Interactive content processing method and electronic equipment

Abstract

The invention provides an interactive content processing method, and relates to the technical field of man-machine interaction, electronic equipment generates image data matched with to-be-stored content according to the to-be-stored content contained in the interactive content in response to a storage instruction of the interactive content aiming at target interaction, so that the image data and the to-be-stored content are at least utilized, and the target interaction content is obtained. And creating and storing interaction entries aiming at the interaction content.

Description

Technical Field

[0001] This application relates to the field of human-computer interaction technology, and in particular, to an interaction content processing method and an electronic device. Background Art

[0002] Nowadays, in application scenarios such as online shopping, online learning / customer service, social media, remote work / medical treatment, or appointment services, users can use electronic devices such as mobile phones, laptops, or smart wearable devices to interact in one or more mixed interaction methods such as text, voice, and video, improving the convenience and diversity of interaction.

[0003] However, in the above-mentioned interaction process, usually users need to manually record some interaction contents received locally. The process is cumbersome, and it is very easy to cause inaccurate stored interaction entries due to users misremembering or misreading the interaction contents, resulting in a poor user experience. Summary of the Invention

[0004] In view of this, the present application provides the following technical solutions:

[0005] In a first aspect of the present application, an interaction content processing method is provided, and the method includes:

[0006] In response to a storage instruction for the interaction content of a target interaction, generate image data matching the content to be stored according to the content to be stored included in the interaction content;

[0007] Create an interaction entry for the interaction content for storage at least using the image data and the content to be stored.

[0008] In a possible implementation, the generating image data matching the content to be stored according to the content to be stored included in the interaction content includes any one of the following:

[0009] Input the interaction content into a first generation model, so that the first generation model extracts the content to be stored in the interaction content according to the interaction entry prompt word for the target interaction, and generates image data matching the content to be stored;

[0010] Extract the content to be stored in the interaction content, and input the target content to be stored into a second generation model to generate image data matching the target content to be stored; the target content to be stored refers to the content to be stored that supports the presentation of text data format and image data format;

[0011] Obtain image description information for the content to be stored included in the interaction content, and input the image description information into a third generation model to generate image data conforming to the image description information.

[0012] In a possible implementation, creating an interaction entry for the interaction content by at least using the image data and the content to be stored includes:

[0013] Outputting an interaction entry creation interface for the interaction content, and displaying the content to be stored and the image data in the interaction entry creation interface;

[0014] Responding to a confirmation operation on the content to be stored and the image data, and creating an interaction entry including the content to be stored and the image data.

[0015] In a possible implementation, creating an interaction entry for the interaction content by at least using the image data and the content to be stored further includes at least one of the following:

[0016] If multiple pieces of the image data are displayed in the interaction entry creation interface, responding to a selection operation on the image data to determine the selected image data, so as to create an interaction entry including the content to be stored and the selected image data during the process of responding to the confirmation operation;

[0017] Responding to an adjustment operation on the content to be stored displayed in the interaction entry creation interface to determine the adjusted content to be stored, so as to create an interaction entry including the adjusted content to be stored and the image data during the process of responding to the confirmation operation;

[0018] Configuring the image data and the interaction object identifier included in the interaction entry in an interaction entry query interface, so that the image data and the interaction object identifier are associated and displayed in the interaction entry query interface, and / or the image data is displayed in an interaction interface for the interaction object identifier; the interaction object identifier belongs to the content to be stored.

[0019] In a possible implementation, the method further includes:

[0020] Matching the interaction content with storage filtering data;

[0021] If the interaction content matches at least part of the data in the storage filtering data, not responding to a storage instruction for the interaction content of a target interaction;

[0022] If the interaction content does not match the storage filtering data, responding to a storage instruction for the interaction content of a target interaction.

[0023] In a possible implementation, the method further includes:

[0024] In response to a storage filtering request for the target interaction, output a filtering configuration interface, and display at least one candidate filtering item on the filtering configuration interface;

[0025] In response to a configuration operation on at least one of the candidate filtering items, obtain storage filtering data for the target interaction;

[0026] Wherein, the storage filtering data is used to configure storage conditions, and the storage conditions are used to indicate the content to be stored,

[0027] Alternatively, the storage filtering data is used to configure storage filtering prompt words to guide the first generation model to identify the content to be stored that meets the storage conditions from the input interaction content.

[0028] In a possible implementation, the method further includes:

[0029] Perform a matching detection on the content to be stored and the stored historical interaction entries;

[0030] If the detected target historical interaction entry contains at least part of the content to be stored but does not contain image data matching the content to be stored, determine the target content in the content to be stored not included in the target historical interaction entry;

[0031] Add the target content and the image data to the target historical interaction entry.

[0032] In a possible implementation, the method further includes any one of the following:

[0033] Output a storage configuration interface for the interaction content of the target interaction, display at least one entry type for the interaction content on the storage configuration interface, and in response to a selection operation on the entry type, generate a storage instruction matching the selected target entry type;

[0034] Determine the interaction content for the target interaction, perform an entry type detection on the interaction content, and generate a storage instruction matching the detected target entry type.

[0035] In a possible implementation, generating image data matching the content to be stored according to the content to be stored included in the interaction content, and creating an interaction entry for the interaction content for storage at least using the image data and the content to be stored includes at least one of the following:

[0036] If the target entry type includes contacts, generate contact image data that matches the contact name according to the contact name included in the interaction content, and create a new contact using at least the contact name, the contact image data, and at least one interaction contact method included in the interaction content.

[0037] If the target entry type includes schedules, generate map data that matches the schedule location according to the schedule location included in the interaction content, and create a new schedule using at least the schedule location, the map data, and the to-do event description included in the interaction content.

[0038] A second aspect of the present application provides an electronic device, which includes: at least one communication component, at least one memory, and at least one processor, where:

[0039] The communication component is used to implement data interaction between the electronic device and other electronic devices;

[0040] The memory is used to store multiple computer instructions;

[0041] The processor is used to load and execute the computer instructions to implement the following steps:

[0042] In response to a storage instruction for the interaction content of a target interaction, generate image data that matches the content to be stored according to the content to be stored included in the interaction content;

[0043] Create and store an interaction entry for the interaction content using at least the image data and the content to be stored. Description of the Drawings

[0044] In combination with the drawings and with reference to the following specific embodiments, the above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic, and the original components and elements are not necessarily drawn to scale.

[0045] Figure 1 It is a schematic flowchart of an interaction content processing method proposed in Embodiment 1 of the present application;

[0046] Figure 2 It is a schematic flowchart of an interaction content processing method proposed in Embodiment 2 of the present application;

[0047] Figure 3a It is a schematic diagram of a storage configuration interface for an interaction content in the interaction content processing method provided by the embodiments of the present application;

[0048] Figure 3bIn the interaction content processing method provided by the embodiments of the present application, it is a schematic diagram of an interaction item creation interface;

[0049] Figure 4 It is a schematic flowchart of an interaction content processing method proposed in Embodiment 3 of the present application;

[0050] Figure 5 It is a schematic flowchart of an interaction content processing method proposed in Embodiment 4 of the present application;

[0051] Figure 6 In the interaction content processing method provided by the embodiments of the present application, it is a schematic flowchart of the summary selection and storage for call content in the call scenario;

[0052] Figure 7 In the interaction content processing method provided by the embodiments of the present application, it is a schematic diagram of contact creation and query for creating a new contact in the call scenario;

[0053] Figure 8 It is a schematic diagram of storing the incoming call number in the SMS scenario;

[0054] Figure 9 It is a schematic flowchart of an interaction content processing method proposed in Embodiment 5 of the present application;

[0055] Figure 10 In the interaction content processing method provided by the embodiments of the present application, it is a custom schematic diagram of harassing calls in the call scenario;

[0056] Figure 11 It is a schematic structural diagram of an interaction content processing device provided by the embodiments of the present application;

[0057] Figure 12 It is a schematic hardware structure diagram of an electronic device proposed by the embodiments of the present application. Detailed implementation manners

[0058] The embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application. The terms used in the embodiments of the present application are only for explaining the specific embodiments of the present application, and are not intended to limit the present application. The embodiments of the present application will be described below with reference to the accompanying drawings. Those skilled in the art know that with the development of technology and the emergence of new scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0059] In the context of the present application and in the above-mentioned drawings, terms such as "first", "second", etc. are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances, and this is only a way of distinguishing objects with the same attributes when describing the embodiments of the present application. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion, so that a process, method, system, product or device including a series of units does not have to be limited to those units, but may include other units that are not clearly listed or are inherent to these processes, methods, products or devices.

