Intelligent service used for internet-of-things device

Abstract

Disclosed in the embodiments of the present disclosure is an intelligent service method used for an Internet-of-Things device. The method comprises: performing face identification on a user to determine identity information of the user; determining personality information of a plurality of personalities associated with the identity information; from amongst the personality information of the plurality of personalities, selecting the personality information of one personality as initial personality information; according to a first service mode correspondingly set for the initial personality information, starting to provide service for the user by means of speech interaction; in the service process, collecting a speech uttered by the user and / or an action performed by the user to generate corresponding user real-time performance data; analyzing the user real-time performance data by using a pre-trained large model to obtain an analysis result; according to the analysis result, determining whether the user has switched to another personality among the plurality of personalities; and if so, automatically switching from the first service mode to a second service mode correspondingly set for the personality information of said another personality, and according to the second service mode, continuing to provide service for the user.

Description

Intelligent service applied to internet of things device TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of internet of things, and particularly relates to an intelligent service applied to an internet of things device. BACKGROUND

[0002] With the development of communication technology and internet technology, many devices can provide better services for users through networking. Moreover, some intelligent applications are helpful to improve the intelligence of the devices, and can serve users more intelligently, such as a mobile phone intelligent assistant based on voice and natural language processing (NLP) technology, a voice assistant for a family, and the like.

[0003] The above intelligent applications are mainly for C-end, are more inclined to entertainment, and have limited capabilities. In comparison, intelligent applications for B-end have greater potential and space for development. Many internet of things devices are for B-end, such as vending machines, self-service cash registers, hotel robots, and the like. The intelligence of the devices can be improved through corresponding intelligent applications for B-end.

[0004] However, in actual applications, these internet of things devices usually only assist users to select device functions through simple guidance by text or voice.

[0005] Therefore, there is a need for a solution that can help to improve the intelligent experience of users for internet of things devices. SUMMARY

[0006] One or more embodiments of the present disclosure provide an intelligent service method and device applied to an internet of things device, and a storage medium, to solve the technical problem that there is a need for a solution that can help to improve the intelligent experience of users for internet of things devices.

[0007] To solve the above technical problem, one or more embodiments of the present disclosure are implemented as follows.

[0008] The one or more embodiments of the present disclosure provide a smart service method applied to an Internet of Things device, comprising: performing face recognition on a user to determine identity information of the user; determining personality information of a plurality of personalities associated with the identity information; selecting personality information of one personality from the personality information of the plurality of personalities as initial personality information; starting to provide service for the user through voice interaction according to a first service mode set for the initial personality information; collecting voice and / or actions of the user during the service to generate corresponding user real-time performance data; analyzing the user real-time performance data by using a pre-trained large model to obtain an analysis result; determining whether the user switches to another personality from the plurality of personalities according to the analysis result; and if so, automatically switching from the first service mode to a second service mode set for the personality information of the another personality, and continuing to provide service for the user according to the second service mode.

[0009] The one or more embodiments of the present disclosure provide a smart service device applied to an Internet of Things device, comprising: a face recognition module configured to perform face recognition on a user to determine identity information of the user; a personality association module configured to determine personality information of a plurality of personalities associated with the identity information; a personality selection module configured to select personality information of one personality from the personality information of the plurality of personalities as initial personality information; a first service module configured to start to provide service for the user through voice interaction according to a first service mode set for the initial personality information; a performance collection module configured to collect voice and / or actions of the user during the service to generate corresponding user real-time performance data; a performance analysis module configured to analyze the user real-time performance data by using a pre-trained large model to obtain an analysis result; a personality switching module configured to determine whether the user switches to another personality from the plurality of personalities according to the analysis result; and a service switching module configured to, if so, automatically switch from the first service mode to a second service mode set for the personality information of the another personality, and continue to provide service for the user according to the second service mode.

[0010] The one or more embodiments of the present disclosure provide a smart service device applied to an Internet of Things device, comprising: at least one processor; and a memory communicatively connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform: performing face recognition on a user to determine identity information of the user;

[0011] determine personality information of a plurality of personalities associated with the identity information; select personality information of one personality from the personality information of the plurality of personalities as initial personality information; start to provide service for the user through voice interaction according to a first service mode set for the initial personality information; in the service process, collect voice and / or actions of the user to generate corresponding user real-time performance data; analyze the user real-time performance data by using a pre-trained large model to obtain an analysis result; determine whether the user switches to another personality from the plurality of personalities according to the analysis result; if yes, automatically switch from the first service mode to a second service mode set for personality information of the another personality, and continue to provide service for the user according to the second service mode.

[0012] The non-volatile computer storage medium provided by one or more embodiments of the present disclosure stores computer executable instructions, which are configured to: perform face recognition on a user to determine identity information of the user; determine personality information of a plurality of personalities associated with the identity information; select personality information of one personality from the personality information of the plurality of personalities as initial personality information; start to provide service for the user through voice interaction according to a first service mode set for the initial personality information; in the service process, collect voice and / or actions of the user to generate corresponding user real-time performance data; analyze the user real-time performance data by using a pre-trained large model to obtain an analysis result; determine whether the user switches to another personality from the plurality of personalities according to the analysis result; if yes, automatically switch from the first service mode to a second service mode set for personality information of the another personality, and continue to provide service for the user according to the second service mode.

