CN116756416A

CN116756416A - Service configuration method, electronic device, storage medium, and program product

Info

Publication number: CN116756416A
Application number: CN202310637853.5A
Authority: CN
Inventors: 柴金详; 谭宏冰; 栾欣洋; 李熹昊
Original assignee: Shanghai Movu Technology Co Ltd; Mofa Shanghai Information Technology Co Ltd
Current assignee: Shanghai Movu Technology Co Ltd; Mofa Shanghai Information Technology Co Ltd
Priority date: 2023-05-31
Filing date: 2023-05-31
Publication date: 2023-09-15

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: acquiring a recommendation request of a user by using terminal equipment, wherein the recommendation request comprises identification information and input information of the user; acquiring an intermediate object from a plurality of alternative objects according to the identification information and the alternative objects; acquiring a recommended object according to the intermediate object and the input information, and recommending the recommended object to a user by using terminal equipment; the recommendation object is used for indicating one or more service items for the user; receiving a selection operation of a user on a recommended object by using terminal equipment; and associating one or more service matters with the identification information of the user according to the selection operation of the user so as to realize service configuration of the user. Screening the intermediate objects by using the identification information of the user, analyzing and matching the input information to obtain recommended objects, and pushing the recommended objects to the user, so that the requirement of the user on personalized service configuration is met.

Description

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

Technical Field

The present application relates to the technical field of computer applications, and in particular, to a service configuration method, an electronic device, a computer readable storage medium, and a computer program product.

Background

With the continuous maturity of streaming media technology and the continuous promotion of network environment, the network live broadcast platform is more and more widespread, and users can live various live broadcasts including games, entertainment programs and audios and videos by using the network live broadcast platform.

The platform needs to provide different services for users with different live broadcast demands through service configuration. The existing service configuration method for the user is only suitable for the traditional field, and the requirements of the user on personalized service configuration after the continuous maturity of streaming media technology and the continuous promotion of network environment are not considered. Based on this, the present application provides a service configuration method, an electronic device, a computer-readable storage medium and a computer program product to improve the prior art.

Disclosure of Invention

The application aims to provide a service configuration method, electronic equipment, a computer readable storage medium and a computer program product, wherein the method comprises the steps of screening intermediate objects by utilizing identification information of a user, analyzing and matching input information to obtain recommended objects and pushing the recommended objects to the user, further refining the intermediate objects to obtain the recommended objects and pushing the recommended objects to the user, carrying out service configuration according to selection operation of the user on the recommended objects, and meeting the requirement of the user on personalized service configuration

The application adopts the following technical scheme:

in a first aspect, the present application provides a service configuration method, the method including:

acquiring a recommendation request of a user by using terminal equipment, wherein the recommendation request comprises identification information and input information of the user;

acquiring an intermediate object from a plurality of candidate objects according to the identification information and the candidate objects;

acquiring a recommended object according to the intermediate object and the input information, and recommending the recommended object to the user by using the terminal equipment; the recommended object is used for indicating one or more service items for the user;

receiving a selection operation of the user on the recommended object by using the terminal equipment;

and associating 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 beneficial effect of this technical scheme lies in: therefore, the service configuration method provided by the embodiment of the application obtains the recommendation request of the user through the terminal equipment, and then obtains the intermediate object from the plurality of candidate objects according to the identification information. And acquiring a recommended object according to the intermediate object and the input information, and recommending the recommended object to the user by using the terminal equipment so as to indicate one or more service items selectable by the user. And after the user performs the selection operation, associating one or more service items selected by the user with the identification information of the user so as to realize personalized service configuration for the user. It can be understood that the recommended object is obtained by using the intermediate object and the input information, so that the accuracy of recommendation is greatly improved, and the user obtains more customized service experience. On the one hand, the terminal equipment is utilized to automatically finish service recommendation, selection and configuration, manual intervention is not needed, the efficiency is greatly improved, and the automation level is high. On the other hand, the preference of the user can be quickly obtained according to the identification information and the input information of the user, so that personalized configuration of the user service is realized. On the other hand, the recommendation request of the user can be responded in real time, and the service configuration can be timely adjusted according to the selection operation of the user, so that the real-time performance of the service is greatly improved.

Compared with the selection of recommended objects in the related service configuration method, the method and the device have the advantages that the recommended objects are directly selected from all the candidate objects according to the input information of the user, and the method and the device only consider the thought of subjective requirements of the user (subjectivity of the input information is strong). And after the intermediate object is selected, the selection range can be reduced, so that the search time is shortened, and the acquisition efficiency of the recommended object is improved. On the other hand, when there are too many candidate objects, there is a problem that the recommendation accuracy is not high by directly selecting the recommended object from the candidate objects. And after the intermediate object is selected, the intermediate object is further screened according to the input information, so that a recommended object which is more matched with the requirement of the user can be obtained, and the recommendation precision is improved. In yet another aspect, the intermediate object may be selected based on user information, user rights, or identification information such as a level of the user, thereby supporting personalized services. Compared with the method for directly selecting the recommended object from the candidate objects, the method can meet the requirement of personalized service of the user. On the other hand, in the case where the number of candidate objects is large, selecting the recommended object directly from the candidate objects results in a large amount of computation, thereby increasing the computation cost. And after the intermediate object is selected, the calculation amount can be reduced, and the calculation cost is reduced. On the other hand, because the intermediate object corresponding to the identification information of the user is determined first, when the recommended object is selected from the commodity library of the intermediate object, the requirement of the user is met better, and the recommendation accuracy is improved.

In summary, the technical scheme of the application firstly utilizes the identification information (objective attributes such as user information, user authority or level) of the user to screen the intermediate object, and then further refines the intermediate object to obtain the recommended object and pushes the recommended object to the user through analysis and matching of the input information. And finally, configuring one or more service items to the user according to the selection operation of the user on the recommended object, so as to meet the requirement of the user on personalized service configuration.

In some possible implementations, the process of obtaining the recommended object includes:

extracting semantic information from the input information by using a semantic extraction model corresponding to the input information;

clustering the semantic information to obtain clustering information, wherein the clustering information is used for indicating service matters required by the user;

obtaining the similarity between the clustering information and each intermediate object;

and selecting at least one intermediate object as the recommended object according to the similarity between the clustering information and each intermediate object.

The beneficial effect of this technical scheme lies in: the clustering information used for indicating the user needs is obtained by extracting semantic information from input information and then clustering the extracted semantic information. And then calculating the similarity between the intermediate object and the clustering information, and selecting the best matched intermediate object as a recommended object. Namely, the embodiment of the application carries out the acquisition of the recommended object based on semantic information extraction, clustering and similarity calculation. On the one hand, through the semantic information extraction and clustering technology, the service item types required by the user can be more accurately prompted, so that the recommendation of the intermediate object with higher matching degree is facilitated, and compared with the recommendation of the intermediate object by only extracting one step through the semantic information, the accuracy of the recommended service is improved. On the other hand, although different users may put forth the same service requirements, the expressions are different. According to the technical scheme, the service requests submitted by different users can be classified through semantic information extraction and clustering technology, namely, the service requests submitted by different users are more universal, so that more proper and comprehensive recommended services can be provided, and the universality of acquiring recommended objects is improved. On the other hand, the embodiment of the application adopts semantic information extraction and clustering technology, so that redundant recommended objects can be reduced, and system resources are saved. On the other hand, more accurate and comprehensive recommended service can be provided, so that the user can be helped to find the required service matters more quickly and easily, and the trust feeling and satisfaction degree of the user on the platform are enhanced.

