A user portrait generation method and device, electronic equipment and storage medium

Abstract

The application provides a user portrait generation method and device, electronic equipment and storage medium, and is used for improving the problem that the accuracy of the user portrait is not high. The method comprises the following steps: obtaining form data and scene information of the form data when the form data is submitted; and generating a user portrait according to the form data and the scene information. In the implementation process of the above scheme, the form data and the scene information of the form data when the form data is submitted are obtained, and a user portrait is generated according to the form data and the scene information. Since the noise of the form data used in the generation process of the user portrait is less, and the scene information of the form data when the form data is submitted is considered, the scene information of the user is effectively described, and the accuracy of the generated user portrait is improved.

Description

Technical Field

[0001] This application relates to the technical fields of big data and artificial intelligence, and more specifically, to a user profile generation method, apparatus, electronic device, and storage medium. Background Technology

[0002] Currently, user profiles are typically generated based on data extracted from various user behavior logs. For example, user characteristic data is extracted from browsing history, purchase records, and shopping cart records, and then a user profile is generated based on this characteristic data. However, in practice, it has been found that the accuracy of user profiles based on data extracted from various user behavior logs is not high. Summary of the Invention

[0003] The purpose of this application is to provide a user profile generation method, apparatus, electronic device, and storage medium to improve the problem of low accuracy in user profiles.

[0004] This application provides a user profile generation method, including: acquiring form data and contextual information of the form data at the time of submission; and generating a user profile based on the form data and contextual information. In the implementation of the above solution, by acquiring form data and contextual information of the form data at the time of submission, and generating a user profile based on the form data and contextual information, the form data used in the user profile generation process has less noise, and the contextual information of the form data at the time of submission is considered, thereby effectively characterizing the user's contextual information and improving the accuracy of user profile generation.

[0005] Optionally, in this embodiment, the contextual information includes: voice emotion information; obtaining form data and contextual information of the form data at the time of submission includes: obtaining voice data in response to input operation of the voice sensor; performing voice recognition on the voice data to obtain form data; and performing contextual recognition on the voice data and form data to obtain voice emotion information. In the implementation of the above solution, by performing voice recognition on the voice data and performing contextual recognition on the voice data and the voice-recognized form data, voice emotion information used to generate user profiles is obtained, thereby taking into account the voice emotion information of the form data at the time of submission and improving the accuracy of generating user profiles.

[0006] Optionally, in this embodiment, the context information further includes: facial emotion state and environmental scene information; obtaining form data and context information of the form data at the time of submission further includes: obtaining image data in response to input operation of the image sensor; performing human emotion recognition on the image data to obtain facial emotion state; and performing environmental recognition on the image data to obtain environmental scene information. In the implementation of the above solution, by performing human emotion recognition on the image data to obtain facial emotion state, and performing environmental recognition on the image data to obtain environmental scene information for generating user profiles, the environmental scene information at the time of submission of the form data is taken into account, thereby improving the accuracy of generating user profiles.

[0007] Optionally, in this embodiment, before obtaining the form data and the context information of the form data at the time of submission, the method further includes: obtaining the current field of the form data at the time of filling, and the context features of the current field; classifying the current field and the context features of the current field to obtain classification results; and generating prompt information corresponding to the current field based on the classification results. The prompt information corresponding to the current field is used to prompt and assist the user in filling in the current field. In the implementation of the above solution, by dynamically adjusting the prompt information to help the user fill in the content data of the current field of the form, the accuracy and timeliness of the prompts during form filling are improved, as well as the efficiency of the user in filling in the form.

[0008] Optionally, in this embodiment, the contextual features of the current field include: the content value of the previous field, the field attribute of the previous field, the content value of the current field, and the field attribute of the current field. Classifying the current field and its contextual features includes: inputting the content value of the previous field, the field attribute of the previous field, the content value of the current field, and the field attribute of the current field into a machine learning model, so that the machine learning model classifies the current field and its contextual features. In the implementation of the above scheme, by inputting the content value of the previous field, the field attribute of the previous field, the content value of the current field, and the field attribute of the current field into the machine learning model, the contextual environment of filling in the current field (including the content value of the previous field and the field attribute of the previous field, etc.) is considered. This effectively helps the user fill in the content data of the current field of the form based on the contextual environment, improving the accuracy and timeliness of prompts when filling in the form, as well as the efficiency of the user filling in the form.