[0060] In addition, it should be understood that before using the technical solutions disclosed in the embodiments of the present application, the types of personal information involved in the present application (such as personal communication addresses, telephone numbers, faces or other identity information, etc.), the scope of use, the usage scenarios, etc. should be informed to users and the authorization of users should be obtained in an appropriate manner in accordance with relevant laws and regulations, and the implementation of the present application is legal use.

[0061] To solve the above technical problems, the present application newly proposes an interactive content processing method. When it is necessary to store the interactive content of a certain interaction (such as any one of voice communication, video communication, or text communication, etc.), image data that matches the content to be stored will be generated, such as the account avatar or personal avatar of the interactive object, or the enterprise image logo, etc., and it can also be map data / navigation route images representing addresses, etc. Thus, at least using these content to be stored and the image data, corresponding interactive entries are created for storage. It can be seen that this automatic storage method of interactive entries does not require users to manually fill in the interactive entry information, avoids handwritten errors in interactive entries, improves the accuracy and reliability of interactive entries for interactive content, and the interactive entries also include the matching image data generated based on the content to be stored, enriching the content of the interactive entries, realizing personalized storage of different interactive content, and the image data is more intuitive than text data, can quickly attract the attention of users, and enhance the user experience. The interactive content processing method of the embodiments of the present application will be introduced in detail below with reference to the drawings.

[0062] Refer to Figure 1, which is a schematic flowchart of an interactive content processing method proposed in the first embodiment of the present application. This method can be applied to an electronic device, which can include terminal devices such as mobile phones, tablets, wearable devices, in-vehicle devices, augmented reality (AR) / virtual reality (VR) devices, laptops, ultra-mobile personal computers (UMPCs), netbooks, intelligent transportation / medical devices, smart home devices, or robots. It supports communication with other devices in ways such as voice, text, or video to meet the communication interaction needs, and the present application does not limit the communication interaction scenario. Based on this, as Figure 1 shown, the interactive content processing method proposed in this embodiment can include:

[0063] Step S11, in response to a storage instruction for the interactive content of the target interaction, generate image data that matches the content to be stored according to the content to be stored included in the interactive content;

[0064] In the embodiments of the present application, the target interaction can be that the user uses the voice, text, video, etc. supported by the electronic device to realize the interactive communication between this electronic device and other devices. It can be through instant messaging software installed on the electronic device (that is, an application that enables users to communicate information in real time through the network, such as a certain WeChat, a certain QQ, or a certain DingTalk, etc.) or other social software, such as a certain Facebook, a certain Douyin, or Tieba, etc. It can also be realized through a dedicated communication software within a private domain, or through a web version software logged in through a browser to realize the interaction between multiple electronic device users. The present application does not limit the communication method of the target interaction and can be determined according to the situation.

[0065] During the implementation of the target interaction, the present application can use an artificial intelligence AI assistant to automatically extract the interactive content without the user having to manually record it, avoiding various problems existing in manual recording, such as recording errors or incompleteness, etc. The present application does not elaborate on the implementation process of how the AI assistant extracts the interactive content. In a possible implementation method, the AI assistant can be implemented locally on the electronic device. For example, in a voice communication scenario, the local voice recognition module can be used to convert the voice signal into text data, and then through natural language processing technology, analyze it to identify the key information and key content in the text data, and generate smooth interactive content through a machine learning model. Exemplarily, the AI call summary function of the electronic device can be started to record the interactive content during the call.

[0066] Optionally, the present application can achieve precise extraction of interaction content through the collaboration between a local electronic device and the cloud. By leveraging the powerful processing capabilities of the cloud's AI model, complex speech and text analysis tasks can be processed to obtain the interaction content during the target interaction process. The implementation process is similar to that of the present application and will not be elaborated here. In addition, the cloud can also achieve cross-device collaboration functions, such as synchronizing the interaction content of the user on different electronic devices to the cloud, facilitating the user to generate corresponding interaction entries on different electronic devices, or view the interaction entries generated by the cloud, etc.

[0067] According to the above analysis, when the present application needs to store the interaction content for the target interaction, compared with directly recording the interaction content extracted / generated by the above method, the present application can automatically create matching interaction entries for storage according to the actual needs and the interaction content. For example, a new contact can be created in the phone / email address book, a new schedule / task / event can be created, etc., to improve the diversity of interaction content storage. Moreover, in order to achieve personalized storage of the interaction memory, enhance its memorability, intuitiveness, and user experience, the present application will generate image data that matches the content to be stored in the interaction content as a part of the interaction entry to be created this time, so that the interaction entry is no longer limited to text / character data.

[0068] Among them, since the interaction content usually includes all or summary content of each interaction object participating in the target interaction during the entire interaction process, which may include content that does not need to be stored, such as words used to ensure the coherence of sentences, etc. To avoid occupying storage resources with these contents, the content to be stored can be extracted from the interaction content, which can be keywords that can express the interaction content, such as the names of interaction objects, accounts, phone numbers, email addresses, the location and time of the event occurrence, etc., which can be determined according to the target interaction type and the type of entry to be stored, etc. The present application does not limit the content to be stored included in the interaction content and its extraction method.

[0069] In addition, it should be noted that the above interaction content can be one or more of text data format, audio data format, or video data format, etc., which can match the communication method of the target interaction, or the interaction content with a matching data format recorded according to the communication method can be converted into text data format. Subsequently, the interaction content in text data format can be directly processed, etc., which can be determined according to the actual processing requirements. The present application does not make any restrictions.

[0070] After the present application determines the content to be stored for the target interaction, for the content to be stored that can be expressed in image data format, image data that matches it can be generated according to the content to be stored, such as an avatar that matches the name of the interaction object, map data / navigation route that matches the event occurrence address, etc. This process can be realized according to a generation model with image generation capabilities, and the implementation process will not be elaborated in the present application.

[0071] Step S12: Create an interaction entry for the interaction content for storage using at least the image data and the content to be stored.

[0072] Following the above analysis, after determining the content to be stored included in the interaction content for the target interaction and generating image data matching the content to be stored accordingly, an interaction entry containing the content to be stored and the image data can be created according to the storage method / format represented by the entry type of the interaction entry to be stored, and stored in the local electronic device, or uploaded to the cloud account to achieve cross-device management of interaction entries, etc. The entry type of the interaction entry in this application is not limited, including but not limited to the contacts, schedules, or events listed above.

[0073] In a possible implementation, to enrich the content of the interaction entry, in addition to the content to be stored and the image data for the target interaction, other content or access links to the other content are configured according to the user's personal preferences or actual scenario requirements, etc., so that when the user clicks on the access link, the corresponding other content can be viewed, that is, in response to the trigger operation on the access link, the corresponding other content is output. Among them, the other content can be one or a combination of text data, image data, audio data, or video data. This application does not limit the content and its storage format included in the interaction entry created for the interaction content of the target interaction, and it can be determined according to the situation.

[0074] In summary, in the embodiment of this application, when it is necessary to store the interaction content for the target interaction, image data matching it will be automatically generated based on the content to be stored included in the interaction content, and used as part of the content of the interaction entry to be created, making the content of the interaction entry intuitive and personalized, and more memorable. Then, at least using the content to be stored and the image data, an interaction entry for the interaction content is automatically created for storage, without the user manually recording the interaction content, avoiding problems such as incorrect or incomplete stored content caused by manual recording, and ensuring the accuracy and reliability of the stored interaction entry.