Compared with the mode of only using a semantic extraction model corresponding to the input information to extract semantic information from the input information, obtaining the similarity of the semantic information and the intermediate objects corresponding to each service item, and selecting at least one intermediate object as the recommended object according to the similarity of the intermediate objects corresponding to each service item. In this regard, after clustering, similar service items are categorized into the same cluster, and only need to be considered once in the recommendation process, and reduction and optimization can be achieved on the number of recommended objects. Therefore, the burden of the user when reading the recommended object can be reduced, and the satisfaction degree and experience feeling of the user are improved. Meanwhile, as the recommended objects more accurately match the required service matters, the subsequent repeated service selection of the user can be reduced, the user loss rate is reduced, and the business competitiveness of the platform side is enhanced.

In summary, the technical scheme of the application firstly uses a semantic extraction model corresponding to the input information to extract semantic information from the input information. The semantic information is then clustered to obtain clustered information, which can be used to indicate the type of service items required by the user, and can reduce redundant recommended objects. The similarity of the intermediate object to the cluster information is then calculated. And finally, selecting at least one of the intermediate objects with high similarity matching degree as a recommended object, reducing the burden of a user when reading the recommended object, and improving the satisfaction and experience of the user.

In some possible implementations, the selecting at least one intermediate object as the recommended object according to the similarity between the cluster information and each intermediate object includes:

when the highest similarity between any intermediate object and the clustering information is larger than a preset similarity, taking the intermediate object corresponding to the highest similarity as the recommended object;

when the highest similarity between any intermediate object and the clustering information is not more than the preset similarity, acquiring one or more associated users of the users according to the identification information;

And aiming at each associated user, taking an object corresponding to the configured service item of the associated user as the recommended object.

The beneficial effect of this technical scheme lies in: in the technical scheme of the application, when the highest similarity between a certain intermediate object and the clustering information is greater than the preset similarity, the intermediate object is used as a recommended object. If the highest similarity between any intermediate object and the clustering information does not exceed the preset similarity, one or more associated users are obtained according to the identification information of the users, and the objects corresponding to the service items configured by the associated users are used as recommended objects for the users to select. On the one hand, the real demands of the user can be better reflected through the clustering of the demands of the user and the matching of the intermediate objects, namely, more personalized and accurate service recommendation is provided. On the other hand, when the similarity between a certain intermediate object and the clustering information is not high, the recommendation can still be provided by associating the configuration information of the user, so that the reliability and diversity of the recommendation are improved, and the satisfaction and service experience of the user are improved.

In some possible implementations, when the highest similarity between any of the intermediate objects and the cluster information is not greater than a preset similarity, the method further includes:

Counting is started and the counted times are added by one;

detecting whether the statistics times are larger than preset statistics times or not, when the statistics times are larger than the preset statistics times, carrying out zero clearing processing on the statistics times, and sending recommendation prompt information to terminal equipment of configuration personnel, wherein the recommendation prompt information is used for reminding the configuration personnel to pay attention to input information of the user.

The application does not limit the content and the form of the recommended prompt information, for example, the prompt is carried out on the terminal configuration equipment in a popup window form, and the text content on the popup window is 'please pay attention to the abnormal input information of the user A'. It is also for example to prompt in the form of voice on the terminal configuration device, the voice content being "please note that the input information of the user a is abnormal".

The beneficial effect of this technical scheme lies in: and when the highest similarity between any intermediate object and the clustering information is not more than the preset similarity, starting counting times, and adding 1 to the times. And detecting whether the statistics times are greater than preset statistics times or not, if so, resetting the statistics times, and sending recommendation prompt information to terminal equipment (namely terminal configuration equipment) of configuration personnel. The configuration personnel can pay attention to the input information of the user according to the recommendation prompt information, so that the situation that the input information of the user is not fed back positively or effectively under partial conditions is avoided, and the recommendation accuracy is improved. On the one hand, when the existing intermediate objects or cluster information cannot meet the user demands, recommendation prompt information is sent to configuration personnel, so that the configuration personnel are promoted to pay attention to the input information of the user, the accuracy and the adaptability of recommendation are improved, and the adaptability of the service configuration method is improved. On the other hand, the accuracy of the intermediate objects and the clustering information is detected by setting the statistics times and the preset statistics times, so that the misjudgment rate can be reduced, and the recommendation accuracy is improved. On the other hand, the configurator can adjust the intermediate objects and the clustering information in time according to the recommendation prompt information so as to update the service options, thereby improving the working efficiency and the recommendation accuracy and reducing unnecessary communication and adjustment cost when the user does not obtain the required service.

In some possible implementations, the associating one or more service items with the identification information of the user according to the selection operation of the user to implement service configuration for the user includes:

when one or more 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;

when any one of the recommended objects is not selected by the user within a preset time interval, acquiring an associated recommended object of the user according to the identification information, and recommending the associated recommended object to the user by using the terminal equipment;

wherein the associated recommendation object is used to indicate one or more configured service items of an associated user of the user.

The beneficial effect of this technical scheme lies in: one or more service items can be associated with the identification information of the user according to the selection operation of the user, so as to implement service configuration for the user. If no one of the recommended objects is selected by the user within the preset time interval, the associated recommended objects of the user can be obtained according to the identification information of the user, and the associated recommended objects are recommended to the user by using the terminal equipment. Users can get useful advice to help them better configure their own services when they cannot make a selection, thereby improving the quality and efficiency of the services.

On the one hand, through the association with the identification information of the user, the user requirement can be accurately judged and identified, and the service items are timely recommended and configured according to the user selection operation and the preset time interval, so that the efficiency of configuring the service items by the user is improved. On the other hand, through setting the preset time interval, the user selection behavior can be observed and known in a certain time, and service matters which are more in line with the user requirements and preferences are provided for recommendation, so that the user experience is improved. On the other hand, the user can select the service items required by the user according to the requirements of the user and correlate the service items with the identification information, so that the service can be more accurately configured, the initiative and the accuracy of the service configuration of the user are enhanced, and the understanding and the cognition of the user on the service are enhanced. On the other hand, when the user selects the recommended object, the service item corresponding to the selected recommended object is automatically associated with the user, so that the time and effort for configuring the service by the configuration personnel can be saved.

In some possible implementations, when any one of the recommended objects is not selected by the user within a preset time interval, acquiring an associated recommended object of the user according to the identification information, and recommending the associated recommended object to the user by using the terminal device, including:

Acquiring the identification similarity of the identification information and the identification information of a plurality of historical users, and taking one or more historical users with the highest identification similarity as the associated users;

acquiring service items of the associated user according to the historical recommendation data of the associated user, and taking an object corresponding to the service items of the associated user as an associated recommendation object of the user;

wherein the historical recommendation data includes one or more service items associated with the associated user, and recommendation feedback for each of the service objects, the recommendation feedback including a score and/or click of the service item by the associated user.

The beneficial effect of this technical scheme lies in: and when the user does not select any recommended object in the preset time interval, acquiring the associated recommended object of the user according to the identification information of the user. Specifically, the similarity of the identification information of the user and the identification information of the history user is obtained. By calculating the similarity, the historical user most similar to the user can be obtained, and then the associated user is determined. That is, these associated users have similar identifying information as the current user, and their service needs and purchasing behavior may also be similar to the current user. Based on the historical recommendation data of the associated user, the service items of the associated user are acquired, and the corresponding recommendation object is used as the associated recommendation object of the current user. These recommended objects are verified by historical users, and can better meet the requirements of the current users. And finally recommending the associated recommended object to the current user to help the current user to select, thereby completing service configuration. According to the technical scheme, more personalized service recommendation can be provided for the user according to the identification information and the historical recommendation data of the user. Meanwhile, participation and feedback of the user to the service can be promoted, and the service quality and the user satisfaction degree are continuously improved.

