Intelligent interaction method and device, electronic equipment and computer storage medium

Abstract

The invention discloses an intelligent interaction method and device, electronic equipment and a computer storage medium. The method comprises the following steps: acquiring target interaction information; the target interaction information comprises at least one of the following information: target problem information, target control information for the target camera equipment, and target event information corresponding to the target camera equipment; analyzing the target interaction information by using the target large model to obtain target task information, and obtaining a target interaction result corresponding to the target interaction information based on the target task information; and displaying the target page based on the target interaction result. According to the method, various interaction functions can be provided for the user, diversified interaction requirements of the user are met, the target interaction information can be analyzed by using the target large model, the intention of the user is fully understood, and the intelligence and convenience of interaction are improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence and intelligent camera technology, and in particular to an intelligent interaction method, device, electronic device and computer storage medium. Background Art

[0002] With the rapid development of technologies such as artificial intelligence and the Internet of Things, modern people have higher and higher requirements for the quality of life, and the demand for home security, pet care, and elderly care is also growing. As an important part of smart homes, smart cameras are becoming more and more widely used. At the same time, as the pace of work accelerates, people need more convenient and efficient tools to assist their daily lives and work, so higher requirements are placed on the efficient and fast application of smart cameras. Summary of the invention

[0003] The embodiments of the present application provide an intelligent interaction method, device, electronic device and computer storage medium. The intelligent interaction method can not only provide users with multiple interaction functions to meet users' diverse interaction needs, but also use a large target model to analyze target interaction information, fully understand users' intentions, and improve the intelligence and convenience of interaction.

[0004] In a first aspect, an embodiment of the present application provides an intelligent interaction method, including:

[0005] Obtain target interaction information; the target interaction information includes at least one of the following: target problem information, target control information for a target camera device, and target event information corresponding to the target camera device;

[0006] Analyze the target interaction information using the target big model to obtain target task information, and obtain the target interaction result corresponding to the target interaction information based on the target task information;

[0007] The target page is displayed based on the above target interaction results.

[0008] In a possible implementation, the target interaction information includes target event information corresponding to the target camera device; the target event information includes video event information obtained by detecting video data collected by the target camera device;

[0009] The target interaction information is analyzed by using the target big model to obtain target task information, and the target interaction result corresponding to the target interaction information is obtained based on the target task information, including:

[0010] Using the target big model, sentiment analysis is performed on the target event information to obtain target sentiment information, and corresponding target sentiment prompt information is generated based on the target sentiment information;

[0011] The target page is displayed based on the target interaction result, including:

[0012] The target interaction page is displayed based on the above target emotion prompt information.

[0013] In a possible implementation manner, the obtaining of target interaction information includes:

[0014] receiving target interaction information input by a target user based on a smart entry in a target application page; the target application page is a page of a target application associated with a target camera device; or

[0015] Receiving a target trigger operation for the smart entrance in the target application page, entering a target interaction page in response to the target trigger operation, and receiving target interaction information input by the target user based on the target interaction page; or

[0016] Receive target event information sent by the target camera device; the target event information includes video event information obtained by detecting video data collected by the target camera device and / or status event information obtained by detecting the status of the target camera device.

[0017] In a possible implementation, the target interaction page includes a function prompt area and / or a question recommendation area; the function prompt area includes one or more function description information; the question recommendation area includes one or more question recommendation description information.

[0018] In a possible implementation, the target interaction information includes target question information;

[0019] The target interaction information is analyzed by using the target big model to obtain target task information, and the target interaction result corresponding to the target interaction information is obtained based on the target task information, including:

[0020] Analyze the target question information using the target big model to obtain target question-answering task information, and generate a target question-answering result corresponding to the target question information based on the target question-answering task information;

[0021] The target page is displayed based on the target interaction result, including:

[0022] The target page is displayed based on the above target question and answer results.

[0023] In a possible implementation, the target interaction information includes target control information for a target camera device;

[0024] The target interaction information is analyzed by using the target big model to obtain target task information, and the target interaction result corresponding to the target interaction information is obtained based on the target task information, including:

[0025] Analyze the target control information using the target big model to obtain target control task information, and generate corresponding target control instructions based on the target control task information;

[0026] The target page is displayed based on the target interaction result, including:

[0027] In the case that the target control instruction is a target page jump instruction, in response to the target control instruction, the program jumps to the target page corresponding to the target page jump instruction.

[0028] In a possible implementation, after analyzing the target control information using the target big model to obtain target control task information and generating corresponding target control instructions based on the target control task information, the method further includes:

[0029] In the case that the target control instruction is a control instruction for the target imaging device, in response to the target control instruction, the target imaging device is controlled to execute a target action corresponding to the target control instruction.

[0030] In a possible implementation, the target interaction information includes target event information corresponding to the target camera device; the target event information includes multiple video event information obtained by detecting video data collected by the target camera device within a target time period;

[0031] The target interaction information is analyzed by using the target big model to obtain target task information, and the target interaction result corresponding to the target interaction information is obtained based on the target task information, including:

[0032] Using the target big model, the above-mentioned multiple video event information is summarized and analyzed to obtain target analysis report generation task information, and based on the above-mentioned target analysis report generation task information, a target event analysis report corresponding to the above-mentioned target camera device in the above-mentioned target time period is generated;

[0033] The target page is displayed based on the target interaction result, including:

[0034] The target page is displayed based on the above target event analysis report.

[0035] In a possible implementation, the target interaction information includes target event information corresponding to the target camera device; the target event information includes state event information obtained by detecting the state of the target camera device;

[0036] After acquiring the target interaction information, the method further includes:

[0037] The device status prompt information is issued according to the above status event information.

