User portrait updating method and device and electronic equipment

Abstract

The embodiment of the invention discloses a user portrait updating method and device and electronic equipment, and belongs to the technical field of smart home. Comprising the steps of obtaining interaction information between a user and intelligent equipment; extracting target information associated with the user portrait of the user from the interaction information; the user portrait comprises a plurality of attribute tags representing different dimension information of the user; and updating the attribute tag of the user portrait according to the target information. According to the embodiment of the invention, the interaction information between the user and the intelligent equipment is automatically collected and analyzed, and the target information related to the user portrait is extracted, so that the attribute tag in the updated user portrait can accurately reflect the demand and change of the user, the dynamic updating of the user portrait is realized, the updating process does not depend on the active participation of the user, and the user experience is improved. The problem that the personalized service quality is reduced due to outdated or inaccurate user portrait information is greatly reduced, and the accuracy of the personalized service is improved.

Description

Technical Field

[0001] The embodiments in this specification belong to the field of smart home technology, and in particular relate to a method, apparatus and electronic device for updating user profiles. Background Technology

[0002] With the rapid development of technology and the widespread application of artificial intelligence, personalized services have become a key factor in enhancing user experience. Especially in the smart home sector, the increasing popularity of devices such as smart refrigerators has led to a growing demand for personalized services, prompting innovation and development in related technologies.

[0003] The construction and application of user profiles are the foundation for realizing personalized services. In the application scenario of smart refrigerators, by analyzing user profiles to determine users' dietary habits and health needs, smart refrigerators can recommend suitable recipes to help users make healthier dietary choices.

[0004] However, in related technologies, the updating of user profiles often relies on users actively updating them. This means that the information in the user profile may not accurately reflect the user's latest needs and changes, resulting in inaccurate personalized services. Summary of the Invention

[0005] This specification aims to address at least one of the technical problems existing in the prior art. To this end, this specification proposes a method, apparatus, and electronic device for updating user profiles, enabling timely updates to user profiles and improving the accuracy of personalized services.

[0006] Firstly, this specification provides a method for updating user profiles, including:

[0007] Acquire user interaction information with smart devices;

[0008] Extract target information associated with the user profile from the interaction information; the user profile includes multiple attribute tags representing different dimensions of user information.

[0009] The attribute tags of the user profile are updated based on the target information.

[0010] According to the user profile update method described in this specification, the user profile is updated by acquiring interaction information between the user and a smart device; extracting target information associated with the user profile from the interaction information; the user profile includes multiple attribute tags representing different dimensions of user information; and updating the attribute tags of the user profile based on the target information. This embodiment of the specification automatically collects and analyzes user interaction information with smart devices and extracts target information related to the user profile, enabling the attribute tags in the updated user profile to accurately reflect the user's needs and changes. This achieves dynamic updating of the user profile, and the update process does not rely on the user's active participation, greatly reducing the problem of decreased personalized service quality due to outdated or inaccurate user profile information, and improving the accuracy of personalized services.

[0011] According to one embodiment of this specification, updating the attribute tags of the user profile based on the target information includes:

[0012] If the first preset condition is met, the attribute tags of the user profile are updated according to the target information.

[0013] In this embodiment, by updating the user profile only when the first preset condition is met, it is possible to more intelligently determine when the user profile needs to be updated, avoiding unnecessary frequent updates, making the update process more targeted, and improving the accuracy of user profile maintenance.

[0014] According to one embodiment of this specification, the first preset condition includes at least one of the following conditions:

[0015] The number of text fragments in the interactive information is greater than or equal to a preset value;

[0016] The user triggers the update operation;

[0017] The current time is the preset update time;

[0018] The time elapsed since the last update is the preset time.

[0019] In this embodiment, by setting a threshold for the number of interactive text fragments, user activity can be identified, thereby capturing and reflecting the user's latest preferences in a timely manner when the user interacts frequently with the smart device. By allowing users to actively trigger update operations, users are given more control, enabling them to refresh their profile information when needed. By setting a preset update time, user profiles can be refreshed periodically, maintaining cyclical updates and preventing information from becoming outdated due to prolonged periods without updates. Automatic updates are scheduled after a preset time interval from the last update, ensuring that user profiles are updated within a certain time period, even if user interaction is infrequent within that period. By applying these conditions, user profile updates become more flexible, timely, and accurate, improving the response speed and service quality of personalized services.