In some possible implementations, the acquiring the service item of the associated user according to the historical recommendation data of the associated user, and taking the object corresponding to the service item of the associated user as the associated recommendation object of the user includes:

acquiring feedback scores of one or more service matters associated with the associated user according to the recommended feedback;

taking an object corresponding to the service item corresponding to the feedback score with the largest value as an associated recommended object of the user;

detecting whether the largest feedback score is smaller than a preset score; and when the maximum feedback score is smaller than the preset score, generating score prompt information and sending the score prompt information to terminal equipment of a configurator, wherein the score prompt information is used for prompting the configurator to pay attention to the identification information of the user.

The beneficial effect of this technical scheme lies in: and when the user does not select the recommended object, similar historical users are obtained according to the identification information of the user, and service matters and feedback scores thereof are obtained from the historical recommended data of the users. And then, taking the service item corresponding to the highest score as an associated recommended object of the user. Meanwhile, if the highest score is smaller than the preset score, score prompt information is generated and sent to the configurator, so that the configurator can provide better service recommendation for specific users. On the one hand, the method and the device can help the user to quickly acquire the associated recommended object when the recommended object is not selected, so that the service experience and satisfaction of the user are improved. On the other hand, by utilizing the historical recommendation data, the user can obtain more personalized and accurate recommendation objects, which also contributes to improving the quality of service. On the other hand, even when the score is lower than the preset value, the generation of the recommended object is finished first, and the score prompt information is regenerated and sent to relevant configurators, so that better service and support of the client are ensured. In conclusion, the self-adaptability and the intelligent degree of the service configuration method can be improved.

In a second aspect, the present application also provides an electronic device comprising a memory storing a computer program and at least one processor configured to implement the following steps when executing the computer program:

In a third aspect, the present application also provides a computer-readable storage medium storing a computer program which, when executed by at least one processor, performs the steps of any of the methods or performs the functions of any of the electronic devices described above.

In a fourth aspect, the application also provides a computer program product comprising a computer program which, when executed by at least one processor, performs the steps of the method or performs the functions of the electronic device described in any of the preceding claims.

Drawings

The application will be further described with reference to the drawings and embodiments.

Fig. 1 is a flow chart of a service configuration method according to an embodiment of the present application.

Fig. 2 is a schematic flow chart of acquiring a recommended object according to an embodiment of the present application.

Fig. 3 is a schematic flow chart of sending recommendation prompt information according to an embodiment of the present application.

Fig. 4 is a flowchart of acquiring an associated recommended object according to an embodiment of the present application.

Fig. 5 is a schematic flow chart of acquiring a service object according to an embodiment of the present application.

Fig. 6 is a block diagram of an electronic device according to an embodiment of the present application.

Fig. 7 is a schematic structural diagram of a computer program product according to an embodiment of the present application.

Detailed Description

The technical scheme of the present application will be described below with reference to the drawings and the specific embodiments of the present application, and it should be noted that, on the premise of no conflict, new embodiments may be formed by any combination of the embodiments or technical features described below.

In embodiments of the application, words such as "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any implementation or design described as "exemplary" or "e.g." in the examples of this application should not be construed as preferred or advantageous over other implementations or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.

The technical field and related terms of the embodiments of the present application are briefly described below.

Artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use the knowledge to obtain optimal results. In other words, artificial intelligence is an integrated technology of computer science that attempts to understand the essence of intelligence and to produce a new intelligent machine that can react in a similar way to human intelligence. The design principle and the implementation method of various intelligent machines are researched by artificial intelligence, so that the machines have the functions of perception, reasoning and decision. The artificial intelligence technology is a comprehensive subject, and relates to the technology with wide fields, namely the technology with a hardware level and the technology with a software level. Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning, automatic driving, intelligent traffic and other directions.

Machine Learning (ML) is a multi-domain interdisciplinary, involving multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, etc. The computer program may learn experience E given a certain class of tasks T and performance metrics P, and increase with experience E if its performance in task T happens to be measured by P. Machine learning is specialized in studying how a computer simulates or implements learning behavior of a human to acquire new knowledge or skills, reorganizing existing knowledge structures to continually improve its own performance. Machine learning is the core of artificial intelligence, a fundamental approach to letting computers have intelligence, which is applied throughout various areas of artificial intelligence.

Deep learning is a special machine learning by which the world is represented using a hierarchy of nested concepts, each defined as being associated with a simple concept, and achieving great functionality and flexibility, while a more abstract representation is computed in a less abstract way. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, induction learning, teaching learning, and the like.

Clustering (Clustering) is an unsupervised learning method that aims to group similar objects together and to divide irrelevant objects into different groups. The basic idea of the clustering algorithm is: given a set of unlabeled samples, similar samples are classified into one class by calculating the distance or similarity between the samples.

Clustering algorithms can be categorized into prototype-based clustering and hierarchical clustering. Prototype-based clustering (e.g., the K-Means algorithm) is performed by selecting prototype points in the dataset, centering on the core sample, and partitioning the space into K regions. The hierarchical clustering algorithm (such as the AGNES algorithm) is a process of gradually merging or dividing clusters to realize clustering, so as to form a clustering hierarchical structure.

Semantic extraction (Semantic Extraction) refers to automatically extracting semantic information from input information, which may be text information, voice information, or image information. Semantic extraction may facilitate the understanding and processing of text information, speech information, or image information by a computer. When the input information is text information, the following steps may be included: firstly, a text is segmented according to words, and a series of words are obtained. And then identifying and labeling the entities such as the name of the person, the name of the place, the name of the organization and the like in the text. And searching and extracting the relation among the entities in the text, and finally searching and extracting the event type, the related information of participants, time, places and the like in the text. That is, the semantic extraction technology can be applied to the fields of natural language processing, text mining, knowledge graph and the like, can improve the understanding and semantic analysis capability of a computer on texts, and provides support for tasks such as information retrieval, intelligent question-answering, machine translation and the like.

The existing service configuration is mostly suitable for the traditional field, and the requirements of users on personalized service configuration after the continuous maturity of streaming media technology and the continuous improvement of network environment are not considered. With the progress of technology, streaming media technology is mature and network environment is improved, and more demands are placed on personalized service configuration by users, so that the application provides a service configuration method, electronic equipment, a computer readable storage medium and a computer program product to improve the prior art.

The scheme provided by the embodiment of the application relates to the technologies of interactive design, artificial intelligence and the like, and is specifically described through the following embodiment. The following description of the embodiments is not intended to limit the preferred embodiments.

Method embodiment

Referring to fig. 1, fig. 1 is a schematic flow chart of a service configuration method according to an embodiment of the present application.