[0013] The above at least one technical solution adopted by one or more embodiments of the present disclosure can achieve the following beneficial effects: the comprehensive ability of visual observation, voice interaction and user real-time performance accurate understanding based on a large model is created for the Internet of Things device, the user can freely and flexibly associate his / her own identity information with personality information of a plurality of personalities, based on the above comprehensive ability and identity-personality association, the personality switching condition of the user is smoothly and instantly perceived and matched, the corresponding service mode is switched accordingly to adapt to the current personality of the user, so that the user can be intelligently and flexibly served in an improvisational performance mode, thereby the immersion and freedom of the user in the service area of the Internet of Things device can be improved, different service and spiritual needs of different users in different states can be more intelligently met, and the use experience of the user for the Internet of Things device can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the related art, the following will briefly introduce the drawings needed to be used in the embodiments or related art description. Obviously, the drawings described below only represent some of the embodiments described in the present disclosure, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0015] FIG. 1 is a flow diagram of a smart service method applied to an Internet of Things device according to one or more embodiments of the present disclosure;

[0016] FIG. 2 is a flow diagram of a smart service scheme based on a virtual personality according to one or more embodiments of the present disclosure;

[0017] FIG. 3 is a flow diagram of a smart service scheme based on a business knowledge difference of different personalities according to one or more embodiments of the present disclosure;

[0018] FIG. 4 is a technical architecture diagram of an Internet of Things device in an application scenario according to one or more embodiments of the present disclosure;

[0019] FIG. 5 is a flow diagram of a smart marketing scheme in an application scenario according to one or more embodiments of the present disclosure;

[0020] FIG. 6 is a structural diagram of a smart service device applied to an Internet of Things device according to one or more embodiments of the present disclosure;

[0021] FIG. 7 is a structural diagram of a smart service device applied to an Internet of Things device according to one or more embodiments of the present disclosure. DETAILED DESCRIPTION

[0022] The embodiments of the present disclosure provide a smart service method, device, equipment and storage medium applied to an Internet of Things device.

[0023] In order to make the technical personnel in the art better understand the technical solutions in the present disclosure, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments only represent some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0024] As mentioned in the background, some existing Internet of Things devices are not smart enough in terms of service mode for users. For example, a vending machine usually only displays a corresponding payment QR code after the user clicks on the goods to be purchased, and the user scans the code to pay, and the machine spits out the corresponding goods. The more intelligent one may only support face payment. For another example, an automatic cash register usually only generates and displays a corresponding payment QR code after the user manually scans the label of the goods or automatically reads the label of the goods through short-distance communication, and the user scans the code to pay, and the machine prints a receipt, and then the user can take the goods away. For another example, a hotel robot usually only patrols according to a planned route or delivers things to a guest room, and some can automatically avoid obstacles, and some can also voice answer simple questions raised by users.

[0025] As can be seen, although these Internet of Things devices have certain automation capabilities in life, they are not smart enough, and for users, they lack immersion and surprise.

[0026] In view of the above problems, the present application provides an intelligent service scheme applicable to an Internet of Things device, which can effectively improve the intelligent service capability of the Internet of Things device and the user's service experience.

[0027] FIG. 1 is a flowchart of an intelligent service method applicable to an Internet of Things device according to one or more embodiments of the present disclosure. The execution subject of the flow can be a vending machine, an automatic cash register, a movable robot, an electric vehicle, or the like. These Internet of Things devices need to have a sensing module and a computing module for supporting some interactions and processing actions mentioned below. The execution subject can be a newly created Internet of Things device, or a device obtained by upgrading the software and / or hardware of an existing Internet of Things device.

[0028] The flow in FIG. 1 includes the following steps.

[0029] S102: Perform face recognition on a user to determine identity information of the user.

[0030] For the sensing place range of the Internet of Things device (such as a certain range around the Internet of Things device in a store where the Internet of Things device is located, an outdoor public scene, etc.), when the user enters the place, even if no specific business is involved at this time, the user can be identified in advance in a timely manner. Such identification can be unnoticeable to the user (in order to improve security, the user's authorization consent can also be obtained in advance, similarly, other operations involving data collection can also be performed based on the user's authorization consent, which will not be described below), so the user does not need to make cooperation actions such as approaching the camera. The experience is better. Similarly, the collection of the actions that the user may take later can also be unnoticeable. In short, the user can be in a natural behavior state freely, and the cooperation behavior required by the user is reduced.

[0031] The sensing place range can be unattended, and accordingly, the service provided by the Internet of Things device can belong to an unattended service. Of course, there can be staff intervention, but the main work is still mainly completed by the Internet of Things device.

[0032] The Internet of Things device accordingly has or is connected to a camera module for supporting face recognition, such as a multi-modal camera, to collect multi-modal data such as RGB, depth, and IR.

[0033] S104: Determine the personality information of the multiple personalities associated with the identity information.

[0034] In one or more embodiments of the present disclosure, the user is allowed to associate one or more personality information of personalities with his own identity information. The present application is particularly concerned with the case where multiple personality information of personalities are associated, and the following embodiments are mainly described based on this case.

[0035] The personality information of different personalities can respectively reflect different speaking styles, and / or behavior styles, and / or visual styles (visual style refers to the visual presentation of the person himself, such as clothing visual, makeup visual, personal belongings visual, etc.), and / or personality, and / or values, and / or specific jokes (such as jokes, catchphrases, anecdotes, other special events, etc.) and the like. Different personalities can be personalities that are obviously different from each other, or even completely different.

[0036] The personality information of each personality can include one or more description information for describing these styles. The form can be a description text, an image, an attribute field, an index, etc.

[0037] In one or more embodiments of the present disclosure, the personality information of the personality associated with the identity information of the user can be edited by the user himself or obtained from the optional personality selection, in which case the personality information of the associated personality can be fictitious, i.e. not necessarily the real personality of the user, but the personality that the user wants to perform, so that the user can experience the service mode corresponding to different personalities, which is flexible and interesting, and can enable the user to freely improvise and immerse in the corresponding service.

[0038] More freely, the user can also perform (which can be of a performance nature) and match the personality matched by the current performance effect through the Internet of Things device, and then associate the matched personality with the identity information of the user based on the confirmation of the user.

[0039] S106: Select the personality information of one personality from the personality information of the plurality of personalities as initial personality information.