[0020] According to one embodiment of this specification, extracting target information associated with the user profile from the interaction information includes:

[0021] Obtain the attribute tags of the user profile;

[0022] The target information associated with the attribute label in the interaction information is analyzed using a large language model.

[0023] In this embodiment, by acquiring the existing attribute tags of the user profile, it is possible to identify the user feature dimensions that need to be focused on and analyzed. By utilizing the powerful analytical capabilities of the large language model, the interaction information can be analyzed in detail, and text fragments related to these attribute tags can be identified and associated, whether they are direct or implicit user preferences and needs, thereby improving the accuracy of updating the user profile.

[0024] According to one embodiment of this specification, updating the attribute tags of the user profile based on the target information includes:

[0025] The target information is compared with the user profile to determine the target attribute tags that need to be updated;

[0026] Update the target attribute label based on the target information.

[0027] In this embodiment, by comparing the target information with the existing user profile, it is possible to accurately identify which attribute tags need to be updated, and make specific updates based on the target information, so that the user profile can reflect the user's new status and needs in a timely manner, thereby improving the accuracy and efficiency of user profile updates.

[0028] According to one embodiment of this specification, the attribute tags include at least one of user basic information, user health status, user dietary preferences, and user interests.

[0029] In this embodiment, by subdividing the attribute tags of the user profile into multiple dimensions such as basic user information, health status, dietary preferences and hobbies, a multi-dimensional user profile can be constructed. This allows for a more accurate capture and understanding of the user's specific needs and preferences in different aspects of life, thereby improving the quality of personalized services.

[0030] According to one embodiment of this specification, obtaining the interaction information between the user and the smart device includes:

[0031] Obtain the interaction request input by the user to the smart device;

[0032] If the interaction request meets the second preset condition, obtain the user profile corresponding to the user;

[0033] Using a large language model and / or a preset reply template, generate reply information based on the interaction request and the user profile;

[0034] The interaction request and the response information are identified as the interaction information.

[0035] In this embodiment, by obtaining the user profile corresponding to the user when the interaction request meets a specific second preset condition, the user's interaction request is analyzed in depth using a large language model, and the accuracy of the response information is improved by combining the rich information in the user profile; the preset response template provides a set of standardized response options, which, combined with the interaction request and user profile, can improve the efficiency of the response.

[0036] According to one embodiment of this specification, the smart device includes a cooling device.

[0037] In this embodiment, when the smart device is a cooling device, by continuously updating the user profile, the cooling device can accurately understand the user's health, diet and other information, thereby providing more personalized dietary advice and recipe recommendations.

[0038] Secondly, this specification provides a user profile updating device, including:

[0039] The acquisition module is used to acquire interaction information between the user and the smart device.

[0040] The extraction module is used to extract target information associated with the user profile of the user from the interaction information; the user profile includes multiple attribute tags representing different dimensions of user information;

[0041] The update module is used to update the attribute tags of the user profile based on the target information.

[0042] The user profile updating device according to this specification acquires interaction information between a user and a smart device; extracts target information associated with the user's profile from the interaction information; the user profile includes multiple attribute tags representing different dimensions of user information; and updates the attribute tags of the user profile according to the target information. This embodiment of the specification automatically collects and analyzes user interaction information with smart devices and extracts target information related to the user profile, enabling the attribute tags in the updated user profile to accurately reflect the user's needs and changes. This achieves dynamic updating of the user profile, and the updating process does not rely on the user's active participation, greatly reducing the problem of decreased personalized service quality due to outdated or inaccurate user profile information, and improving the accuracy of personalized services.

[0043] Thirdly, this specification provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the user profile update method as described in the first aspect above.

[0044] Fourthly, this specification provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the user profile update method as described in the first aspect above.

[0045] Fifthly, this specification provides a chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the user profile update method as described in the first aspect above.

[0046] Sixthly, this specification provides a computer program product, including a computer program that, when executed by a processor, implements the user profile update method as described in the first aspect above.

