similarity model may include:

[0123] Obtain a training set, which includes multiple training data, each of which includes training clustering information, training intermediate objects, and labeled data on the similarity between the training clustering information and the training intermediate objects;

[0124] For each training data point in the training set, the following processing is performed:

[0125] The training clustering information and intermediate training objects in the training data are input into a preset deep learning model to obtain predicted data on the similarity between the training clustering information and the intermediate training objects.

[0126] The model parameters of the deep learning model are updated based on the training clustering information and the predicted and labeled data of the similarity of the intermediate training objects.

[0127] Check whether the preset training termination condition is met; if yes, use the trained deep learning model as the similarity model; if no, continue training the deep learning model using the next training data.

[0128] This application does not limit the training process of the similarity model, which may be trained using supervised learning, semi-supervised learning, or unsupervised learning.

[0129] This application does not limit the preset training termination conditions. For example, it may be that the number of training sessions reaches a preset number (the preset number of training sessions may be 1, 3, 10, 100, 1000, 10000, etc.), or it may be that the training data in the training set has been trained once or multiple times, or it may be that the total loss value obtained in this training is not greater than the preset loss value.

[0130] This application does not limit the preset similarity threshold, which can be, for example, 81%, 83%, 92%, 95%, 99.9%, etc.

[0131] As an example, a user enters the following information: "I want to create an educational live stream, specifically for yoga, and recruit middle-aged female students." The recommended audience can be obtained through the following methods:

[0132] The platform uses a semantic extraction model to process user input and extract key information. For example, the model might identify keywords such as "educational live stream," "yoga education," and "middle-aged female students." The extracted key information is then clustered to determine the type of service the user needs. For instance, based on keywords in the user input, clustering might yield data such as "health exercise" and "education for middle-aged women." The platform can select appropriate intermediate objects, such as "Level 2 Member," "Level 3 Member," "Gold Member," and "Template Member." The similarity between the user's cluster information and each intermediate object is calculated. For example, the platform can use methods such as cosine similarity to obtain the similarity between the user's needs and "Level 2 Member."

[0133] One or more intermediate objects that best match the user's needs can be selected as recommendation objects. For example, in the example above, if the user's needs are clustered as "education for middle-aged women," and "Level 2 Membership" has the highest similarity, then the platform can recommend "Level 2 Membership" to the user.

[0134] In some embodiments, selecting at least one of the intermediate objects as the recommended object based on the similarity between the clustering information and each of the intermediate objects (i.e., step S204) includes:

[0135] When the highest similarity between any of the intermediate objects and the clustering information is greater than a preset similarity, the intermediate object corresponding to the highest similarity is taken as the recommended object;

[0136] When the highest similarity between any of the intermediate objects and the clustering information is not greater than a preset similarity, one or more associated users of the user are obtained based on the identification information; for each associated user, the object corresponding to the configured service item of the associated user is used as the recommended object.

[0137] The embodiments of this application do not limit the preset similarity, which may be, for example, 0.9, 0.8 or 70%.

[0138] Therefore, in the technical solution of this application, when the highest similarity between an intermediate object and the cluster information is greater than a preset similarity, the intermediate object is used as a recommended object. If the highest similarity between any intermediate object and the cluster information does not exceed the preset similarity, one or more associated users will be obtained based on the user's identification information, and the objects corresponding to the service items configured by these associated users will be used as recommended objects for the user to choose from. On the one hand, by clustering user needs and matching intermediate objects, the user's real needs can be better reflected, that is, more personalized and accurate service recommendations can be provided. On the other hand, when the similarity between an intermediate object and the cluster information is not high, recommendations can still be provided through the configuration information of associated users, increasing the reliability and diversity of recommendations and improving user satisfaction and service experience.

[0139] As an example, a user enters the following information: "I want to create a live legal consultation room, specifically on intellectual property law." The recommended audience can be selected in the following ways:

[0140] For user input, semantic extraction technology is used to process the input information and extract key information. For example, it might identify key information such as "legal consultation live stream" or "intellectual property law." Based on the key information, user needs are clustered and categorized into "intellectual property law consultation." For each candidate intermediate object (e.g., "Level 2 Member," "Level 3 Member," "Gold Member"), the similarity between it and the cluster information of the user's needs can be calculated. For example, the platform can use methods such as cosine similarity to calculate the similarity between it and the user's needs. For each candidate intermediate object, if its highest similarity with the user's cluster information is greater than a preset similarity, then the intermediate object will be selected as a recommended object. For example, if the similarity of "Level 2 Member" exceeds a set threshold, the platform will select "Level 2 Member" as the recommended object.