[0040] The personality information of the default personality can be selected as the initial personality information. Alternatively, the personality information of the personality first performed by the user after entering can be identified in real time, and the personality information of the personality can be selected as the initial personality information.

[0041] Taking the latter mode as an example, when determining the personality information of the plurality of personalities associated with the identity information, one or more personality information of the personality associated with the identity information of the user set by the user in advance can be obtained, and the current performance of the user is identified and matched. If a personality other than one or more personalities is matched, the personality information of the personality other than the one or more personalities is associated with the identity information, so as to obtain the personality information of the plurality of personalities associated with the identity information; in this case, the personality information of the personality other than the one or more personalities that reflects the current situation can be selected as the initial personality information. If the personality information of one personality set in advance is matched, the personality information of the personality is selected as the initial personality information; and if the matching is not successful, the personality information of one personality set by default can be selected as the initial personality information.

[0042] S108: According to the first service mode set for the initial personality information, the service for the user is started through voice interaction.

[0043] In one or more embodiments of the present disclosure, different service modes can be set correspondingly for different personalities, and a corresponding relationship can be established with the corresponding personality information, so as to switch the service mode correspondingly according to the personality change, and the interaction style of the service mode is adapted to the corresponding personality. Just like a smart and wise waiter, when facing different styles and personalities of customers (such as quiet students, rude uncles, enthusiastic young people, stubborn old people, visual music people, and rigorous scholars, etc., whose personalities are usually obviously different), different interaction modes are used to serve them. In the present application, a waiter is simulated through an Internet of Things device, and a user can possibly perform customers of different styles and personalities, just like the user has diversified personalities, so as to obtain a corresponding diversified instant fitting service experience. The specific content of the service depends on the business involved by the Internet of Things device, and can also depend on the current personality of the user.

[0044] In order to improve the immersion of the user, at least voice interaction is used for service. In addition, visual interaction can be performed between the virtual character image of the Internet of Things device and the user, and even based on holographic images or physical robots, more stereoscopic interaction can be performed with the user. Of course, in order to support voice interaction, modules such as microphones and speakers are needed. Further, in order to improve intelligence, the ability of a large model is used to accurately understand the user's intention during interaction, and then voice, visual and other interaction forms are used for service.

[0045] S110: In the service process, the voice uttered by the user and / or the action made by the user are collected to generate corresponding user instant performance data.

[0046] The voice uttered by the user is collected in real time through a microphone, and the action made by the user is also collected in real time through a camera to generate collection data in the form of audio and image as user instant performance data, or the collection data is further processed (such as extracting features of interest, converting to the same form of data and fusing, classifying, etc.) to be used as user instant performance data for the model.

[0047] In one or more embodiments of the present disclosure, voice collection can be tried first, and the collection data can be converted into text for further analysis. For example, it can be judged whether the user is uttering voice, if so, the voice is collected and recognized to generate voice text as corresponding user instant performance data, otherwise, multiple frames of images of the user can be collected, action features are extracted from the multiple frames of images, and the action features are mapped to action semantic text as corresponding user instant performance data, so as to help more efficiently and accurately understand the instant performance of the user.

[0048] S112: Analyze the user immediate performance data by using the pre-trained large model to obtain an analysis result.

[0049] If the user immediate performance data is in the form of text, a large language model can be directly used for analysis. In this case, for the action semantic text mentioned above, the user's speaking style can also be described (for example, if the user nods, the corresponding converted action semantic text can be "I agree" or "OK"; similarly, the user's corresponding inner speech can be inferred according to the collected action to form the action semantic text). That is, although the user's action is collected, the action semantic text is converted to make the user seem to have spoken a voice, and the semantics expressed by the voice is consistent with the semantics expressed by the action. Using the action semantic text to record this hypothetical voice makes it easier for the large language model to use and understand.

[0050] In one or more embodiments of the present disclosure, the user immediate performance data in the form of text can be determined, and the user immediate performance data is converted into machine instructions of the Internet of Things device by using a pre-trained large model, to switch the service mode or continue to execute the current service mode. In this way, the analysis process and the service process can be smoothly connected more efficiently, which helps to improve the response speed to the user and reduces the abruptness that may be caused by mode changes in the service process.

[0051] S114: According to the analysis result, it is judged whether the user switches to another personality in the plurality of personalities.

[0052] In one or more embodiments of the present disclosure, the user can change the personality he or she expresses by actively changing the speaking style, behavior style, speaking specific speech, making specific actions, etc. in order to expect the Internet of Things device to timely cooperate and make corresponding service adaptability changes.

[0053] The Internet of Things device perceives the immediate change of the user's personality based on the analysis of the continuously collected user immediate performance data. If there is no change, the previous service mode can be continued to serve. If there is a change, it can be considered whether to timely switch the service mode to adapt to the changed personality.

[0054] S116: If yes, automatically switch from the first service mode to a second service mode corresponding to the personality information of the another personality, and continue to serve the user according to the second service mode.

[0055] In one or more embodiments of the present disclosure, the second service mode is different from the first service mode, and when it is judged that the user has undergone a personality switch, the service mode is switched in time to adapt to the personality after the switch.

[0056] Through the method of FIG. 1, the Internet of Things device is provided with the comprehensive ability of visual observation, voice interaction, and accurate understanding of user instant performance based on a large model. The user can freely and flexibly associate his own identity information with the personality information of multiple personalities. Based on the above-mentioned comprehensive ability and identity-personality association, the personality switching of the user is smoothly and instantaneously perceived and matched, and the corresponding service mode is switched to adapt to the current personality of the user, so as to intelligently realize the improvisational performance service for the user, thereby improving the immersion and freedom of the user in the service area of the Internet of Things device, more intelligently coping with different service needs and spiritual needs of different users in different states, and helping to improve the user experience of the Internet of Things device.