[0047] The above-described one or more technical solutions in the embodiments of this specification have at least one of the following technical effects:

[0048] According to the user profile update method described in this specification, the user profile is updated by acquiring interaction information between the user and a smart device; extracting target information associated with the user profile from the interaction information; the user profile includes multiple attribute tags representing different dimensions of user information; and updating the attribute tags of the user profile based on the target information. This embodiment of the specification automatically collects and analyzes user interaction information with smart devices and extracts target information related to the user profile, enabling the attribute tags in the updated user profile to accurately reflect the user's needs and changes. This achieves dynamic updating of the user profile, and the update process does not rely on the user's active participation, greatly reducing the problem of decreased personalized service quality due to outdated or inaccurate user profile information, and improving the accuracy of personalized services.

[0049] In some embodiments, by updating the user profile only when a first preset condition is met, it is possible to more intelligently determine when the user profile needs to be updated, avoiding unnecessary frequent updates, making the update process more targeted, and improving the accuracy of user profile maintenance.

[0050] In some embodiments, by setting a threshold for the number of interactive text fragments, user activity can be identified, thereby capturing and reflecting the user's latest preferences in a timely manner when the user interacts frequently with the smart device. By allowing users to actively trigger update operations, users are given more control, enabling them to refresh their profile information when needed. By setting a preset update time, user profiles can be refreshed periodically, maintaining the periodic updates of user profiles and avoiding information staleness due to prolonged periods without updates. By specifying an automatic update after a preset time interval from the last update, user profiles are updated within a certain time period, even if the user does not interact frequently within that period. By applying these conditions, user profile updates become more flexible, timely, and accurate, improving the response speed and service quality of personalized services.

[0051] In some embodiments, by obtaining existing attribute tags of user profiles, it is possible to identify user feature dimensions that need to be focused on and analyzed. By leveraging the powerful analytical capabilities of large language models, detailed analysis of interaction information can be performed, enabling the identification and association of text fragments related to these attribute tags, whether direct or implicit user preferences and needs, thereby improving the accuracy of updating user profiles.

[0052] In some embodiments, by comparing the target information with existing user profiles, it is possible to accurately identify which attribute tags need to be updated, and make specific updates based on the target information, so that the user profile can reflect the user's new status and needs in a timely manner, thereby improving the accuracy and efficiency of user profile updates.

[0053] In some embodiments, by subdividing the attribute tags of user profiles into multiple dimensions such as basic user information, health status, dietary preferences, and hobbies, a multi-dimensional user profile can be constructed, which can more accurately capture and understand the specific needs and preferences of users in different aspects of life, thereby improving the quality of personalized services.

[0054] In some embodiments, by obtaining the user profile corresponding to the user when the interaction request meets a specific second preset condition, the user's interaction request is analyzed in depth using a large language model, and the rich information in the user profile is combined to improve the accuracy of the response information; the preset response template provides a set of standardized response options, which, combined with the interaction request and user profile, can improve the efficiency of the response.

[0055] In some embodiments, when the smart device is a cooling device, by continuously updating the user profile, the cooling device can accurately understand the user's health, diet, and other information, thereby providing more personalized dietary advice and recipe recommendations.

[0056] Additional aspects and advantages of this specification will be set forth in part in the description which follows, and in part will be obvious from the description or may be learned by practice of this specification. Attached Figure Description

[0057] The above and / or additional aspects and advantages of this specification will become apparent and readily understood in conjunction with the following description of the embodiments in conjunction with the accompanying drawings, wherein:

[0058] Figure 1 This is a flowchart illustrating the user profile update method provided in the embodiments of this specification;

[0059] Figure 2 This is a schematic diagram of the structure of the user profile updating device provided in the embodiments of this specification;

[0060] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this specification. Detailed Implementation

[0061] The technical solutions in the embodiments of this specification will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments in this specification are within the scope of protection of this specification.

[0062] The terms "first," "second," etc., used in this specification and claims are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this specification can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0063] The following description, in conjunction with the accompanying drawings, details the user profile updating method, apparatus, and electronic device provided in this specification through specific embodiments and application scenarios.

[0064] It is understood that in the specific implementation of the specification, data related to users, such as user profiles and interaction information, are involved. When the embodiments of this specification are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0065] The method for updating user profiles can be applied to the terminal, specifically executed by the hardware or software within the terminal.

[0066] The terminal includes, but is not limited to, portable communication devices such as mobile phones or tablets with touch-sensitive surfaces (e.g., touchscreen displays and / or touchpads). It should also be understood that, in some embodiments, the terminal may not be a portable communication device, but rather a desktop computer with touch-sensitive surfaces (e.g., touchscreen displays and / or touchpads).

