WO2025156276A1

WO2025156276A1 - Information interaction method and apparatus, electronic device, storage medium, and program product

Info

Publication number: WO2025156276A1
Application number: PCT/CN2024/074293
Authority: WO
Inventors: Lianwei YANG; Rober NEWTON; Anne GREEN
Original assignee: Jiu Tai Group Co Ltd
Current assignee: Jiu Tai Group Co Ltd
Priority date: 2024-01-26
Filing date: 2024-01-26
Publication date: 2025-07-31
Anticipated expiration: 2026-07-26

Abstract

The present disclosure provides an information interaction method and apparatus, an electronic device, a storage medium and a program product. The method includes: obtaining a plurality of pieces of interaction information of a target object and obtaining environment information of an environment where the target object is located; determining correlation information according to the plurality of pieces of interaction information and the environment information, the correlation information representing a correlation between the plurality of pieces of interaction information and a correlation between the plurality of pieces of interaction information and the environment information; determining information to be pushed according to the plurality of pieces of interaction information, the environment information, and the correlation information; and pushing the information to be pushed.

Description

INFORMATION INTERACTION METHOD AND APPARATUS, ELECTRONIC DEVICE, STORAGE MEDIUM, AND PROGRAM PRODUCT

TECHNICAL FIELD

The present application relates to the field of computer technology, and more particularly, to an information interaction method and apparatus, an electronic device, a storage medium, and a program product.

BACKGROUND

As mobile phones, tablets, smart home appliances, virtual reality and other technologies become more and more popular, users have increasingly higher requirements for interactive experience.

Currently, when an electronic device interacts with a user, it typically processes text information inputted by the user and display a processing result in an interactive interface for the user to view. For example, when the user needs to search for a product on a shopping website, the user can enter a keyword of the product on the shopping website based on the electronic device. Then, the electronic device can determine the product that matches the keyword of the product based on the keyword of the product and display it on the shopping website.

However, in the above interaction scheme, since the electronic device can only determine the display content based on the text information inputted by the user, there is a problem that the interaction scheme is limited, with low intelligence and personalization of the interaction.

SUMMARY

The present disclosure provides an information interaction method and apparatus, an electronic device, a storage medium and a program product, capable of improving the diversity of interaction schemes, improving the intelligence and personalization of interaction, and improving user experience.

In a first aspect, an information interaction method is provided. The method includes: obtaining a plurality of pieces of interaction information of a target object and obtaining environment information of an environment where the target object is located; determining correlation information according to the plurality of pieces of interaction information and the environment information, the correlation information representing a correlation between the plurality of pieces of interaction information and a correlation between the plurality of pieces of interaction information and the environment information; determining information to be pushed according to the plurality of pieces of interaction information, the environment information, and the correlation information; and pushing the information to be pushed.

In a second aspect, an information interaction apparatus is provided. The apparatus includes: an obtaining module configured to obtain a plurality of pieces of interaction information of a target object and obtain environment information of an environment where the target object is located; a first determining module configured to determine correlation information according to the plurality of pieces of interaction information and the environment information, the correlation information representing a correlation between the plurality of pieces of interaction information and a correlation between the plurality of pieces of interaction information and the environment information; a second determining module configured to determine information to be pushed according to the plurality of pieces of interaction information, the environment information, and the correlation information; and a pushing module configured to push the information to be pushed.

In a third aspect, an electronic device is provided. The electronic device includes a processor and a memory. The memory is configured to store a computer program, and the processor is configured to call and run the computer program stored in the memory to perform the method according to the first aspect or any implementation thereof.

In a fourth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program causing a computer to perform the method according to the first aspect or any implementation thereof.

In a fifth aspect, a computer program product is provided. The computer program product contains computer program instructions causing a computer to perform the method according to the first aspect or any implementation thereof.

In a sixth aspect, a computer program is provided. The computer program causes a computer to perform the method according to the first aspect or any implementation thereof.

With the technical solutions according to the present disclosure, an electronic device can first obtain a plurality of pieces of interaction information of a target object and environment information of an environment where the target object is located. Then, the electronic device can determine correlation information according to the plurality of pieces of interaction information and the environment information. The correlation information represents a correlation between the plurality of pieces of interaction information and a correlation between the plurality of pieces of interaction information and the environment information. Then, the electronic device can determine information to be pushed according to the plurality of pieces of interaction information, the environment information, and the correlation information. Finally, the electronic device can push the information to be pushed. In the above process, when determining the information to be pushed, the electronic device will not only consider the plurality of pieces of interaction information of the target object, but also consider the environment information of the environment where the target object is located and the correlation information, such that the determined information to be pushed can be more accurate, more intelligent and personalized, thereby improving the diversity of interaction schemes.

BRIEF DESCRIPTION OF DRAWINGS

In order to describe the technical solutions according to the embodiments of the present disclosure more clearly, figures used in description of the embodiments will be introduced briefly below. Obviously, the figures described below only illustrate some embodiments of the present disclosure, and other figures can be obtained by those of ordinary skill in the art based on these drawings without any inventive efforts.

FIG. 1 is a schematic diagram showing an application scenario according to an embodiment of the present disclosure;

FIG. 2 is a flowchart illustrating an information interaction method according to an embodiment of the present disclosure;

FIG. 3 is a schematic diagram showing an information interaction method according to an embodiment of the present disclosure;

FIG. 4 is a schematic diagram showing an information interaction method according to another embodiment of the present disclosure;

FIG. 5 is a schematic diagram showing an information interaction method according to yet another embodiment of the present disclosure;

FIG. 6 is a schematic diagram showing an information interaction method according to still another embodiment of the present disclosure;

FIG. 7 is a schematic diagram showing an information interaction apparatus 700 according to an embodiment of the present disclosure; and

FIG. 8 is a schematic block diagram of an electronic device 800 according to an embodiment of the present disclosure.

DESCRIPTION OF EMBODIMENTS

The technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the figure in the embodiments of the present disclosure. Obviously, the described embodiments are only some embodiments, rather than all embodiments, of the present disclosure. All other embodiments obtained by those skilled in the art based on the embodiments in the present disclosure without inventive efforts are to be encompassed by the scope of the present disclosure.

It is to be noted that the terms "first" and "second" in the description and claims of the present disclosure and the above-mentioned figures are used to distinguish similar objects from each other, and are not necessarily used to describe a specific sequence or order. It should be understood that the data used in this way can be interchanged as appropriate such that the embodiments of the present disclosure can be implemented in orders other than those shown or described herein. In addition, the terms "comprising" and "having" and any variants thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, and may include other steps or units that are not explicitly listed or are inherent to the process, method, product, or device.