[0075] Refer to Figure 2 , which is a schematic flowchart of an interaction content processing method proposed in the second embodiment of this application. This embodiment can refine and describe an optional implementation method of the above interaction content processing method. For example, Figure 2 As shown, this implementation method may include:

[0076] Step S21: Output a storage configuration interface for the interaction content of the target interaction, and display at least one entry type for the interaction content on the storage configuration interface;

[0077] Step S22, in response to the selection operation of the entry type, generate a storage instruction that matches the selected target entry type;

[0078] In the actual application of this application, for the storage instruction for the interaction content in the above step S11, it can be generated based on the user interaction operation. In a possible implementation, after obtaining the interaction content for the target interaction according to the method described in the above embodiment, a storage configuration interface for the interaction content can be automatically output to guide the user interaction operation to store the actual required interaction entries. In this embodiment, at least one entry type for the interaction content can be displayed on the storage configuration interface, such as creating a new contact / schedule / event, etc. The user can select the entry type for the interaction content from them according to the actual needs, which is recorded as the target entry type, so as to generate a matching storage instruction. As Figure 3a shown, one type of interaction entry, creating a new contact, can be selected to generate a storage instruction for storing the new contact, etc.

[0079] Among them, for each entry type, it can be tiled and displayed on the storage configuration interface (as Figure 3a shown), or configured in the entry storage selection box (such as a drop-down menu) on the storage configuration interface. The user triggers the entry storage selection box, and an entry type window pops up on the storage configuration interface. Through the entry type window, various entry types supported by the electronic device are presented for the user to select the entry type of the interaction entry to be stored this time. It should be noted that this application does not limit the display method and selection method of each entry type, which can be determined according to the layout structure of the storage configuration interface. Figure 3a This is only an optional example of the storage configuration interface, and does not constitute a limitation on the interface content and the entry type selection method.

[0080] In some embodiments, for the storage configuration interface output by the electronic device, in addition to displaying the above at least one entry type, as Figure 3a shown, the interaction content for the target interaction can also be displayed. The interaction content here can be the interaction summary / abstract content generated based on the AI assistant. If the target interaction is implemented based on a voice or video communication method, the AI assistant can record the corresponding audio / video data, and a playback window of the audio / video data can be displayed in the storage configuration interface for the user to select for playback, etc. This application does not limit the content displayed in the storage configuration interface, which can be determined according to the situation.

[0081] Step S23, in response to the storage instruction, input the interaction content into the first generation model, so that the first generation model extracts the content to be stored in the interaction content according to the interaction entry prompt word for the target interaction, and generates image data that matches the content to be stored;

[0082] Following the above analysis, after determining which type of interaction entry the interaction content for the target interaction needs to be stored as, since the stored content, storage location, storage process, and storage format corresponding to different entry types may be different, the storage instructions generated for different entry types of the same interaction content are often different. During the process of responding to the storage instruction that matches the target entry type for the interaction content, the interaction content can be processed according to the stored content, storage location, storage process, and storage format corresponding to the target entry type, etc., to create the corresponding interaction entry for storage.

[0083] Among them, during the process of processing the interaction content, the content to be stored included in the interaction content can be determined first, and then the image data that matches the content to be stored can be generated. This process can be implemented using an artificial intelligence AI generation model with powerful data processing capabilities and image generation capabilities (denoted as the first generation model). The first generation model can be a multi-modal generation model, GPT (Generative Pre-trained Transformer) series models, LLaMA (Large Language Model Application) series models, Bard model, or other image generation models, etc. An appropriate AI generation model can be selected according to the actual interaction scenario to process the input interaction content.

[0084] In the embodiments of the present application, in order to guide the first generation model to generate image data that matches the content to be stored in the interaction content for constructing the interaction entry, an interaction entry prompt for the target interaction can be constructed based on prompt engineering. Through this interaction entry prompt, the processing process of the interaction content input into the first generation model is represented. In this embodiment, the first generation model is guided to extract the content to be stored in the interaction content, and based on the content to be stored, image data that matches the content to be stored is generated. It can be seen that for the interaction content of the target interaction, when different entry types of interaction entries are selected for storage, the content of the constructed interaction entry prompts can be different. The construction process of each interaction entry prompt in the present application will not be elaborated in detail.

[0085] Exemplarily, if the target entry type is a contact, the contact prompt for the target interaction is: Analyze the interaction communication method 1 (such as a phone number, etc.) in the interaction content, create a new contact in the address book, what should the contact name be, and provide the contact's avatar. In this way, after inputting the interaction content into the first generation model, through this contact prompt, the first generation model is guided to extract the contact name from the interaction content and generate image data of the avatar that matches the contact name.

[0086] If the target entry type is a schedule, the schedule prompt words for the target interaction can be: Analyze the schedule theme, schedule event description, event occurrence time and location in the schedule interaction content, and provide map data / navigation routes from the current location to the event occurrence location. In this way, after inputting the interaction content into the first generation model, through the schedule prompt words, the first generation model will be guided to extract the schedule theme, schedule event description, event occurrence time and location from it, and generate map data / navigation routes that match the event occurrence location.

[0087] It should be understood that if the content to be stored in the interaction entry also needs to include other content in the interaction content, or additional content to be stored, the extraction description of the corresponding content to be stored can be added to the interaction entry prompt words. It can be seen that the content of the interaction entry prompt words for the target interaction in this application can be dynamically updated according to changes in the actual storage situation, or new interaction entry prompt words can be created for the user to select. The implementation process is not elaborated in this application.

[0088] In a possible implementation, after constructing different entry types with corresponding interaction entry prompt words, after obtaining the interaction content for the target interaction and determining the target entry type of the interaction content, the target interaction entry prompt words corresponding to the target entry type can also be read, and the target prompt information can be constructed using the interaction content and the target interaction entry prompt words, and the target prompt information can be input into the first generation model; or, directly input the interaction content and the target interaction entry prompt words into the first generation model, so as to guide the first generation model to extract the content to be stored in the interaction content through the target prompt words and generate image data that matches the content to be stored.

[0089] Exemplarily, combined with the contact prompt word content listed above, the prompt information constructed by combining the interaction content can be: For all the interaction content / summary interaction content of the target interaction: "xxxx (communication content including the contact person and their communication method)" Please help analyze the interaction content, create a new contact in the address book for the interaction communication method 1 (such as phone number, etc.) in it, what should the contact name be, and provide the contact's avatar. Similarly, combining the schedule prompt words with the schedule interaction content, the constructed prompt information can be: The interaction content of the target interaction is "xxxx (schedule-related content)" Please help analyze, and give the schedule theme, schedule event description, event occurrence time and location in it, and provide map data / navigation routes from the current location to the event occurrence location. The construction process of the prompt information corresponding to other entry types is similar and will not be elaborated one by one in this application.

[0090] It should be understood that the first generation model can be deployed locally on the electronic device to directly implement step S23 on the local device of the electronic device. Optionally, if the first generation model is deployed on the server, the electronic device can send the interaction content or prompt information that needs to be input into the first generation model, or the interaction content and interaction item prompt words to the server, and then, according to but not limited to the method described above, the server feeds back the content to be stored in the interaction content and its matching image data to the electronic device, and the electronic device continues to execute the subsequent steps.

[0091] Step S24: Output an interaction item creation interface for the interaction content, and display the content to be stored and the image data in the interaction item creation interface;

[0092] In the embodiment of the present application, after calling the first generation model to obtain the content to be stored and its matching image data, an interaction item creation interface for the interaction content can be automatically output, and the content to be stored and the image data are displayed in the interaction item creation interface.