[0141] If the similarity of any candidate intermediate object does not meet the preset threshold, then the user's identification information will be used to obtain related users. For example, the platform may query other users with similar needs and select the intermediate objects corresponding to the service items configured by these users as the recommendation objects.

[0142] Referring to Figure 3, Figure 3 is a schematic diagram of a process for sending recommendation prompt information provided in an embodiment of this application.

[0143] In some embodiments, when the highest similarity between any of the intermediate objects and the clustering information is not greater than a preset similarity, the method further includes:

[0144] Step S106: Start the statistics and increment the count by one;

[0145] Step S107: Detect whether the number of statistical counts is greater than the preset number of statistical counts. If the number of statistical counts is greater than the preset number of statistical counts, clear the number of statistical counts and send a recommendation prompt message to the terminal device of the configuration personnel. The recommendation prompt message is used to remind the configuration personnel to pay attention to the user's input information.

[0146] In other embodiments, statistics continue to be performed when the number of statistical counts is not greater than the preset number of statistical counts.

[0147] The embodiments of this application do not limit the preset number of times, such as 9 times, 8 times or 3 times.

[0148] Therefore, when the highest similarity between any intermediate object and the cluster information is no greater than the preset similarity, the count is started and incremented by 1. Simultaneously, it is checked whether the count exceeds the preset count; if so, the count is reset to zero, and a recommendation prompt is sent to the configuration personnel's terminal device (i.e., the terminal configuration device). Configuration personnel can use this recommendation prompt to pay attention to user input, avoiding situations where user input does not receive positive or effective feedback, thus improving recommendation accuracy. On one hand, when existing intermediate objects or cluster information cannot meet user needs, recommendation prompts are sent to configuration personnel, prompting them to pay attention to user input, thereby improving the accuracy and adaptability of recommendations and enhancing the adaptability of the service configuration method. On the other hand, by setting and pre-setting the count to check the accuracy of intermediate objects and cluster information, the false positive rate can be reduced, improving recommendation accuracy. Furthermore, configuration personnel can adjust intermediate objects and cluster information promptly based on the recommendation prompts to update service options, thereby improving work efficiency and recommendation accuracy, and reducing unnecessary communication and adjustment costs when users do not receive the services they need.

[0149] In some embodiments, associating one or more service items with the user's identification information based on the user's selection operation to configure services for the user (i.e., step S105) includes:

[0150] When one or more of the recommended objects are selected by the user within a preset time interval, the service items corresponding to the selected recommended objects are associated with the user.

[0151] When no recommended object is selected by the user within a preset time interval, the associated recommended object of the user is obtained according to the identification information, and the associated recommended object is recommended to the user using the terminal device.

[0152] The associated recommendation object is used to indicate one or more configured service items of the user's associated users. This application embodiment does not limit the preset time interval, which may be, for example, 1 hour, 10 minutes, or 3 minutes.

[0153] Therefore, based on the user's selections, one or more service items can be matched with the user's identification information to configure services for the user. If no recommended item is selected by the user within a preset time interval, the associated recommended items can be obtained based on the user's identification information and recommended to the user using the terminal device. This allows users to receive helpful suggestions when unable to make a choice, helping them better configure their services, thereby improving service quality and efficiency.

[0154] On the one hand, by associating with user identification information, user needs can be accurately determined and identified, and services can be recommended and configured in a timely manner based on user selections and preset time intervals, improving the efficiency of service configuration. On the other hand, by setting preset time intervals, user selection behavior can be observed and understood over a certain period, providing recommendations for services that better meet user needs and preferences, thereby improving the user experience. Furthermore, users can select the services they need based on their own requirements and associate them with identification information, enabling more accurate service configuration, enhancing user initiative and accuracy in service configuration, and improving user understanding and awareness of the services. Moreover, when a user selects a recommended service, the service corresponding to the selected service is automatically associated with the user, saving configuration personnel time and effort.