[0038] In a possible implementation manner, the obtaining of target interaction information includes:

[0039] Obtain voice interaction information;

[0040] Perform voiceprint recognition on the above voice interaction information to obtain target voiceprint features;

[0041] If the target voiceprint feature matches the preset voiceprint feature, the voice interaction information corresponding to the target voiceprint feature is determined as the target interaction information.

[0042] In a second aspect, an embodiment of the present application provides an intelligent interaction device, including:

[0043] An acquisition module, used for acquiring target interaction information; the target interaction information includes at least one of the following: target problem information, target control information for a target camera device, and target event information corresponding to the target camera device;

[0044] An analysis module is used to analyze the target interaction information using a target macro model to obtain target task information, and obtain a target interaction result corresponding to the target interaction information based on the target task information;

[0045] The display module is used to display the target page based on the above target interaction result.

[0046] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory; wherein the memory stores executable program code, and the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method steps provided in the first aspect of the embodiment of the present application.

[0047] In a fourth aspect, an embodiment of the present application provides a computer storage medium, wherein the computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method steps provided in the first aspect of the embodiment of the present application.

[0048] The beneficial effects brought about by the technical solutions provided by some embodiments of the present application include at least:

[0049] In the embodiment of the present application, by receiving target interaction information, using the target macro model, analyzing the target interaction information, obtaining target task information, and obtaining the target interaction result corresponding to the target interaction information based on the target task information; and displaying the target page based on the target interaction result. This intelligent interaction method can not only provide users with multiple interactive functions such as question-and-answer interaction, control interaction, and event interaction for video recording by camera equipment, meet users' diverse interactive needs, and improve the flexibility and diversity of interaction, but also use the target macro model to analyze the target interaction information, fully understand the user's intention, better answer the user's questions or conveniently control the target camera equipment to perform multiple quick operations, and improve the intelligence and convenience of interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 A schematic diagram of the architecture of an intelligent interactive system provided by an exemplary embodiment of the present application;

[0052] Figure 2 A flowchart of an intelligent interaction method provided by an exemplary embodiment of the present application;

[0053] Figure 3 A schematic diagram of a target application page and a target interaction page provided for an exemplary embodiment of the present application;

[0054] Figure 4 A schematic diagram of a process for obtaining target interaction information provided by an exemplary embodiment of the present application;

[0055] Figure 5 A schematic diagram of another target interaction page provided for an exemplary embodiment of the present application;

[0056] Figure 6 A schematic diagram of another target interaction page provided for an exemplary embodiment of the present application;

[0057] Figure 7 A schematic diagram of the effect of page jump interaction provided by an exemplary embodiment of the present application;

[0058] Figure 8 A flowchart of another intelligent interaction method provided by an exemplary embodiment of the present application;

[0059] Fig. 9A schematic diagram of the structure of an intelligent interactive device provided by an exemplary embodiment of the present application;

[0060] Fig.10 A schematic diagram of the structure of an electronic device provided as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0061] In order to make the features and advantages of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0062] The terms "first", "second", "third", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations 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 limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0063] Please refer to the following Figure 1 , which is a schematic diagram of the architecture of an intelligent interactive system provided by an exemplary embodiment of this specification. Figure 1 As shown, the intelligent interaction system may include: a terminal 110, a server 120 and a target camera device 130. Among them:

[0064] The terminal 110 can interact with the server 120 and the target camera device 130 through the network to receive messages from the server 120 or the target camera device 130, or send messages to the server 120 or the target camera device 130. The terminal 110 can be hardware or software. When the terminal 110 is hardware, it can be various electronic devices, including but not limited to smart watches, smart phones, tablet computers, laptop portable computers, and desktop computers. When the terminal 110 is software, it can be installed in the electronic devices listed above, which can be implemented as multiple software or software modules (for example: used to provide distributed services), or it can be implemented as a single software or software module, which is not specifically limited here.

[0065] In the embodiments of the present specification, the terminal 110 may be a user terminal corresponding to a user who needs to perform intelligent interaction, such as a developer. Intelligent interaction software may be installed in the terminal 110, and the software may be, but is not limited to, bound with one or more target camera devices 130 to implement the interaction functions related to the target user and the target camera device 130, such as, but not limited to, receiving target question information input by the target user or target control information of the target user for the target camera device 130.

[0066] Optionally, the software may be built with a trained target large model, but not limited to, for semantic analysis of received target interaction information and generating corresponding target interaction results. When the target user wants to perform intelligent interaction or the target camera device 130 detects target event information that triggers intelligent interaction, the terminal 110 corresponding to the target user or the target camera device 130 may, but not limited to, obtain the corresponding target interaction information; the target interaction information includes at least one of the following: target question information, target control information for the target camera device, and target event information corresponding to the target camera device; then, the target large model is used to analyze the target interaction information to obtain target task information, and based on the target task information, the target interaction result corresponding to the target interaction information is obtained; finally, the target page is displayed based on the target interaction result.

[0067] The server 120 may be a server that provides intelligent interactive functions. It should be noted that the server 120 may be hardware or software. When the server 120 is hardware, it may be implemented as a distributed server cluster consisting of multiple servers, or it may be implemented as a single server. When the server 120 is software, it may be implemented as multiple software or software modules (for example, for providing distributed services), or it may be implemented as a single software or software module, which is not specifically limited here. The server 120 may be, but is not limited to, a hardware server, a virtual server, a cloud server, etc.

[0068] Optionally, after receiving the target interaction information sent by the terminal 110 or the target camera device 130 through the network, the server 120 can analyze the target interaction information using the target macro model to obtain the target task information, and obtain the target interaction result corresponding to the target interaction information based on the target task information. Then, the target interaction result is sent to the terminal 110. Finally, the terminal 110 can display the target page according to the target interaction result.

[0069] It can be understood that the intelligent interaction method provided in the embodiment of the present application can be executed by the terminal 110 alone, or can be executed by the terminal 110 and the server 120 together, and the embodiment of the present application is not limited to this.