As described above, in the existing technology, since an electronic device can only determine a display content based on text information inputted by the user, there is a problem that the interaction scheme is limited, with low intelligence and personalization of the interaction.

In order to solve the above technical problem, the inventive concept of the present disclosure is that an electronic device can determine information to be pushed based on a plurality of pieces of interaction information of a target object, environment information of an environment where the target object is located, and correlation information. The correlation information is used to represent a correlation between the plurality of pieces of interaction information and a correlation between the plurality of pieces of interaction information and the environment information. In this way, the diversity of interaction schemes can be improved, the intelligence and personalization of interaction can be improved, and the user experience can be improved.

It should be understood that the technical solutions of the present disclosure can be, but not limited to being, applied to the following scenarios:

In some implementations, the technical solutions of the present disclosure can be applied to scenarios such as smart home appliances, games, virtual reality, and real-time recommendations, but the present disclosure is not limited to any of these examples.

For example, in a smart home appliance scenario, a user can control operating conditions of home appliance, such as on/off or display through gestures, voice, etc. For example, when the user is sitting on a stool and needs to turn on the light, the user can make Gesture 1 and say "turn on the light" . Then the electronic device can obtain Gesture 1 and the voice "turn on the light" and take a picture of the user's environment. Next, the electronic device can determine that the information to be pushed is to control the light next to the stool to be turned on based on the Gesture 1, the voice "turn on the lights" and the user's environment. After that, the electronic device can control the light next to the stool to be turned on based on the information to be pushed.

For example, in a game scenario, the electronic device can obtain the user's gesture and facial expression as well as the user's environment, determine the information to be pushed based on the user's gesture and facial expression and the user's environment, and control the game the user is currently participating in based on the information to be pushed, thereby providing the user with a more intuitive and natural game control experience. For example, when the user is playing a game in the living room and needs to control the character in the game to take a step forward, the user can make Gesture 2 and smile. Then the electronic device can obtain Gesture 2 and the facial expression "smile" and take a picture of the user's environment. Then, the electronic device can determine that the information to be pushed is to control the character in the game to take a step forward in the living room environment in the game based on Gesture 2, the facial expression "smile" , and the user’s environment. After that, the electronic device can control the character in the game to take a step forward in the living room in the game according to the information to be pushed, .

For example, in a virtual reality scene, the electronic device can obtain the user's posture information and voice information as well as the environment information of the user’s real environment, determine the information to be pushed based on the user's posture information and voice information and the environment information of the user’s real environment, control and optimize the content displayed in the virtual reality device used by the user based on the information to be pushed, so as to provide the user with a more realistic and immersive virtual experience. Here, the virtual reality device used by the user and the electronic devices may be the same device or different devices. For example, assuming that the electronic device is the virtual reality device currently used by the user, when the user wears the electronic device and the user takes a step forward in the living room and makes a voice "take a step forward" , then the electronic device can obtain the gesture information "take a step forward" and the voice "take a step forward" , and take a picture of the user's environment. Then, the electronic device can determine that the information to be pushed is to control the character in the virtual scene to take a step forward in the living room environment in the virtual scene based on the gesture information "take a step forward" and the voice "take step forward" as well as the user's environment. After that, the electronic device can control the character in the virtual scene to take a step forward in the living room environment in the virtual scene based on the information to be pushed.

For example, in a real-time recommendation scenario, the user can input text information and voice information based on the electronic device, and the electronic device can obtain the text information and voice information, and obtain the location information of the user's environment. Then, the electronic device can determine the information to be pushed based on the text information, voice information and location information, and display the information to be pushed in the target interactive interface of the electronic device. For example, when the text information is "weather" , the voice information is "how is the weather today" , and the location information is "Region 1" , the electronic device can determine, based on "weather" , "how is the weather today" , and "Region 1" , the information to be pushed as: the weather in Region 1 today is sunny, and display the information to be pushed on the target interactive interface.

For example, in a real-time recommendation scenario, the user can input the voice "Location 1" based on the electronic device and make a gesture "Gesture 3" . Then, the electronic device can obtain "Gesture 3" and the voice "Region 1" , obtain the location information "Location 2" of the user's environment, and determine, based on "Gesture 3" , the voice "Location 1" , and the location information "Location 2" , the information to be pushed as route information from Location 2 to Location 1, and display the information to be pushed on the target interactive interface.

For example, in a real-time recommendation scenario, the electronic device can actively obtain the user's user profile information and preference information as well as the image information of the user's environment, determine the information to be pushed based on the user profile information, preference information and image information, and display the information to be pushed on the target interactive interface of the electronic device. For example, if the user profile information obtained by the electronic device indicates "ever purchased a water cup" , the preference information indicates "like water cups" , and the image information is "Image of Mall 1" , then based on "ever purchased a water cup" , "like water cups" , and "Mall "Image of 1" , the electronic device can determine that the information to be pushed is Store 1 in Mall 1 is selling water cups and the location information of Store 1 in Mall 1, and display the information to be pushed on the target interactive interface.

It should be noted that the electronic device can also display a plurality of pieces of information to be pushed on the target interactive interface at the same time. For example, the electronic device can display "the weather in Region 1 is sunny today" , "route information from Location 2 to Location 1" , and "Store 1 in Mall 1 is selling water cups, and the location information of Store 1 in Mall 1" in the target interactive interface at the same time.

It should be noted that the process for the electronic device to determine the information to be pushed will be introduced in the following embodiments of the present disclosure, details thereof will not be described first here.

In some implementations, FIG. 1 is a schematic diagram showing an application scenario according to an embodiment of the present disclosure. As shown in FIG. 1, the application scenario may include an electronic device 110 and a network device 120. The electronic device 110 can establish a connection with the network device 120 through a wired network or a wireless network.

For example, the electronic device 110 may be a mobile phone, a tablet computer, a desktop, a laptop, a handheld computer, a notebook computer, a vehicle-mounted device, an Ultra-Mobile Personal Computer (UMPC) , a netbook, and a cellular phone, a Personal Digital Assistant (PDA) , an Augmented Reality (AR) /Virtual Reality (VR) device, etc., and the present disclosure is not limited to these examples. The network device 120 may be a server, which may be one server or a server cluster composed of a plurality of servers, or a cloud platform control center, and the present disclosure is not limited to these examples.