[0009] Optionally, in this embodiment, the prompt information corresponding to the current field includes: prompt content and / or display style; after generating the prompt information corresponding to the current field based on the classification result, it further includes: sending the prompt content and / or display style to the target device, so that the target device can prompt the current field according to the prompt content, and / or, visualizing the prompt information corresponding to the current field according to the display style. In the implementation of the above solution, by sending the prompt content and / or display style to the target device, the user can effectively fill in the content data of the current field according to the prompt information, achieving the effect of sending more accurate prompt information to the target device.

[0010] Optionally, in this embodiment, the display style includes: background color, text size, paragraph line spacing, and display method. In implementing the above solution, by including the display style in terms of background color, text size, paragraph line spacing, display method, and question format, the display style of the prompt information becomes more in line with user habits, thereby improving the efficiency of users filling in form data and achieving the technical effect of providing personalized prompts for each user.

[0011] This application also provides a user profile generation device, including: a form context acquisition module for acquiring form data and context information of the form data at the time of submission; and a user profile generation module for generating a user profile based on the form data and context information.

[0012] Optionally, in this embodiment, the context information includes: voice emotion information; the form context acquisition module includes: a voice data acquisition submodule, used to acquire voice data in response to input operation of the voice sensor; a form data acquisition submodule, used to perform voice recognition on the voice data to acquire form data; and a data context recognition submodule, used to perform context recognition on the voice data and form data to acquire voice emotion information.

[0013] Optionally, in this embodiment, the context information further includes: facial emotion state and environmental scene information; the form context acquisition module further includes: an image data acquisition submodule, used to acquire image data in response to the input operation of the image sensor; a facial emotion acquisition submodule, used to perform human emotion recognition on the image data to acquire facial emotion state; and an environmental scene acquisition submodule, used to perform environmental recognition on the image data to acquire environmental scene information.

[0014] Optionally, in this embodiment of the application, the user profile generation device further includes: a context feature acquisition module, used to acquire the current field of the form data when it is filled in, and the context features of the current field; a classification result acquisition module, used to classify the current field and the context features of the current field to obtain a classification result; and a prompt information generation module, used to generate prompt information corresponding to the current field based on the classification result, wherein the prompt information corresponding to the current field is used to prompt and help fill in the current field.

[0015] Optionally, in this embodiment, the contextual features of the current field include: the content value of the previous field, the field attribute of the previous field, the content value of the current field, and the field attribute of the current field; the classification result acquisition module includes: a contextual feature classification submodule, used to input the content value of the previous field, the field attribute of the previous field, the content value of the current field, and the field attribute of the current field into the machine learning model, so that the machine learning model classifies the current field and the contextual features of the current field.

[0016] Optionally, in this embodiment of the application, the prompt information corresponding to the current field includes: prompt content and / or display style; the user profile generation device further includes: a current field prompt module, used to send prompt content and / or display style to the target device, so that the target device prompts the current field according to the prompt content, and / or visualizes the prompt information corresponding to the current field according to the display style.

[0017] Optionally, in the embodiments of this application, the display style includes: background color, text size, paragraph line spacing, and display method.

[0018] This application also provides an electronic device, including a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the machine-readable instructions, when executed by the processor, perform the method described above.

[0019] This application also provides a computer-readable storage medium storing a computer program that is executed by a processor to perform the methods described above. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1The illustrated flowchart shows a user profile generation method provided in an embodiment of this application.