[0070] The target camera device 130 may be an intelligent device with a camera function, including but not limited to an intelligent camera, an intelligent video doorbell, etc., which is not limited in this embodiment. The target camera device 130 may interact with the terminal 110 and the server 120 through a network, such as but not limited to receiving a control instruction from the terminal 110 or the server 120, or sending a message to the terminal 110 or the server 120. The target camera device 130 may automatically detect the collected video and filter out the video event information. The above video event information may be a video clip in which a person appears, or a video clip in which a crying sound appears, etc., which may be set according to the actual event detection requirements of the user, which is not limited in this embodiment of the present application. The target camera device 130 may also automatically detect its own device status as status event information, which may be that the power is lower than a preset value, the local storage capacity of the target camera device exceeds a preset value, or the network status of the target camera device, the camera is blocked, etc., which is not limited in this embodiment of the present application. Then, the target camera device 130 sends the video event information and the status event information to the terminal 110 or the server 120 for further processing.

[0071] The network may be a medium providing a communication link between the terminal 110, the server 120 and the target camera device 130, or may be the Internet including network devices and transmission media, but is not limited thereto. The transmission media may be a wired link, such as but not limited to coaxial cable, optical fiber and digital subscriber line (DSL), or a wireless link, such as but not limited to wireless Internet access (WI FI), Hypertext Transfer Protocol (HTTP), Bluetooth and mobile device network, etc.

[0072] Understandably, Figure 1 The number of terminals 110 , servers 120 , and target camera devices 130 in the intelligent interaction system shown is only an example. In a specific implementation, the intelligent interaction system may include any number of terminals 110 , servers 120 , and target camera devices 130 .

[0073] Next, combine Figure 1 , taking the terminal 110 performing intelligent interaction as an example, an intelligent interaction method provided by an exemplary embodiment of the present application is introduced. For details, please refer to Figure 2 , which exemplarily shows a flow chart of an intelligent interaction method provided by an embodiment of the present application. Figure 2 As shown, the intelligent interaction method may include the following steps:

[0074] S201, obtaining target interaction information, where the target interaction information includes at least one of the following: target problem information, target control information for a target camera device, and target event information corresponding to the target camera device.

[0075] Specifically, the terminal may be installed with intelligent interaction software, which may be, but is not limited to, bound to one or more target camera devices, and the target camera device may receive control instructions sent by the terminal when connected to the Internet. The above-mentioned target interaction information may be voice interaction information or text interaction information, which is not limited in the embodiments of the present application. The above-mentioned target interaction information may include, but is not limited to, at least one of the following: target question information raised by the target user, target control information for the target camera device, and target event information corresponding to the target camera device. The above-mentioned target event information includes video event information automatically detected and screened by the above-mentioned target camera device for the collected video data and / or status event information obtained by detecting the status of the above-mentioned target camera device.

[0076] Optionally, when the target user wants to ask questions or wants to control the smart camera device or wants to view historical video records, the target application on the terminal can be opened, and the target interaction information can be directly input by voice or text based on the smart entrance in the target application page of the target application. The terminal can receive the target interaction information input by the target user based on the smart entrance in the target application page. The above-mentioned target application page is the homepage or any page of the target application associated with the target camera device.

[0077] For example, Figure 3 As shown in (a), after the target user opens the target application and enters the target application page 300a, the smart entrance 310 in the target application page will display information such as "Your smart voice assistant is online", prompting the target user to perform smart interaction at this time. The target user can directly send interaction information through voice, and the terminal can receive the voice interaction information sent by the target user through the smart entrance 310.

[0078] Optionally, when the target user wants to ask questions or wants to control the smart camera device or wants to view historical video records, the target trigger operation can also be performed on the smart entrance in the above-mentioned target application page first. After receiving the target trigger operation for the smart entrance in the above-mentioned target application page, the terminal can enter the target interaction page in response to the target trigger operation, and receive the target interaction information input by the above-mentioned target user based on the above-mentioned target interaction page. The above-mentioned target trigger operation can be a click or a slide, which is not limited in the embodiment of the present application. After receiving the target trigger operation for the smart entrance in the above-mentioned target application page, it means that the triggerer wants to enter the target interaction page for intelligent interaction, then the target application will automatically jump to the target interaction page. The above-mentioned target interaction page includes a target interaction input control, and the target user can input voice interaction information or text interaction information based on the target interaction input control in the target interaction page.

[0079] Furthermore, the target interaction page may include, but is not limited to, a function prompt area and / or a question recommendation area; the function prompt area may include, but is not limited to, one or more function description information. The function description information is exemplary description information of the functions supported by the target application, so that the target user can quickly understand the available functions of the target application through the function prompt area of ​​the target interaction page, thereby enhancing the functional usability; the question recommendation area may include, but is not limited to, one or more question recommendation description information, so that the target user can quickly understand how to intuitively describe their own needs through the question recommendation area, and then provide more accurate intelligent interaction services based on the user's own needs.

[0080] For example, when the target user wants to perform intelligent interaction, such as Figure 3 As shown in (a), the target application page 300a may also be first subjected to a target triggering operation such as clicking or sliding on the smart portal 310. After receiving the target triggering operation for the smart portal 310, the terminal may respond to the target triggering operation and enter the following Figure 3(b) The target interaction page 300b shown. The target user can input the corresponding target interaction information through the target interaction input control 340 (such as but not limited to a keyboard, a voice input bar, etc.) of the target interaction page 300b. At the same time, the target interaction page 300b may include but is not limited to a question recommendation area 320 and a function prompt area 330. The above-mentioned function prompt area 330 may, but is not limited to, display function guidance information (such as "I can also help you complete the following instructions") and function description information (such as "View the camera's historical usage records", "Let the camera play nursery rhymes", etc.), so that the target user can quickly understand the available functions of the target application and enhance the usability of the interactive function. The above-mentioned question recommendation area 320 may, but is not limited to, display question guidance information (such as "You can ask me this") and question recommendation description information (such as "What's the weather like today?", "What should I do if I don't receive notifications?", etc.), so that the target user can quickly understand how to intuitively describe their own needs, and then make more accurate intelligent interactive services for the user's own needs.