[0155] As an example, a user enters the following information: "I want to create a live music tutoring room for violin lessons, with a requirement of 200 students taking classes simultaneously." The service can be configured for the user in the following ways:

[0156] For user input, semantic extraction technology is first used to process the input information, extracting key information such as "music tutoring live stream," "violin teaching," and "200 students taking classes simultaneously." Clustering is then performed based on this key information, categorizing the user's service needs into "violin teaching live stream." For each candidate intermediate member (e.g., "Level 2 Member," "Level 3 Member," "Gold Member"), corresponding service items can be configured. For example, "Gold Member" might include the service item "supports large-scale online live streaming." "Gold Member" is then recommended. When a user selects "Gold Member," the platform associates the service items corresponding to "Gold Member" with the user's identification information.

[0157] If a user selects one or more recommended items within a preset time interval, the service corresponding to that recommended item will be associated with the user's identification information. For example, assuming a user selects "Gold Membership" within a week, the "Support for large-scale online live streaming" service will be associated with the user's identification information based on the user's selected action.

[0158] If no recommended item is selected by the user within a preset time interval, then the platform will retrieve associated recommended items using the user's identification information and recommend these associated recommended items to the user using the terminal device. For example, the platform may query other users with similar needs to retrieve the recommended items used by these users and send these recommended items to the current user.

[0159] Referring to Figure 4, Figure 4 is a schematic diagram of a process for obtaining associated recommendation objects provided in an embodiment of this application.

[0160] In some embodiments, when no recommended object is selected by the user within a preset time interval, obtaining the user's associated recommended objects based on the identification information and recommending the associated recommended objects to the user using the terminal device includes:

[0161] Step S301: Obtain the identifier similarity between the identifier information and the identifier information of multiple historical users, and identify one or more of the historical users with the highest identifier similarity as the associated users;

[0162] Step S302: Based on the historical recommendation data of the associated user, obtain the service items of the associated user, and use the objects corresponding to the service items of the associated user as the associated recommendation objects of the user;

[0163] The historical recommendation data includes one or more service items associated with the associated user, and recommendation feedback for each service item, including the associated user's rating and / or clicks on the service item.

[0164] Therefore, when a user does not select any recommended object within a preset time interval, the system retrieves the user's associated recommended objects based on the user's identification information. Specifically, it obtains the similarity between the user's identification information and the identification information of historical users. By calculating the similarity, the historical users most similar to the current user can be identified, thus determining associated users. In other words, these associated users have similar identification information to the current user, and their service needs and purchasing behaviors may also be similar to the current user. Based on the historical recommendation data of associated users, their service items are obtained, and their corresponding recommended objects are used as associated recommended objects for the current user. These recommended objects have been verified by historical users and can better meet the current user's needs. Finally, the associated recommended objects are recommended to the current user to help them make a selection and complete the service configuration. The technical solution of this application can provide users with more personalized service recommendations based on user identification information and historical recommendation data. At the same time, it can also promote user participation and feedback on services, continuously improving service quality and user satisfaction.

[0165] As an example, the historical user database records each user's identification information, service items, and recommendation feedback. If no candidate is selected by the user within a preset time interval, associated recommended objects can be retrieved and recommended to the user through the following process:

[0166] First, based on the user's identifier information, query the historical user database for historical users similar to this user. Various existing algorithms can be used for the query, such as cosine similarity and Jaccard similarity. Suppose three historical users similar to this user are found: UserA, UserB, and UserC.

[0167] For each historical user similar to the current user, their historical recommendation data is analyzed. For example, we can extract that UserA's historical recommendation data includes the service item "live violin lessons," and the recommended target for this service item is "Gold Membership." Furthermore, UserA rated this service item 4 stars (out of 5 stars).

[0168] The platform statistically analyzes and sorts the historical recommendation data of all users with similar histories, and selects the recommended services with higher scores as the associated recommended services for that user. For example, for the "violin lesson live stream" service, the platform calculates that the corresponding recommended service "Gold Member" has a score of 12 (meaning that User A, User B, and User C all have this recommended service), while the scores for other alternative services are 6 and 8 respectively. Therefore, "Gold Member" is selected as the associated recommended service for that user.

[0169] The device is used to recommend relevant items to the user. The recommendations may include information such as the name, price, and service details of the recommended item.

[0170] Referring to Figure 5, Figure 5 is a schematic diagram of a process for obtaining a service object provided in an embodiment of this application.