[0022] Figure 2 The illustration shown is a schematic diagram of form data for filling out a login form provided in an embodiment of this application;

[0023] Figure 3 The diagram shown is a structural schematic of the user profile generation device provided in an embodiment of this application;

[0024] Figure 4 The diagram shows a structural schematic of an electronic device provided in an embodiment of this application. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in the embodiments of this application are for illustrative and descriptive purposes only and are not intended to limit the protection scope of the embodiments of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in the embodiments of this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of the embodiments of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0026] Furthermore, the described embodiments are merely a part of the embodiments of this application, and not all of them. The components of the embodiments of this application described and illustrated herein can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed embodiments of this application, but merely to illustrate selected embodiments of this application.

[0027] It is understood that the terms "first" and "second" in the embodiments of this application are used to distinguish similar objects. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that "first" and "second" do not necessarily imply that they are different. In the description of the embodiments of this application, the term "and / or" is merely a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship. The term "multiple" refers to two or more (including two), and similarly, "multiple groups" refers to two or more groups (including two groups).

[0028] Before introducing the user profile generation method provided in the embodiments of this application, let's first introduce some concepts involved in the embodiments of this application:

[0029] A user profile is a user image constructed through data tags. For example, each specific piece of information in a user's historical data (such as browsing history or shopping order records) is abstracted into a tag. These tags are used to concretize the user image, thereby providing targeted services to the user.

[0030] A form is an area that contains form elements, and a form can include multiple form elements. These form elements allow users to enter content into the form, such as text areas, select lists, radio buttons, checkboxes, etc.

[0031] It should be noted that the user profile generation method provided in this application embodiment can be executed by an electronic device. Here, an electronic device refers to a device terminal or server with the function of executing computer programs. Device terminals include, for example, smartphones, personal computers, tablets, personal digital assistants, or mobile internet devices. A server refers to a device that provides computing services through a network. Servers include, for example, x86 servers and non-x86 servers. Non-x86 servers include, for example, mainframes, minicomputers, and UNIX servers.

[0032] The following describes the application scenarios for this user profile generation method. These scenarios include, but are not limited to: using this user profile generation method to help enterprises better generate user profiles. For example, when users fill out registration forms, login forms, or survey forms, contextual information such as the user's voice and emotional state, or environmental scenery can be added. This allows enterprises to better generate user profiles based on the form data and contextual information. Furthermore, the design of form templates can be optimized based on contextual information and user profiles.

[0033] Please see Figure 1 The illustrated flowchart shows a user profile generation method provided in this application embodiment. The main idea of ​​this user profile generation method is that, because the form data used in the user profile generation process has less noise and takes into account the contextual information of the form data at the time of submission, it effectively portrays the user's contextual information. Implementation methods of the above-described user profile generation method may include:

[0034] Step S110: Obtain the form data and the context information of the form data at the time of submission.

[0035] Please see Figure 2 The illustration shown is a schematic diagram of form data for filling out a login form according to an embodiment of this application; form data is the content data filled in from all the form elements in a form, for example... Figure 2 The login form includes form elements such as a text field for username, a text field for password, and a text field for verification code. After the user fills in these form elements (i.e., each form element has corresponding content data) through their terminal device and clicks submit, the terminal device will submit the content data corresponding to all form elements in the login form to the server. At this time, the server receives the content data corresponding to all form elements in the login form, which is the form data.

[0036] Scenario information refers to information related to a user's emotions or environment. Examples of scenario information include a user's voice emotion, facial emotion state, or environmental scene information.

[0037] It is understandable that when a user fills out form data in System A application via their mobile phone, if System A application can access the phone's camera and / or microphone, it can also obtain contextual information when the form data is filled out and submitted, such as the user's voice emotion information, facial emotion state, or environmental scene information.

[0038] Step S120: Generate a user profile based on the form data and contextual information.

[0039] Understandingly, user profiles generated from form data and contextual information can be considered as user personas. For example, considering data from numerous completed surveys, if a user completed a survey about travel and food with great enthusiasm, then the contextual information could include "happiness." Similarly, if a user completed a survey about work or occupation calmly, then the contextual information could include "calmness." Happiness and calmness are the specific values ​​within this contextual information. Ultimately, user profiles generated from form data and contextual information can include both form data and contextual information. These profiles could include data such as name, age, gender, occupation, and interests. These user profiles can also be visualized to facilitate better analysis by data analysts or product analysts.