[0081] Optionally, the target camera device can detect the video or its own state collected by it, and filter out the target event information, and then send the target event information to the terminal. The above-mentioned target event information includes the video event information obtained by detecting the video data collected by the above-mentioned target camera device and / or the state event information obtained by detecting the state of the above-mentioned target camera device. Then, the terminal can receive the target event information sent by the above-mentioned target camera device. The above-mentioned video event information can be a video clip in which someone appears, or a video clip in which crying sounds appear, etc., which can be set according to the actual event detection needs of the user, and the embodiment of the present application does not limit this. The above-mentioned state event information can include the power information of the target camera device (the power is lower than the preset value), and can also include the storage information of the target camera device (the local storage exceeds the set value), and can also include the operating status information of the target camera device (for example, but not limited to detecting that the camera is currently blocked, the target camera device cannot operate normally, etc.), which can be set according to the actual intelligent interaction needs of the user, and the embodiment of the present application does not limit this.

[0082] In an embodiment of the present application, by associating the target application on the terminal with the target camera device, the terminal can receive both video event information sent by the target camera device and status event information of the target camera device, and then realize intelligent interaction between the target camera device, the terminal and the target user based on the above-mentioned video event information or status event information, thereby improving the intelligence and diversity of the intelligent interaction.

[0083] Alternatively, if Figure 4 As shown, the implementation process of obtaining target interaction information in S201 may include but is not limited to the following steps:

[0084] S401, obtaining voice interaction information.

[0085] Specifically, the voice interaction information input by the target user may be received through a smart entrance in a target application page, or the voice interaction information input by the target user may be received through a target interaction page.

[0086] S402: Perform voiceprint recognition on the voice interaction information to obtain target voiceprint features.

[0087] Specifically, when receiving voice interaction information, there may be a situation where other people's voice interaction information is collected. At this time, in order to avoid accidental touches of other people's voices, voiceprint recognition can be performed on the collected voice interaction information, and the target voiceprint features in the voice interaction information can be extracted. And through the target voiceprint features, it is judged whether the sound source corresponding to the voice interaction information is the preset target user, for example but not limited to matching the target voiceprint features with the preset voiceprint features to obtain the corresponding target matching results.

[0088] S403: If the target voiceprint feature matches the preset voiceprint feature, the speech interaction information corresponding to the target voiceprint feature is determined as the target interaction information.

[0089] Specifically, the preset voiceprint features may be, but are not limited to, the voiceprint features of the target users that can be pre-set for intelligent interaction. If the target voiceprint features match the preset voiceprint features, it means that the speaker (target user) corresponding to the target voiceprint features belongs to the pre-set target users that can be intelligently interacted with, and the voice interaction information corresponding to the target voiceprint features can be determined as the target interaction information that can be intelligently interacted with, thereby avoiding accidental touches by others.

[0090] Please continue to refer to Figure 2 ,like Figure 2 As shown, after the target interaction information is obtained in S201, the intelligent interaction method may also include but is not limited to:

[0091] S202, using the target big model, analyzing the target interaction information to obtain target task information, and obtaining a target interaction result corresponding to the target interaction information based on the target task information.

[0092] Specifically, after obtaining the target interaction information, the target interaction information can be analyzed using a target large model (for example, but not limited to a large model based on a deep neural network). For example, but not limited to, the target interaction information can be input into the target large model, and the language model, word sense disambiguation, grammatical analysis and other technologies therein can be used to perform a deep semantic analysis of the target interaction information, understand the intention of the target user and the specific content of the instruction, and obtain the target task information. Then, the target task information is parsed into specific operations and executed to obtain the target interaction result corresponding to the target interaction information.

[0093] Optionally, when the above-mentioned target interaction information includes video event information obtained by detecting the video data collected by the above-mentioned target camera device, the target large model can be used to perform sentiment analysis on the target event information to obtain target sentiment information. For example, but not limited to, the video event information can be preprocessed first (for example, but not limited to decomposing the video into frames, normalization, etc.), and then the visual features (for example, but not limited to color, texture, motion trajectory, etc.) and audio features (for example, but not limited to tone, volume, rhythm, etc.) in the above-mentioned video event information are extracted. Then, the extracted visual features and audio features are fused to obtain a more comprehensive video emotion representation. Next, the target large model can be used to perform sentiment classification on the above-mentioned fusion features to obtain target sentiment information (for example, but not limited to positive, negative, neutral, etc.). Finally, the target large model can also generate corresponding target sentiment prompt information based on the above-mentioned target sentiment information, which can prompt or guide the target user to perform certain operations or instructions, thereby providing users with highly intelligent services. The above-mentioned target sentiment prompt information can be for asking the target user whether to perform corresponding soothing operations when negative emotions are detected, etc., which can be set according to the actual needs of the user, and the embodiment of the present application is not limited to this.

[0094] Optionally, when the above-mentioned target interaction information includes target question information, indicating that the target interaction information is question-and-answer information, the target big model can be used to perform semantic analysis on the above-mentioned target question information, clarify the specific needs of the target user, and obtain the target question-and-answer task information, based on the analyzed target question-and-answer task information. Then, the target big model can trigger the target application to call the built-in functions in the terminal system or interact with other applications, perform operations corresponding to the target question-and-answer task information, and generate target question-and-answer results corresponding to the above-mentioned target question information. For example, if the received target question information is to inquire about the weather, after analysis by the target big model, the target big model will trigger the target application to call the weather service interface, obtain weather information, and generate corresponding weather question-and-answer results based on the weather information.