The embodiment of the application provides a service configuration method, which comprises the following steps:

step S101: acquiring a recommendation request of a user by using terminal equipment, wherein the recommendation request comprises identification information and input information of the user;

step S102: acquiring an intermediate object from a plurality of candidate objects according to the identification information and the candidate objects;

Step S103: acquiring a recommended object according to the intermediate object and the input information, and recommending the recommended object to the user by using the terminal equipment; the recommended object is used for indicating one or more service items for the user;

step S104: receiving a selection operation of the user on the recommended object by using the terminal equipment;

step S105: and associating 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 service configuration method can be operated on the electronic equipment, the electronic equipment and the terminal equipment (used by a user) can be independent, and the electronic equipment and the terminal equipment can be integrated. When the electronic device and the terminal device are independent, the electronic device may be a computer, a server (including a cloud server), or the like having computing power. The terminal device is not limited in the embodiment of the application, and may be, for example, an intelligent terminal device having a display screen, a microphone and a speaker, such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, an intelligent wearable device, or the terminal device may be a workstation or a console having a display screen, a microphone and a speaker. The display screen may be a touch display screen or a non-touch display screen. The terminal device mentioned in the present application generally refers to a terminal device used by a user, and the terminal device of a configurator mentioned below may be expressed by a terminal configuration device in an example.

A platform refers to a platform for users to provide content sharing. When the platform is a live broadcasting platform, the live broadcasting platform is used for providing online live broadcasting service for users by utilizing a live broadcasting room and allowing the users to live broadcast own content and activities through the live broadcasting room, and the names of the live broadcasting platform can be 'manual teaching of infants', 'body-building live broadcasting room of middle-aged people', 'big remuneration of seafood products', 'recommendation of insurance business' and the like. The platform combines the live broadcasting technology with social networks, video sharing and real-time interaction, so that users can live broadcasting at any time and any place by using various terminal devices (such as smart phones, tablet computers, computers and the like). The platform can also be a non-live platform such as a knowledge payment platform, an electronic commerce platform and the like. The following mainly uses a live platform for example to facilitate understanding of the technical solution, but the embodiment of the application does not limit the type of the platform.

Platform manager refers to the staff of the platform, i.e. the person who configures the service items required by the user using the live room. Platform management personnel manage and supervise aspects of technology, user experience, content security and the like of a platform (live broadcast room). In general, platform management personnel can supervise the technical operation and stability of the live broadcasting room, ensure smooth live broadcasting, high audio and video quality and good user experience. The platform manager can also formulate and execute user management policies including registration and auditing, account management, violation processing, etc. The platform manager can also collect and analyze user data or user audience data, understand user requirements and market changes, and adjust platform policies based on the data.

The user refers to a person who performs knowledge sharing, teaching and interaction between the platform and the audience by using service matters provided by the platform, for example, the user can log in and use the platform by registering the account number of the platform, and can display own skills or skills by interaction between the platform and the audience, or output information required by the audience. When the user is educational trained using a platform, the user is, for example, a receptionist (or customer manager), and the audience is, for example, a learner (or learner) who learns skills or learning knowledge. In some implementations, users may utilize content provided by a platform to provide services to viewers using virtual objects.

The virtual objects include virtual humans, virtual animals, virtual cartoon figures, and the like. The virtual person is a personified image constructed by CG technology and operated in a code form, and has various interaction modes such as language communication, expression, action display and the like. The technology of virtual persons has been rapidly developed in the field of artificial intelligence and has been applied in many technical fields such as virtual living rooms, videos, media, games, finance, travel, education, medical treatment, etc., and not only can virtual moderators, virtual anchor, virtual idol, virtual customer service, virtual lawyers, virtual training lecturers, virtual doctors, virtual lecturers, virtual assistants, etc., but also videos can be generated through text or audio one-key. In the virtual people, the service type virtual people mainly have the functions of replacing real people to serve and provide daily accompaniment, are the virtualization of service type roles in reality, and have the industrial value of mainly reducing the cost of the existing service type industry and enhancing the cost reduction of the stock market.

The application embodiment does not limit the services provided by the virtual object, and the virtual object can provide various types of services for users through interactive videos, such as programming teaching, foreign language teaching, insurance consultation, shopping consultation, travel service and the like, so that the requirements of various users are covered.

Therefore, the service configuration method provided by the embodiment of the application obtains the recommendation request of the user through the terminal equipment, and then obtains the intermediate object from the plurality of candidate objects according to the identification information. And acquiring a recommended object according to the intermediate object and the input information, and recommending the recommended object to the user by using the terminal equipment so as to indicate one or more service items selectable by the user. And after the user performs the selection operation, associating one or more service items selected by the user with the identification information of the user so as to realize personalized service configuration for the user. It can be understood that the recommended object is obtained by using the intermediate object and the input information, so that the accuracy of recommendation is greatly improved, and the user obtains more customized service experience. On the one hand, the terminal equipment is utilized to automatically finish service recommendation, selection and configuration, manual intervention is not needed, the efficiency is greatly improved, and the automation level is high. On the other hand, the preference of the user can be quickly obtained according to the identification information and the input information of the user, so that personalized configuration of the user service is realized. On the other hand, the recommendation request of the user can be responded in real time, and the service configuration can be timely adjusted according to the selection operation of the user, so that the real-time performance of the service is greatly improved.

As an example, the user's concha establishes a "baby manual" living room on the platform, and the concha finds that the pages displayed in the living room are monotonous and cannot bring the interests of the small audience. The small armor inputs text information 'the color of a page displayed when the small armor is live broadcast is too monotonous and needs more template selection', and a recommendation request of the small armor is acquired by using terminal equipment, wherein the identification information can be: the ID, registration date, duration of use, and user class of the concha are golden members, etc., wherein the input information is the text information "i now show the page color too monotonous when live broadcast, more template selection is needed.

And acquiring an intermediate object from the plurality of candidate objects according to the identification information. The alternative information may include "platinum member", "gold member", "platinum member", "template member" and "diamond member". Since the identification information of the concha indicates that it is already a gold member, the intermediate objects may be "platinum member", "template member" and "diamond template member". At this time, the template member and the diamond template member are selected from the intermediate objects according to the input information and are recommended to the small nail by using the computer of the small nail. The recommended mode of the recommended object can be in the form of a check box or an option button, and the embodiment of the application does not limit the mode.

The small nail selects the recommended object of the template member according to the recommended object, and the service items selected by more templates corresponding to the template member are associated with the identification information of the small nail, so that the small nail can select the template required by the small nail in more templates, and the display of the live broadcast room is more attractive to small audiences.

In this example, the user can obtain a plurality of recommended objects related to the requirement for self selection by only inputting the requirement of the user, so that better use experience can be provided for the user, and user satisfaction and loyalty are improved.

As another example, the difference from the previous example is that the anchor of the living room is a virtual anchor (i.e., virtual object), and the alternative information may include decorations, special effects, hairstyles, make-ups, etc. for the virtual anchor.

The embodiment of the application does not limit the types of service matters, such as improving the bandwidth support of more audiences, providing marketing support (i.e. assisting users in making marketing plans, providing tools such as sales promotion and advertisement delivery), providing data analysis support (i.e. providing data analysis tools for users, helping users know their audience groups and their performance), providing financial settlement support (i.e. providing financial settlement support for users), and the like.

In some embodiments, the obtaining, according to the identification information and the candidate objects, the intermediate object from the plurality of candidate objects may be an object corresponding to a service item not indicated by the user by selecting the identification information from the candidate objects, or may be an object with a higher authority than the current (service) authority of the user.

As an example, a user with service rights 3 in a platform may enjoy more discounted offers than a user with service rights 1, 2, and may also receive additional points rewards when purchasing platform services. Meanwhile, if the service authority is 5, the user can enjoy more exclusive services, such as exclusive customer service, etc. Such service items may increase member satisfaction, promote user loyalty, and thereby increase platform camping.