[0040] In the implementation of the above scheme, by acquiring form data and contextual information of the form data at the time of submission, and generating user profiles based on the form data and contextual information, the user profiles are effectively characterized by less noise in the form data used in the user profile generation process and the contextual information of the form data at the time of submission is taken into account, thus improving the accuracy of generating user profiles.

[0041] As an optional implementation of step S110 above, the aforementioned contextual information may include: voice emotion information; the implementation of obtaining form data and contextual information of the form data at the time of submission may include:

[0042] Step S111: In response to the input operation of the voice sensor, acquire voice data.

[0043] It is understood that the aforementioned electronic device can be a smartphone, and that smartphone can obtain the voice data input by the voice sensor (e.g., a microphone) in response to a voice input operation. It is also understood that the aforementioned voice sensor can be a microphone.

[0044] Step S112: Perform speech recognition on the speech data to obtain form data.

[0045] Step S113: Perform context recognition on the voice data and form data to obtain voice emotion information.

[0046] For example, when a user fills out form data in System A application via voice interaction on their mobile phone, System A application, responding to the input operation of the voice sensor, can acquire the user's voice data through the phone's microphone. Then, the mobile application or its corresponding server can perform voice recognition on the voice data to obtain the form data. Simultaneously, it can analyze the user's voice features, such as pitch, speed, and rhythm, and extract data features from the form data. Finally, the mobile application or its corresponding server can perform context recognition on the voice data and form data, for example, matching the voice features extracted from the voice data with the data features extracted from the form data using preset context rules to obtain emotional information about the voice.

[0047] As an optional implementation of step S110 above, the aforementioned context information may further include: facial emotion state and environmental scene information; the implementation of obtaining form data and context information of the form data at the time of submission may further include:

[0048] Step S114: In response to the input operation of the image sensor, acquire image data.

[0049] An image sensor, also known as an image acquisition device, refers to a device that acquires images of a target. Specific examples of image sensors include: DSLR color cameras, black and white cameras, surveillance cameras, cameras, or terminals with cameras, such as mobile phones, smart bracelets, tablets, or laptops.

[0050] Step S115: Perform human emotion recognition on the image data to obtain the human facial emotion state.

[0051] For example, the implementation of steps S114 and S115 above is as follows: Assuming a user fills out form data in system A application via their mobile phone, if system A application can access the phone's camera and / or microphone, then the user's facial image and / or voice data can also be obtained through the phone's camera and / or microphone. Then, the user's emotional state (e.g., happy, sad, excited, or angry) in the facial image can be analyzed, as well as the user's voice features such as pitch, speed, and rhythm in the voice data. Preset rules are used to match these voice features to obtain the user's voice state. Finally, the user's facial emotional state is determined based on their emotional state and voice state.

[0052] Step S116: Perform environmental recognition on the image data to obtain environmental scene information.

[0053] For example, when a user fills in form data in a system application using a mobile phone, if the system application can access the phone's light sensor, camera, and / or microphone, it can also obtain the user's environmental image data and / or environmental voice data through the phone's light sensor, camera, and / or microphone, and perform environmental recognition on the environmental image data and / or environmental voice data to obtain environmental scene information. The environmental scene information here includes, but is not limited to, light, humidity, weather, temperature, and / or noise.

[0054] Specifically, when a user is filling out a lengthy survey form on their phone in a coffee shop at night, the phone's operating system can first detect that the ambient light is dim through the phone's light sensor. Then, through voice recognition, it can determine that the user is slightly tired. Therefore, the phone's operating system can automatically adjust the background color of the form to a warm tone and increase the font and line spacing to reduce the user's visual fatigue.

[0055] Optionally, after obtaining the form data and the context information at the time of submission, prompts can be provided based on the form data and context information. For example, when a user submits their shipping address for online shopping and is required to fill in a postal code field, the electronic device can search for city terms in the shipping address and return prompt information based on the search results. Specifically, if the shipping address includes "Beijing," the device can prompt "Postal codes in Beijing usually start with 10" when the user fills in the postal code field, thereby effectively improving the efficiency of form completion and the accuracy of the form data.