[0095] Optionally, when the target interaction information includes target control information for the target camera device, it indicates that the target user wants to perform some control operations on the target camera device, such as but not limited to viewing the video / camera screen, turning on / off the machine, and letting the camera play nursery rhymes. After receiving the target control information, the target large model can be used to perform semantic analysis on the target control information to clarify the specific control operations that the user needs to perform and obtain the target control task information. Then, the corresponding target control instructions are generated according to the target control task information. The target application can complete the control operation of the target camera device by executing the target control instruction.

[0096] Optionally, when the target interaction information includes a plurality of video event information obtained by detecting the video data collected by the target camera device within the target time period, a target event analysis report can be finally generated by analyzing the content of the video event information. For example, but not limited to, the target macro model can be used to summarize and analyze the plurality of video event information to obtain target analysis report generation task information. The target analysis report generation task information can include description information of the target analysis report generation task, which is not limited to the embodiment of the present application. Then, the target event analysis report corresponding to the target time period is automatically generated through the target analysis report generation task information. For example, but not limited to, the target macro model can perform corresponding tasks according to the description information of the target analysis report generation task and the plurality of video event information. The target event analysis report can include information such as the type and frequency of the video event information occurring within the target time period, which is not limited to the embodiment of the present application. The target time period can be daily or weekly, which is not limited to the embodiment of the present application.

[0097] Please continue to refer to Figure 2 ,like Figure 2 As shown, in the above S202, after using the target big model to analyze the target interaction information to obtain the target task information, and obtaining the target interaction result corresponding to the target interaction information based on the target task information, the intelligent interaction method may further include:

[0098] S203: Display a target page based on the target interaction result.

[0099] Specifically, the target page can be the target interaction page or a page jumped based on the target interaction information, which is not limited in the present embodiment. After obtaining the final target interaction result using the target macro model, different target pages can be displayed according to different tasks or target interaction results. For example, but not limited to, the terminal can display the target interaction result text in the target interaction page of the target application and feed it back to the target user.

[0100] Optionally, after obtaining the final target interaction result using the target large model, the terminal can also, but is not limited to, play the target interaction result to the target user in the form of voice broadcast to achieve voice intelligent interaction with the target user.

[0101] Optionally, when the target interaction result is target emotion prompt information, the terminal can display the target interaction page based on the target emotion prompt information. For example, but not limited to, Figure 5 As shown, after receiving the video event information of a crying child captured by the target camera device, the terminal can use the target large model to perform sentiment analysis on the video event information. If it is considered that the sentiment information corresponding to the above video event information is negative, then the corresponding target sentiment prompt information will be generated and displayed on the target interaction page for this situation, such as "A crying child is detected, do you want to execute 'Let the camera play nursery rhymes'", so as to comfort the child.

[0102] Optionally, when the target interaction information includes target question information and the target interaction result is a target question-answer result corresponding to the target question information, the target page may be directly displayed based on the target question-answer result. Figure 6 As shown, if the received target interaction information is "How is the weather today" (target question information), after the target big model performs semantic analysis on the above target question information, it is clear that the target user wants to know today's weather information. The target big model can trigger the terminal to call the weather service interface to obtain today's weather conditions according to the corresponding weather question and answer task, and generate the corresponding weather question and answer result (target question and answer result). Finally, the above weather question and answer result (target question and answer result) can be displayed in the target interaction page in the form of text, or the above weather question and answer result (target question and answer result) can be processed by speech synthesis, and the text can be converted into a smooth voice signal to be played to the target user.

[0103] Optionally, when the target interaction information includes target control information for the target camera device, and the target interaction result is a target control instruction corresponding to the target control information, when the target control instruction is a target page jump instruction, the target page corresponding to the target page jump instruction can be jumped to in response to the target control instruction. Figure 7As shown, when the target user enters the target interaction information "view all videos in which someone appeared yesterday" or "open the living room camera screen" in the target interaction page 710, the terminal can use the target macro model to perform semantic analysis on the above target interaction information and generate a corresponding target page jump instruction (such as a dynamic tap page jump instruction or an open stream page jump instruction). The terminal can respond to the above dynamic tap page jump instruction and jump from the target interaction page 710 to the dynamic tap page 720 that filters out all videos in which someone appeared yesterday. The terminal can respond to the above open stream page jump instruction and jump from the target interaction page 710 to the open stream page 730 of the living room camera, so that the target user can watch the screen captured by the living room camera in real time.

[0104] Optionally, when the target interaction information includes target control information for the target camera device, and the target interaction result is a target control instruction corresponding to the target control information, in the case where the target control instruction is a control instruction for the target camera device, the target camera device can be controlled to execute the target action corresponding to the target control instruction in response to the target control instruction. For example, when the target interaction information is "turn off all cameras", a shutdown instruction for all cameras will be generated after the target large model analysis; the terminal can send the shutdown instruction to all target camera devices associated with it, so that all target camera devices associated with the terminal execute the corresponding shutdown instruction, so that users can easily and quickly realize the unified management of multiple camera devices.

[0105] Optionally, when the target interaction information includes multiple video event information of the target camera device within the target time period, and the target interaction result is a target event analysis report corresponding to the multiple video event information, the target page can be displayed based on the target event analysis report. The target event analysis report may include information such as the type and frequency of the video event information occurring within the target time period, which is not limited in the embodiments of the present application. The target user can understand the occurrence of events within the target time period by viewing the target event analysis report corresponding to the target time period.

[0106] In the embodiment of the present application, by receiving target interaction information, using the target macro model, analyzing the target interaction information, obtaining target task information, and obtaining the target interaction result corresponding to the target interaction information based on the target task information; and displaying the target page based on the target interaction result. This intelligent interaction method can not only provide users with multiple interactive functions such as question-and-answer interaction, control interaction, and event interaction for video recording by camera equipment, meet users' diverse interactive needs, and improve the flexibility and diversity of interaction, but also use the target macro model to analyze the target interaction information, fully understand the user's intention, better answer the user's questions or conveniently control the target camera equipment to perform multiple quick operations, and improve the intelligence and convenience of interaction.