For example, the electronic device 110 can transmit a plurality of pieces of interaction information and environment information to the network device 120. Then, the network device 120 can determine correlation information based on the plurality of pieces of interaction information and the environment information, and transmit the correlation information to the electronic device 110, such that the electronic device 110 can determine the correlation information.

In addition, FIG. 1 exemplarily shows one electronic device and one network device. Actually other numbers of electronic devices and network devices may be included, and the present disclosure is not limited to this.

In other implementations, the technical solutions of the present disclosure can be executed by the above electronic device 110, or the technical solutions of the present disclosure can be executed by the above network device 120, and the present disclosure is not limited to this.

After introducing the application scenarios of the technical solutions of the present disclosure, the technical solutions of the present disclosure will be elaborated below:

FIG. 2 is a flowchart illustrating an information interaction method according to an embodiment of the present disclosure. The method can be performed by the electronic device 110 shown in FIG. 1, and the present disclosure is not limited to this. As shown in FIG. 2, the method may include the following steps:

at S210, obtaining a plurality of pieces of interaction information of a target object and obtaining environment information of an environment where the target object is located;

at S220, determining correlation information according to the plurality of pieces of interaction information and the environment information, the correlation information representing a correlation between the plurality of pieces of interaction information and a correlation between the plurality of pieces of interaction information and the environment information;

at S230, determining information to be pushed according to the plurality of pieces of interaction information, the environment information, and the correlation information; and

at S240, pushing the information to be pushed.

In some implementation methods, the target object can be one or more users. When the target object is one user, the plurality of pieces of interaction information of the target object is the plurality of pieces of interaction information of the user. When the target object is a plurality of users, the plurality of pieces of interaction information of the target object includes at least one piece of interaction information of each of the plurality of users.

In some implementations, the target object may be an object in a real environment. For example, the target object may be a person in the real environment. The target object may be an object in a virtual environment. For example, the target object may bepeople in a virtual scene. The environment where the target object is located can be a real environment or a virtual environment. When the environment where the target object is located is a real environment, the environment information can be real environment information. When the environment where the target object is located is a virtual environment, the environment information may be virtual environment information.

In some implementations, the plurality of pieces of interaction information may include at least two of: text information, image information, voice information, gesture information, posture information, face information, a touch operation on an interactive interface, user profile information, preference information, and historical interaction information.

In some implementations, the electronic device may include a plurality of sensors to collect interaction information of the target object and environment information of the environment where the target object is located. For example, the electronic device may include a camera, a microphone, a touch screen, etc.

For example, the user can input text information and image information based on the touch screen of the electronic device, and input voice information based on the microphone of the electronic device. Then, the electronic device can obtain text information, image information, and voice information from the user. In an online shopping scenario, the text information can be a product name, the image information can be a product image, and the voice information can be a product name spoken by the user.

For example, the electronic device can collect the user's touch operation on the interactive interface through the touch screen. The interactive interface can be an interface displayed on the electronic device. The user's touch operation on the interactive interface may be the user's click operation on the text, image or button displayed on the interactive interface, and the present disclosure is not limited to this.

For example, the face information can be human face information, expression information, mouth shape information, etc., and the present disclosure is not limited to this. The electronic device can collect the user's face information, gesture information, and posture information through the camera, thereby obtaining the user's face information, gesture information, and posture information. For example, the user's gesture may be a gesture of spreading fingers, and the user's gesture may be a gesture of raising an arm.

For example, the environment information of the environment where the target object is located may be an environment image of the environment where the target object is located, or location information of the environment where the target object is located, and the present disclosure is not limited to this. For example, the electronic device can take a picture of the user's environment through a camera, thereby obtaining an environment image of the user's environment, and determine the environment image of the user's environment as the environment information of the user's environment. Alternatively, the electronic device can obtain a location of the user's environment and determine it as the environment information of the user's environment.

For example, the profile information may include: the user's permanent address, the user's age and gender, the user's browsing and purchase records, and the user's search records, and the present disclosure is not limited to this. The preference information may include favorite regions and favorite products, and the present disclosure is not limited to this. The historical interaction information can be interaction information the electronic device can obtain in historical time periods. For example, the historical interaction information can include the user's historical browsing records, historical click data on the interactive interface, historical purchase data, etc.

In some implementations, before the above step S210, the method may further include: determining a target interaction mode from a plurality of interaction modes, the plurality of interaction modes including an autonomous interaction mode and an intelligent interaction mode. In response to determining that the target interaction mode is the autonomous interaction mode, the above step S210 may include: obtaining at least two of following information of the target object: text information, image information, voice information, gesture information, posture information, face information, and touch operation on the interactive interface. In response to determining that the target interaction mode is the intelligent interaction mode, the above step S210 may include: obtaining at least two of following information of the target object: user profile information, preference information, and historical interaction information.

For example, when it is determined that the target interaction mode is the intelligent interaction mode, the electronic device can send out inquiry voice information, which is used for conversation with the user to inquire about the user's needs. Afterwards, the electronic device can obtain the user's reply information to the inquiry voice information, and determine the reply information as the plurality of pieces of interaction information of the target object. Here, the reply information may include, but not limited to, at least one of: voice information, text information, picture information, gesture information, and posture information.

For example, as shown in FIG. 3, after the electronic device is started, the electronic device can first display two interaction modes: the autonomous interaction mode and the intelligent interaction mode. Next, the electronic device can obtain the user's selection operation of either one of the above two interaction modes. In response to the selection operation, the electronic device can obtain interaction information corresponding to the interaction mode selected by the user. If the electronic device obtains the user's selection operation for the autonomous interaction mode, the electronic device can determine that the target interaction mode is the autonomous interaction mode. If the electronic device obtains the user's selection operation for the intelligent interaction mode, the electronic device can determine that the target interaction mode is the intelligent interaction mode.

For example, after obtaining the user's selection operation for the autonomous interaction mode, the electronic device can display a target interactive interface corresponding to the autonomous interaction mode. In the target interactive interface, the electronic device can determine the information to be pushed according to the interaction information corresponding to the autonomous interaction mode, and display the information to be pushed in the target interactive interface. The target interactive interface corresponding to the autonomous interaction mode can be as shown in (a) in FIG. 4.

For example, after obtaining the user's selection operation for the intelligent interaction mode, the electronic device can display a target interactive interface corresponding to the intelligent interaction mode. In the target interactive interface, the electronic device can determine the information to be pushed according to the interaction information corresponding to the intelligent interaction mode, and display the information to be pushed in the target interactive interface. The target interactive interface corresponding to the intelligent interaction mode can be as shown in (b) in FIG. 4.