[0057] Based on the method of FIG. 1, the present disclosure also provides some specific embodiments and extension schemes of the method, which will be described below.

[0058] In one or more embodiments of the present disclosure, most normal users do not have multiple real personalities in real life, but only have one real personality. Only a small number of abnormal users have multiple real personalities. The present application mainly considers the case of normal users. The multiple personalities associated with the identity information of the same normal user can not be real personalities, but only personalities that the user wants to temporarily perform or experience. In this case, the personality can actually be the real personality of another person, or even a virtual personality, so that the user can experience the fun of personality performance in daily life, and the intelligent interaction of the Internet of Things device can cooperate and cater to such personality performance, which is a surprising service experience for the user. Furthermore, in this case and scenario, the user can perform more freely because the interaction is with a machine rather than a real person (unattended service), which helps to relieve the user's stress in real life.

[0059] Based on such an idea, one or more embodiments of the present disclosure provide a flowchart of a scheme for intelligent service based on virtual personality, as shown in FIG. 2. The scheme can be applied to the Internet of Things device or the server of the Internet of Things device described above.

[0060] The flowchart in FIG. 2 includes the following steps.

[0061] S202: Pre-extracting false assumption information from literary and artistic works for fictional characters in the literary and artistic works, so that the user uses at least part of the personality of the fictional character.

[0062] In one or more embodiments of the present disclosure, similarly, if a real person (such as a star, a friend of the current user, etc.) agrees to authorize, the setting information of the real person can also be used for the user to use the corresponding personality.

[0063] S204: Show the user selectable information for setting personality including the false setting information.

[0064] In one or more embodiments of the present disclosure, a fictional character with distinctive personality and prominent characteristics can be selected to extract information, so that the user can more easily deduce its personality, and different false setting information of different fictional characters can be mixed and provided to the user for selection to build an original mixed personality, so as to help improve the diversity and interest of the personality.

[0065] For false setting information, different information granularity can be used for extraction as needed, so that the same personality can be represented in different levels of detail. If the information granularity is coarse, it helps the user to easily deduce, and also helps to improve the judgment efficiency when switching personalities, and if the information granularity is fine, it helps to create a more precise service mode that fits better, and helps to improve the user's immersion. Of course, the user's opinion can also be solicited in advance to determine whether the user wants to "roughly deduce the personality" or "detailedly deduce the personality", and the strictness of the personality switching judgment is adjusted accordingly.

[0066] S206: Determine the personality information of the personality set by the user according to the information selected by the user in each of the selectable information, and pre-associate the personality information with the identity information of the user.

[0067] The user can select multiple information in the selectable information, and then match an existing personality or generate a personality according to the multiple information as the personality set by the user. By analogy, the user can set multiple personalities for himself, and the personality information representing the corresponding personality will be associated with the identity information of the user.

[0068] S208: For Internet of Things devices, when the user enters, obtain the personality information of at least one personality pre-associated with the identity information from the local or server, wherein the personality information contains at least part of the false setting information set by the user for himself.

[0069] In this example, the user associates at least one virtual personality based on false setting information for himself, so as to break through the limitations of the user's real personality, and through the simple deduction of the user to the virtual personality, a new service experience brought by the service mode specially created for the virtual personality can be obtained.

[0070] S210: If it is judged that the user exhibits the at least one personality based on the false setting information, a service mode corresponding to the at least one personality is adopted, and the user is served as the corresponding fictional character.

[0071] In one or more embodiments of the present disclosure, the false setting information can include a specific meme belonging to the virtual character. The user can trigger the Internet of Things device to judge that the user exhibits the virtual personality by performing the specific meme (such as saying a catchphrase of the virtual character, making a habitual action of the virtual character, etc.). In this way, the user operation is facilitated, and the fault tolerance and reliability are higher.

[0072] In one or more embodiments of the present disclosure, in order to improve the immersion of the user after switching to the virtual personality, in the service mode corresponding to the virtual personality, specific service content can be created according to the environment and experience of the virtual character corresponding to the virtual personality in the literary and artistic work to which it belongs (such as role voice feedback, light effects, etc. created for the virtual character or other important characters in the literary and artistic work, which can be used for current service; for example, a gift, a discount, or a membership title that is exclusive to the virtual character can be created for gifting), and only the virtual personality is allowed to open the specific service content. Further, the specific service content can be hidden, and the virtual personality needs to explore to a certain extent (such as solving puzzles in the literary and artistic work, choosing the next plot, etc.) according to the environment and experience, so as to trigger the appearance of the specific service content. In this way, the interest experienced by the user can be effectively improved, and the enthusiasm of the user in using the Internet of Things device can be improved.

[0073] In one or more embodiments of the present disclosure, the initial personality information and the personality information of another personality described above respectively reflect different degrees of understanding of the business knowledge related to the Internet of Things device. For example, assuming that the Internet of Things device is used to sell financial products, the initial personality information may reflect a housewife mainly responsible for taking care of the family, and the another personality information may reflect a middle-aged person with a financial background. The understanding of the financial business knowledge related to the Internet of Things device of the another personality is probably much higher than that of the initial personality information. In this case, differentiated services can be provided to make the user easily understand the service and also have additional knowledge gain. Based on this idea, one or more embodiments of the present disclosure provide a flowchart of a scheme for intelligent service based on differences in business knowledge of different personalities, as shown in FIG. 3.

[0074] The flowchart in FIG. 3 includes the following steps.

[0075] S302: Determine that the initial personality information and the personality information of the other personality respectively reflect different degrees of understanding of the business knowledge related to the Internet of Things device.

[0076] S304: Before the service is provided for the user, determine a service mode that matches the degree of understanding reflected by the personality information of the specified personality from a plurality of service modes with different degrees of expertise as a knowledge-adapted service mode.