[0171] In some embodiments, the step of obtaining the service items of the associated user based on the historical recommendation data of the associated user, and using the object corresponding to the service item of the associated user as the associated recommendation object of the user (i.e., step S302) includes:

[0172] Step S401: Based on the recommendation feedback, obtain feedback scores for one or more service items associated with the associated user;

[0173] Step S402: The object corresponding to the service item with the highest feedback rating is used as the associated recommendation object for the user;

[0174] Step S403: Detect whether the largest feedback score is less than the preset score; when the largest feedback score is less than the preset score, generate a score prompt message and send it to the terminal device of the configuration personnel. The score prompt message is used to prompt the configuration personnel to pay attention to the user's identification information.

[0175] This application does not limit the preset score, which may be, for example, 100 points, 80 points, A, or B+. This application does not limit the content and form of the score prompt information. For example, it may be a pop-up notification on the terminal configuration device, with the text "Please note that user A's identification information is abnormal." Alternatively, it may be a voice notification on the terminal configuration device, with the voice message "Please note that user A's identification information is abnormal."

[0176] Therefore, when a user does not select a recommended service, similar historical users are identified based on the user's identifiers, and service items and their feedback ratings are retrieved from their historical recommendation data. The service item corresponding to the highest rating is then selected as the user's associated recommended service. Simultaneously, if the highest rating is lower than a preset rating, a rating alert is generated and sent to the configuration personnel, allowing them to provide better service recommendations for specific users. On one hand, this helps users quickly obtain associated recommended services when they haven't selected one, thereby improving their service experience and satisfaction. On the other hand, by utilizing historical recommendation data, users can obtain more personalized and accurate recommendations, which also helps improve service quality. Furthermore, even when the rating is lower than the preset value, recommended services are generated first, followed by a rating alert sent to the relevant configuration personnel, ensuring customers receive better service and support. In summary, this improves the adaptability and intelligence of the service configuration method.

[0177] In some embodiments, before step S402 and after step S401, the following steps may also be included:

[0178] Based on the user profile, multiple objects corresponding to the service items of the user profile are used as alternative recommendation objects for the user;

[0179] The candidate recommended objects are used as associated recommended objects for the user, and the recommended objects are recommended to the user using the terminal device. The terminal device is used to receive the user's selection operation for the recommended objects.

[0180] User profiling refers to the analysis and modeling of users in order to better understand their needs and launch content or services that better match their interests and preferences.

[0181] User profiles can include the following aspects: basic information (user's gender, age, geographical location, etc.), behavioral preferences (user's browsing history, search history, purchase history), and psychological characteristics (user's personality traits, attitudes, emotions, etc.).

[0182] In a specific application scenario, this application embodiment provides a service configuration method, the method including:

[0183] The user's recommendation request is obtained using a terminal device, and the recommendation request includes the user's identification information and input information;

[0184] Based on the identification information and the candidate objects, an intermediate object is obtained from a plurality of candidate objects;

[0185] Based on the intermediate object and the input information, a recommended object is obtained, and the recommended object is recommended to the user using the terminal device; the recommended object is used to indicate one or more service items for the user;

[0186] The terminal device is used to receive the user's selection of the recommended object;

[0187] Based on the user's selected action, one or more of the service items are associated with the user's identification information to achieve service configuration for the user.

[0188] The process of obtaining the recommended object includes:

[0189] Using the semantic extraction model corresponding to the input information, semantic information is extracted from the input information;

[0190] The semantic information is clustered to obtain cluster information, which is used to indicate the service items required by the user.

[0191] Obtain the similarity between the clustering information and each of the intermediate objects;

[0192] When the highest similarity between any of the intermediate objects and the clustering information is greater than a preset similarity, the intermediate object corresponding to the highest similarity is taken as the recommended object;

[0193] When the highest similarity between any of the intermediate objects and the clustering information is not greater than a preset similarity, one or more associated users of the user are obtained according to the identification information; at the same time, statistics are started and the number of statistics is incremented by one; it is detected whether the number of statistics is greater than a preset number of statistics. When the number of statistics is greater than the preset number of statistics, the number of statistics is cleared to zero, and a recommendation prompt message is sent to the terminal device of the configuration personnel. The recommendation prompt message is used to remind the configuration personnel to pay attention to the user's input information.

[0194] For each associated user, the object corresponding to the configured service item of the associated user is used as the recommended object.