For example, after the electronic device is started, the electronic device can determine the target interaction mode from a plurality of interaction modes according to a current application scenario. For example, the application scenario can be any of the following scenarios: game scenario, shopping scenario, intelligent home appliance usage scenario, and virtual reality scenario. If the electronic device determines that the current application scenario is a game scenario or a virtual reality scenario, the electronic device can determine the target interaction mode as the autonomous interaction mode. If the electronic device determines that the current application scenario is a shopping scenario or an intelligent home appliance usage scenario, the electronic device can determine the target interaction mode as the intelligent interaction mode.

For example, the electronic device can determine whether the user inputs interaction information within a target time length. If the electronic device determines that the user inputs the interaction information within the target time length, the electronic device can determine that the target interaction mode is the autonomous interaction mode. If the electronic device determines that the user does not input the interaction information within the target time length, the electronic device can determine that the target interaction mode is the intelligent interaction mode. The target time length may be 30 minutes, and the present disclosure is not limited to this.

For example, as shown in FIG. 5, the electronic device can determine the information to be pushed corresponding to the autonomous interaction mode based on the interaction information corresponding to the autonomous interaction mode, and determine the information to be pushed corresponding to the intelligent interaction mode based on the interaction information corresponding to the intelligent interaction mode, and display both the information to be pushed corresponding to the autonomous interaction mode and the information to be pushed corresponding to the intelligent interaction mode in the target interactive interface.

It can be appreciated that the autonomous interaction mode can also be referred to as "user to scenario" mode. In the autonomous interaction mode, the user can actively input interaction information such as text information and a touch operation on the interactive interface based on the electronic device. The electronic device can determine the information to be pushed according to the interaction information actively inputted by the user. For example, in the autonomous interaction mode, the user can enter keywords in a search engine of the electronic device, or select filtering conditions such as category, price, brand, etc. in an e-commerce platform installed on the electronic device. Next, the electronic device can obtain the keywords inputted by the user or the filtering conditions selected by the user, determine products or services that meet the user's requirements, determine the information to be pushed based on the products or services that meet the user's requirements, and push the information to be pushed. The intelligent interaction mode can also be referred to as "scenario to user" mode. In the intelligent interaction mode, the electronic device can directly determine the information to be pushed based on the user profile information, preference information and historical interaction information, so as to actively push the push information to the user.

The main difference between the autonomous interaction mode and the intelligent interaction mode lies in the way the interaction information is obtained and the degree of user participation. In the autonomous interaction mode, the interaction information obtained by the electronic device is mainly information actively inputted by the user, with a high degree of user participation. The autonomous interaction mode has the characteristics of user autonomy and flexibility, and requires the user to have a certain level of information retrieval and filtering capabilities. In the intelligent interaction mode, the interaction information obtained by the electronic device is mainly obtained actively by the electronic device. The intelligent interaction mode is more intelligent than the autonomous interaction mode.

In the above embodiments, the electronic device can provide a plurality of interaction modes, thereby improving the diversity of interactions and providing the user with a more comprehensive and efficient service experience.

In some implementations, as shown in FIG. 6, the target interactive interface may include: a text input box, a voice input box, and a picture input box. The user can input interaction information based on the text input box, voice input box or picture input box, such that the electronic device can obtain the interaction information of the target object.

It should be noted that the present disclosure is not limited to specific positions and specific styles of the text input box, voice input box, and picture input box in the target interactive interface.

In some implementations, the electronic device can use correlation values to represent correlations between the plurality of pieces of interaction information. The higher the correlation between two pieces of interaction information, the greater the correlation values corresponding to the two pieces of interaction information. The electronic device can use a correlation value to represent the correlation between the interaction information and the environment information. The higher the correlation between the interaction information and the environment information, the greater the correlation value corresponding to the interaction information and the environment information.

In some implementations, the electronic device can determine template correlation information in advance, and the template correlation information can include: a template correlation value between interaction information, a template correlation value between interaction information and environment information. Then, when the electronic device performs the above step S220, the electronic device can determine the correlation information based on the template correlation information.

For example, the electronic device may determine in advance that the template correlation information includes: a correlation value between Gesture 1 and Voice 1 is 5, a correlation value between Gesture 2 and Voice 1 is 10, a correlation value between Gesture 1 and Text 1 is 9, a correlation value between Gesture 1 and Location 1 is 5, a correlation value between Voice 1 and Location 1 is 10, and a correlation value between Gesture 2 and Location 1 is 10. Assuming that the plurality of pieces of interaction information of the target object obtained by the electronic device are Gesture 1 and Voice 1, and the environment information of the environment where the target object is located is Location 1, then the electronic device can look for the correlation information corresponding to Gesture 1, Voice 1 and Location 1 from the template correlation information, and determine the correlation information as follows: the correlation value between Gesture 1 and Voice 1 is 5, the correlation value between Gesture 1 and Location 1 is 5, and the correlation value between Voice 1 and Location 1 is 10.

In the above embodiment, the electronic device can determine the template correlation information in advance, such that when performing the step S220, the correlation information can be determined more efficiently and quickly based on the template correlation information, thereby improving interaction efficiency.

In some implementations, the above step S230 may include: determining a target feature vector according to the plurality of pieces of interaction information and the environment information; and determining the information to be pushed according to the target feature vector and the correlation information.

For example, the electronic device can determine the target feature vector according to the plurality of pieces of interaction information and the environment information in any of the following non-limiting schemes:

Scheme 1: The electronic device can perform data fusion on the plurality of pieces of interaction information and the environment information to obtain first information. Then, the electronic device can perform feature extraction on the first information to obtain the target feature vector.

Scheme 2: The electronic device can perform feature extraction on each of the plurality of pieces of interaction information to obtain a plurality of first feature vectors, and perform feature extraction on the environment information to obtain a second feature vector. Then, the electronic device can perform feature fusion on the plurality of first feature vectors and the second feature vector to obtain the target feature vector.

For example, the electronic device can first train a machine learning model based on a deep learning algorithm, and then the electronic device can perform feature extraction on the interaction information, environment information, or first information based on the trained machine learning model.

For example, the electronic device may perform feature fusion on the plurality of first feature vectors and the second feature vector by concatenating the plurality of first feature vectors and the second feature vector, and the present disclosure is not limited to this.

For example, said the electronic device performing data fusion on the plurality of pieces of interaction information and the environment information to obtain the first information may include: the electronic device first determining values corresponding to the plurality of pieces of interaction information and the environment information, and then combining the values corresponding to the plurality of pieces of interaction information and the environment information to obtain the first information.