[0093] Exemplarily, taking the item type as a contact person as an example, as Figure 3b shown in the contact person creation interface, which is a schematic diagram of an interaction item creation interface, the content to be stored that can be displayed may include but is not limited to: the name of the interaction object (such as the contact person's name), at least one interaction communication method (such as Figure 3b the mobile phone number, email address, WeChat account number, etc. shown, which can be determined according to the actual interaction content), the contact person's address, etc. The image data may include the contact person's avatar, map data / navigation route, etc. The present application does not limit the display position relationship between each content to be stored and the image data, which can be determined or adjusted according to the interface layout structure.

[0094] Step S25: In response to the confirmation operation on the content to be stored and the image data, create an interaction item containing the content to be stored and the image data for storage.

[0095] In some embodiments, for each content displayed in the interaction item creation interface, the user can also modify it according to the actual situation, such as adding or deleting one or more contents to be stored. The present application does not limit the implementation method.

[0096] Based on this, when it is determined that each content displayed in the interaction item creation interface is correct and complete, the user can perform a confirmation operation on it, such as Figure 3bAs shown, trigger the "√" symbol representing "confirm" or "create" in the interactive entry creation interface. However, it is not limited to this way of implementing the confirmation operation. It can be implemented according to the input methods supported by the display of the electronic device, such as using input devices like keyboards, mice, joysticks, or styluses. Moreover, for the triggered function button, in addition to "√", if the interactive entry creation interface has a function menu, the function menu can be clicked to output various processing functions for this interactive entry creation interface and select the creation function, etc.

[0097] After that, the electronic device responds to the above confirmation operation, uses the contents displayed in the interactive entry creation interface to create an interactive entry containing these contents, and stores the newly created interactive entry. Regarding the storage method and location of the interactive entry, etc., it can be determined according to the target entry type. For example, for an interactive entry of a contact, it can be stored in the address book; for an interactive entry of a schedule, it can be stored in a dedicated schedule software, etc.

[0098] In practical applications, for each stored interactive entry, for the convenience of querying, the content to be stored with the highest matching degree to the target entry type (i.e., important content or representative content that can distinguish other interactive entries of the same type) and image data can be selected from the contents it contains, and determined as the directory / index of this interactive entry in the storage interface / query interface. In this way, when the user needs to query the content of a certain interactive entry, through the image data and important content included in this directory / index, the content of this entry can be quickly and accurately selected, making the storage interface / query interface more user-friendly and easy to use, and enhancing the user experience.

[0099] In addition, the image data in the interactive entries created by this application can help users better remember or distinguish different interactive entries. Especially when the image data has a high correlation with the interactive object, such as the generated contact avatar is related to the real appearance or personality of the contact, it improves the memorability of the interactive entry, making it personalized and emotional. Moreover, image data is more intuitive than text data, can quickly attract the user's attention, and also enriches the diversity of the content of the interactive entry.

[0100] In some other embodiments proposed in the present application, in the process of generating image data that matches the content to be stored in the interaction content, after determining the interaction content for the target interaction, the content to be stored in the interaction content can also be extracted first, and the target content to be stored for which image data needs to be generated (i.e., the content to be stored that supports presentation in text data format and image data format) can be determined, or from the multiple contents to be stored extracted, the target content to be stored can be selected, etc. The present application does not limit the method for determining the target content to be stored. After that, the target content to be stored can be input into a second generation model, such as a pre-trained image generation model or other AI generation models listed above, to generate image data that matches the target content to be stored.

[0101] Among them, the extraction of the content to be stored in this embodiment can be implemented based on a target detection algorithm / entity recognition algorithm or keyword detection algorithm, etc., or a corresponding extraction model can be pre-trained based on the corresponding algorithm, such as deep learning models like LSTM (Long Short-Term Memory), BERT (Bidirectional Encoder Representations from Transformers), etc., or machine learning models trained based on support vector machines or random forests; or, a named entity recognition model based on natural language processing technology, etc., to input the interaction content into the extraction model to obtain each content to be stored included in the interaction content.

[0102] Optionally, the present application can also adopt a rule-based extraction method, an extraction method based on the interaction record of the interaction software that matches the target interaction, or an extraction method based on multi-modal data to implement the extraction of the content to be stored in the interaction content. The present application does not limit the implementation method for extracting the content to be stored and can be selected according to the actual application scenario and its requirements.

[0103] Refer to Figure 4 , which is a schematic flowchart of an interaction content processing method proposed in Embodiment 3 of the present application. This embodiment can refine and describe another optional implementation method of the above interaction content processing method. For example, Figure 4 As shown, this implementation method can include:

[0104] Step S41, determine the interaction content for the target interaction;

[0105] Step S42, perform item type detection on the interaction content to generate a storage instruction that matches the detected target item type;

[0106] In the embodiments of the present application, after determining the interaction content according to the method described above but not limited to it, in addition toFigure 3a In addition to the implementation method of determining the target entry type based on user interaction operations shown, the target entry type of the interaction entry suitable for creating can be automatically detected by analyzing the interaction content.

[0107] Optionally, this application can pre-train an entry type detection model based on machine learning / deep learning algorithms, or retrieve an open-source artificial intelligence model or other intent detection models, etc., to perform semantic analysis on the determined interaction content to determine which entry type the interaction content intends to create. It can be based on the keywords or named entities included in the interaction content, or the content to be matched corresponding to different preset entry types, etc., thereby determining the target entry type, such as the entry type that needs to store keywords or named entities, or the entry type represented by the keywords or named entities, or the entry type corresponding to the actually detected content to be matched, etc. This application does not limit the implementation method of step S42.

[0108] Step S43, in response to the storage instruction, obtain the image description information for the content to be stored in the interaction content;

[0109] Step S44, input the image description information into a third generation model to generate image data that conforms to the image description information;

[0110] Following the above analysis, when determining which entry type to use to store the interaction content for the target interaction, during the process of responding to the corresponding storage instruction, in addition to automatically generating image data that matches the content to be stored in the interaction content based on the first generation model or the second generation model according to the method described above, in order to achieve personalization / stylization of the image data and make it more in line with the user's personal preferences / image storage habits / style of the target entry type. For example, generate image data in a cartoon style or a realistic style, etc.

[0111] Therefore, after the user learns the content to be stored extracted from the interaction content, they can describe the image data expected to match the content to be stored accordingly, obtain the corresponding image description information, and input it into the third generation model, so that the third generation model uses its powerful image generation ability to automatically generate image data that conforms to the image description information according to the image description information. In this implementation process, the user uses input methods such as voice or text, and uses input devices such as the pick-up microphone or keyboard, mouse, stylus pen, etc. of the electronic device to perform an image description input operation, so that the electronic device synchronously collects the corresponding image description information. This application does not limit the content of the image description information and its acquisition method.

[0112] It should be understood that if the data format of the directly collected image description information does not match the input data format required by the third generation model, the data format of the collected image description information can be first converted into the input data format and then input into the third generation model. For example, converting the image description information in audio format into text format, etc., depending on the situation.

[0113] In addition, the third generation model can be the same as the above-mentioned first generation model or second generation model, or can be an image generation model different from the first generation model and the second generation model. The present application does not limit the network structure of the third generation model.

[0114] In some other embodiments proposed by the present application, for the above-mentioned image description information, it can also be automatically generated based on the semantic analysis result of the interaction content. For example, after analyzing that the interaction content contains the content to be stored, screening out the target content to be stored that can support the image data format, and then using an image description generation model, such as the above-mentioned AI generation model, to generate image description information matching the target content to be stored, and then generating matching image data according to the method described above.

[0115] In the process of generating image data described in the above embodiments, the present application can also construct image generation prompts corresponding to different entry types based on prompt engineering. According to actual needs, corresponding image styles (such as cartoon style or realistic style, etc.) can also be configured in the image generation prompts. Then, the image description information and the image generation prompts corresponding to the target entry type are input into the third generation model, or the image generation prompt information composed of the image description information and the image generation prompts is input into the third generation model. Through the image generation prompts, the third generation model is guided to generate image data according to the image description information, such as generating image data in a style or realistic style or default style (that is, in the case where the image style is not given in the image generation prompts or the image description information).