[0195] As an example, the platform provides users with various services, such as live stream recommendations, live stream management, and display templates. To improve user experience, services can be configured in the following way in one example:

[0196] Users send recommendation requests using terminal devices (such as mobile apps), which include the user's identification information and input information. For example, a Level 1 member user might comment during a live stream that the currently displayed page is too plain and needs more template options. Their identification information would be UserA, and their input information would be "The page currently displayed during my live stream is too plain; I need more template options."

[0197] Based on the user's identification information and candidate objects, an intermediate object is obtained from multiple candidate objects. In this example, the criteria for selecting an intermediate object from the candidate objects may include user level, online time, historical viewing records, etc. Assume that the platform analyzes user levels to obtain all members who meet the requirements of the current level, and uses "Level 2 Member", "Level 3 Member", "Gold Member", and "Template Member" as intermediate objects.

[0198] The recommended object is obtained based on the intermediate object and user input information. The recommended object refers to an object used to indicate one or more service items to the user. The recommended object could be "Template Membership," whose corresponding service item is "Open more template display permissions." The recommended object is then presented to the user, awaiting their selection. In this example, "Template Membership" is recommended to UserA, and the member's template resources can be simultaneously displayed on the user's terminal device's app page.

[0199] Users select from the recommended services and send their selection via their terminal devices. Based on the user's selection, the chosen service is associated with the user's identification information.

[0200] As another example, building upon the previous one, to better recommend services suitable for users, a semantic extraction model corresponding to the input information was used during the process of obtaining recommendation objects. After the user sends a recommendation request, the platform uses the semantic extraction model to extract semantic information from the input information, such as "need more template options" and "personalized templates".

[0201] User needs are clustered based on the extracted semantic information to obtain cluster information. For example, user needs can be clustered into "templates". The similarity between each intermediate object and the cluster information is calculated, and the intermediate object with the highest similarity is selected as the recommendation object. For example, if "template member" is found to have the highest similarity to the cluster information among all intermediate objects, it is selected as the recommendation object.

[0202] Additionally, if no intermediate object has a similarity score higher than a preset similarity threshold (e.g., 0.8) with the cluster information, then associated users are obtained based on user identification information, along with their configuration information. For example, if UserA's associated user is UserB, the platform will retrieve the service items already configured by UserB, such as UserB having selected "Gold Membership." "Gold Membership" will then be used as the recommended service.

[0203] Simultaneously, when the highest similarity between any of the intermediate objects and the clustering information is no greater than a preset similarity, the number of user recommendations is counted, and it is checked whether the number of recommendations exceeds a preset threshold. When the count exceeds the preset threshold, a recommendation prompt message is sent to the administrator's terminal configuration device to remind the administrator to pay attention to user needs in order to optimize the service.

[0204] In another specific application scenario, this application embodiment provides yet another service configuration method, the method comprising:

[0205] The user's recommendation request is obtained using a terminal device, and the recommendation request includes the user's identification information and input information;

[0206] Based on the identification information and the candidate objects, an intermediate object is obtained from a plurality of candidate objects;

[0207] Based on the intermediate object and the input information, a recommended object is obtained, and the recommended object is recommended to the user using the terminal device; the recommended object is used to indicate one or more service items for the user;

[0208] The terminal device is used to receive the user's selection of the recommended object;

[0209] When one or more of the recommended objects are selected by the user within a preset time interval, the service items corresponding to the selected recommended objects are associated with the user.

[0210] When no recommended object is selected by the user within a preset time interval, the similarity between the identifier information and the identifier information of multiple historical users is obtained, and one or more historical users with the highest identifier similarity are identified as associated users; based on the recommendation feedback, the feedback ratings of one or more service items associated with the associated user are obtained; the object corresponding to the service item with the highest feedback rating is identified as the associated recommended object of the user; it is detected whether the highest feedback rating is less than a preset rating; when the highest feedback rating is less than the preset rating, a rating prompt message is generated and sent to the terminal device of the configuration personnel, and the rating prompt message is used to prompt the configuration personnel to pay attention to the user's identifier information.

[0211] The historical recommendation data includes one or more service items associated with the associated user, and recommendation feedback for each service item. The recommendation feedback includes the associated user's rating and / or clicks on the service item. The associated recommendation item is used to indicate one or more configured service items of the user's associated users.

[0212] Electronic device examples

[0213] This application also provides an electronic device, the specific embodiments of which are consistent with the embodiments and technical effects achieved in the above method embodiments, and some contents will not be repeated.