[0056] As an optional implementation of the above-mentioned user profile generation method, before obtaining the form data and the context information of the form data at the time of submission in step S110, a prompt can also be given when the user fills in the current field. This implementation may include:

[0057] Step S101: Obtain the current field of the form data when it is filled in, and the contextual characteristics of the current field.

[0058] It is understandable that the form templates corresponding to the above form data can be developed using Hyper Text Markup Language (HTML), Cascading Style Sheets (CSS), and JavaScript.

[0059] For example, in the implementation of step S101 above, the electronic device can obtain the current field of the form data at the time of filling in, as well as the contextual characteristics of the current field, through an executable program compiled or interpreted using a preset programming language. The programming languages ​​that can be used include, for example, C, C++, Java, BASIC, JavaScript, LISP, Shell, Perl, Ruby, Python, and PHP, etc.

[0060] Step S102: Classify the current field and its contextual features to obtain classification results.

[0061] One implementation of step S102 above is, for example, using a decision tree, random forest, or convolutional neural network (CNN) to classify the current field and the contextual features of the current field to obtain a classification result; wherein, the convolutional neural network that can be used is, for example, LeNet network model, AlexNet network model, VGG network model, GoogLeNet network model, and ResNet network model, etc.

[0062] Another implementation of step S102 above is as follows: The electronic device inputs the current field and the context features of the current field into a pre-training language model (PLM). The PLM model that can be used is, for example, a Bidirectional Encoder Representations from Transformers (BERT) model, a Bidirectional and Auto-Regressive Transformers (BART) model, a RoBERTa model, a UNILM model, an XLNET model, a GloVe model, an ELMo model, or a SentenceBERT model, etc.

[0063] Step S103: Generate prompt information corresponding to the current field based on the classification result. The prompt information corresponding to the current field is used to prompt and help fill in the current field.

[0064] One implementation of step S103 above is as follows: The electronic device inputs the current field and classification result into a generative pre-training (GPT) model such as GPT model, GPT-2 model, GPT-3 model, or ChatGPT, and receives the prompt information corresponding to the current field generated by the GPT model. It then uses the prompt information corresponding to the current field to prompt and assist the user in filling in the current field. By dynamically adjusting the prompt information, the electronic device helps the user fill in the content data of the current field of the form, thereby improving the accuracy and timeliness of prompts when filling in the form, as well as the efficiency of the user in filling in the form.

[0065] Another implementation of step S103 above is as follows: Rules for "generating prompt information corresponding to the current field based on the classification result" can be set based on a large amount of historical data and expert experience. These rules define the specific prompt information that should be generated under a given classification result. For example, when a user enters a city name when filling in an address, the system should provide the city's postal code. For instance, if a user enters "Beijing" in the city field of their delivery address, the system might provide "Postal codes in Beijing usually start with 10." This generates prompt information that is both accurate and context-appropriate, thereby improving the accuracy of the generated prompt information.

[0066] As an optional implementation of step S102 above, the contextual features of the current field may include: the content value of the previous field, the field attribute of the previous field, the content value of the current field, and the field attribute of the current field; the implementation of classifying the current field and the contextual features of the current field may include:

[0067] Step S102a: Input the content value of the previous field, the field attribute of the previous field, the content value of the current field, and the field attribute of the current field into the machine learning model so that the machine learning model can classify the current field and the contextual features of the current field and obtain the classification result.

[0068] One implementation of step S102a above is as follows: The content value of the previous field, the field attribute of the previous field, the content value of the current field, and the field attribute of the current field are input into a machine learning model such as a decision tree, random forest, or Text-Convolutional Neural Network (Text-CNN), so that the machine learning model classifies the current field and its contextual features to obtain a classification result. For example, if a user enters "Beijing" when filling in an address, the classification result is the city "Beijing," and the model can generate a prompt based on the city "Beijing" such as "The postal codes in Beijing usually start with 10."