[0107] Please refer to the following Figure 8 , which exemplarily shows a flow chart of another intelligent interaction method provided by an embodiment of the present application. Figure 8 As shown, the intelligent interaction method may include the following steps:

[0108] S801, acquiring target interaction information, where the target interaction information includes target event information corresponding to a target camera device, and the target event information includes status event information obtained by detecting a status of the target camera device.

[0109] Specifically, a target application capable of managing camera devices and performing intelligent interaction is installed on the terminal, and the target application can be, but is not limited to, associated with one or more target camera devices. The terminal can receive status event information obtained by detecting the status of the target camera device. The above status event information can be that the power is lower than a preset value, the local storage capacity of the target camera device exceeds a preset value, or the network status of the target camera device, the camera is blocked, etc., which is not limited in the embodiments of the present application.

[0110] S802: Send device status prompt information according to the status event information.

[0111] Specifically, after receiving the status event information of the target camera device, device status prompt information may be issued according to the content of the status event information to remind the user of the target camera device to perform corresponding operations.

[0112] For example, upon receiving the status event information of low battery of the target camera device, the terminal may, but is not limited to, issue a device status prompt information similar to “the target camera device is low battery, please charge it in time”. Upon receiving the status event information of low local storage card capacity of the target camera device, the terminal may, but is not limited to, issue a device status prompt information similar to “the local storage card capacity of the target camera device is low, please clean it in time”.

[0113] Please refer to the following Fig. 9, which exemplarily shows a structural diagram of an intelligent interaction device provided in an embodiment of the present application. Fig. 9 As shown, the intelligent interaction device 900 may include:

[0114] The acquisition module 910 is used to acquire target interaction information; the target interaction information includes at least one of the following: target problem information, target control information for a target camera device, and target event information corresponding to the target camera device;

[0115] The analysis module 920 is used to analyze the target interaction information using the target macro model to obtain target task information, and obtain the target interaction result corresponding to the target interaction information based on the target task information;

[0116] The display module 930 is used to display the target page based on the above target interaction result.

[0117] In some possible embodiments, the target interaction information includes target event information corresponding to the target camera device; the target event information includes video event information obtained by detecting video data collected by the target camera device; the analysis module 920 is specifically used for: using the target big model to perform sentiment analysis on the target event information to obtain target sentiment information, and generating corresponding target sentiment prompt information based on the target sentiment information; the display module 930 is specifically used for: displaying the target interaction page based on the target sentiment prompt information.

[0118] In some possible embodiments, the acquisition module 910 is specifically used for:

[0119] receiving target interaction information input by a target user based on a smart entry in a target application page; the target application page is a page of a target application associated with a target camera device; or

[0120] Receiving a target trigger operation for the smart entrance in the target application page, entering a target interaction page in response to the target trigger operation, and receiving target interaction information input by the target user based on the target interaction page; or

[0121] Receive target event information sent by the target camera device; the target event information includes video event information obtained by detecting video data collected by the target camera device and / or status event information obtained by detecting the status of the target camera device.

[0122] In some possible embodiments, the target interaction page includes a function prompt area and / or a question recommendation area; the function prompt area includes one or more function description information; the question recommendation area includes one or more question recommendation description information.

[0123] In some possible embodiments, the target interaction information includes target question information; the analysis module 920 is specifically used to: use the target big model to analyze the target question information to obtain target question and answer task information, and generate a target question and answer result corresponding to the target question information based on the target question and answer task information; the display module 930 is specifically used to: display the target page based on the target question and answer result.

[0124] In some possible embodiments, the target interaction information includes target control information for a target camera device; the analysis module 920 is specifically used to: use a target large model to analyze the target control information, obtain target control task information, and generate corresponding target control instructions based on the target control task information; the display module 930 is specifically used to: in the case where the target control instruction is a target page jump instruction, respond to the target control instruction and jump to the target page corresponding to the target page jump instruction.

[0125] In some possible embodiments, the intelligent interaction device 900 further includes:

[0126] The control execution module is used for controlling the target camera device to execute the target action corresponding to the target control instruction in response to the target control instruction when the target control instruction is a control instruction for the target camera device.

[0127] In some possible embodiments, the target interaction information includes target event information corresponding to the target camera device; the target event information includes multiple video event information obtained by detecting video data collected by the target camera device within the target time period; the analysis module 920 is specifically used for: using the target big model, summarizing and analyzing the multiple video event information, obtaining target analysis report generation task information, and generating a target event analysis report corresponding to the target camera device in the target time period based on the target analysis report generation task information; the display module 930 is specifically used for: displaying the target page based on the target event analysis report.

[0128] In some possible embodiments, the target interaction information includes target event information corresponding to the target camera device; the target event information includes state event information obtained by detecting the state of the target camera device; the intelligent interaction device 900 further includes:

[0129] The information issuing module is used to issue device status prompt information according to the above status event information.

[0130] In some possible embodiments, the acquisition module 910 includes:

[0131] An acquisition unit, used for acquiring voice interaction information;

[0132] A recognition unit, used to perform voiceprint recognition on the above-mentioned voice interaction information to obtain target voiceprint features;

[0133] A determination unit is configured to determine the speech interaction information corresponding to the target voiceprint feature as the target interaction information if the target voiceprint feature matches a preset voiceprint feature.

[0134] The division of each module in the above-mentioned intelligent interactive device is only for illustration. In other embodiments, the intelligent interactive device can be divided into different modules as needed to complete all or part of the functions of the above-mentioned intelligent interactive device. The implementation of each module in the intelligent interactive device provided in the embodiments of this specification can be in the form of a computer program. The computer program can be run on a terminal or a server. The program modules constituted by the computer program can be stored in the memory of the terminal or the server. When the computer program is executed by the processor, all or part of the steps of the intelligent interaction method described in the embodiments of this specification are implemented.