[0077] In the knowledge-adapted service mode, the user will be able to understand the service interaction based on the business knowledge related to the Internet of Things device with a high probability corresponding to the specified personality.

[0078] S306: Set the knowledge-adapted service mode as the service mode corresponding to the personality information of the specified personality.

[0079] S308: When the service is provided for the user, determine a service mode with a higher degree of understanding as a tutoring service mode in the current service mode corresponding to the personality information of the current personality of the user.

[0080] In one or more embodiments of the present disclosure, the service mode with a higher degree of understanding relative to the current service mode can be determined as the tutoring service mode to avoid a large degree of understanding that exceeds the user's needs and may hinder the user's understanding.

[0081] S310: Determine the professional knowledge blind spot existing in the current service mode according to the degree of understanding adapted by the tutoring service mode and the degree of understanding adapted by the current service mode.

[0082] Based on the professional knowledge blind spot, on the one hand, the missing knowledge can be supplemented for the user, and on the other hand, the user can be guided to explore unknown business fields, which helps to develop more business possibilities for the user, thereby improving the user's sense of acquisition and improving the professionalism of the platform in the user's mind, so that the user trusts the platform more.

[0083] S312: Generate additional service content containing the professional knowledge blind spot according to the professional knowledge blind spot and the preset business knowledge base.

[0084] S314: Provide service for the user using the additional service content.

[0085] In one or more embodiments of the present disclosure, the professional knowledge blind spot corresponds to knowledge that the user does not currently understand, but by narrowing the knowledge gap between the current service mode and the higher service mode described above, the user can be more quickly and effectively guided to understand this part of knowledge, thereby enhancing the user's self-confidence and improving the user's enthusiasm for using the services related to this part of knowledge, and further introducing these related services in further services, and performing actions such as recommendations. When business operation and marketing are performed in this way, users can better feel the sincerity of the platform, which helps to reduce user misunderstanding.

[0086] According to the foregoing description, more intuitively, one or more embodiments of the present disclosure also provide a technical architecture diagram of an Internet of Things device in an application scenario, as shown in FIG. 4.

[0087] In FIG. 4, the collection hardware and the playback hardware include a multi-modal camera, a microphone array, a speaker, and the like. The multi-modal camera can be used to complete face entry detection, face recognition, and living body recognition, and the like. Here, since the voice modal living body and speaker recognition are combined, it can be tried to reduce the requirements of the face recognition hardware, such as, in a payment scenario, the RGB+depth+IR camera is downgraded to the RGB+IR camera, and in a relatively common identity verification scenario, the RGB+IR camera is downgraded to the RGB camera; the microphone array can be used to process noise reduction and directional speaker voice extraction, and in some scenarios, such as a small shop without an attendant at night with little noise, a normal microphone can be reduced; the speaker can be used to broadcast sound to the user, and a speaker with the ability to broadcast to the user directionally can be tried to reduce disturbance to others.

[0088] The acquisition of the original visual signal can also use the existing monitoring system to acquire the collection and playback of the voice, and similarly, in addition to the microphone and the speaker on the Internet of Things device, the user's hardware system (such as a mobile phone) can also be used to acquire the voice; the service is extensible and open to the ecology, which can be provided and implemented by a third party, such as a selected product guide, a payment service, a member service, and the like.

[0089] At the software level, the IoT device is configured with a smart butler component, which integrates face recognition, voice, large language model, and other algorithm capabilities to complete functions such as user entry and identity recognition, voice synthesis and broadcast (TTS), visual + audio user semantic conversion into machine-understandable instructions (ASR + TTI), and other functions. On the other hand, it also provides personality setting, personality recognition, personality switching detection, and other functions, and adapts corresponding differentiated service capabilities for different personalities. For different personalities exhibited by users, corresponding service modes can be used to provide corresponding operation and marketing services, and voice synthesis can be performed on the corresponding operation and marketing service scripts to complete the service process through voice and visual interaction with the user. Among them, ASR can be used to convert user speech into text, TTI represents semantic conversion instructions, and based on the text output by ASR processing, a large language model is used to understand semantics and convert them into machine-understandable instructions, such as confirmation, cancellation, automatic text input, confirmation of the current personality, correction of the personality, switching of the personality, and other instructions.

[0090] The component can also provide a more natural will confirmation method, such as face and mouth dynamic + voice recognition for will confirmation, and for example, the user can say "confirm payment" instead of clicking the "confirm payment" button on the screen, which is more convenient and natural. Similarly, some existing functions can also be enhanced, such as for live body recognition, face and mouth dynamic + voice can be used to improve the accuracy of live body recognition and improve the protection performance against 3D head model attacks.

[0091] Further, the IoT device can also be configured with an operation and marketing component that can be called during the service process. The functions implemented by the component can be part of the services provided, and third parties can also be connected to the services and personality information required by users, thereby facilitating the introduction of third-party service supply and personality information supply. The component can operate according to the scene, such as recommending coupons, packages, and membership services to users. Intuitively, the flowchart of the intelligent marketing scheme provided by one or more embodiments of the present disclosure in an application scenario is shown in FIG. 5.

[0092] The scenario in FIG. 5 can be an unattended store scenario, and the access control, intelligent service component and voice operation marketing component can jointly constitute the above-mentioned Internet of Things device. In this scenario, the entrance of the store is provided with an access control, and the user can enter by scanning the face. It should be noted that the access control here is mainly to determine the identity information of the user by scanning the face, and is not intended to block the user. Therefore, the face scanning process can be unnoticeable; the access control triggers the intelligent service component and passes the identity information of the user to the intelligent service component; the intelligent service component can identify the initial personality of the user based on the identity information, and can further detect whether the personality of the user has changed during the stay in the store; the voice operation marketing component perceives the entry of the user and the identity information, the current personality information through the callback information of the intelligent service component, and then generates a corresponding entry recommendation script suitable for the current personality, calls the voice synthesis capability of the intelligent service component, and recommends the user to enter the meeting by voice, for example, recommends the user to open a membership to obtain a corresponding payment discount (it should be noted that the entry recommendation scripts for different personalities can be obviously different); then, the confirmation of the entry instruction of the user is perceived and completed through the callback of the intelligent small clerk, and the user can be operated to enter the meeting; after the user finishes selecting the product, the user can self-settle the payment by scanning the face and use the payment discount obtained just now, thereby completing the payment.