It can be appreciated that when the interaction information includes image information, the target feature vector can represent features such as a color histogram and a texture in the image information. When the interaction information includes voice information, the target feature vector can represent features such as frequency, energy and zero-crossing rate of the sound. When the interaction information includes a touch operation, the target feature vector can represent features such as touch point, moving speed, and acceleration corresponding to the touch operation. Therefore, the electronic device can infer the content the user likes or desires based on the features in the interaction information and environment information as represented by the target feature vector, and thereby determining the information to be pushed based on the content the user likes or desires.

Exemplarily, the above operation of determining the information to be pushed according to the target feature vector and the correlation information may include: determining a plurality of element combinations in the target feature vector, each element combination representing features of one of the plurality of pieces of interaction information and the environment information; determining, according to the correlation information, a first similarity between each of a plurality of first element combinations and a target element combination, the target element combination being any of the plurality of element combinations, and each of the plurality of first element combinations being any of the plurality of element combinations other than the target element combination; determining whether the plurality of first similarities corresponding to the target element combination are all greater than a predetermined similarity; and determining the information to be pushed based on the target feature vector in response to determining that the plurality of first similarities corresponding to the target element combination are all greater than the predetermined similarity; or adjusting the target element combination to obtain an adjusted target feature vector in response to determining that not all of the plurality of first similarities corresponding to the target element combination are greater than the predetermined similarity, such that a plurality of first similarities corresponding to the adjusted target element combination are all greater than the predetermined similarity, and determining the information to be pushed based on the adjusted target feature vector. In this way, the electronic device can adjust the target feature vector based on the correlation information to ensure that the target feature vector can more accurately reflect the features of the interaction information and environment information, such that the information to be pushed can be determined more accurately and the interaction effect can be improved.

For example, the electronic device may determine a correlation value between two pieces of interaction information as a first similarity between respective element combinations of the two pieces of interaction information, and determine the correlation value between the interaction information and the environment information as a first similarity between respective element combinations of the interaction information and the environment information.

For example, it is assumed that the plurality of pieces of interaction information obtained by the electronic device are Gesture 1 and Voice 1, and the obtained environment information is Location 1. The electronic device performs feature extraction on Gesture 1 and Voice 1 based on Machine Learning Model 1, to obtain a first feature vector corresponding to Gesture 1 as (0, 0, 1) , and a first feature vector corresponding to Voice 1 as (0, 1, 1) , and performs feature extraction on a second feature vector corresponding to Location 1 based on Machine Learning Model 2, to obtain a second feature vector corresponding to Location 1 as (1, 1, 1) . Then, the electronic device can concatenate the above three feature vectors to obtain the target feature vector as (0, 0, 1, 0, 1, 1, 1, 1, 1) . Next, the electronic device can determine that the element combination in the target feature vector that represents the features of Gesture 1 is {0, 0, 1} , the element combination that represents the features of Voice 1 is {0, 1, 1} , and the element combination that represents the features of Location 1 is {1, 1, 1} . Assuming that the electronic device determines the correlation information as: the correlation value between Gesture 1 and Voice 1 is 5, the correlation value between Gesture 1 and Location 1 is 5, and the correlation value between Voice 1 and Location 1 is 10, then the electronic device can determine, based on the correlation information, that the first similarity between the element combination {0, 0, 1} and the element combination {0, 1, 1} is 5, the first similarity between the element combination {0, 0, 1} and the element combination {1, 1, 1} is 5, and the first similarity between the element combination {0, 1, 1} and the element combination {1, 1, 1} is 10. Assuming that the predetermined similarity is 6, taking the target element combination as the element combination corresponding to Gesture 1 as an example, the electronic device can determine neither of the first similarity between the element combination {0, 0, 1} and the element combination {0, 1, 1} and the first similarity between the element combination {0, 0, 1} and the element combination {1, 1, 1} is greater than the predetermined similarity, and then the electronic device can adjust the target element combination to obtain the adjusted the target element combination as {1, 0, 1} . Then, the electronic device can determine that the interaction information corresponding to the element combination {1, 0, 1} is Gesture 2, and determine the correlation value between Gesture 2 and Voice 1 as 10 and the correlation value between Gesture 2 and Location 1 is 10, so as to determine that the first similarity between the element combination {1, 0, 1} and the element combination {0, 1, 1} is 10, and the first similarity between the element combination {1, 0, 1} and the element combination {1, 1, 1} is 10. That is, the electronic device can determine that the plurality of first similarities corresponding to the adjusted target element combination {1, 0, 1} are all greater than the predetermined similarity, and the electronic device can determine that the adjusted target feature vector is (1, 0, 1, 0, 1, 1, 1, 1, 1) . Then, the electronic device can determine the information to be pushed based on the target feature vector.

In some implementations, before the step S230, the electronic device can perform data preprocessing on the plurality of pieces of interaction information and the environment information. Specifically, the electronic device can perform noise reduction processing and image enhancement processing on image information, perform filter processing and noise reduction processing on the voice information, and perform filtering and denoising processing on the touch operation, to remove noise in the interaction information, thereby improving data quality and reducing noise interference, so as to more accurately determine the data to be pushed.

In some implementations, the electronic device can determine a correspondence between the target feature vector and the information to be pushed in advance, and then the electronic device can determine the information to be pushed based on the correspondence and the target feature vector.

For example, assuming that the correspondence determined in advance by the electronic device include: Feature Vector 1 corresponding to adjusting the living room temperature to 25 degrees, and Feature Vector 1 corresponding to turning on Desk Lamp 1. If the electronic device determines that the target feature vector is Feature Vector 1, the electronic device can look for Feature Vector 1 in the correspondence and determine that Feature Vector 1 corresponds to adjusting the living room temperature to 25 degrees. Then the electronic device can determine that the information to be pushed is to adjust the living room temperature to 25 degrees.

In the above embodiments, the electronic device can fuse and extract features from the plurality of pieces of interaction information and the environment information to obtain a higher-dimensional target feature vector, thereby representing the intention of the target object in a more comprehensive, accurate and diverse manner, and determining the information to be pushed more intelligently and accurately. For example, for a visually impaired user, the information to be pushed to the user can be determined through sound and tactile interaction, that is, based on the voice information and the touch operation.

In some implementations, the electronic device can use natural language processing technology to process the text information or voice information in the interaction information and the environment information to obtain a processing result. Then, the electronic device can infer the user's language intention based on the processing result and the correlation information, thereby determining the information to be pushed based on the user's language intention. The natural language processing technology may include: word segmentation technology, part-of-speech tagging technology, named entity recognition technology, syntactic analysis technology, etc.