[0135] See next Fig.10 , which is a schematic diagram of the structure of an electronic device provided by an exemplary embodiment of this specification. Fig.10 As shown, the electronic device 1000 may include: at least one processor 1010 , at least one communication bus 1020 , a user interface 1030 , at least one network interface 1040 , and a memory 1050 .

[0136] The communication bus 1020 may be used to realize the connection and communication among the above-mentioned components.

[0137] The user interface 1030 may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.

[0138] The network interface 1040 may optionally include a Bluetooth module, an NFC module, a Wi-Fi module, etc.

[0139] Among them, the processor 1010 may include one or more processing cores. The processor 1010 uses various interfaces and lines to connect the various parts of the entire electronic device 1000, and executes various functions and processes data of the routing device 1000 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1050, and calling data stored in the memory 1050. Optionally, the processor 1010 can be implemented in at least one hardware form of DSP, FPGA, and PLA. The processor 1010 can integrate one or a combination of CPU, GPU, modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1010, but may be implemented separately through a chip.

[0140] The memory 1050 may include a RAM or a ROM. Optionally, the memory 1050 includes a non-transitory computer-readable medium. The memory 1050 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 1050 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as obtaining target interaction information, generating target interaction results, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1050 may optionally be at least one storage device located away from the aforementioned processor 1010. As Fig.10 As shown, the memory 1050 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0141] In some possible embodiments, the electronic device 1000 may be the aforementioned Fig. 9 In the illustrated intelligent interactive device 900, the processor 1010 may be used to call program instructions stored in the memory 1050 and specifically perform the following operations:

[0142] Obtain target interaction information; the target interaction information includes at least one of the following: target problem information, target control information for a target camera device, and target event information corresponding to the target camera device; use a target big model to analyze the target interaction information to obtain target task information, and obtain a target interaction result corresponding to the target interaction information based on the target task information; display a target page based on the target interaction result.

[0143] In some possible embodiments, the target interaction information includes target event information corresponding to the target camera device; the target event information includes video event information obtained by detecting video data collected by the target camera device;

[0144] When the processor 1010 executes the target macro model to analyze the target interaction information to obtain target task information, and obtains the target interaction result corresponding to the target interaction information based on the target task information, it is specifically used to execute:

[0145] Using the target big model, sentiment analysis is performed on the target event information to obtain target sentiment information, and corresponding target sentiment prompt information is generated based on the target sentiment information;

[0146] When the processor 1010 executes the above-mentioned display of the target page based on the above-mentioned target interaction result, it is specifically used to execute: displaying the target interaction page based on the above-mentioned target emotion prompt information.

[0147] In some possible embodiments, when the processor 1010 executes the acquiring of the target interaction information, it is specifically configured to execute:

[0148] Receive target interaction information input by the target user based on the smart entrance in the target application page; the above-mentioned target application page is a page of the target application associated with the target camera device; or receive a target trigger operation for the smart entrance in the above-mentioned target application page, respond to the above-mentioned target trigger operation, enter the target interaction page, and receive the target interaction information input by the above-mentioned target user based on the above-mentioned target interaction page; or receive target event information sent by the above-mentioned target camera device; the above-mentioned target event information includes video event information obtained by detecting the video data collected by the above-mentioned target camera device and / or status event information obtained by detecting the status of the above-mentioned target camera device.

[0149] In some possible embodiments, the target interaction page includes a function prompt area and / or a question recommendation area; the function prompt area includes one or more function description information; the question recommendation area includes one or more question recommendation description information.

[0150] In some possible embodiments, the target interaction information includes target question information; when the processor 1010 executes the target macro model to analyze the target interaction information to obtain target task information, and obtains a target interaction result corresponding to the target interaction information based on the target task information, it is specifically used to execute:

[0151] Analyze the target question information using the target big model to obtain target question-answering task information, and generate a target question-answering result corresponding to the target question information based on the target question-answering task information;

[0152] When the processor 1010 executes the above-mentioned display of the target page based on the above-mentioned target interaction result, it is specifically used to execute: display the target page based on the above-mentioned target question and answer result.

[0153] In some possible embodiments, the target interaction information includes target control information for a target camera device; when the processor 1010 executes the target macro model to analyze the target interaction information to obtain target task information, and obtains a target interaction result corresponding to the target interaction information based on the target task information, it is specifically used to execute:

[0154] Analyze the target control information using the target big model to obtain target control task information, and generate corresponding target control instructions based on the target control task information;

[0155] When the processor 1010 executes the display of the target page based on the target interaction result, it is specifically used to execute:

[0156] In the case that the target control instruction is a target page jump instruction, in response to the target control instruction, the program jumps to the target page corresponding to the target page jump instruction.

[0157] In some possible embodiments, after the processor 1010 executes the above-mentioned use of the target large model to analyze the above-mentioned target control information to obtain the target control task information, and generates the corresponding target control instruction based on the above-mentioned target control task information, it is also used to execute:

[0158] In the case that the target control instruction is a control instruction for the target imaging device, in response to the target control instruction, the target imaging device is controlled to execute a target action corresponding to the target control instruction.

[0159] In some possible embodiments, the target interaction information includes target event information corresponding to the target camera device; the target event information includes a plurality of video event information obtained by detecting video data collected by the target camera device within a target time period;

[0160] When the processor 1010 executes the target macro model to analyze the target interaction information to obtain target task information, and obtains the target interaction result corresponding to the target interaction information based on the target task information, it is specifically used to execute:

[0161] Using the target big model, the above-mentioned multiple video event information is summarized and analyzed to obtain target analysis report generation task information, and based on the above-mentioned target analysis report generation task information, a target event analysis report corresponding to the above-mentioned target camera device in the above-mentioned target time period is generated;

[0162] When the processor 1010 executes the display of the target page based on the target interaction result, it is specifically used to execute: display the target page based on the target event analysis report.