[0214] The electronic device includes a memory and at least one processor, the memory storing a computer program, and the at least one processor being configured to execute the computer program to perform the following steps:

[0215] The user's recommendation request is obtained using a terminal device, and the recommendation request includes the user's identification information and input information;

[0216] Based on the identification information and the candidate objects, an intermediate object is obtained from a plurality of candidate objects;

[0217] Based on the intermediate object and the input information, a recommended object is obtained, and the recommended object is recommended to the user using the terminal device; the recommended object is used to indicate one or more service items for the user;

[0218] The terminal device is used to receive the user's selection of the recommended object;

[0219] Based on the user's selected action, one or more of the service items are associated with the user's identification information to achieve service configuration for the user.

[0220] In some embodiments, the at least one processor is configured to obtain the recommended object when executing the computer program in the following manner:

[0221] Using the semantic extraction model corresponding to the input information, semantic information is extracted from the input information;

[0222] The semantic information is clustered to obtain cluster information, which is used to indicate the service items required by the user.

[0223] Obtain the similarity between the clustering information and each of the intermediate objects;

[0224] Based on the similarity between the clustering information and each of the intermediate objects, at least one of the intermediate objects is selected as the recommended object.

[0225] In some embodiments, the at least one processor is configured to select at least one of the intermediate objects as the recommended object based on the similarity between the clustering information and each of the intermediate objects when executing the computer program:

[0226] When the highest similarity between any of the intermediate objects and the clustering information is greater than a preset similarity, the intermediate object corresponding to the highest similarity is taken as the recommended object;

[0227] When the highest similarity between any of the intermediate objects and the clustering information is not greater than a preset similarity, one or more associated users of the user are obtained based on the identification information;

[0228] For each associated user, the object corresponding to the configured service item of the associated user is used as the recommended object.

[0229] In some embodiments, when the highest similarity between any of the intermediate objects and the clustering information is no greater than a preset similarity, the at least one processor configured to execute the computer program further implements the following steps:

[0230] Start the statistics and increment the count by one;

[0231] The system checks whether the number of statistical counts is greater than a preset number of statistical counts. If the number of statistical counts is greater than the preset number of statistical counts, the number of statistical counts is cleared to zero, and a recommendation prompt message is sent to the terminal device of the configuration personnel. The recommendation prompt message is used to remind the configuration personnel to pay attention to the user's input information.

[0232] In some embodiments, the at least one processor is configured to, when executing the computer program, associate one or more of the service items with the user's identification information based on the user's selected operation, in order to configure services for the user:

[0233] When one or more of the recommended objects are selected by the user within a preset time interval, the service items corresponding to the selected recommended objects are associated with the user.

[0234] When no recommended object is selected by the user within a preset time interval, the associated recommended object of the user is obtained according to the identification information, and the associated recommended object is recommended to the user using the terminal device.

[0235] The associated recommendation object is used to indicate one or more configured service items of the user's associated users.

[0236] In some embodiments, when no recommended object is selected by the user within a preset time interval, the at least one processor is configured to, when executing the computer program, obtain the user's associated recommended objects based on the identification information, and recommend the associated recommended objects to the user using the terminal device:

[0237] Obtain the identifier similarity between the identifier information and the identifier information of multiple historical users, and identify one or more of the historical users with the highest identifier similarity as the associated users;

[0238] Based on the historical recommendation data of the associated users, the service items of the associated users are obtained, and the objects corresponding to the service items of the associated users are used as the associated recommendation objects of the users.

[0239] The historical recommendation data includes one or more service items associated with the associated user, and recommendation feedback for each service item, including the associated user's rating and / or clicks on the service item.

[0240] In some embodiments, the at least one processor is configured to, when executing the computer program, obtain the service items of the associated user based on the historical recommendation data of the associated user, and use the objects corresponding to the service items of the associated user as the associated recommendation objects of the user:

[0241] Based on the recommended feedback, obtain feedback ratings for one or more service items associated with the associated user;

[0242] The service item corresponding to the highest feedback score will be used as the associated recommendation object for the user.

[0243] Detect whether the maximum feedback score is less than a preset score;

[0244] When the maximum feedback score is less than the preset score, a score prompt message is generated and sent to the configuration personnel's terminal device. The score prompt message is used to remind the configuration personnel to pay attention to the user's identification information.