[0116] It should be understood that in the above implementation method of generating image data matching the content to be stored based on the first generation model or the second generation model, the image style can also be configured in the corresponding prompts, further improving the personalization and diversity of the image data matching the content to be stored. The implementation process is similar, and the present application will not elaborate.

[0117] Step S46, create an interaction entry for the interaction content for storage by using at least the image data and the content to be stored.

[0118] Regarding the implementation process of step S46, reference can be made to the description of the corresponding part of the context embodiments, and the present application will not elaborate here.

[0119] In summary, when a user uses the interactive software of an electronic device in a target interaction scenario, such as video conferencing, voice calls, online teaching, or sending notifications via voice / sms, after the AI assistant of the electronic device automatically obtains the interaction content for the target interaction, it can automatically or manually trigger the storage process of the interaction content. During this process, it can automatically detect the entry type of the interaction content to determine which type of interaction entry the interaction content is suitable for storage, automatically generate a matching storage instruction. In response to the storage instruction, after extracting the content to be stored, instead of directly creating an interaction entry that only contains the content to be stored, the present application will obtain the matching image description information, input it into the third generation model to generate the matching image data, and then store the image data as part of the interaction entry to improve the diversity and personalization of the content of the interaction entry. Moreover, the image data is more intuitive and memorable than text data, which is convenient for users to use later and enhances the user experience. This process does not require the user to remember the interaction content and then manually fill in the content to be stored in the interaction entry content, improving the reliability and accuracy of the interaction entry.

[0120] Referring to Figure 5 , which is a schematic flowchart of an interaction content processing method proposed in the fourth embodiment of the present application. This embodiment can refine and describe an optional implementation method for creating an interaction entry for the interaction content proposed above. For example, Figure 5 as shown, the method may include but is not limited to the following steps:

[0121] Step S51, in response to a storage instruction for the interaction content of the target interaction, generate multiple image data that match the content to be stored according to the content to be stored included in the interaction content;

[0122] Step S52, output an interaction entry creation interface for the interaction content, and display the content to be stored and multiple image data in the interaction entry creation interface;

[0123] Step S53, in response to a selection operation on the image data, determine the selected image data;

[0124] Combined with the image data generation method described in the above embodiment, when the present application generates image data that matches the content to be stored through a generation model, it can generate multiple image data with a relatively high matching degree with the content to be stored. For example, in the order of decreasing matching degree, select 3 or 4 or 5 matching image data for the user to further select the appropriate target image data from them. Among them, the number of generated image data that matches the content to be stored can be determined according to the corresponding prompt words / prompt information. For example, it is indicated in the prompt words that three image data are recommended, or for the same content to be stored, the default number of image data is generated.

[0125] In the schematic diagram of the interactive entry creation interface as shown in Figure 3b When the target entry type includes contacts, contact image data (such as a contact avatar) that matches the contact name can be generated based on the contact name included in the interaction content. In this embodiment, multiple pieces of contact image data that match the contact name can be generated at this time. These multiple pieces of contact image data can be of the same style or different styles. The user can flexibly select one of the contact image data according to the actual situation. Thus, when creating a new contact, at least use the contact name (such as the user's name or company name, etc.), the selected contact image data, and at least one interaction contact method (such as a mobile phone number and / or an email address, etc.) included in the interaction content to create a new contact.

[0126] Similarly, when the target entry type includes a schedule, map data that matches the schedule location can be generated based on the schedule location included in the interaction content. Different display modes of map data can be generated here for the user to select. After that, a new schedule can be created by at least using the schedule location, the map data, and the to-do event description included in the interaction content. This application does not limit the content of the newly created schedule, its storage method, location, etc., which can be determined according to the situation.

[0127] In some embodiments, for the image data that matches the content to be stored, it can also be obtained by searching from an open-source database using the search engine of the electronic device. For example, when searching for image data associated with the contact name, it can be used together with the image data generated based on the same content to be stored as candidate image data for the content to be stored, and displayed on the interactive entry creation interface for the user to select from. According to actual needs, auxiliary information such as the matching degree between each piece of image data and the content to be stored can also be displayed to ensure that the user selects appropriate image data to be stored as part of the interactive entry content.

[0128] Step S54, in response to an adjustment operation on the content to be stored displayed on the interactive entry creation interface, determine the adjusted content to be stored;

[0129] Step S55, in response to a confirmation operation on the adjusted content to be stored and the selected image data, create an interactive entry containing the adjusted content to be stored and the selected image data for storage;

[0130] In some embodiments, after determining the content to be stored for the target interaction and its matching image data according to the method described in steps S51 - S53, an interactive entry containing the content to be stored and the image data can be created and stored in response to a confirmation operation input by the user or directly.

[0131] In a possible implementation, for the content to be stored directly displayed on the interactive entry creation interface in the methods described in steps S54 and S55, the present application can also flexibly adjust it according to actual needs, improving the diversity and personalization of the text content stored in the interactive entries. The implementation methods for adjusting the content to be stored may include but are not limited to: deleting one or more pieces of content to be stored; adding one or more pieces of content to be stored; modifying one or more pieces of content to be stored that have been displayed, etc. Especially when there is a large amount of content to be stored extracted from the interactive content, if the user is only interested in a small amount of the content to be stored and does not need to record the other content to be stored, it can be directly deleted. It should be understood that the adjustment operations proposed in the present application solve the problem of inaccurate or incomplete extraction of the content to be stored in the interactive content by the model, further improving the content accuracy and integrity of the interactive entries.

[0132] It should be noted that the present application does not show the implementation methods for the adjustment operations of the content to be stored listed above, and can be implemented according to the editing methods supported by the corresponding interface. For example, trigger the corresponding "Add" button to add the content to be stored, trigger the "Delete" button corresponding to the content to be stored that needs to be deleted and has been displayed to delete the content to be stored; select the content to be stored that needs to be modified to enter the editing state, and then edit or modify the content to be stored again, etc. The implementation process will not be described in detail with examples one by one in the present application.

[0133] Step S56, in response to an interactive entry query operation, output an interactive entry query interface, and display the image data and interactive object identifier corresponding to each interactive entry in the interactive entry query interface.

[0134] For the interactive entries created for the interactive content described in the above embodiments but not limited to, such as each contact / schedule, etc., they can be viewed according to actual needs. For example, if the user needs to call contact A, they can enter the corresponding query interface to query the avatars and names of each contact to quickly determine the relevant information stored by contact A, and click to call to automatically dial the phone number of contact A.

[0135] Thus, the present application can configure the image data and interactive object identifier included in the interactive entry (which belong to the content to be stored in the interactive content, such as the avatar and name of contact A above) in the interactive entry query interface, so that the image data and interactive object identifier are associated and displayed in the interactive entry query interface, or the image data is displayed in the interactive interface for the interactive object identifier, such as the call interface. The implementation method of automatically generating and displaying the image data matching the interactive object identifier proposed in the present application does not require manually selecting the image data and adding it to the interactive entry after creating the interactive entry, greatly reducing the user operation steps.

[0136] Moreover, after the user queries an interactive entry of a certain entry type and performs the corresponding query operation, the electronic device outputs an interactive entry query interface corresponding to the entry type in response to the corresponding interactive entry query operation, such as the contact interface in the address book, or the schedule query interface in the x note, etc. Among them, for the output interactive entry query interface, the image data and interactive object identifier corresponding to each interactive entry can be displayed, so that the user can quickly and accurately determine the target interactive entry to be queried, enhancing the user experience. For example, the names and avatars of each contact are displayed on the contact interface. This application does not specify the layout structure and display content of the interactive entry query interface, and can be adjusted or configured by entering the corresponding setting interface according to the actual situation. The implementation process is not described in detail in this application.