Referring to fig. 2, fig. 2 is a schematic flow chart of acquiring a recommended object according to an embodiment of the present application.

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

step S201: extracting semantic information from the input information by using a semantic extraction model corresponding to the input information;

step S202: clustering the semantic information to obtain clustering information, wherein the clustering information is used for indicating service matters required by the user;

Step S203: obtaining the similarity between the clustering information and each intermediate object;

step S204: and selecting at least one intermediate object as the recommended object according to the similarity between the clustering information and each intermediate object.

Therefore, the clustering information used for indicating the user needs is obtained by extracting semantic information from the input information and then clustering the extracted semantic information. And then calculating the similarity between the intermediate object and the clustering information, and selecting the best matched intermediate object as a recommended object. Namely, the embodiment of the application carries out the acquisition of the recommended object based on semantic information extraction, clustering and similarity calculation. On the one hand, through the semantic information extraction and clustering technology, the service item types required by the user can be more accurately prompted, so that the recommendation of the intermediate object with higher matching degree is facilitated, and compared with the recommendation of the intermediate object by only extracting one step through the semantic information, the accuracy of the recommended service is improved. On the other hand, although different users may put forth the same service requirements, the expressions are different. According to the technical scheme, the service requests submitted by different users can be classified through semantic information extraction and clustering technology, namely, the service requests submitted by different users are more universal, so that more proper and comprehensive recommended services can be provided, and the universality of acquiring recommended objects is improved. On the other hand, the embodiment of the application adopts semantic information extraction and clustering technology, so that redundant recommended objects can be reduced, and system resources are saved. On the other hand, more accurate and comprehensive recommended service can be provided, so that the user can be helped to find the required service matters more quickly and easily, and the trust feeling and satisfaction degree of the user on the platform are enhanced.

The embodiment of the application does not limit the type of the input information, and is, for example, text information, voice information or picture information. When the input information is text information, the input of the text information by the user can be achieved using a touch screen, a keyboard, or the like. When the input information is voice information, the input of voice information can be achieved by using a microphone. When the input information is image information, the input of the image information may be realized by a camera, a mouse, or the like.

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 voice information, the semantic extraction model corresponding to the input information comprises a voice-to-text model based on deep learning and a pre-training 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.

Thus, a deep learning based model can be used to extract semantic features of the input information. For different types of input information, different deep learning models are adopted for semantic extraction, including a pre-training language model, a voice-to-text model, a semantic segmentation model and the like.

For text information, pre-trained language models such as BERT, roBERTa, etc. are employed to extract semantic features of the input text. The models can learn the structure and semantic information of the language by pre-training a large amount of texts, so that the semantic information of the input texts can be effectively extracted.

For voice information, a voice-to-text model based on deep learning, such as CTC, transformer, is adopted to convert the voice information into text information, and a pre-training language model is adopted to extract semantic features of the text information. Thus, semantic information related to the input information can be extracted from the voice information.

For image information, a semantic segmentation model based on deep learning, such as UNet, deep Lab and the like, is adopted to segment the image, and semantic information corresponding to each pixel point is extracted. Thus, semantic information related to the input information can be accurately extracted from the image.

The method has the advantages that semantic features of input information can be extracted more accurately by using a semantic extraction model based on deep learning, so that accuracy and efficiency of semantic understanding are improved; the pre-training language model can improve the natural language processing capacity, including text classification, emotion analysis, machine translation and other aspects; by adopting different deep learning models, the multi-mode information can be processed, including text information, voice information, image information and the like, so that more comprehensive information processing is realized.

As an example, when the user's input information is text information "i am a teacher, i am like to teach to children, and one education live-broadcasting room with one hundred students is to be opened", semantic extraction and understanding can be performed using a pre-trained language model. Through the text processing technology, an input text 'I are a teacher, I like to teach with children', an education live broadcasting room with hundreds of students is started to perform word segmentation, word vectorization, sentence coding and other operations, and then a pre-training model is used for semantic understanding to obtain corresponding semantic information.

Specifically, the semantic understander based on the BERT model is used to convert the input text into corresponding expression vectors, and then calculate and compare the vectors, so as to obtain the final semantic information. Aiming at input information' I are a teacher, I like to teach with children, an educational live broadcast room with one hundred students is required to be opened, and semantic understanding is carried out according to the following steps: firstly, word segmentation is carried out on a text and the text is converted into a corresponding word vector representation; then inputting the word vector into the BERT model to obtain a representation vector (including the output of all layers) of each position; then carrying out weighted summation on the representation vectors of each position to obtain the representation vector of the whole sentence; finally, sentence expression vectors are input into a classification model, and final semantic classification results of education, one hundred students and the like are obtained.

In addition, if the keyword extractor based on deep learning is used for semantic processing, the keyword extraction is performed on the input text, and then the keyword is classified and generalized through the prediction model, so that corresponding semantic information is obtained. For example, for the input information "i live room template is too simple", it can be processed by using a keyword extractor based on deep learning, so as to obtain keywords "lack template", "template is simple", etc. And then inputting the keywords into a prediction model to obtain a semantic classification result.

Similarity of the cluster information to each of the intermediate objects may be calculated using a similarity model.

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

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

acquiring a training set, wherein the training set comprises a plurality of training data, and each training data comprises training cluster information, training intermediate objects and annotation data of similarity between the training cluster information and the training intermediate objects;

For each training data in the training set, performing the following processing:

inputting training cluster information and training intermediate objects in the training data into a preset deep learning model to obtain prediction data of similarity of the training cluster information and the training intermediate objects;

updating model parameters of the deep learning model based on the training cluster information and the prediction data and the annotation data of the similarity of the training intermediate object;

detecting whether a preset training ending condition is met; if yes, taking the trained deep learning model as the similarity model; if not, continuing to train the deep learning model by using the next training data.

The application is not limited to the training process of the similarity model, and for example, a training mode of supervised learning, a training mode of semi-supervised learning or a training mode of unsupervised learning can be adopted.

The preset training ending condition is not limited, and for example, the training times can reach the preset times (the preset times are, for example, 1 time, 3 times, 10 times, 100 times, 1000 times, 10000 times, etc.), or the training data in the training set can be all trained once or a plurality of times, or the total loss value obtained in the training is not more than the preset loss value.

The present application is not limited to the preset similarity threshold, and may be 81%, 83%, 92%, 95%, 99.9%, etc., for example.

As one example, the user inputs the following information: "I want to do an educational live broadcast room, be yoga education, and recruit middle-aged female students". The recommended object may be obtained by:

and processing the user input information by using a semantic extraction model to extract key information therein. For example, the model may identify keywords such as "educational living room", "yoga education", "middle-aged female student", and the like. And clustering the extracted key information to determine the type of service items required by the user. For example, clustering data such as "health exercise", "middle-aged female education" and the like are obtained after clustering is performed according to keywords in the user input information. The platform may select corresponding intermediate objects such as "secondary member", "tertiary member", "gold member" and "template member". And calculating the similarity between the user cluster information and each intermediate object. For example, the platform may use cosine similarity or the like to obtain the user's requirements and the similarity between "secondary members".

One or more intermediate objects that best match the user's needs may be selected as recommended objects. For example, if in the above example, the user's needs are clustered as "middle-aged female education" and the similarity of "secondary members" is highest, the platform may recommend "secondary members" to the user as recommendation objects.