[0093] Taking the current personality of the user as the personality of a fictional character in a literary work with a certain battle group as an example, the entry recommendation script is not a direct word such as "entry", but a statement such as "XX (the name of the fictional character), the battle group has finally found you, please become our comrade in arms". Similarly, for other personalities, scripts with dramatic appeal can also be created according to the situation of the personality itself and the situation of the prototype character in the prototype scene.

[0094] Of course, not only scripts, but also the execution of business logic can be differentiated according to different personalities.

[0095] Based on the same idea, one or more embodiments of the present disclosure also provide a device and equipment corresponding to the above-mentioned method, as shown in FIG. 6 and FIG. 7. The device and equipment can correspondingly execute the above-mentioned method and the related optional solutions.

[0096] Fig. 6 is a structural schematic diagram of an intelligent service device applied to an Internet of Things device according to one or more embodiments of the present disclosure, the device comprising: a face recognition module 602 configured to perform face recognition on a user and determine identity information of the user; a personality association module 604 configured to determine personality information of a plurality of personalities associated with the identity information; a personality selection module 606 configured to select personality information of one personality from among the personality information of the plurality of personalities as initial personality information; a first service module 608 configured to start providing service for the user through voice interaction according to a first service mode set for the initial personality information; a performance collection module 610 configured to collect voice and / or actions of the user during the service process and generate corresponding user real-time performance data; a performance analysis module 612 configured to analyze the user real-time performance data using a pre-trained large model to obtain an analysis result; a personality switching module 614 configured to determine whether the user switches to another personality from among the plurality of personalities according to the analysis result; and a service switching module 616 configured to, if so, automatically switch from the first service mode to a second service mode set for the personality information of the another personality and continue to provide service for the user according to the second service mode.

[0097] Optionally, the personality association module 604 obtains one or more personality information of personalities pre-associated with the identity information by the user, and performs recognition matching on real-time performance of the user, and if a personality other than the one or more personalities is matched, associates the personality information of the other personality with the identity information to obtain the personality information of the plurality of personalities associated with the identity information. The personality selection module 606 selects the personality information of the other personality as the initial personality information.

[0098] Optionally, the personality association module 604 obtains at least one personality information of a personality pre-associated with the identity information by the user from a server, and the personality information contains at least part of false setting information set by the user for himself / herself.

[0099] Optionally, the false setting information is extracted from literary and artistic works for a fictional character therein and provided to the user for setting, so that the user uses at least part of the personality of the fictional character.

[0100] Optionally, the personality information of different personalities respectively reflects different speaking styles, and / or behavior styles, and / or visual styles.

[0101] Optionally, the large model comprises a large language model; the performance collection module 610 determines whether the user is speaking; if so, the voice is collected and recognized to generate voice text as the corresponding user's real-time performance data for the large language model to analyze; otherwise, multiple frames of images of the user are collected, action features are extracted from the multiple frames of images, the action features are mapped into action semantic text as the corresponding user's real-time performance data for the large language model to analyze.

[0102] Optionally, the performance analysis module 612 determines the user's real-time performance data in the form of text; and uses a pre-trained large model to convert the user's real-time performance data into machine instructions of the Internet of Things device for switching service modes or continuing to execute the current service mode.

[0103] Optionally, the initial personality information and the personality information of the other personality respectively reflect different levels of understanding of the business knowledge related to the Internet of Things device; the first service module 608 or the service switching module 616 determines, before the user is served, a service mode that matches the understanding level reflected by the personality information of the specified personality from a plurality of service modes with different professional levels, as a knowledge-adapted service mode; and sets the knowledge-adapted service mode as the service mode corresponding to the personality information of the specified personality.

[0104] Optionally, the first service module 608 or the service switching module 616 determines, in the current service mode corresponding to the user's current personality information, a service mode with a higher adapted understanding level as a tutoring service mode; determines a professional knowledge blind spot existing in the current service mode according to the adapted understanding level of the tutoring service mode and the adapted understanding level of the current service mode; generates additional service content containing the professional knowledge blind spot according to the professional knowledge blind spot and a preset business knowledge base; and serves the user using the additional service content.

[0105] Optionally, the service is an unattended service.

[0106] Fig. 7 is a structural schematic diagram of an intelligent service device applied to an Internet of Things device according to one or more embodiments of the present disclosure, the device comprising: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform: facial recognition on a user to determine identity information of the user; determining personality information of a plurality of personalities associated with the identity information; selecting personality information of one personality from the personality information of the plurality of personalities as initial personality information; starting to provide service for the user through voice interaction according to a first service mode set for the initial personality information; in the service process, collecting voice and / or actions of the user to generate corresponding user real-time performance data; using a pre-trained large model to analyze the user real-time performance data to obtain an analysis result; determining whether the user switches to another personality from the plurality of personalities according to the analysis result; if yes, automatically switching from the first service mode to a second service mode set for the personality information of the another personality, and continuing to provide service for the user according to the second service mode.