[0069] As an optional implementation of the above-mentioned user profile generation method, the prompt information corresponding to the current field may include: prompt content and / or display style; after generating the prompt information corresponding to the current field based on the classification results, the prompt content and / or display style can also be used to prompt the user to fill in the current field. This implementation may include:

[0070] Step S104: The electronic device sends a prompt content and / or display style to the target device, so that the target device can prompt the current field according to the prompt content, and / or visualize the prompt information corresponding to the current field according to the display style.

[0071] For example, in the implementation of step S104 above: if the user corresponding to the target device is filling in the content data of the current field, the target device can send the content data of the current field to the electronic device. After receiving the content data of the current field sent by the target device, the electronic device can also generate prompt content and / or display style according to the content data, and then send the prompt content and / or display style to the target device, so that the target device can provide prompts for the current field according to the prompt content, and / or use libraries such as D3.js or Plotly to load the display style, and use the display style to visualize the prompt information corresponding to the current field, thereby completing the function of the user filling in the content data of the current field, enabling the user to effectively fill in the content data of the current field according to the prompt information, and achieving the effect of sending more accurate prompt information to the target device.

[0072] As an optional implementation of the above-mentioned user profile generation method, the display style may include: background color, text size, paragraph line spacing, display method, and question format, etc., so that the display style of the prompt information is more in line with the user's habits, thereby improving the efficiency of users filling in form data and achieving the technical effect of providing personalized prompts for each user.

[0073] Please see Figure 3 The diagram shown is a structural schematic of the user profile generation device provided in an embodiment of this application; this application provides a user profile generation device 200, including:

[0074] The form context acquisition module 210 is used to acquire form data and context information of the form data at the time of submission.

[0075] User profile generation module 220 is used to generate user profiles based on form data and contextual information.

[0076] Optionally, in this embodiment, the context information includes: voice emotion information; the form context acquisition module includes:

[0077] The voice data acquisition submodule is used to acquire voice data in response to input operations from the voice sensor.

[0078] The form data acquisition submodule is used to perform speech recognition on voice data and obtain form data.

[0079] The data context recognition submodule is used to perform context recognition on voice data and form data to obtain voice emotion information.

[0080] Optionally, in this embodiment, the context information further includes: facial emotion state and environmental scene information; the form context acquisition module further includes:

[0081] The image data acquisition submodule is used to acquire image data in response to input operations from the image sensor.

[0082] The facial emotion acquisition submodule is used to perform human emotion recognition on image data and obtain the facial emotion state.

[0083] The environmental scene acquisition submodule is used to perform environmental recognition on image data and obtain environmental scene information.

[0084] Optionally, in this embodiment of the application, the user profile generation device further includes:

[0085] The context feature acquisition module is used to obtain the current field of the form data when it is filled in, as well as the context features of the current field.

[0086] The classification result acquisition module is used to classify the current field and its contextual features to obtain the classification result.

[0087] The prompt information generation module is used to generate prompt information corresponding to the current field based on the classification results. The prompt information corresponding to the current field is used to prompt and help fill in the current field.

[0088] Optionally, in this embodiment, the contextual features of the current field include: the content value of the previous field, the field attribute of the previous field, the content value of the current field, and the field attribute of the current field; the classification result acquisition module includes:

[0089] The context feature classification submodule is used to input the content value of the previous field, the field attribute of the previous field, the content value of the current field, and the field attribute of the current field into the machine learning model so that the machine learning model can classify the current field and the context features of the current field.

[0090] Optionally, in this embodiment, the prompt information corresponding to the current field includes: prompt content and / or display style; the user profile generation device further includes:

[0091] The current field prompt module is used to send prompt content and / or display style to the target device, so that the target device can prompt the current field according to the prompt content, and / or visualize the prompt information corresponding to the current field according to the display style.

[0092] Optionally, in the embodiments of this application, the display style includes: background color, text size, paragraph line spacing, and display method.

[0093] It should be understood that this device corresponds to the user profile generation method embodiment described above and is capable of performing the various steps involved in the above method embodiment. The specific functions of this device can be found in the description above, and detailed descriptions are appropriately omitted here. The device includes at least one software functional module that can be stored in memory or embedded in the device's operating system (OS) in the form of software or firmware.