[0067] The following embodiments describe a terminal including a display and a touch-sensitive surface. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, mouse, and joystick.

[0068] The user profile update method provided in the embodiments of this specification can be executed by an electronic device or a functional module or entity in an electronic device that can implement the user profile update method. The electronic devices mentioned in the embodiments of this specification include, but are not limited to, smart devices, servers, etc. The following describes the user profile update method provided in the embodiments of this specification using an electronic device as the execution subject.

[0069] like Figure 1 As shown, the method for updating the user profile includes steps 110, 120, and 130.

[0070] Step 110: Obtain interaction information between the user and the smart device.

[0071] In the embodiments of this specification, a smart device can be a device capable of interacting with a user. A smart device may include sensors, a processor, etc. The sensors capture the user's voice input, text input, gesture input, etc., and the processor analyzes the user's input and generates corresponding input, thereby achieving interaction with the user. Alternatively, the smart device can also connect to a server via a network, where the server analyzes the user's input and generates corresponding input.

[0072] The smart device can be a refrigeration device, such as a smart refrigerator, or other devices, such as a smart thermostat, a smart light bulb, or a smart security camera. In this embodiment, when the smart device is a refrigeration device, by continuously updating the user profile, the refrigeration device can accurately understand the user's health, diet, and other information, thereby providing more personalized dietary advice and recipe recommendations.

[0073] User interaction with smart devices can take many forms, including but not limited to physical buttons, touchscreens, mobile applications, voice assistants, and gesture control. Smart devices can acquire user input through touchscreens, microphones, motion sensors, etc. For example, in the case of a smart refrigerator, users can interact with it by speaking to it or typing on its screen. After acquiring the user's input, the smart refrigerator can either generate corresponding output locally or send the input to a server, which will then generate the corresponding output. For instance, if the user inputs "Please recommend a dinner recipe," the smart refrigerator can generate one or more recipes, which will then be displayed on its screen.

[0074] In the embodiments described in this specification, a Large Language Model (LLM) can be invoked from a smart device or server to generate corresponding output based on user input. Alternatively, a response template can be pre-deployed in the smart device or server, defining the framework of the response and then filling in the specific content. When the user's input contains specific keywords, corresponding output can be generated based on the content of the response template. Alternatively, a response template can be combined with Natural Language Processing (NLP) technology to respond to user input. Interaction information can include both user input and the output of the smart device.

[0075] In some embodiments, obtaining user interaction information with a smart device includes:

[0076] Acquire user interaction requests to smart devices;

[0077] If the interaction request meets the second preset condition, obtain the user profile corresponding to the user;

[0078] Use large language models and / or preset response templates to generate response information based on interaction requests and user profiles;

[0079] Interaction requests and response information are identified as interaction information.

[0080] In this embodiment, users can input interaction requests to the smart device in any way, such as through voice input, touchscreen input, or remote input via mobile device. After detecting the user's interaction request to the smart device, it is determined whether the interaction request meets a second preset condition. For example, the second preset condition could be that the interaction request is associated with a user profile. The interaction request can be analyzed using a large language model. If the interaction request contains the user's needs related to diet, health, etc., it can be determined that the interaction request is associated with a user profile and meets the second preset condition; if the interaction request is a weather inquiry, it can be determined that the interaction request is not associated with a user profile and does not meet the second preset condition. Of course, other methods can also be used for judgment, such as analyzing keywords in the interaction request or using natural language processing technology to analyze whether the interaction request is associated with a user profile.

[0081] In some embodiments, the second preset condition may be other conditions, such as whether the interaction request meets a predetermined format or whether the content meets preset requirements. This specification does not limit this aspect in the embodiments.

[0082] In this embodiment, if the interaction request meets the second preset condition, a user profile corresponding to the user can be obtained, thereby enabling the generation of a targeted response to the interaction request based on the user profile. In one example, the user's interaction request is:

[0083] {

[0084] "content":"I want to make a healthy dinner, are there any recommended recipes?"

[0085] "timestamp":"2024-06-01 18:30:00"

[0086] }

[0087] The content contains the user's specific request or instruction, and the timestamp records the time when the interaction occurred.

[0088] Analysis reveals that the user's request in this interaction request is for a healthy dinner recipe. This request aligns with the user's health status and dietary preferences in the user profile, thus fulfilling the second pre-defined condition. The user profile can then be retrieved, revealing that the user is diabetic, follows a low-sugar diet, and prefers meat-based recipes. Based on this user profile, a response is generated.