In some embodiments, the selecting at least one intermediate object as the recommended object according to the similarity between the cluster information and each intermediate object (i.e. step S204) includes:

when the highest similarity between any intermediate object and the clustering information is not more than the preset similarity, acquiring one or more associated users of the users according to the identification information; and aiming at each associated user, taking an object corresponding to the configured service item of the associated user as the recommended object.

The embodiment of the application does not limit the preset similarity, which is, for example, 0.9, 0.8 or 70%.

Therefore, in the technical scheme of the application, when the highest similarity between a certain intermediate object and the clustering information is greater than the preset similarity, the intermediate object is taken as the recommended object. If the highest similarity between any intermediate object and the clustering information does not exceed the preset similarity, one or more associated users are obtained according to the identification information of the users, and the objects corresponding to the service items configured by the associated users are used as recommended objects for the users to select. On the one hand, the real demands of the user can be better reflected through the clustering of the demands of the user and the matching of the intermediate objects, namely, more personalized and accurate service recommendation is provided. On the other hand, when the similarity between a certain intermediate object and the clustering information is not high, the recommendation can still be provided by associating the configuration information of the user, so that the reliability and diversity of the recommendation are improved, and the satisfaction and service experience of the user are improved.

As one example, the user inputs the following information: "I want to do a legal consultation living broadcast room, which is intellectual property law". The recommended object may be selected by:

aiming at the input information of the user, the semantic extraction technology is used for processing the input information, and the key information is extracted. For example, key information such as "legal consultation living broadcasting room", "intellectual property law" may be identified. And clustering the user demands according to the key information and classifying the user demands into 'intellectual property law consultation'. For each candidate intermediate object (e.g. "secondary member", "tertiary member", "golden member"), the similarity between it and the clustering information of the user's needs can be calculated. For example, the platform may calculate the similarity between the platform and the user's needs using cosine similarity or the like. For each candidate intermediate object, if the highest similarity with the user cluster information is greater than the preset similarity, the intermediate object is selected as the recommended object. For example, if the similarity of "secondary members" exceeds a set threshold, the platform will select "secondary members" as recommended objects.

If the similarity of any of the alternative intermediate objects does not meet the preset threshold, the identification information of the user will be used to obtain the associated user. For example, the platform may query other users that are similar to the user's needs and select intermediate objects corresponding to service items configured by the users as recommended objects.

Referring to fig. 3, fig. 3 is a schematic flow chart of sending recommendation prompt information according to an embodiment of the present application.

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

step S106: counting is started and the counted times are added by one;

step S107: detecting whether the statistics times are greater than preset statistics times or not, when the statistics times are greater than the preset statistics times, carrying out zero clearing processing on the statistics times, and sending recommended prompt information to terminal equipment of configuration personnel; the recommendation prompt information is used for reminding configuration personnel of paying attention to the input information of the user.

In other embodiments, counting is continued when the count is not greater than the preset count.

The preset number of times is not limited in the embodiment of the present application, and is, for example, 9 times, 8 times, 3 times, or the like.

Therefore, when the highest similarity between any intermediate object and the clustering information is not greater than the preset similarity, counting times is started, and the times are added by 1. And detecting whether the statistics times are greater than preset statistics times or not, if so, resetting the statistics times, and sending recommendation prompt information to terminal equipment (namely terminal configuration equipment) of configuration personnel. The configuration personnel can pay attention to the input information of the user according to the recommendation prompt information, so that the situation that the input information of the user is not fed back positively or effectively under partial conditions is avoided, and the recommendation accuracy is improved. On the one hand, when the existing intermediate objects or cluster information cannot meet the user demands, recommendation prompt information is sent to configuration personnel, so that the configuration personnel are promoted to pay attention to the input information of the user, the accuracy and the adaptability of recommendation are improved, and the adaptability of the service configuration method is improved. On the other hand, the accuracy of the intermediate objects and the clustering information is detected by setting the statistics times and the preset statistics times, so that the misjudgment rate can be reduced, and the recommendation accuracy is improved. On the other hand, the configurator can adjust the intermediate objects and the clustering information in time according to the recommendation prompt information so as to update the service options, thereby improving the working efficiency and the recommendation accuracy and reducing unnecessary communication and adjustment cost when the user does not obtain the required service.

In some embodiments, the associating one or more service items with the identification information of the user according to the selection operation of the user to implement service configuration for the user (i.e. step S105) includes:

wherein the associated recommendation object is used to indicate one or more configured service items of an associated user of the user. The preset time interval is not limited in the embodiment of the present application, and is, for example, 1 hour, 10 minutes, 3 minutes, or the like.

Thus, one or more service items and the identification information of the user can be corresponding according to the selection operation of the user, so as to realize the service configuration of the user. If no one of the recommended objects is selected by the user within the preset time interval, the associated recommended objects of the user can be obtained according to the identification information of the user, and the associated recommended objects are recommended to the user by using the terminal equipment. Users can get useful advice to help them better configure their own services when they cannot make a selection, thereby improving the quality and efficiency of the services.

As one example, the user inputs the following information: "I want to do a music coaching live broadcasting room, do violin teaching, there is a need for 200 students to take lessons at the same time. The user may be configured for services by:

Aiming at information input by a user, firstly, the input information is processed by using a semantic extraction technology, and key information of the input information, namely a music coaching live broadcast room, violin teaching and 200 students, is extracted. And clustering according to the key information, namely classifying the service types of the user demands, and classifying the user demands as 'violin teaching live broadcast'. For each alternative intermediate object (e.g. "secondary member", "tertiary member", "gold member") a corresponding service item may be configured for it. For example, a "golden member" may include a service item that "supports large-scale online live broadcast". The "golden member" is taken as the recommendation object. When the user selects the gold member, the platform associates the service item corresponding to the gold member with the identification information of the user.

If one or more recommended objects are selected by the user within a preset time interval, the service item corresponding to the recommended object is associated with the identification information of the user. For example, assume that the user selects "golden member" within a week, and the "support large-scale live online" service item is associated with the identification information of the user according to the operation selected by the user.

If no recommended object is selected by the user within the preset time interval, the associated recommended objects are acquired by using the identification information of the user, and are recommended to the user by using the terminal equipment. For example, the platform may query other users that are similar to the user's needs, obtain recommended objects used by the users, and send the recommended objects to the user.

Referring to fig. 4, fig. 4 is a schematic flow chart of acquiring an associated recommended object according to an embodiment of the present application.

In some embodiments, when any one of the recommended objects is not selected by the user within a preset time interval, acquiring an associated recommended object of the user according to the identification information, and recommending the associated recommended object to the user by using the terminal device, including:

step S301: acquiring the identification similarity of the identification information and the identification information of a plurality of historical users, and taking one or more historical users with the highest identification similarity as the associated users;

step S302: acquiring service items of the associated user according to the historical recommendation data of the associated user, and taking an object corresponding to the service items of the associated user as an associated recommendation object of the user;

Thus, when the user does not select any recommended object in the preset time interval, the associated recommended object of the user is obtained according to the identification information of the user. Specifically, the similarity of the identification information of the user and the identification information of the history user is obtained. By calculating the similarity, the historical user most similar to the user can be obtained, and then the associated user is determined. That is, these associated users have similar identifying information as the current user, and their service needs and purchasing behavior may also be similar to the current user. Based on the historical recommendation data of the associated user, the service items of the associated user are acquired, and the corresponding recommendation object is used as the associated recommendation object of the current user. These recommended objects are verified by historical users, and can better meet the requirements of the current users. And finally recommending the associated recommended object to the current user to help the current user to select, thereby completing service configuration. According to the technical scheme, more personalized service recommendation can be provided for the user according to the identification information and the historical recommendation data of the user. Meanwhile, participation and feedback of the user to the service can be promoted, and the service quality and the user satisfaction degree are continuously improved.