For example, the electronic device can convert the text inputted by the user and the text in the environment information into a form that can be processed by a computer, and infer the user's language intention based on the form that can be processed by a computer. For example, word segmentation processing can be performed on the user input "how will the weather be in Region 1 tomorrow? " , to obtain words such as "tomorrow" , "Region 1" , "weather" , etc., and named entity recognition can be performed on these words to obtain the time "tomorrow" , the place name "Region 1" , and the event "weather" . Word segmentation processing can be performed on the text "the current location is Region 1" in the environment information to obtain words such as "location" and "Region 1" , and named entity recognition can be performed on these words to obtain the time "location" and the place name "Region 1" . Based on the above word segmentation processing result, the correlation information can be determined as: the text inputted by the user is related to the text of the environment information. It can thus be inferred that the user's language intention is to query the weather condition of Region 1 tomorrow, and the information to be pushed can be determined as the weather condition of Region 1 tomorrow.

In some implementations, the electronic device can use a classification model to classify the interaction information and the environment information, thereby inferring the user's intention and requirement, and determining the information to be pushed based on the user's intention and requirement. Here, the electronic device can first train the classification model based on historical data, so as to improve the accuracy and efficiency of the classification model and thereby more accurately inferring the user's intention and requirement. For example, the classification model can classify the interaction information and the environment information into types such as "query type" , "consultation type" or "purchase type" , thereby inferring the user's intention and requirement based on the classification type.

In some implementations, the electronic device can match the interaction information and the environment information with existing templates, thereby inferring the user's intention and requirement, and determining the information to be pushed based on the user's intention and requirement. For example, if the user inputs "check the weather tomorrow" , the electronic device can match "check the weather tomorrow" with a "weather query" template, thereby inferring that the user's intention and requirement is to query the weather.

In some implementations, the electronic device can process the interaction information and the environment information based on rule-based semantic analysis technology, thereby inferring the user's intention and requirement, and determining the information to be pushed based on the user's intention and requirement. For example, electronic devices can use the rule-based semantic analysis technology to formulate specific rules for each application scenario. After obtaining the interaction information and the environment information, the electronic device can first determine the application scenario corresponding to the interaction information and the environment information, determine the rules according to the application scenario, and analyze the interaction information and the environment information according to the rules to infer the user's intention and requirement.

In some implementations, the electronic device can process image information based on image processing technology, and determine the information to be pushed based on the processing result, the environment information, and the correlation information. For example, the electronic device can process photos uploaded by the user using facial recognition technology to identify the people in the photos and extract relevant information.

In some implementations, when the text information includes data currently inputted by the user and historical text information, the electronic device can use the data currently inputted by the user and the historical text information as context information to establish a context information model, perform intent classification prediction on the data currently inputted by the user and the historical text information, output a prediction result, and determine the information to be pushed based on the prediction result. For example, the context information model may be a recurrent neural network model.

For example, when the data inputted by the user is "apple" , if the electronic device only considers "apple" when determining the information to be pushed, it will be difficult to determine what the user's specific intention is. However, if the user's historical query information is also taken into account, for example, if the historical query information is information related to the origin of fruit, then the electronic device can determine from the historical query information and the above user inputted data "apple" that the user's intention is to query the origin of apples. Therefore, intention analysis based on the context information can improve the intelligence of interaction and personalized service capabilities, so as to avoid misjudgment, and improve the accuracy and reliability of interaction.

In some implementations, the above step S240 may include at least one of the following: displaying the information to be pushed and playing the information to be pushed.

For example, when the information to be pushed is in the form of image and text, the electronic device can display the information to be pushed. When the information to be pushed is in the form of voice or video, the electronic device can play the information to be pushed.

In some implementations, the above step S240 may include: displaying the information to be pushed in the target interactive interface.

In some implementations, the interactive interface of the electronic device and the interactive effect of the interactive interface can be constructed and laid out based on front-end interfacing and interacting technologies such as HTML, CSS, JavaScript, HTML, CSS, and JavaScript.

In some implementations, the front-end interface and components of the electronic device can be created and the responsive layout of the interactive interface of the electronic device can be implemented based on front-end frameworks such as React and Angular JS.

In some implementations, based on visualization libraries and data visualization technologies such as D3. js and Echarts, the information to be pushed can be displayed in the form of visual charts to improve the user experience.

In some implementations, dynamic User Interface (UI) generation technology can be used to push the information to be pushed to the interactive interface of the electronic device, such that the user can obtain the information to be pushed through the interactive interface.

In some implementations, the layout and style of the interactive interface of the electronic device can be automatically adjusted based on UI adaption technology, such that the interactive interface can be adapted to the size and screen resolution of the electronic device. For example, the UI adaption technology can include Flexbox layout and media query.

In some implementations, the interactive interface in intelligent interaction mode can be created based on front-end frameworks such as React and Angular JS. The interactive interface in the autonomous interaction mode can be created based on responsive web design, GUI generator, user interface template library, dynamic user interface generator, open source UI component library, etc.

In some implementations, the electronic device can push the information to be pushed based on machine learning and deep learning technologies. For example, when the information to be pushed includes an image, the electronic device can use a Generative Adversarial Network (GAN) to generate the image in the information to be pushed. Alternatively, when the information to be pushed includes text, the electronic device can use a Recurrent Neural Network (RNN) to generate the text in the information to be pushed.

In some implementations, in order to achieve multi-end adaptation, cross-platform development technology, such as React Native, Flutter, Electron and other cross-platform development frameworks, can be used to write codes corresponding to the technical solutions of the present disclosure, such that the technical solutions of the present disclosure can be executed on a variety of terminals and platforms, thereby reducing development and maintenance costs and ensuring that the user can obtain a unified experience from different electronic devices.

In some implementations, the electronic device may include: a multi-mode scenario perception module, a user intention analysis module, a dynamic interface generation module, and a multi-end adaptation module. Here, the multi-mode scenario perception module can be configured to obtain a plurality of pieces of interaction information of a target object and obtain environment information of an environment where the target object is located. The user intention analysis module can be configured to determine correlation information based on the plurality of pieces of interaction information and the environment information, and determine the information to be pushed based on the plurality of pieces of interaction information, the environment information and the correlation information. The dynamic interface generation module and the multi-end adaptation module can be configured to push the information to be pushed.

It should be noted that all the above technical solutions can be combined in any way to form optional embodiments of the present disclosure, and description thereof will be omitted here.