[0089] {

[0090] "content":"Considering your health needs, I recommend you try making a grilled chicken breast with a vegetable salad, using olive oil and vinegar as dressing. This will keep it low in sugar and nutritionally balanced."

[0091] "timestamp":"2024-06-01 18:30:02"

[0092] }

[0093] The content contains the specific reply information, and the timestamp records the time when the reply was generated.

[0094] In this way, user profiles can be effectively utilized to provide personalized services and responses, thereby enhancing the user experience.

[0095] In this embodiment, response information can be generated using a large language model, a preset response template, or a combination of response templates and natural language processing techniques. The preset response template is a set of predefined text or message structures that can quickly generate response information in specific contexts. The response template provides a standardized way to respond to common questions or requests. For example, if a user asks about the weather, the preset response format in the response template might be "Today's weather forecast is [weather conditions], the highest temperature is [highest temperature], and the lowest temperature is [lowest temperature]. Enjoy your day!" Based on the content of the response template, local weather station data can be retrieved to obtain today's weather forecast. According to the weather forecast, information such as weather conditions, highest temperature, and lowest temperature can be filled into the response format. For example, the output response information could be "Today's weather forecast is sunny, the highest temperature is 30 degrees Celsius, and the lowest temperature is 25 degrees Celsius. Enjoy your day!"

[0096] In this embodiment, by obtaining the user profile corresponding to the user when the interaction request meets a specific second preset condition, the user's interaction request is analyzed in depth using a large language model, and the accuracy of the response information is improved by combining the rich information in the user profile; the preset response template provides a set of standardized response options, which, combined with the interaction request and user profile, can improve the efficiency of the response.

[0097] Step 120: Extract target information related to the user profile from the interaction information; the user profile includes multiple attribute tags representing different dimensions of user information.

[0098] A user persona is a virtual user model created by integrating information from different dimensions such as a user's typical characteristics, behavioral habits, needs, and preferences. The purpose of creating user personas is to better understand the target user group, thereby providing more personalized services or products.

[0099] In the embodiments of this specification, user profiles can be pre-built. A user profile includes multiple attribute tags representing different dimensions of user information; these attribute tags collectively form the user profile. Attribute tags include at least one of the following: basic user information, user health status, user dietary preferences, and user interests. Of course, attribute tags may also include other information, and this embodiment of the specification does not limit this.

[0100] The user's basic information may include:

[0101] Age: The user's age group, such as children, teenagers, adults, or seniors;

[0102] Gender: The user's gender;

[0103] Family members: The number and structure of family members, such as whether there are children or elderly people;

[0104] Residential area: The geographical location where the user lives, which may affect dietary habits and the availability of ingredients.

[0105] User health status can include:

[0106] Do you have any special dietary requirements, such as vegetarianism, low sugar, or low salt?

[0107] Health issues: Does the user have specific health problems, such as diabetes, high blood pressure, food allergies, etc.?

[0108] Exercise habits: The amount of daily exercise a user does, which may affect their energy needs and dietary choices.

[0109] User dietary preferences may include:

[0110] Preferred food types: The types of food that users prefer, such as Chinese, Western, Japanese, etc.

[0111] Dietary habits: The frequency and timing of a user's meals, such as whether they are accustomed to eating breakfast and dinner at certain times;

[0112] Food preferences: Users' preferences for specific foods, such as seafood, meat, and vegetables.

[0113] User interests may include:

[0114] Personal interests: The user's broad interests, such as reading, music, sports, travel, etc.

[0115] Social activities: Social activities that users participate in, such as parties, club activities, community services, etc.

[0116] Learning and Career: Users' professional background and learning interests, such as professional skills, online courses, etc.

[0117] In this embodiment, by subdividing the user profile's attribute tags into multiple dimensions such as basic user information, health status, dietary preferences, and hobbies, a multi-faceted and comprehensive user profile can be constructed. This allows for a more accurate capture and understanding of users' specific needs and preferences in different aspects of their lives, thereby improving the quality of personalized services. For example, when a user wants a smart device to recommend a dinner recipe, the user profile can be combined with analysis of the user's health status and dietary preferences. If the user's dietary preference is for spicy food, recipes corresponding to spicy cuisines such as Sichuan and Hunan can be recommended, thus achieving a more accurate personalized recommendation.