[0094] Please see Figure 4 The diagram shows a structural schematic of an electronic device provided in an embodiment of this application. An electronic device 300 provided in this application includes a processor 310 and a memory 320. The memory 320 stores machine-readable instructions executable by the processor 310. When the machine-readable instructions are executed by the processor 310, the method described above is performed.

[0095] This application embodiment also provides a computer-readable storage medium 330, on which a computer program is stored. This computer program is executed by a processor 310 to perform the methods described above. The computer-readable storage medium 330 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0096] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For apparatus embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0097] It should be understood that the disclosed apparatus and methods can also be implemented in other ways, as provided in the embodiments of this application. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, or they may sometimes be executed in reverse order, depending primarily on the functions involved.

[0098] Furthermore, the functional modules of each embodiment in this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part. In addition, in the description of this specification, the reference to terms such as "one embodiment," "some embodiments," "example," "specific example," "some examples," etc., means that the 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 application. Moreover, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification and the features of the different embodiments or examples.

[0099] The above description is only an optional implementation of the embodiments of this application, but the protection scope of the embodiments of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the embodiments of this application should be covered within the protection scope of the embodiments of this application.

Claims

1. A user profiling method, characterized by, The method comprises: obtaining form data and context information of the form data at the time of submission; generating a user portrait according to the form data and the context information; wherein, before the obtaining of the form data and the context information of the form data at the time of submission, the method further comprises: obtaining a current field of the form data at the time of filling and a context feature of the current field; classifying the current field and the context feature of the current field to obtain a classification result; and generating prompt information corresponding to the current field according to the classification result, the prompt information corresponding to the current field being used to prompt and assist in filling the current field.

2. The method of claim 1, wherein, The context information comprises: sound emotion information; and the obtaining of the form data and the context information of the form data at the time of submission comprises: obtaining voice data in response to an input operation of a voice sensor; performing voice recognition on the voice data to obtain the form data; performing context recognition on the voice data and the form data to obtain the sound emotion information.

3. The method of claim 2, wherein, The context information further comprises: a facial emotion state and environmental scene information; and the obtaining of the form data and the context information of the form data at the time of submission further comprises: obtaining image data in response to an input operation of an image sensor; performing character emotion recognition on the image data to obtain the facial emotion state; performing environment recognition on the image data to obtain the environmental scene information.

4. The method of claim 1, wherein, The context feature of the current field comprises: a content value of a previous field, a field attribute of the previous field, a content value of the current field, and a field attribute of the current field; and the classifying of the current field and the context feature of the current field comprises: inputting the content value of the previous field, the field attribute of the previous field, the content value of the current field, and the field attribute of the current field into a machine learning model, so that the machine learning model classifies the current field and the context feature of the current field.

5. The method of claim 1, wherein, The prompt information corresponding to the current field comprises: prompt content and / or display style; and after the generating of the prompt information corresponding to the current field according to the classification result, the method further comprises: sending the prompt content and / or the display style to a target device, so that the target device prompts the current field according to the prompt content, and / or visualizes the prompt information corresponding to the current field according to the display style.

6. The method of claim 5, wherein, The display style comprises: background color, text size, paragraph line spacing, and display mode.

7. A user profiling apparatus characterized by comprising: The method comprises: a form context obtaining module, configured to obtain form data and context information of the form data at the time of submission; a user portrait generating module, configured to generate a user portrait according to the form data and the context information; and In the scenario, before the form data is acquired and the scenario information of the form data at the time of submission, the method further includes: acquiring a current field of the form data at the time of filling, and a scenario feature of the current field; classifying the current field and the scenario feature of the current field to obtain a classification result; and generating prompt information corresponding to the current field according to the classification result, the prompt information corresponding to the current field being used to prompt and assist in filling the current field.

8. An electronic device, comprising: The method comprises: A processor and a memory, the memory storing machine readable instructions executable by the processor, the machine readable instructions being executed by the processor to perform the method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to perform the method of any one of claims 1 to 6.

Images