It should be noted that in the above embodiments, relevant data such as voice, images, text, geographical location, etc., has obtained user permission, consent or authorization, and comply with relevant laws, regulations and standards.

FIG. 7 is a schematic diagram showing an information interaction apparatus 700 according to an embodiment of the present disclosure. As shown in FIG. 7, the information interaction apparatus 700 includes:

an obtaining module 710 configured to obtain a plurality of pieces of interaction information of a target object and obtain environment information of an environment where the target object is located;

a first determining module 720 configured to determine correlation information according to the plurality of pieces of interaction information and the environment information, the correlation information representing a correlation between the plurality of pieces of interaction information and a correlation between the plurality of pieces of interaction information and the environment information;

a second determining module 730 configured to determine information to be pushed according to the plurality of pieces of interaction information, the environment information, and the correlation information; and

a pushing module 740 configured to push the information to be pushed.

In some implementations, the second determining module 730 may be configured to determine a target feature vector according to the plurality of pieces of interaction information and the environment information; and determine the information to be pushed according to the target feature vector and the correlation information.

In some implementations, the second determining module 730 may be configured to perform data fusion on the plurality of pieces of interaction information and the environment information to obtain first information; and perform feature extraction on the first information to obtain the target feature vector.

In some implementations, the second determining module 730 may be configured to perform feature extraction on each of the plurality of pieces of interaction information to obtain a plurality of first feature vectors; perform feature extraction on the environment information to obtain a second feature vector; and perform feature fusion on the plurality of first feature vectors and the second feature vector to obtain the target feature vector.

In some implementations, the second determining module 730 may be configured to determine a plurality of element combinations in the target feature vector, each element combination representing features of one of the plurality of pieces of interaction information and the environment information; determine, according to the correlation information, a first similarity between each of a plurality of first element combinations and a target element combination, the target element combination being any of the plurality of element combinations, and each of the plurality of first element combinations being any of the plurality of element combinations other than the target element combination; determine whether a plurality of first similarities corresponding to the target element combination are all greater than a predetermined similarity; and determine the information to be pushed based on the target feature vector in response to determining that the plurality of first similarities corresponding to the target element combination are all greater than the predetermined similarity; or adjust the target element combination to obtain an adjusted target feature vector in response to determining that not all of the plurality of first similarities corresponding to the target element combination are greater than the predetermined similarity, such that a plurality of first similarities corresponding to the adjusted target element combination are all greater than the predetermined similarity, and determine the information to be pushed based on the adjusted target feature vector.

In some implementations, the plurality of pieces of interaction information may include at least two of: text information, image information, voice information, gesture information, posture information, face information, touch operation on an interactive interface, user profile information, preference information, and historical interaction information. The information interaction apparatus 700 may further include: a third determining module 750 configured to determine a target interaction mode from a plurality of interaction modes, the plurality of interaction modes including an autonomous interaction mode and an intelligent interaction mode. In response to determining that the target interaction mode is the autonomous interaction mode, the obtaining module 710 may be configured to: obtain at least two of following information of the target object: text information, image information, voice information, gesture information, posture information, face information, and touch operation on the interactive interface. In response to determining that the target interaction mode is the intelligent interaction mode, the obtaining module 710 may be configured to obtain at least two of following information of the target object: user profile information, preference information, and historical interaction information.

It should be understood that the apparatus embodiments and the method embodiments may correspond to each other, and for similar descriptions, reference can be made to the method embodiments and the details will be omitted here for simplicity. Specifically, the apparatus 700 shown in FIG. 7 can execute the above method embodiments, and the above and other operations and/or functions of the respective modules in the apparatus 700 are provided to implement the corresponding processes in the above method, and for the sake of brevity, details thereof will be omitted here.

The apparatus 700 according to the embodiment of the present disclosure has been described above from the perspective of functional modules in conjunction with the figures. It should be understood that these functional modules can be implemented in the form of hardware, by means of instructions in the form of software, or as a combination of hardware and software modules. In particular, the steps of the above method embodiments of the present disclosure can be implemented by hardware integrated logic circuits in a processor or instructions in the form of software. The steps of the methods disclosed in the embodiments of the present disclosure may be directly embodied as being performed and completed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. Optionally, the software modules can be located in a known storage medium in the related art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or register. The storage medium can be located in the memory, and the processor can read information from the memory and perform the steps of the above methods in combination with its hardware.

As shown in FIG. 8, the electronic device 800 may include a memory 810 and a processor 820. The memory 810 is configured to store a computer program and transmit program codes to the processor 820. In other words, the processor 820 can call and run the computer program from the memory 810 to implement the methods in the embodiments of the present disclosure.

For example, the processor 820 may be configured to execute the above method embodiments according to instructions in the computer program.

In some embodiments of the present disclosure, the processor 820 may include, but not limited to, a general purpose processor, a Digital Signal Processor (DSP) , an Application Specific Integrated Circuit (ASIC) , a Field Programmable Gate Array (FPGA) or another programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component.

In some embodiments of the present disclosure, the memory 810 may include, but not limited to, a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Here, the non-volatile memory may be a Read-Only Memory (ROM) , a Programmable ROM (PROM) , an Erasable PROM (EPROM) , an Electrically EPROM (EEPROM) , or a flash memory. The volatile memory may be a Random Access Memory (RAM) , which is used as an external cache. As illustrative, rather than limiting, examples, many forms of RAMs are available, including Static RAM (SRAM) , Dynamic RAM (DRAM) , Synchronous DRAM (SDRAM) , Double Data Rate SDRAM (DDR SDRAM) , Enhanced SDRAM (ESDRAM) , Synchlink DRAM (SLDRAM) ) , and Direct Rambus RAM (DR RAM) .

In some embodiments of the present disclosure, the computer program can be divided into one or more modules, and the one or more modules may be stored in the memory 810 and executed by the processor 820 to complete the methods according to the present disclosure. The one or more modules may be a series of computer program instruction segments capable of completing specific functions. The instruction segments are used to describe the execution process of the computer program in the electronic device.

As shown in FIG. 8, the electronic device may further include: a transceiver 830, which may be connected to the processor 820 or the memory 810.

Here, the processor 820 can control the transceiver 830 to communicate with other devices. Specifically, it can send information or data to other devices, or receive information or data sent by other devices. The transceiver 830 may include a transmitter and a receiver. The transceiver 830 may further include one or more antennas.

It should be understood that various components in the electronic device are connected through a bus system. In addition to a data bus, the bus system further includes a power bus, a control bus, and a status signal bus.