[0118] User profiles can be stored in databases, such as relational databases like MySQL; other types of databases, such as MongoDB, which is suitable for storing unstructured or semi-structured data and can handle complex data types in user profiles more flexibly; or distributed databases, such as Cassandra or HBase, which are suitable for large-scale data storage and processing, improving data scalability and fault tolerance.

[0119] Taking user profiles stored in a relational database as an example, each user's profile is stored in an independent data record. The field design includes user ID, age, gender, family members, health status, dietary preferences, hobbies, etc., and indexes are created for these fields to improve query efficiency.

[0120] In the embodiments of this specification, information related to the user profile can be extracted from the interaction information by analysis. For example, an interaction may contain the following dialogue:

[0121] User input: I want to make a healthy dinner, are there any recommended recipes?

[0122] The smart device responded: "Considering your health needs, I recommend you try making a grilled chicken breast with a vegetable salad, using olive oil and vinegar as dressing. This will keep it low in sugar and nutritionally balanced."

[0123] User input: I don't like chicken breast, grilled shrimp is more suitable for me.

[0124] Natural language processing techniques can be used to analyze the semantic information in interactive information and identify which information in the interactive information is associated with the attribute tags in the user profile. The extracted target information can be: the user prefers healthy food, prefers low-sugar food, dislikes chicken breast, and prefers shrimp.

[0125] In some embodiments, large language models, such as Tongyi Qianwen, Xunfei Xinghuo, Kimi, Wenxin Yiyan, and GPT (Generative Pre-trained Transformer), can be invoked to analyze interaction information and extract target information associated with the user's profile.

[0126] Step 130: Update the attribute tags of the user profile based on the target information.

[0127] In the embodiments of this specification, after obtaining the target information, the attribute tags of the user profile can be updated using the target information. For example, the target information may include: a preference for low-sugar foods, a dislike for chicken breast, and a preference for shrimp. Then, "a preference for low-sugar foods" can be added to the attribute tags of the user's health status, and "a dislike for chicken breast" and "a preference for shrimp" can be added to the attribute tags of the user's dietary preferences, thereby updating the attribute tags of the user profile.

[0128] The user profile update method described in this specification involves acquiring user interaction information with smart devices; extracting target information related to the user profile from the interaction information; the user profile including multiple attribute tags representing different dimensions of user information; and updating the attribute tags of the user profile based on the target information. This embodiment of the specification automatically collects and analyzes user interaction information with smart devices and extracts target information related to the user profile, ensuring that the attribute tags in the updated user profile accurately reflect user needs and changes. This achieves dynamic updating of the user profile, and the update process does not rely on active user participation, greatly reducing the problem of decreased personalized service quality due to outdated or inaccurate user profile information, and improving the accuracy of personalized services.

[0129] In some embodiments, updating the attribute tags of the user profile based on target information includes:

[0130] If the first preset condition is met, the attribute tags of the user profile are updated according to the target information.

[0131] In this embodiment, when updating the attribute tags of the user profile based on the target information, it can be determined whether the first preset condition is met. If it is met, the update is performed; if it is not met, the update is temporarily suspended.

[0132] The first preset condition can be a pre-set condition, such as a significant change in user behavior, the frequent occurrence of a specific behavior, or reaching a certain threshold of user interaction.

[0133] In this embodiment, by updating the user profile only when the first preset condition is met, it is possible to more intelligently determine when the user profile needs to be updated, avoiding unnecessary frequent updates, making the update process more targeted, and improving the accuracy of user profile maintenance.

[0134] In some embodiments, the first preset condition includes at least one of the following conditions:

[0135] The number of text fragments in the interactive information is greater than or equal to a preset value;

[0136] The user triggered the update operation;

[0137] The current time is the preset update time;

[0138] The time elapsed since the last update is the preset time.

[0139] In this embodiment, a text fragment can be a basic unit of text, such as a word, phrase, symbol, or any other form of text element. For example, in a large language model, the large language model converts the user's input into tokens corresponding to individual text fragments, forming an input token sequence. Then, it generates an output token sequence based on the input token sequence, with each text fragment corresponding to one token. The large language model can determine the number of text fragments in the interaction information by recognizing the number of tokens. If the number of text fragments in the interaction information is greater than or equal to a preset value, the attribute tags of the user profile can be updated. The preset value can be 1000, 2000, or other values, which can be set by those skilled in the art according to actual conditions. This embodiment of the specification does not limit this.