[0107] Based on the same idea, one or more embodiments of the present disclosure also provide a non-volatile computer storage medium storing computer executable instructions configured to: perform facial recognition on a user to determine identity information of the user; determine personality information of a plurality of personalities associated with the identity information; select personality information of one personality from the personality information of the plurality of personalities as initial personality information; start to provide service for the user through voice interaction according to a first service mode set for the initial personality information; in the service process, collect voice and / or actions of the user to generate corresponding user real-time performance data; use a pre-trained large model to analyze the user real-time performance data to obtain an analysis result; determine whether the user switches to another personality from the plurality of personalities according to the analysis result; if yes, automatically switch from the first service mode to a second service mode set for the personality information of the another personality, and continue to provide service for the user according to the second service mode.

[0108] In the 1990s, it was quite obvious to distinguish whether an improvement in a technology was in hardware (e.g., improvement in circuit structures of diodes, transistors, switches, etc.) or in software (improvement in method flow). However, as technology has evolved, many improvements in method flow today can be considered as direct improvements in hardware circuit structures. Designers almost always obtain the corresponding hardware circuit structures by programming the improved method flow into hardware circuits. Therefore, it cannot be said that an improvement in a method flow cannot be implemented by hardware entity modules. For example, a programmable logic device (PLD) (e.g., a field programmable gate array (FPGA)) is an integrated circuit whose logic function is determined by user programming of the device. A digital system is "integrated" on a PLD by the designer programming it, rather than by asking a chip manufacturer to design and fabricate a custom integrated circuit chip. Moreover, instead of manually fabricating integrated circuit chips, this programming is now mostly implemented by "logic compiler" software, which is similar to software compilers used in program development, and the original code to be compiled is written in a specific programming language, which is called a hardware description language (HDL), and there are many such languages, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., and the most commonly used are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. It should be clear to those skilled in the art that, as long as the method flow is logically programmed in the above-mentioned hardware description languages and programmed into an integrated circuit, a hardware circuit that implements the logical method flow can be easily obtained.

[0109] The controller can be implemented in any suitable way, for example, the controller can take the form of a microprocessor or processor and a computer readable medium storing computer readable program code, such as software or firmware, executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320, the memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also know that, in addition to being implemented in pure computer readable program code, the controller can also be implemented to perform the same functions in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers and embedded microcontrollers, etc. by logically programming the method steps. Therefore, such a controller can be considered as a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can even be considered as both a software module implementing a method and a structure within a hardware component.

[0110] The systems, apparatuses, modules or units illustrated by the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0111] For the sake of description, the above apparatuses are described in various units by functions respectively. Of course, the functions of each unit can be implemented in the same or multiple software and / or hardware in implementing the present disclosure.

[0112] Those skilled in the art will understand that the embodiments of the present disclosure can be provided as a method, a system or a computer program product. Therefore, the embodiments of the present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present disclosure can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0113] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0114] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks.

[0115] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0116] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0117] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory, for storing, in general, data and / or program instructions. The memory can also include non-volatile memory, such as read-only memory (ROM), electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or non-volatile random access memory (NVRAM) for storing, in general, data and / or program instructions. The memory is an example of computer readable media.

[0118] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0119] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not only include those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0120] The present disclosure can be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like, which perform particular tasks or implement particular abstract data types. The present disclosure can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are connected through a communication network. In a distributed computing environment, program modules can be located in both local and remote computer storage media including storage devices.

[0121] The various embodiments in the present disclosure are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments. In particular, for the device, apparatus, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0122] The above describes particular embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order and still achieve desirable results. Additionally, the processes depicted in the figures do not necessarily require the particular order shown or sequential order in order to achieve the desired results. In some implementations, multitasking and parallel processing can be advantageous or necessary.

[0123] The above merely provides one or more embodiments of the present disclosure and is not intended to limit the present disclosure. One of ordinary skill in the art can make various modifications and changes to the one or more embodiments of the present disclosure. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the one or more embodiments of the present disclosure shall be included in the scope of the claims of the present disclosure.

Claims

1. A smart service method applied to Internet of Things (IoT) devices, comprising: Perform facial recognition on the user to determine the user's identity information; To determine the personality information of multiple personalities associated with the aforementioned identity information; Among the personality information of the various personalities, the personality information of one personality is selected as the initial personality information; According to the first service mode set for the initial personality information, services are provided to the user through voice interaction; During the service process, the voice and / or actions of the user are collected to generate corresponding real-time user performance data; The user's real-time performance data is analyzed using a pre-trained large model to obtain analysis results; Based on the analysis results, it is determined whether the user has switched to another personality among the multiple personalities; If so, the system will automatically switch from the first service mode to the second service mode set for the personality information of the other personality, and continue to provide services to the user according to the second service mode.

2. The method as described in claim 1, wherein determining the personality information of multiple personalities associated with the identity information specifically includes: Obtain personality information of one or more personalities that the user has pre-set to associate with the identity information; The user's current real-time behavior is identified and matched. If a match is found with one or more personalities other than those mentioned above; Then, the personality information of the other personalities is associated with the identity information to obtain the personality information of multiple personalities associated with the identity information; The step of selecting one personality type from the multiple personality types as the initial personality information specifically includes: Select personality information from individuals other than those mentioned above as initial personality information.

3. The method as described in claim 1, wherein determining the personality information of multiple personalities associated with the identity information specifically includes: Obtain personality information of at least one personality type that the user has pre-associated with the identity information from the server; The personality information includes at least some false information that the user sets for themselves.

4. The method as described in claim 3, wherein the false setting information is extracted from fictional characters in literary and artistic works and provided to the user for setting, so that the user can use at least part of the personality of the fictional character.

5. The method as described in claim 1, wherein the personality information of the different personalities respectively reflects different speaking styles, and / or behavioral styles, and / or visual styles.