The present disclosure further provides a computer storage medium having a computer program stored thereon. When the computer program is executed by a computer, the computer can perform the methods according to the above method embodiments. In other words, an embodiment of the present disclosure also provide a computer program product containing instructions which, when executed by a computer, cause the computer to perform the methods according to the above method embodiments.

When implemented in software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present disclosure are generated. The computer may be a general purpose computer, a special purpose computer, a computer network, or any other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from a website, computer, server, or data center to another website, computer, server, or data center via wired communication (e.g., coaxial cable, optical fiber, or Digital Subscriber Line (DSL) ) or wireless communication (e.g., infrared, wireless, microwave, etc. ) . The computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device including one or more available mediums, such as a server, a data center, etc. The available mediums may include magnetic mediums (e.g., floppy disks, hard disks, magnetic tapes) , optical medium (e.g., Digital Video Disc (DVD) ) , or semiconductor mediums (e.g., Solid State Disk (SSD) ) , etc.

It can be appreciated by those skilled in the art that modules and algorithm steps in the examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware or any combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on specific applications and design constraint conditions of the technical solutions. Those skilled in the art may use different methods for each specific application to implement the described functions, and such implementation is to be encompassed by the scope of this disclosure.

In the embodiments of the present disclosure, it can be appreciated that the disclosed systems, devices, and methods may be implemented in other ways. For example, the device embodiments described above are illustrative only. For example, the divisions of the modules are only divisions based on logical functions, and there may be other divisions in actual implementations. For example, more than one module or component may be combined or integrated into another system, or some features can be ignored or omitted. In addition, the mutual coupling or direct coupling or communicative connection as shown or discussed may be indirect coupling or communicative connection between devices or modules via some interfaces which may be electrical, mechanical, or in any other forms.

The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be co-located or distributed across a number of network elements. Some or all of the modules may be selected according to actual needs to achieve the objects of the solutions of the embodiments. For example, the functional modules in the embodiments of the present disclosure may be integrated into one processing module, or alternatively be separate physical modules, or two or more modules may be integrated into one module.

While the specific embodiments of the present disclosure have been described above, the scope of the present disclosure is not limited to these embodiments. Various variants and alternatives can be made by those skilled in the art without departing from the scope of the present disclosure. These variants and alternatives are to be encompassed by the scope of the present disclosure as defined by the claims as attached.

Claims

An information interaction method, comprising:

obtaining a plurality of pieces of interaction information of a target object and obtaining environment information of an environment where the target object is located;

determining correlation information according to the plurality of pieces of interaction information and the environment information, the correlation information representing a correlation between the plurality of pieces of interaction information and a correlation between the plurality of pieces of interaction information and the environment information;

determining information to be pushed according to the plurality of pieces of interaction information, the environment information, and the correlation information; and

pushing the information to be pushed.
The method according to claim 1, wherein said determining the information to be pushed according to the plurality of pieces of interaction information, the environment information, and the correlation information comprises:

determining a target feature vector according to the plurality of pieces of interaction information and the environment information; and

determining the information to be pushed according to the target feature vector and the correlation information.
The method according to claim 2, wherein said determining the target feature vector according to the plurality of pieces of interaction information and the environment information comprises:

performing data fusion on the plurality of pieces of interaction information and the environment information to obtain first information; and

performing feature extraction on the first information to obtain the target feature vector.
The method according to claim 2, wherein said determining the target feature vector according to the plurality of pieces of interaction information and the environment information comprises:

performing feature extraction on eachof the plurality of pieces of interaction information to obtain a plurality of first feature vectors;

performing feature extraction on the environment information to obtain a second feature vector; and

performing feature fusion on the plurality of first feature vectors and the second feature vector to obtain the target feature vector.
The method according to any one of claims 2 to 4, wherein said determining the information to be pushed according to the target feature vector and the correlation information comprises:

determining a plurality of element combinations in the target feature vector, each element combination representing features of one of the plurality of pieces of interaction information and the environment information;

determining, according to the correlation information, a first similarity between each of a plurality of first element combinations and a target element combination, the target element combination being any of the plurality of element combinations, and each of the plurality of first element combinations being any of the plurality of element combinations other than the target element combination;

determining whether the plurality of first similarities corresponding to the target element combination are all greater than a predetermined similarity; and

determining the information to be pushed based on the target feature vector in response to determining that the plurality of first similarities corresponding to the target element combination are all greater than the predetermined similarity; or

adjusting the target element combination to obtain an adjusted target feature vector in response to determining that not all of the plurality of first similarities corresponding to the target element combination are greater than the predetermined similarity, such that a plurality of first similarities corresponding to the adjusted target element combination are all greater than the predetermined similarity, and determining the information to be pushed based on the adjusted target feature vector.
The method according to any one of claims 1 to 4, wherein the plurality of pieces of interaction information comprise at least two of: text information, image information, voice information, gesture information, posture information, face information, touch operation on an interactive interface, user profile information, preference information, and historical interaction information, and wherein the method further comprises, prior to obtaining the plurality of pieces of interaction information of the target object:

determining a target interaction mode from a plurality of interaction modes, the plurality of interaction modes comprising an autonomous interaction mode and an intelligent interaction mode, and

in response to determining that the target interaction mode is the autonomous interaction mode, said obtaining the plurality of pieces of interaction information of the target object comprises:

obtaining at least two of following information of the target object: text information, image information, voice information, gesture information, posture information, face information, and touch operation on the interactive interface;

in response to determining that the target interaction mode is the intelligent interaction mode, said obtaining the plurality of pieces of interaction information of the target object comprises:

obtaining at least two of following information of the target object: user profile information, preference information, and historical interaction information.
An information interaction apparatus, comprising:

an obtaining module configured to obtain a plurality of pieces of interaction information of a target object and obtain environment information of an environment where the target object is located;

a first determining module configured to determine correlation information according to the plurality of pieces of interaction information and the environment information, the correlation information representing a correlation between the plurality of pieces of interaction information and a correlation between the plurality of pieces of interaction information and the environment information;

a second determining module configured to determine information to be pushed according to the plurality of pieces of interaction information, the environment information, and the correlation information; and

a pushing module configured to push the information to be pushed.
An electronic device, comprising:

a processor and a memory, wherein the memory is configured to store a computer program, the processor is configured to call and run the computer program stored in the memory to perform the method according to any one of claims 1to6.
A computer-readable storage medium for storing a computer program, the computer program causing a computer to perform the method according to any one of claims 1to6.
A computer program product containing instructions, the computer program product, when running on an electronic device, causing the electronic device to perform the method accordingto any one of claims 1to6.