[0137] Combined with the interactive content processing method described in the above embodiments, the following will be described by taking the call scenario as an example:

[0138] Such as Figure 6 As shown in the schematic diagram of the generation process of the storage instruction for the interactive content of the target interaction, if xxx calls and the user answers, the AI intelligent summary function can be enabled. As shown in Figure 6 Figure (b) in, the user can click the function button "AI Intelligent Summary" on the call interface, and the system of the electronic device will start recording and automatically convert the call content into text, which is equivalent to call subtitles. As shown in Figure 6 Figure (c) in. During this process, through the intelligent summary function of the AI assistant, the key information in the call content, such as the contact name, phone number, important matters, etc., can be automatically extracted, thereby generating a summary of the call content. Optionally, the summary of the call content can also be generated after the call ends. As shown in Figure 6 Figure (d) in. After the call ends, a summary prompt window for this call (such as a floating window above the screen, etc.) can be output to inform the user that the summary of the current call content is being generated, including but not limited to the prompt content shown in the drawings, and can be flexibly configured according to the actual situation.

[0139] In this embodiment, the target interaction can be the current call, and the interactive content can be the call content or the summary of the call content, etc. Based on this, after the call ends and the interactive content of this call is determined, relevant prompts indicating that the summary has been completed can be output to prompt the user to view or save. At this time, "View" and "Save" buttons can be displayed in the summary prompt window for the user to select and click. If the "View" button is clicked, in response to the summary viewing instruction for this call, a summary viewing interface, such as the viewing interface of the x note, etc., can be output according to the pre-configured storage path for the user to view the summary of this call content. According to actual needs, the stored summary can also be exported as a text file or a PDF file, etc., to meet the corresponding management requirements.

[0140] In addition, this application can also save important information in the summary of the current call. The user can click the "Save" button. Or, as shown in the floating window in Figure (e), it is the trigger interface for saving the summary. When the user clicks on this floating window, in response to the storage operation, a storage configuration interface as shown in Figure (f) is output, and the interactive content (i.e., the content summary, which is the summary of the call content just ended), the call recording, and the information that can be saved, namely various entry types, such as Figure 6 "Add to Contacts" shown in Figure (f) means adding the contact person and their phone number of the current incoming call to the contacts, and "Create New Schedule" means creating a new schedule for the matters notified in the content of the current call, etc. The user can select one as the target entry type according to the actual situation. For example, if the user clicks on the entry type of "Add to Contacts", it can be used as the target entry type. In response to the corresponding storage instruction, one or more avatars matching the contact name are generated. Figure 6 In actual application, in response to the selection operation of the entry type, an interactive entry creation interface corresponding to the selected target entry type can be output. Taking the target entry type of "Add to Contacts" as an example, when the user clicks on "Add to Contacts", a new contact creation interface as shown in Figure (a) can be output. In this new contact creation interface, the contact name, mobile phone number, home use, and multiple recommended avatars matching the contact name are displayed, etc., for the user to select one of the multiple recommended avatars as the avatar of the new contact, and the user can directly click on it for operation. Figure 6 In addition, as shown in the embodiment, operations can also be performed on other display contents in the new contact creation interface (such as deleting, modifying, or adding more fields, and the contacts can also be grouped, and select which group to store the newly created contact in, such as each group divided according to the first letter of the contact name or input identifier, etc.). After determining that the display content is accurate and complete, the user can click the confirmation button (such as the √ mark shown in Figure (c)), that is, the confirmation operation for the content to be stored and the image data, and a new contact containing these display contents is created. At the same time, the corresponding contact can be added to the contacts. As shown in the contact interface in Figure (d), the avatar and name of the newly created contact can be displayed, which is convenient for the user to quickly and accurately query this contact.

[0141] In actual application, in response to the selection operation of the entry type, an interactive entry creation interface corresponding to the selected target entry type can be output. Taking the target entry type of "Add to Contacts" as an example, when the user clicks on "Add to Contacts", a new contact creation interface as shown in Figure (a) can be output. In this new contact creation interface, the contact name, mobile phone number, home use, and multiple recommended avatars matching the contact name are displayed, etc., for the user to select one of the multiple recommended avatars as the avatar of the new contact, and the user can directly click on it for operation. Figure 7 In this new contact creation interface, the contact name, mobile phone number, home use, and multiple recommended avatars matching the contact name are displayed, etc., for the user to select one of the multiple recommended avatars as the avatar of the new contact, and the user can directly click on it for operation.

[0142] In addition, as Figure 5 shown in the embodiment, operations can also be performed on other display contents in the new contact creation interface (such as deleting, modifying, or adding more fields, and the contacts can also be grouped, and select which group to store the newly created contact in, such as each group divided according to the first letter of the contact name or input identifier, etc.). After determining that the display content is accurate and complete, the user can click the confirmation button (such as the √ mark shown in Figure (c)), that is, the confirmation operation for the content to be stored and the image data, and a new contact containing these display contents is created. At the same time, the corresponding contact can be added to the contacts. As shown in the contact interface in Figure (d), the avatar and name of the newly created contact can be displayed, which is convenient for the user to quickly and accurately query this contact. Figure 7 shown in Figure (c)), that is, the confirmation operation for the content to be stored and the image data, and a new contact containing these display contents is created. At the same time, the corresponding contact can be added to the contacts. As shown in the contact interface in Figure (d), the avatar and name of the newly created contact can be displayed, which is convenient for the user to quickly and accurately query this contact. Figure 7 shown in the contact interface in Figure (d), the avatar and name of the newly created contact can be displayed, which is convenient for the user to quickly and accurately query this contact.

[0143] It should be understood that for the interaction content in the video interaction scenario, the implementation process of automatically creating corresponding interaction entries by executing the interaction content processing method proposed in this application is similar, and this application will not elaborate. In addition, in addition to the audio and video interaction scenarios, this application is also applicable to the text interaction scenario. Taking the text message interaction as an example, when a phone number is mentioned in the text message content and the user hopes to save the phone number, usually in the manner as shown in Figure 8 After selecting the phone number in the text message content and right-clicking the mouse button, a function menu for the phone number is output to display the operation methods for the phone number therein, such as "Copy", "Save Phone Number", and "Dial", etc. After selecting to save the phone number, a new contact interface is output to display the phone number and enter the contact name, but an avatar that matches the contact name cannot be automatically generated. If an avatar is needed, usually a picture needs to be taken or selected from the image library as the contact avatar, and the operation process is complex and the personalization of the contact avatar cannot be achieved.

[0144] However, by adopting the interaction content processing method proposed in this application, the text message content can be automatically analyzed to extract the content to be stored therein, such as the contact name, phone number, etc., and the corresponding image data can be generated. In the new contact interface, as shown in Figure 7 In the process shown in Figures (a)-(d) in, a contact for the text message content is created and stored. The implementation process can refer to the processing steps described in the above embodiments, and this application will not elaborate. It should be understood that the generated image data is not limited to the 3 recommended avatars shown in the drawings, and the number of avatars to be selected can be pre-configured according to the actual situation.

[0145] In addition, this application can also be applicable to the creation of contacts in the email scenario. And for the call scenario, text message interaction scenario, or email scenario described above, in addition to creating new contacts, the target entry type of creating a new schedule can also be selected, and the implementation process of creating a schedule is similar and this application will not give examples one by one and elaborate.

[0146] Referring to Figure 9 , which is a schematic flowchart of an interaction content processing method proposed in Embodiment 5 of this application. On the basis of the interaction content processing methods described in the above embodiments, this embodiment proposes to selectively store the interaction content of the target interaction to avoid storing interference content and causing resource waste and security problems. Therefore, as shown in Figure 9 The above interaction content processing method may further include:

[0147] Step S91, in response to a storage filtering request for the target interaction, output a filtering configuration interface, and display at least one candidate filtering item on the filtering configuration interface;

[0148] Step S92: In response to a configuration operation on at least one candidate filtering item, obtain storage filtering data for the target interaction;

[0149] In practical applications, considering factors such as data security and resource conservation, for different interaction contents of each interaction of the same interaction type (i.e., the target interaction), this application does not store all interaction contents, but selectively stores them. This application can customize the storage conditions for whether the interaction content needs to be stored (or the storage filtering data including at least one filtering item for rejecting storage), and determine whether the interaction content needs to be stored according to the storage conditions (or storage filtering data). This application places no restrictions on the content of the storage conditions (or storage filtering data) and its configuration implementation method.