[0245] Referring to Figure 6, which is a structural block diagram of an electronic device provided in an embodiment of this application.

[0246] Electronic device 10 may include, for example, at least one memory 11, at least one processor 12, and a bus 13 connecting different platform systems.

[0247] The memory 11 may include a (computer) readable medium in the form of volatile memory, such as random access memory (RAM) 111 and / or cache memory 112, and may further include read-only memory (ROM) 113.

[0248] The memory 11 also stores a computer program, which can be executed by the processor 12 to enable the processor 12 to implement the steps of any of the above methods.

[0249] The memory 11 may also include a utility 114 having at least one program module 115, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0250] Accordingly, processor 12 can execute the aforementioned computer program, and can also execute utility 114.

[0251] The processor 12 may employ one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0252] Bus 13 can represent one or more types of bus structures, including a memory bus or memory controller, peripheral bus, graphics acceleration port, processor, or a local bus using any bus structure with multiple bus structures.

[0253] Electronic device 10 can also communicate with one or more external devices, such as keyboards, pointing devices, Bluetooth devices, etc., and with one or more devices capable of interacting with it, and / or with any device that enables it to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication can be performed through input / output interface 14. Furthermore, electronic device 10 can communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via network adapter 15. Network adapter 15 can communicate with other modules of electronic device 10 via bus 13. It should be understood that, although not shown in the figures, in practical applications, other hardware and / or software modules can be used in conjunction with electronic device 10, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0254] Computer-readable storage medium embodiments

[0255] This application also provides a computer-readable storage medium, the specific embodiments of which are consistent with the embodiments and technical effects achieved in the above method embodiments, and some contents will not be repeated.

[0256] The computer-readable storage medium stores a computer program that, when executed by at least one processor, implements the steps of any of the above methods or the functions of any of the above electronic devices.

[0257] A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. In embodiments of this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0258] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable storage medium may also be any computer-readable medium capable of sending, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, or any suitable combination thereof. Program code for performing operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar programming languages. The program code may be executed entirely on a user computing device, partially on a user device, as a standalone software package, partially on a user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to user computing devices via any type of network, including local area networks (LANs) or wide area networks (WANs), or they can be connected to external computing devices (e.g., via the Internet using an Internet service provider).

[0259] Computer program product examples

[0260] This application also provides a computer program product, the specific embodiments of which are consistent with the embodiments and technical effects achieved in the above method embodiments, and some contents will not be repeated.

[0261] This application provides a computer program product comprising a computer program that, when executed by at least one processor, implements the steps of any of the above-described methods or the functions of any of the above-described electronic devices.

[0262] Referring to Figure 7, Figure 7 is a schematic diagram of the structure of a computer program product provided in an embodiment of this application.

[0263] The computer program product is used to implement the steps of any of the above methods or to implement the functions of any of the above electronic devices. The computer program product may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the computer program product of the present invention is not limited thereto, and the computer program product may employ any combination of one or more computer-readable media.

[0264] It should be noted that in the embodiments of this application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes 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, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "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, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple. It is worth noting that "at least one" can also be interpreted as "one or more".

[0265] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are configured to distinguish similar objects and are not necessarily configured to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0266] This application describes the invention from the perspectives of purpose, performance, progress, and novelty, and it meets the functional enhancement and use requirements emphasized by the Patent Law. The above description and drawings are merely preferred embodiments of this application and are not intended to limit this application. Therefore, all structures, devices, features, etc., that are similar to or identical to those of this application, i.e., all equivalent substitutions or modifications made in accordance with the scope of this patent application, shall fall within the scope of protection of this patent application.

Claims

1. A service configuration method, characterized in that, The method includes: acquiring a user's recommendation request using a terminal device, the recommendation request including the user's identification information and input information; acquiring an intermediate object from a plurality of candidate objects based on the identification information and candidate objects; wherein the intermediate object is an object filtered based on the user's identification information; acquiring a recommended object based on the intermediate object and the input information, and recommending the recommended object to the user using the terminal device; the recommended object is used to indicate one or more service items for the user; receiving the user's selection operation on the recommended object using the terminal device; associating one or more service items with the user's identification information based on the user's selection operation to realize service configuration for the user; the process of acquiring the recommended object includes: making Using the semantic extraction model corresponding to the input information, semantic information is extracted from the input information; the semantic information is clustered to obtain cluster information, which is used to indicate the service items required by the user; the similarity between the cluster information and each intermediate object is obtained; if there is an intermediate object with a similarity greater than a preset similarity with the cluster information, the intermediate object with the highest similarity is selected as the recommended object; if there is no intermediate object with a similarity greater than the preset similarity with the cluster information, a backup recommendation step is executed, which includes: matching associated users based on the identification information and selecting the configured service items of the associated users as recommended objects; the method further includes: if the user does not select any recommended object within a preset time interval, the backup recommendation step is executed.