[0163] In some possible embodiments, the target interaction information includes target event information corresponding to the target camera device; the target event information includes state event information obtained by detecting the state of the target camera device;

[0164] After executing the above-mentioned acquisition of target interaction information, the above-mentioned processor 1010 is further used to execute: issuing device status prompt information according to the above-mentioned status event information.

[0165] In some possible embodiments, when the processor 1010 executes the acquiring of the target interaction information, it is specifically configured to execute:

[0166] Acquire voice interaction information; perform voiceprint recognition on the voice interaction information to obtain target voiceprint features; if the target voiceprint features match the preset voiceprint features, determine the voice interaction information corresponding to the target voiceprint features as the target interaction information.

[0167] The embodiment of the present application also provides a computer storage medium, which stores instructions, and when the instructions are executed on a computer or a processor, the computer or the processor executes one or more steps in any of the above methods. If the components of the above intelligent interactive device are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above storage medium.

[0168] 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 above computer program product includes one or more computer instructions. When the above computer program instructions are loaded and executed on a computer, the above process or function according to the embodiment of the present application is generated in whole or in part. The above computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The above computer instructions can be stored in a computer-readable storage medium or transmitted by the above computer-readable storage medium. The above computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The above computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integration. The above available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0169] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes. In the absence of conflict, the technical features in this embodiment and the implementation scheme can be combined arbitrarily.

[0170] The above-mentioned embodiments are merely preferred embodiments of the present application and are not intended to limit the scope of the present application. Without departing from the design spirit of the present application, various modifications and improvements made to the technical solutions of the present application by ordinary technicians in this field should fall within the protection scope determined by the claims of the present application.

Claims

1. An intelligent interaction method, characterized in that: include: Obtain target interaction information; The target interaction information includes at least one of the following: target problem information, target control information for a target camera device, and target event information corresponding to the target camera device; Analyzing the target interaction information using the target macro model to obtain target task information, and obtaining a target interaction result corresponding to the target interaction information based on the target task information; A target page is displayed based on the target interaction result.

2. The method according to claim 1, characterized in that The target interaction information includes target event information corresponding to the target camera device; the target event information includes video event information obtained by detecting video data collected by the target camera device; The target interaction information is analyzed by using the target macro model to obtain target task information, and a target interaction result corresponding to the target interaction information is obtained based on the target task information, including: Using the target big model, sentiment analysis is performed on the target event information to obtain target sentiment information, and corresponding target sentiment prompt information is generated based on the target sentiment information; The displaying of the target page based on the target interaction result includes: A target interaction page is displayed based on the target emotion prompt information.

3. The method according to claim 1, characterized in that The acquiring target interaction information includes: receiving target interaction information input by a target user based on a smart entry in a target application page; the target application page is a page of a target application associated with a target camera device; or Receiving a target trigger operation for a smart entry in the target application page, entering a target interaction page in response to the target trigger operation, and receiving target interaction information input by the target user based on the target interaction page; or Receive target event information sent by the target camera device; the target event information includes video event information obtained by detecting video data collected by the target camera device and / or status event information obtained by detecting the status of the target camera device.

4. The method according to claim 1, characterized in that The target interaction information includes target question information; The target interaction information is analyzed by using the target macro model to obtain target task information, and a target interaction result corresponding to the target interaction information is obtained based on the target task information, including: Analyze the target question information using the target big model to obtain target question-answering task information, and generate a target question-answering result corresponding to the target question information based on the target question-answering task information; The displaying of the target page based on the target interaction result includes: A target page is displayed based on the target question and answer result.

5. The method according to claim 1, characterized in that The target interaction information includes target control information for the target camera device; The target interaction information is analyzed by using the target macro model to obtain target task information, and a target interaction result corresponding to the target interaction information is obtained based on the target task information, including: Analyzing the target control information using the target big model to obtain target control task information, and generating corresponding target control instructions based on the target control task information; The displaying of the target page based on the target interaction result includes: In the case that the target control instruction is a target page jump instruction, in response to the target control instruction, the program jumps to the target page corresponding to the target page jump instruction.

6. The method according to claim 1, characterized in that The target interaction information includes target event information corresponding to the target camera device; the target event information includes a plurality of video event information obtained by detecting the video data collected by the target camera device within a target time period; The target interaction information is analyzed by using the target macro model to obtain target task information, and a target interaction result corresponding to the target interaction information is obtained based on the target task information, including: Using the target big model, the plurality of video event information are summarized and analyzed to obtain target analysis report generation task information, and based on the target analysis report generation task information, a target event analysis report corresponding to the target camera device in the target time period is generated; The displaying of the target page based on the target interaction result includes: A target page is displayed based on the target event analysis report.

7. The method according to claim 1, characterized in that The target interaction information includes target event information corresponding to the target camera device; the target event information includes status event information obtained by detecting the status of the target camera device; After acquiring the target interaction information, the method further includes: Device status prompt information is issued according to the status event information.

8. An intelligent interactive device, characterized in that: include: An acquisition module, used to acquire target interaction information; The target interaction information includes at least one of the following: target problem information, target control information for a target camera device, and target event information corresponding to the target camera device; An analysis module, used to analyze the target interaction information using a target macro model to obtain target task information, and obtain a target interaction result corresponding to the target interaction information based on the target task information; A display module is used to display a target page based on the target interaction result.

9. An electronic device, characterized in that: include: A processor and a memory; wherein the memory stores an executable program code, and the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The computer storage medium stores a plurality of instructions, which are suitable for being loaded by a processor and executing the method steps according to any one of claims 1-7.

Images