[0150] In a possible implementation manner, when it is necessary to configure the storage conditions for the interaction content, a storage filtering request for the target interaction can be initiated, which can be implemented by clicking a storage filtering configuration button or identifier or triggering a corresponding function button in the setting interface. In response to the storage filtering request, a filtering configuration interface for the target interaction can be output, and at least one candidate filtering item is displayed in the filtering configuration interface. By performing a configuration operation on the candidate filtering item, storage filtering data for the target interaction can be obtained to configure the storage conditions, and the storage conditions can be used to indicate the content to be stored, that is, to explain which content can trigger the interaction content processing method proposed by this application to implement the storage of the interaction memory. Similarly, it can also indicate the content that is refused to be stored to reject the storage of the interaction content containing this content.

[0151] Exemplarily, still taking the call scenario described above as an example, this application does not create new contacts for all unfamiliar incoming calls. It is necessary to first determine whether this unfamiliar incoming call number is worthy of being stored, or whether it is a call number that the user hopes / needs to store, to avoid harassing the user. For this, this application can allow the user to customize the incoming calls belonging to "harassment" (i.e., the incoming calls for which new contacts are refused to be created, and even can be automatically blocked) to help the AI assistant automatically identify and filter them.

[0152] Refer to Figure 10 In the filtering configuration interface shown in Figure (a) in [reference], the user can select the incoming calls that they are not interested in and define them as harassing calls, including but not limited to candidate filtering items such as real estate, bank loans, insurance, training, fraud, and advertisements shown in the attached drawings (i.e., the service types obtained by automatically identifying the incoming call numbers, which can be determined based on open-source data and data provided by telecommunications units, and this process is implemented within the legal scope). If these system-default candidate filtering items are incomplete, the user can also click the "Add New Item" button to enter as Figure 10The filtering item definition interface shown in Figure (b) is used to customize the candidate filtering items. The user can pop up an input box in the middle of the interface to customize the filtering items. After clicking the "Confirm" button, the customized filtering items will be added to the filtering configuration interface shown in Figure (a) below, so that one or more filtering items selected by the user constitute the stored filtering data for calls. The configuration implementation process of the stored filtering data in other interaction scenarios is similar, and will not be described in detail one by one in this application. Figure 10 The filtering configuration interface shown in Figure (a) below, so that one or more filtering items selected by the user constitute the stored filtering data for calls. The configuration implementation process of the stored filtering data in other interaction scenarios is similar, and will not be described in detail one by one in this application.

[0153] It should be understood that the same incoming call or other target interaction may or may not need to be stored for different users. That is to say, for the same interaction scenario, the stored filtering data customized by different users is different, realizing personalized filtering of the interaction content in this interaction scenario.

[0154] In some embodiments, the above-mentioned stored filtering data can be used to configure stored filtering prompt words to guide the above-mentioned generation model to identify the content to be stored that meets the storage conditions from the input interaction content. Among them, the stored filtering prompt words can be based on the prompt words / prompt information described above, and add storage conditions or filtering conditions determined based on the stored filtering data.

[0155] Still taking the above call scenario as an example, the stored filtering prompt words can be "This user thinks that 'real estate' and 'bank loan' XXXXXXX are harassing calls to him and he is not interested in such calls. So for the call that just ended, do you think the content of the conversation is valuable to the user? Should the unfamiliar number of this incoming call be saved to the address book? If it is recommended to save, please also give the recommended contact name for this unfamiliar number and recommend three candidate contact avatars." In this way, after inputting the interaction content or the content to be stored extracted therefrom into any of the above generation models, the generation model can be guided by the stored filtering prompt words to determine whether this call is a harassing call. If so, directly end the storage process of the interaction memory and output a harassing prompt message; if not, continue to generate three candidate contact avatars that match the contact name, thus avoiding the storage of harassing calls and improving the processing efficiency after the user answers the call.

[0156] Similarly, for the SMS scenario or email scenario, etc., according to the method described above, after obtaining the corresponding stored filtering data, the corresponding stored filtering prompt words can be configured to implement the filtering of spam SMS / emails. The implementation process will not be described in detail in this application.

[0157] Step S93: Match the interaction content of the target interaction with the stored filtering data;

[0158] Step S94, if the interaction content matches at least part of the stored filtering data, do not respond to the storage instruction for the interaction content of the target interaction;

[0159] Step S95, if the interaction content does not match the stored filtering data, in response to the storage instruction for the interaction content of the target interaction, generate image data that matches the content to be stored according to the content to be stored included in the interaction content;

[0160] Step S96, create an interaction entry for the interaction content for storage by using at least the image data and the content to be stored.

[0161] In a possible implementation, when the present application performs a storage filtering process on the actually obtained interaction content for the target interaction based on the stored filtering data, the interaction content can be matched with the stored filtering data. If at least part of the data matches, that is, at least one matching content is stored, it indicates that the interaction content is the content that needs to be filtered out for the user. The processing of the interaction content can be directly ended, and the storage instruction for the interaction content is no longer responded to. Even corresponding filtering prompt information can be output. On the contrary, if the interaction content does not match the stored filtering data, it indicates that the interaction content is the content that needs to be stored for the user. The method described in the above embodiments can be used to generate image data that matches the content to be stored in the interaction content, and create an interaction entry including the image data and the content to be stored. The generation and creation processes can refer to the description of the corresponding parts of the above embodiments, and will not be elaborated here.

[0162] Among them, for the above-mentioned stored filtering data used to determine whether to store the determined interaction content this time, in addition to customizing and configuring it according to the methods described in step S91 and step S92 above, the default stored filtering data of the electronic device system can also be directly used. It can be the filtering items for identifying the interaction content commonly recognized in the industry, or the filtering items summarized from the user feedback to the system, etc. In this case, after determining the interaction content for the target interaction, the custom configuration or the default stored filtering data of the system stored in advance can be directly read, and step S93 is executed.

[0163] In some embodiments, after determining the content to be stored included in the interaction content, it can be first matched and detected with the stored historical interaction entries. If the detected target historical interaction entry includes at least part of the content to be stored, but does not include the image data that matches the content to be stored, determine the target content in the content to be stored not included in the target historical interaction entry, and the target content and the image data can be added to the target historical interaction entry.

[0164] It can be seen that for the process of creating an interaction entry for interaction content, if relevant historical interaction entries have been created previously (such as interaction entries manually created by users), but the content they contain is incomplete, especially without image data, the method for automatically generating image data based on the interaction content proposed in this application can still be used to generate image data that matches the content to be stored, and supplement the target content that was not stored previously, such as one or more contents to be stored extracted from the interaction content of the current target interaction, or the content obtained through the above addition or modification, etc., so as to enrich the content of the target historical interaction entry for the target interaction, without the need for users to manually supplement the content, improving the processing efficiency and enhancing the user experience.

[0165] The above introduced an interaction content processing method provided by an embodiment of this application. Next, a device for executing the above interaction content processing method will be introduced.

[0166] Refer to Figure 11 , which is a schematic structural diagram of an interaction content processing device provided by an embodiment of this application. As Figure 11 shown, the interaction content processing device may include:

[0167] An image data generation module 111, configured to generate image data that matches the content to be stored according to the content to be stored included in the interaction content in response to a storage instruction for the interaction content of a target interaction;

[0168] An interaction entry creation module 112, configured to create an interaction entry for the interaction content for storage by at least using the image data and the content to be stored.

[0169] Those skilled in the art can understand that the functions and technical effects of each module in the above device embodiment are equivalent to the corresponding steps described in the foregoing method embodiment. The specific implementation details can refer to the description of the method part and will not be elaborated here.

[0170] An embodiment of this application also provides a computer-readable storage medium. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can be enabled to implement any interaction content processing method provided by an embodiment of this application.