[0140] In this embodiment, the user-triggered update operation can be an active operation, such as an update button on the screen of the smart refrigerator. When the user presses the button, the update operation can be detected. Alternatively, the user-triggered update operation can be passively triggered, such as when the user changes their dietary preferences. If the change in dietary preferences is detected, it is determined that the user has triggered the update operation.

[0141] In this embodiment, the update time can be preset, such as updating at midnight every day or updating at noon every day. Of course, the update cycle can also be set. The update cycle can be a preset duration, such as 8 hours, in which case it updates once every 8 hours. Of course, the preset duration can also be other values, such as 12 hours, 24 hours, 36 hours, etc. This embodiment of the specification does not limit this.

[0142] In this embodiment, by setting a threshold for the number of interactive text fragments, user activity can be identified, thereby capturing and reflecting the user's latest preferences in a timely manner when the user interacts frequently with the smart device. By allowing users to actively trigger update operations, users are given more control, enabling them to refresh their profile information when needed. By setting a preset update time, user profiles can be refreshed periodically, maintaining cyclical updates and preventing information from becoming outdated due to prolonged periods without updates. Automatic updates are scheduled after a preset time interval from the last update, ensuring that user profiles are updated within a certain time period, even if user interaction is infrequent within that period. By applying these conditions, user profile updates become more flexible, timely, and accurate, improving the response speed and service quality of personalized services.

[0143] In some embodiments, extracting target information associated with a user's profile from the interaction information includes:

[0144] Obtain the attribute tags of the user profile;

[0145] Use large language models to analyze target information associated with attribute tags in interactive information.

[0146] In this embodiment, the large language model can analyze the interaction information, understand the context of the interaction information, match and analyze the attribute tags in the interaction information with the user profile, identify the information associated with the attribute tags, and determine the information as the target information.

[0147] For example, prompts can be pre-inputted into the large language model. For example, the prompts could be: "User attribute tags include user basic information, user health status, user dietary preferences, and user interests. Please extract the information associated with any one or more attribute tags from the interaction information and output that information as the target information."

[0148] In this embodiment, by acquiring the existing attribute tags of the user profile, it is possible to identify the user feature dimensions that need to be focused on and analyzed. By utilizing the powerful analytical capabilities of the large language model, the interaction information can be analyzed in detail, and text fragments related to these attribute tags can be identified and associated, whether they are direct or implicit user preferences and needs, thereby improving the accuracy of updating the user profile.

[0149] The user profile updating method provided in the embodiments of this specification can be executed by a user profile updating device. This specification describes the user profile updating device provided in the embodiments of this specification by using a user profile updating device to execute the user profile updating method as an example.

[0150] This specification also provides a user profile updating device in its embodiments.

[0151] like Figure 2 As shown, the device for updating the user profile includes:

[0152] The acquisition module 210 is used to acquire interaction information between the user and the smart device;

[0153] Extraction module 220 is used to extract target information related to the user profile from the interaction information; the user profile includes multiple attribute tags representing different dimensions of user information;

[0154] Update module 230 is used to update the attribute tags of the user profile based on the target information.

[0155] The user profile updating device according to this specification acquires user interaction information with a smart device; extracts target information related to the user's profile from the interaction information; the user profile includes multiple attribute tags representing different dimensions of user information; and updates the attribute tags of the user profile based on the target information. This embodiment of the specification automatically collects and analyzes user interaction information with a smart device and extracts target information related to the user profile, enabling the updated attribute tags in the user profile to accurately reflect the user's needs and changes. This achieves dynamic updating of the user profile, and the updating process does not rely on the user's active participation, greatly reducing the problem of decreased personalized service quality due to outdated or inaccurate user profile information, and improving the accuracy of personalized services.

[0156] In some embodiments, the update module 230 is further configured to:

[0157] If the first preset condition is met, the attribute tags of the user profile are updated according to the target information.

[0158] In some embodiments, the first preset condition includes at least one of the following conditions:

[0159] The number of text fragments in the interactive information is greater than or equal to a preset value;

[0160] The user triggered the update operation;

[0161] The current time is the preset update time;

[0162] The time elapsed since the last update is the preset time.