As one example, identification information, service matters, recommendation feedback, and the like of each user are recorded in the history user database. When any one of the candidate objects is not selected by the user within the preset time interval, the associated recommended object can be acquired and recommended to the user through the following processes:

firstly, according to the identification information of the user, inquiring the historical user similar to the user from a historical user database. The query may be made using various existing algorithms, such as cosine similarity, jaccard similarity, and the like. Suppose three historical users similar to the user are found: userA, userB, and UserC.

For each historical user similar to the user, its historical recommendation data is analyzed. For example, the history recommended data of UserA may be extracted to include a service item of "live violin teaching", where the recommended object corresponding to the service item is "golden member". Meanwhile, userA scores 4 stars (5 stars maximum) for this service event.

And counting and sequencing the historical recommendation data of all similar historical users, and taking the recommendation object corresponding to the service item with higher score as the associated recommendation object of the user. For example, for a "live violin teaching" service, the platform calculates the score of "golden member" for its corresponding recommended object as 12 (i.e., the recommended object is included in each of representative UserA, userB, and UserC), while the scores for the other candidate objects are 6 and 8, respectively. Thus, the gold member is recommended as an associated recommended object of the user.

And recommending the associated recommended object to the user by using the terminal equipment. The recommended content may include information of the name of the recommended object, price, service content, etc.

Referring to fig. 5, fig. 5 is a schematic flow chart of acquiring a service object according to an embodiment of the present application.

In some embodiments, the acquiring the service item of the associated user according to the historical recommendation data of the associated user, and taking the object corresponding to the service item of the associated user as the associated recommendation object of the user (i.e. step S302) includes:

step S401: acquiring feedback scores of one or more service matters associated with the associated user according to the recommended feedback;

step S402: taking an object corresponding to the service item corresponding to the feedback score with the largest value as an associated recommended object of the user;

step S403: detecting whether the largest feedback score is smaller than a preset score; and when the maximum feedback score is smaller than the preset score, generating score prompt information and sending the score prompt information to terminal equipment of a configurator, wherein the score prompt information is used for prompting the configurator to pay attention to the identification information of the user.

The preset score is not limited in the embodiment of the present application, and is, for example, 100 points, 80 points, a or b+. The application does not limit the content and the form of the scoring prompt information, for example, the scoring prompt information is prompted on the terminal configuration equipment in a popup window form, and the text content on the popup window is 'please pay attention to the abnormal identification information of the user A'. It is also for example to prompt in the form of voice on the terminal configuration device, the voice content being "please note that the identification information of the user a is abnormal".

Thus, similar historical users are obtained according to the identification information of the users when the users do not select the recommended objects, and service matters and feedback scores thereof are obtained from the historical recommended data of the users. And then, taking the service item corresponding to the highest score as an associated recommended object of the user. Meanwhile, if the highest score is smaller than the preset score, score prompt information is generated and sent to the configurator, so that the configurator can provide better service recommendation for specific users. On the one hand, the method and the device can help the user to quickly acquire the associated recommended object when the recommended object is not selected, so that the service experience and satisfaction of the user are improved. On the other hand, by utilizing the historical recommendation data, the user can obtain more personalized and accurate recommendation objects, which also contributes to improving the quality of service. On the other hand, even when the score is lower than the preset value, the generation of the recommended object is finished first, and the score prompt information is regenerated and sent to relevant configurators, so that better service and support of the client are ensured. In conclusion, the self-adaptability and the intelligent degree of the service configuration method can be improved.

In some embodiments, before step S402, after step S401, the steps may further include:

Taking a plurality of objects corresponding to the service matters corresponding to the user image as alternative recommended objects of the user according to the user image;

and recommending the candidate recommended object to the user by using the terminal equipment by taking the candidate recommended object as an associated recommended object of the user, and receiving the selection operation of the user on the recommended object by using the terminal equipment.

User portrayal, among other things, refers to analyzing and modeling users to better understand user needs and to promote content or services that better meet user interests and preferences.

The user representation may include the following aspects: basic information (basic information such as gender, age, geographical location, etc. of the user), behavioral preferences (browsing history, search history, purchase history, etc. of the user), psychological characteristics (personality characteristics, attitudes, moods, etc. of the user), and the like.

In a specific application scenario, the embodiment of the application provides a service configuration method, which comprises the following steps:

The process of obtaining the recommended object comprises the following steps:

when the highest similarity between any intermediate object and the clustering information is not more than the preset similarity, acquiring one or more associated users of the users according to the identification information; simultaneously, starting statistics and adding one to the statistics times; detecting whether the statistics times are larger than preset statistics times or not, when the statistics times are larger than the preset statistics times, carrying out zero clearing processing on the statistics times, and sending recommendation prompt information to terminal equipment of configuration personnel, wherein the recommendation prompt information is used for reminding the configuration personnel to pay attention to input information of the user;

As one example, the platform is used to provide a variety of service items for users, such as live recommendations, live room management, presentation templates, and the like. To enhance the user experience, the following may be used in one example:

the user sends a recommendation request by using a terminal device (for example, a mobile phone App), wherein the recommendation request comprises identification information and input information of the user. For example, when a first-class member user is live, feedback that the currently displayed page is too prime, more template selection is needed, the identification information is UserA, and the input information is "i currently live the currently displayed page is too prime, and more template selection is needed".

And acquiring an intermediate object from the plurality of candidate objects according to the identification information of the user and the candidate objects. In this example, the conditions for selecting an intermediate object from the candidate objects may include user level, online time duration, history viewing record, and the like. The platform is assumed to acquire all members meeting the current level requirement by analyzing the user level, and takes a second-level member, a third-level member, a gold member and a template member as intermediate objects.

And acquiring a recommended object according to the intermediate object and the user input information. A recommended object refers to an object for indicating one or more service items to a user. The recommended object may be a "template member" whose corresponding service is "open more exposed template rights". Recommending the recommended object to the user, and waiting for the selection operation of the user. In this example, a "template member" is recommended to UserA, and the template resources of the member can be simultaneously shown on the APP page of the user's terminal device.

And the user selects the recommended object and sends the selection operation by using the terminal equipment. And associating the selected service item with the user identification information according to the selection operation of the user.

As another example, in order to better recommend a service suitable for a user on the basis of the above example, in acquiring a recommended object, a semantic extraction model corresponding to input information is used. After the user sends the recommendation request, the platform uses the semantic extraction model to extract semantic information from the input information, for example, to extract information such as "more template selection is needed", "personalized template" and the like.

And clustering the user demands according to the extracted semantic information to obtain clustering information. For example, user requirements are clustered into "templates". And calculating the similarity between each intermediate object and the clustering information, and selecting the intermediate object with the highest similarity as a recommended object. For example, if the similarity between the template member and the cluster information is found to be the highest in all the intermediate objects, the template member is taken as a recommended object.

In addition, if the similarity between the intermediate object and the clustering information is higher than a preset similarity threshold (for example, 0.8), acquiring the associated user according to the user identification information, and acquiring the configuration information of the associated user. For example, if the associated user of UserA is UserB, the platform will obtain service items that UserB has configured, e.g., userB has selected "gold member". The "golden member" is taken as the recommendation object.