6. The method of claim 1, wherein the large model includes a large language model; The process of collecting the user's voice or actions to generate corresponding real-time user performance data specifically includes: Determine whether the user is making a voice call; If so, the speech is collected and recognized to generate speech text, which serves as the corresponding real-time user performance data for analysis by the large language model. Otherwise, multiple frames of images of the user are collected, action features are extracted from the multiple frames of images, and the action features are mapped into action semantic text as corresponding real-time user performance data for analysis by the large language model.

7. The method as described in claim 1, wherein the step of analyzing the user's real-time performance data using a pre-trained large model to obtain analysis results specifically includes: Determine the user's real-time performance data in text form; Using a pre-trained large model, the user's real-time performance data is converted into machine instructions for the IoT device, which are used to switch service modes or continue to execute the current service mode.

8. The method as described in claim 1, wherein the initial personality information and the personality information of the other personality respectively reflect different levels of understanding of the business knowledge involved in the Internet of Things device; Before providing services to the user, the method further includes: Among various service models with different levels of professionalism, one service model that matches the level of understanding reflected in the personality information of the specified personality is identified as the knowledge-matching service model. The knowledge adaptation service mode is set as the service mode corresponding to the personality information of the specified personality.

9. The method of claim 8, wherein providing services to the user specifically includes: Under the current service mode corresponding to the user's current personality information, determine the service mode with a higher level of understanding and use it as the tutoring service mode. Based on the level of understanding adapted to the tutoring service model and the level of understanding adapted to the current service model, the professional knowledge gaps existing in the current service model are determined. Based on the aforementioned professional knowledge gaps and a pre-set business knowledge base, additional service content is generated to fill in the aforementioned professional knowledge gaps. The user is provided with services using the aforementioned additional service content.

10. The method as described in claim 1, wherein the service is an unattended service.

11. A smart service device for use in Internet of Things (IoT) devices, comprising: The facial recognition module performs facial recognition on the user to determine the user's identity information; The personality association module determines the personality information of multiple personalities associated with the identity information; The personality selection module selects one personality from the multiple personality profiles as the initial personality profile. The first service module, based on the first service mode set for the initial personality information, begins to provide services to the user through voice interaction; The performance acquisition module collects the user's voice and / or actions during the service process and generates corresponding real-time user performance data. The performance analysis module uses a pre-trained large model to analyze the user's real-time performance data and obtain analysis results. The personality switching module determines, based on the analysis results, whether the user has switched to another personality among the multiple personalities. If so, the service switching module will automatically switch from the first service mode to the second service mode set for the personality information of the other personality, and continue to provide services to the user according to the second service mode.

12. The apparatus of claim 11, wherein the personality association module acquires personality information of one or more personalities that the user has pre-set to associate with the identity information; The user's current real-time behavior is identified and matched. If a match is found with one or more personalities other than those mentioned above; Then, the personality information of the other personalities is associated with the identity information to obtain the personality information of multiple personalities associated with the identity information; The personality selection module selects personality information from individuals other than those mentioned above as initial personality information.

13. The apparatus of claim 11, wherein the personality association module obtains from the server personality information of at least one personality that the user has pre-associated with the identity information; in, The personality information includes at least some false information that the user sets for themselves.

14. The apparatus of claim 13, wherein the false setting information is extracted from a literary or artistic work for a fictional character therein and provided to the user for setting, so that the user uses at least a portion of the personality of the fictional character.

15. The apparatus of claim 11, wherein the personality information of the different personalities respectively reflects different speaking styles, and / or behavioral styles, and / or visual styles.

16. The apparatus of claim 11, wherein the large model comprises a large language model; The performance acquisition module determines whether the user is uttering a voice message. If so, the speech is collected and recognized to generate speech text, which serves as the corresponding real-time user performance data for analysis by the large language model. Otherwise, multiple frames of images of the user are collected, action features are extracted from the multiple frames of images, and the action features are mapped into action semantic text as corresponding real-time user performance data for analysis by the large language model.

17. The apparatus of claim 11, wherein the performance analysis module determines the user's real-time performance data in text form; Using a pre-trained large model, the user's real-time performance data is converted into machine instructions for the IoT device, which are used to switch service modes or continue to execute the current service mode.

18. The apparatus of claim 11, wherein the initial personality information and the personality information of the other personality respectively reflect different levels of understanding of the business knowledge involved in the Internet of Things device; Before providing services to the user, the first service module or the service switching module determines, from among various service modes with different levels of professionalism, a service mode that matches the level of understanding reflected by the personality information of the specified personality, as the knowledge-adapted service mode. The knowledge adaptation service mode is set as the service mode corresponding to the personality information of the specified personality.

19. The apparatus of claim 18, wherein the first service module or the service switching module, under the current service mode corresponding to the personality information of the user's current personality, determines a service mode with a higher level of understanding as a tutoring service mode; Based on the level of understanding adapted to the tutoring service model and the level of understanding adapted to the current service model, the professional knowledge gaps existing in the current service model are determined. Based on the aforementioned professional knowledge gaps and a pre-set business knowledge base, additional service content is generated to fill in the aforementioned professional knowledge gaps. The user is provided with services using the aforementioned additional service content.

20. The apparatus of claim 11, wherein the service is an unattended service.

21. A smart service device applied to Internet of Things (IoT) devices, comprising: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform: Perform facial recognition on the user to determine the user's identity information; To determine the personality information of multiple personalities associated with the aforementioned identity information; Among the personality information of the various personalities, the personality information of one personality is selected as the initial personality information; According to the first service mode set for the initial personality information, services are provided to the user through voice interaction; During the service process, the voice and / or actions of the user are collected to generate corresponding real-time user performance data; The user's real-time performance data is analyzed using a pre-trained large model to obtain analysis results; Based on the analysis results, it is determined whether the user has switched to another personality among the multiple personalities; If so, the system will automatically switch from the first service mode to the second service mode set for the personality information of the other personality, and continue to provide services to the user according to the second service mode.

Images