[0163] In some embodiments, the extraction module 220 is further configured to:

[0164] Obtain the attribute tags of the user profile;

[0165] Use large language models to analyze target information associated with attribute tags in interactive information.

[0166] In some embodiments, the update module 230 is further configured to:

[0167] Compare the target information with the user profile to determine the target attribute tags that need to be updated;

[0168] Update the target attribute labels based on the target information.

[0169] In some embodiments, the acquisition module 210 is further configured to:

[0170] Acquire user interaction requests to smart devices;

[0171] If the interaction request meets the second preset condition, obtain the user profile corresponding to the user;

[0172] Use large language models and / or preset response templates to generate response information based on interaction requests and user profiles;

[0173] Interaction requests and response information are identified as interaction information.

[0174] The user profile updating device in the embodiments of this specification can be an electronic device or a component within an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices besides a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine, etc. The embodiments of this specification do not specifically limit the scope of the device.

[0175] The user profile updating device in the embodiments of this specification can be a device with an operating system. This operating system can be a Microsoft (Windows) operating system, an Android operating system, an iOS operating system, or other possible operating systems; this specification does not specifically limit the embodiments to any particular operating system.

[0176] In some embodiments, such as Figure 3 As shown, this specification also provides an electronic device 300, including a processor 301, a memory 302, and a computer program stored in the memory 302 and executable on the processor 301. When the program is executed by the processor 301, it implements the various processes of the above-described user profile update method embodiment and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0177] It should be noted that the electronic devices in the embodiments of this specification include the mobile electronic devices and non-mobile electronic devices described above.

[0178] This specification also provides a non-transitory computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described user profile update method embodiment and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0179] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0180] This specification also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method for updating user profiles.

[0181] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0182] This specification also provides a chip in its embodiments. The chip includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-described user profile update method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0183] It should be understood that the chip mentioned in the embodiments of this specification may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0184] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this specification is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0185] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solutions of this specification, in essence, or the parts that contribute to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this specification.

[0186] The embodiments of this specification have been described above with reference to the accompanying drawings. However, this specification is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other modifications under the guidance of this specification without departing from the spirit and scope of the claims, and all such modifications are within the scope of protection of this specification.

[0187] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this specification. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0188] Although embodiments of the present specification have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the present specification, the scope of which is defined by the claims and their equivalents.

Claims

1. A method for updating user profiles, characterized in that, include: Acquire user interaction information with smart devices; Extract target information associated with the user's user profile from the interaction information; The user profile includes multiple attribute tags that represent different dimensions of user information; The attribute tags of the user profile are updated based on the target information.

2. The method according to claim 1, characterized in that, The step of updating the attribute tags of the user profile based on the target information includes: If the first preset condition is met, the attribute tags of the user profile are updated according to the target information.

3. The method according to claim 2, characterized in that, The first preset condition includes at least one of the following conditions: The number of text fragments in the interactive information is greater than or equal to a preset value; The user triggers the update operation; The current time is the preset update time; The time elapsed since the last update is the preset time.

4. The method according to claim 1, characterized in that, The step of extracting target information associated with the user profile from the interaction information includes: Obtain the attribute tags of the user profile; The target information associated with the attribute label in the interaction information is analyzed using a large language model.

5. The method according to claim 1, characterized in that, The step of updating the attribute tags of the user profile based on the target information includes: The target information is compared with the user profile to determine the target attribute tags that need to be updated; Update the target attribute label based on the target information.

6. The method according to claim 1, characterized in that, The attribute tags include at least one of the following: user basic information, user health status, user dietary preferences, and user interests.

7. The method according to claim 1, characterized in that, The acquisition of user interaction information with smart devices includes: Obtain the interaction request input by the user to the smart device; If the interaction request meets the second preset condition, obtain the user profile corresponding to the user; Using a large language model and / or a preset reply template, generate reply information based on the interaction request and the user profile; The interaction request and the response information are identified as the interaction information.

8. The method according to claim 1, characterized in that, The smart device includes a refrigeration device.

9. A user profile updating device, characterized in that, include: The acquisition module is used to acquire interaction information between the user and the smart device. The extraction module is used to extract target information associated with the user profile of the user from the interaction information; The user profile includes multiple attribute tags that represent different dimensions of user information; The update module is used to update the attribute tags of the user profile based on the target information.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1-8.

Images