2. The service configuration method according to claim 1, characterized in that, The step of matching associated users based on the identification information includes: obtaining one or more associated users of the user according to the identification information; and for each associated user, using the object corresponding to the configured service item of the associated user as the recommended object.

3. The service configuration method according to claim 2, characterized in that, When executing the backup recommendation step, the method further includes: starting statistics and incrementing the number of statistics by one; detecting whether the number of statistics is greater than a preset number of statistics; when the number of statistics is greater than the preset number of statistics, clearing the number of statistics to zero and sending a recommendation prompt message to the terminal device of the configuration personnel, the recommendation prompt message being used to remind the configuration personnel to pay attention to the user's input information.

4. The service configuration method according to claim 1, characterized in that, The step of associating one or more of the service items with the user's identification information based on the user's selection operation to realize service configuration for the user includes: when one or more of the recommended objects are selected by the user within a preset time interval, associating the service items corresponding to the selected recommended objects with the user.

5. The service configuration method according to claim 4, characterized in that, When performing the backup recommendation step, the step of using the configured service items of the associated user as recommendation objects includes: obtaining the identifier similarity between the identifier information and the identifier information of multiple historical users, and selecting one or more of the historical users with the highest identifier similarity as the associated user; obtaining the service items of the associated user based on the historical recommendation data of the associated user, and selecting the objects corresponding to the service items of the associated user as the associated recommendation objects of the user; wherein, the historical recommendation data includes one or more service items associated with the associated user, and recommendation feedback for each service object, and the recommendation feedback includes the associated user's rating and / or clicks on the service items.

6. The service configuration method according to claim 5, characterized in that, The step of obtaining the service items of the associated user based on the historical recommendation data of the associated user, and using the objects corresponding to the service items of the associated user as the associated recommendation objects of the user, includes: obtaining the feedback ratings of one or more service items associated with the associated user based on the recommendation feedback; using the object corresponding to the service item with the highest feedback rating as the associated recommendation object of the user; detecting whether the highest feedback rating is less than a preset rating; when the highest feedback rating is less than the preset rating, generating a rating prompt message and sending it to the terminal device of the configuration personnel, wherein the rating prompt message is used to prompt the configuration personnel to pay attention to the user's identification information.

7. An electronic device, characterized in that, The electronic device includes a memory and at least one processor. The memory stores a computer program, and the at least one processor is configured to execute the computer program to perform the following steps: obtaining a user's recommendation request using a terminal device, the recommendation request including the user's identification information and input information; obtaining an intermediate object from a plurality of candidate objects based on the identification information and candidate objects; wherein the intermediate object is an object filtered based on the user's identification information; obtaining a recommended object based on the intermediate object and the input information, and recommending the recommended object to the user using the terminal device; the recommended object is used to indicate one or more service items for the user; receiving the user's selection operation on the recommended object using the terminal device; and, based on the user's selection operation, recommending one or more service items and the user's identification information to the user. The process of obtaining the recommended object includes: using a semantic extraction model corresponding to the input information to extract semantic information from the input information; clustering the semantic information to obtain clustering information, which is used to indicate the service items required by the user; obtaining the similarity between the clustering information and each intermediate object; if there is an intermediate object with a similarity greater than a preset similarity with the clustering information, then the intermediate object with the highest similarity is taken as the recommended object; if there is no intermediate object with a similarity greater than the preset similarity with the clustering information, then a backup recommendation step is executed, which includes: matching associated users based on the identification information and taking the configured service items of the associated users as recommended objects; if the user does not select any recommended object within a preset time interval, then the backup recommendation step is executed.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by at least one processor, implements the steps of the method of any one of claims 1-6 or the function of the electronic device of claim 7.

9. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by at least one processor, implements the steps of the method of any one of claims 1-6 or the function of the electronic device of claim 7.

Images