And when the highest similarity between any intermediate object and the clustering information is not more than the preset similarity, counting the recommended times of the user, and detecting whether the recommended times exceed a preset time threshold. When the counted times exceeds a preset time threshold, recommendation prompt information is sent to terminal configuration equipment of an administrator to remind the administrator to pay attention to the requirements of users so as to optimize services.

In another specific application scenario, the embodiment of the application provides a service configuration method, which comprises the following steps:

when any one of the recommended objects is not selected by the user within a preset time interval, acquiring the identification similarity between the identification information and the identification information of a plurality of historical users, and taking one or more historical users with the highest identification similarity as the associated user; acquiring feedback scores of one or more service matters associated with the associated user according to the recommended feedback; taking an object corresponding to the service item corresponding to the feedback score with the largest value as an associated recommended object of the user; detecting whether the largest feedback score is smaller than a preset score; and when the maximum feedback score is smaller than the preset score, generating score prompt information and sending the score prompt information to terminal equipment of a configurator, wherein the score prompt information is used for prompting the configurator to pay attention to the identification information of the user.

Wherein the historical recommendation data includes one or more service items associated with the associated user, and recommendation feedback for each of the service objects, the recommendation feedback including scoring and/or clicking of the service items by the associated user; the associated recommendation object is to indicate one or more configured service items of an associated user of the user.

Electronic device embodiment

The embodiment of the application also provides an electronic device, the specific embodiment of which is consistent with the embodiment described in the method embodiment and the achieved technical effect, and part of the contents are not repeated.

The electronic device comprises a memory storing a computer program and at least one processor configured to implement the following steps when executing the computer program:

In some embodiments, the at least one processor is configured to obtain the recommended object when executing the computer program by:

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 of the cluster information to each of the intermediate objects when executing the computer program in the following manner:

In some embodiments, when the highest similarity of any of the intermediate objects to the cluster information is not greater than a preset similarity, the at least one processor is configured to execute the computer program to further implement the steps of:

counting is started and the counted times are added by one;

In some embodiments, the at least one processor is configured to associate one or more of the service items with the identification information of the user in accordance with a selection operation of the user when executing the computer program in a manner to enable service configuration for the user:

In some embodiments, when none of the recommended objects is selected by the user within a preset time interval, the at least one processor is configured to obtain an associated recommended object of the user from the identification information and recommend the associated recommended object to the user using the terminal device when executing the computer program in the following manner:

In some embodiments, the at least one processor is configured to obtain service items of the associated user according to the historical recommendation data of the associated user when executing the computer program, and take an object corresponding to the service items of the associated user as an associated recommendation object of the user by:

detecting whether the largest feedback score is smaller than a preset score;

and when the maximum feedback score is smaller than the preset score, generating score prompt information and sending the score prompt information to terminal equipment of a configurator, wherein the score prompt information is used for prompting the configurator to pay attention to the identification information of the user.

Referring to fig. 6, fig. 6 is a block diagram of an electronic device according to an embodiment of the present application.

The electronic device 10 may for example comprise at least one memory 11, at least one processor 12 and a bus 13 connecting the different platform systems.

Memory 11 may include (computer) readable media 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.

The memory 11 also stores a computer program executable by the processor 12 to cause the processor 12 to implement the steps of any of the methods described above.

Memory 11 may also include utility 114 having at least one program module 115, such program modules 115 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.

Accordingly, the processor 12 may execute the computer programs described above, as well as may execute the utility 114.

The processor 12 may employ one or more application specific integrated circuits (ASICs, application Specific Integrated Circuit), DSPs, programmable logic devices (PLDs, programmable Logic Device), complex programmable logic devices (CPLDs, complex Programmable Logic Device), field programmable gate arrays (FPGAs, fields-Programmable Gate Array), or other electronic components.

Bus 13 may be a local bus representing one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or any of a variety of bus architectures.

The electronic device 10 may also communicate with one or more external devices such as a keyboard, pointing device, bluetooth device, etc., as well as one or more devices capable of interacting with the electronic device 10 and/or with any device (e.g., router, modem, etc.) that enables the electronic device 10 to communicate with one or more other computing devices. Such communication may be via the input-output interface 14. Also, the electronic device 10 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through a network adapter 15. The network adapter 15 may communicate with other modules of the electronic device 10 via the bus 13. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with the electronic device 10 in actual applications, including, but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, data backup storage platforms, and the like.

Computer-readable storage medium embodiments

The embodiment of the application also provides a computer readable storage medium, and the specific embodiment of the computer readable storage medium is consistent with the embodiment recorded in the method embodiment and the achieved technical effect, and part of the contents are not repeated.

The computer readable storage medium stores a computer program which, when executed by at least one processor, performs the steps of any of the methods or performs the functions of any of the electronic devices described above.

The computer readable medium may be a computer readable signal medium or a computer readable storage medium. In embodiments of the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable storage medium may also be any computer readable medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing. Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the C programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

Computer program product embodiments

The embodiment of the application also provides a computer program product, the specific embodiment of which is consistent with the embodiment described in the method embodiment and the achieved technical effect, and part of the contents are not repeated.

The present application provides a computer program product comprising a computer program which, when executed by at least one processor, performs the steps of any of the methods or performs the functions of any of the electronic devices described above.

Referring to fig. 7, fig. 7 is a schematic structural diagram of a computer program product according to an embodiment of the present application.

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

In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a alone, a and B together, and B alone, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b or c may represent: a, b, c, a and b, a and c, b and c or a and b and c, wherein a, b and c can be single or multiple. It is noted that "at least one" may also be interpreted as "one (a) or more (a)".

The terms first, second and the like in the description and in the claims and in the above-described figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The present application has been described in terms of its purpose, performance, advancement, and novelty, and the like, and is thus adapted to the functional enhancement and use requirements highlighted by the patent statutes, but the description and drawings are not limited to the preferred embodiments of the present application, and therefore, all equivalents and modifications that are included in the construction, apparatus, features, etc. of the present application shall fall within the scope of the present application.

Claims

1. A method of service configuration, the method comprising:

2. The service configuration method according to claim 1, wherein the process of acquiring the recommended object includes:

3. The service configuration method according to claim 2, wherein the selecting at least one of the intermediate objects as the recommended object according to the similarity of the cluster information to each of the intermediate objects includes:

4. The service configuration method according to claim 3, wherein when the highest similarity between any one of the intermediate objects and the cluster information is not greater than a preset similarity, the method further comprises:

Counting is started and the counted times are added by one;

5. The service configuration method according to claim 1, wherein the associating one or more of the service items with the identification information of the user according to the selection operation of the user to realize the service configuration for the user includes:

6. The service configuration method according to claim 5, wherein when any one of the recommended objects is not selected by the user within a preset time interval, acquiring the associated recommended object of the user according to the identification information, and recommending the associated recommended object to the user using the terminal device, comprises:

7. The service configuration method according to claim 6, wherein the obtaining the service item of the associated user according to the historical recommendation data of the associated user, and taking the object corresponding to the service item of the associated user as the associated recommendation object of the user, comprises:

detecting whether the largest feedback score is smaller than a preset score;

8. An electronic device comprising a memory and at least one processor, the memory storing a computer program, the at least one processor being configured to implement the following steps when executing the computer program:

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

10. A computer program product, characterized in that it comprises a computer program which, when executed by at least one processor, implements the steps of the method of any one of claims 1-7 or the functions of the electronic device of claim 8.