[0171] Among them, the computer-readable storage medium can be any available medium that can be stored by the electronic device or a data storage device such as a training device or a data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state disk (SSD)), etc.

[0172] An embodiment of the present application also provides a computer program product, including computer-readable instructions, which, when running on an electronic device, enable the electronic device to implement any one of the interactive content processing methods provided by the embodiments of the present application.

[0173] Among them, when the computer-readable instructions are loaded and executed on the electronic device, the processes or functions described in the embodiments of the present application are fully or partially generated. The electronic device may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer-readable instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0174] Refer to Figure 12 , which is a schematic diagram of the hardware structure of an electronic device proposed by an embodiment of the present application. As Figure 12 shown, the electronic device may include: at least one communication component 121, at least one memory 122, and at least one processor 123, where:

[0175] The at least one communication component 121, the at least one memory 122, and the at least one processor 123 may communicate through a bus. The bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 12 only a single bidirectional line is shown in

[0176]

[0177] but it does not mean that there is only one bus or one type of bus. The communication component 121 may be used to receive interactive content for a target interaction, or to generate original interaction data of the interactive content, such as call audio data or short message data, etc. It may also be used to implement data or instruction transmission between internal components of the electronic device.Based on this, in the embodiments of the present application, the communication component 121 may include communication components corresponding to wireless communication methods such as wifi, Bluetooth, 5G / 6G, etc., so that the electronic device can implement data transmission with other devices through the communication components. It may also include one or more interfaces supporting wired communication methods, such as general-purpose input / output (GPIO) interfaces, USB interfaces, universal asynchronous receiver / transmitter (UART) interfaces, etc., to achieve data transmission between various components within the electronic device. The present application does not limit the component structure of the communication component 121 to implement this function and its corresponding communication transmission mechanism, which can be determined according to the situation.

[0178] The memory 122 can be used to store multiple computer program instructions for implementing the interactive content processing method proposed in the embodiments of the present application; the processor 123 can load and execute the computer instructions stored in the memory 122 to implement each step of the interactive content processing method proposed in the embodiments of the present application. The implementation process can refer to the description of the corresponding part in the above method embodiments.

[0179] In the embodiments of the present application, the memory 122 may include storage media such as floppy disks, USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs. The processor 123 may include any one or more of processors such as central processing unit (CPU), graphics processing unit (GPU), micro processor (MP), digital signal processor (DSP), application specific integrated circuit (ASIC), or field-programmable gate array (FPGA).

[0180] It should be understood that Figure 12 the structure of the shown electronic device does not constitute a limitation on the electronic device in the embodiments of the present application. In practical applications, the electronic device may include more than Figure 12More or fewer components as shown, or combining certain components, such as pickups, speakers, display screens, various sensors, antennas, power modules, radio frequency components, external ports, and other input / output components, etc., can be determined according to the processing function requirements, and this application will not give detailed examples one by one.

[0181] In addition, it should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the device embodiments provided in this application, the connection relationships between the modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines.

[0182] Through the description of the above embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by dedicated hardware including application-specific integrated circuits, dedicated CPUs, dedicated memories, dedicated components, etc. That is to say, in the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product in the form of a software product can be stored in a readable storage medium, including several instructions for causing a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the interactive content processing method described in each embodiment of this application.

[0183] In addition, each embodiment in this specification is described in a progressive or parallel manner. Each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the devices, electronic devices, products, and media disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

Claims

1. A method for processing interactive content, the method comprising: In response to a storage instruction for the interactive content of the target interaction, generating image data matching the content to be stored according to the content to be stored contained in the interactive content; An interactive entry for the interactive content is created and stored by at least using the image data and the content to be stored.

2. The method according to claim 1, wherein generating image data matching the content to be stored based on the content to be stored contained in the interactive content comprises any one of the following: Inputting the interaction content into a first generation model, so that the first generation model extracts the content to be stored in the interaction content according to the interaction item prompt word for the target interaction, and generates image data matching the content to be stored; Extracting the content to be stored in the interactive content, and inputting the target content to be stored into a second generation model to generate image data matching the target content to be stored; The target content to be stored refers to the content to be stored that supports presentation in text data format and image data format; Image description information of the content to be stored contained in the interactive content is obtained, and the image description information is input into a third generation model to generate image data that conforms to the image description information.

3. The method according to claim 1, wherein the step of creating an interactive item for the interactive content by at least using the image data and the content to be stored comprises: outputting an interactive item creation interface for the interactive content, and displaying the content to be stored and the image data in the interactive item creation interface; In response to a confirmation operation on the content to be stored and the image data, an interactive entry including the content to be stored and the image data is created.

4. The method according to claim 3, wherein the step of creating an interactive item for the interactive content by at least using the image data and the content to be stored further comprises at least one of the following: If a plurality of the image data are displayed in the interactive item creation interface, in response to a selection operation on the image data, determining the selected image data, so as to create an interactive item including the content to be stored and the selected image data in response to the confirmation operation; In response to an adjustment operation on the content to be stored displayed on the interactive item creation interface, determining the adjusted content to be stored, so as to create an interactive item including the adjusted content to be stored and the image data in response to the confirmation operation; The image data and interactive object identifier contained in the interactive item are configured in the interactive item query interface so that the image data and the interactive object identifier are associated and displayed on the interactive item query interface, and / or the image data is displayed on the interactive interface for the interactive object identifier; the interactive object identifier belongs to the content to be stored.

5. The method according to claim 1, further comprising: matching the interactive content with stored filtering data; If the interaction content matches at least part of the stored filtering data, not responding to a storage instruction for the interaction content of the target interaction; If the interaction content does not match the stored filtering data, a storage instruction for the interaction content of the target interaction is responded to.

6. The method according to any one of claims 1 to 5, further comprising: In response to the storage filter request for the target interaction, output a filter configuration interface, and display at least one candidate filter item on the filter configuration interface; In response to a configuration operation on at least one of the candidate filter items, obtaining stored filter data for the target interaction; The storage filter data is used to configure storage conditions, and the storage conditions are used to indicate the content to be stored. Alternatively, the storage filtering data is used to configure storage filtering prompt words to guide the first generation model to identify the to-be-stored content that meets the storage condition from the input interactive content.

7. The method according to any one of claims 1 to 5, further comprising: Performing a match detection between the content to be stored and the stored historical interaction entries; If the detected target historical interaction entry contains at least part of the content to be stored but does not contain image data matching the content to be stored, determining the target content in the content to be stored that is not contained in the target historical interaction entry; The target content and the image data are added to the target history interaction entry.

8. The method according to any one of claims 1 to 5, further comprising any one of the following: Outputting a storage configuration interface for interactive content of a target interaction, displaying at least one item type for the interactive content on the storage configuration interface, and generating the storage instruction matching the selected target item type in response to a selection operation of the item type; Determine the interactive content for the target interaction, perform item type detection on the interactive content, and generate the storage instruction matching the detected target item type.

9. The method according to claim 8, wherein generating image data matching the content to be stored based on the content to be stored contained in the interactive content, and creating an interactive entry for the interactive content for storage by at least using the image data and the content to be stored, comprises at least one of the following: If the target entry type includes a contact, generating contact image data matching the contact name according to the contact name included in the interactive content, and creating a new contact using at least the contact name, the contact image data, and at least one interactive contact method included in the interactive content; If the target entry type includes a schedule, map data matching the schedule location is generated based on the schedule location included in the interactive content, and a new schedule is created using at least the schedule location, the map data, and a description of a to-do event included in the interactive content.

10. An electronic device, comprising: at least one communication element, at least one memory and at least one processor, wherein: The communication element is used to implement data interaction between the electronic device and other electronic devices; The memory is used to store a plurality of computer instructions; The processor is used to load and execute the computer instructions to implement the following steps: In response to a storage instruction for the interactive content of the target interaction, generating image data matching the content to be stored according to the content to be stored contained in the interactive content; An interactive entry for the interactive content is created and stored by at least using the image data and the content to be stored.

Images