Intelligent interaction method, device, electronic device and readable storage medium

Abstract

The present application discloses an intelligent interaction method, device, electronic device, and readable storage medium, in the field of computer technology, specifically, the field of human-computer interaction. The specific implementation scheme is: obtaining interaction data between an object and an intelligent interactive device, determining the type of the interaction data, and in response to the type of the interaction data being a non-natural language interaction data type, generating corresponding natural language text information based on the interaction data, and generating a corresponding first reply statement based on the natural language text information. The present application realizes the generation of reply statements of intelligent interactive devices based on non-natural language interaction data, thereby improving the intelligence level of intelligent interactive devices and enhancing the user experience of users when using intelligent interactive devices.

Description

Technical Field

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

[0002] In related technologies, intelligent systems can be deployed on multiple terminals, including smart speakers, in-vehicle interactive systems, and smart health devices. User interaction with intelligent interactive devices can generate both voice interaction data and non-natural language interaction data. However, intelligent interactive devices have poor interactivity with non-natural language interaction data. Summary of the Invention

[0003] The present application provides an intelligent interaction method, device, electronic device and readable storage medium.

[0004] According to a first aspect of the present application, there is provided an intelligent interaction method, comprising:

[0005] Obtaining interaction data between objects and intelligent interactive devices;

[0006] Determining the type of the interaction data;

[0007] In response to the type of the interaction data being a non-natural language interaction data type, generating corresponding natural language text information based on the interaction data;

[0008] A corresponding first reply statement is generated according to the natural language text information.

[0009] According to a second aspect of the present application, there is provided an intelligent interaction device, comprising:

[0010] An acquisition module is used to obtain interaction data between the object and the intelligent interactive device;

[0011] A determination module, configured to determine the type of the interaction data;

[0012] a first generating module, configured to generate corresponding natural language text information based on the interaction data in response to the interaction data belonging to a non-natural language interaction data type;

[0013] The second generating module is used to generate a corresponding first reply statement according to the natural language text information.

[0014] According to a third aspect of the present application, an electronic device is provided, including:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the method according to the first aspect.

[0018] According to a fourth aspect of the present application, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the first aspect.

[0019] According to a fifth aspect of the present application, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of the intelligent interaction method as described in the first aspect.

[0020] According to the technical solution of the present application, corresponding natural language text information is generated based on non-natural language interaction data, and a corresponding first reply statement is generated based on the natural language text information, thereby realizing the generation of reply statements of intelligent interactive devices based on non-natural language interaction data, improving the intelligence level of intelligent interactive devices, and enhancing the user experience of users when using intelligent interactive devices.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present application.

[0023] Figure 1 is a schematic diagram according to the first embodiment of the present application;

[0024] Figure 2 is a schematic diagram according to the second embodiment of the present application;

[0025] Figure 3 is a schematic diagram according to the third embodiment of the present application;

[0026] Figure 4 is a schematic diagram according to a fourth embodiment of the present application;

[0027] Figure 5 is a schematic diagram according to a fifth embodiment of the present application;

[0028] Figure 6 is a schematic diagram according to a sixth embodiment of the present application;

[0029] Figure 7 is a schematic diagram according to a seventh embodiment of the present application;

[0030] Figure 8 is a schematic diagram according to an eighth embodiment of the present application;

[0031] Figure 9 is a schematic diagram according to a ninth embodiment of the present application;

[0032] Figure 10 is a schematic diagram according to the tenth embodiment of the present application;

[0033] Figure 11 is a schematic diagram according to the eleventh embodiment of the present application;

[0034] Figure 12 is a schematic diagram according to the twelfth embodiment of the present application;

[0035] Figure 13 is a schematic diagram according to the thirteenth embodiment of the present application;

[0036] Figure 14 It is a block diagram of an electronic device used to implement the intelligent interaction method of the embodiment of the present application. DETAILED DESCRIPTION

[0037] The following description of exemplary embodiments of the present application is made in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0038] In related technologies, intelligent systems can be deployed on multiple terminals, including smart speakers, in-vehicle interactive systems, and smart health devices. User interaction with intelligent interactive devices can generate both voice interaction data and non-natural language interaction data. However, intelligent interactive devices have poor interactivity with non-natural language interaction data.

[0039] Based on the above problems, the present application proposes an intelligent interaction method, device, electronic device and readable storage medium, which can generate corresponding natural language text information based on non-natural language interaction data, and generate a corresponding first reply statement based on the natural language text information, thereby realizing the generation of reply statements of intelligent interactive devices based on non-natural language interaction data, improving the intelligence level of intelligent interactive devices, and enhancing the user experience of users when using intelligent interactive devices.

[0040] Figure 1 This is a schematic diagram according to the first embodiment of the present application. It should be noted that the intelligent interaction method in the embodiment of the present application can be used for the intelligent interaction device in the embodiment of the present application, and the device can be configured in an electronic device. Figure 1 As shown, the intelligent interaction method includes the following steps:

[0041] Step 101: Acquire interaction data between an object and an intelligent interactive device.

[0042] It should be noted that the aforementioned objects may be intelligent interactive devices such as smart speakers, smart wearable devices, and smart detection devices, and may also be users of such intelligent interactive devices. The aforementioned intelligent interactive devices may be smart speakers, smart wearable devices, and smart detection devices. The aforementioned interaction data may be user physiological parameter data acquired by the smart wearable device or smart detection device, or may be interaction data obtained through direct interaction between the user and the aforementioned intelligent interactive device.

[0043] As a possible example, the server obtains the interaction data generated by the interaction between the object and the intelligent interactive device.

[0044] Step 102: Determine the type of the interaction data.

[0045] As a possible example, the server determines the type of the interaction data based on the interaction data, and the type may be a non-natural language interaction data type.

[0046] Step 103 : In response to the interaction data being of a non-natural language interaction data type, generating corresponding natural language text information based on the interaction data.

[0047] It is understood that interaction data can be of various types, and different types of interaction data require different processing methods to be converted into natural language text. Therefore, it is necessary to determine the type of interaction data and determine the processing method that matches the interaction data based on the type of interaction data.

[0048] It should be noted that the aforementioned interaction data of the non-natural language interaction data type may be interaction data in a non-natural language format generated during the interaction between a user and an intelligent interactive device. For example, the interaction data of the non-natural language interaction data type may be physiological parameter data obtained by an intelligent detection device detecting the user's physiological state.

[0049] For example, interaction data of non-natural language interaction type can be a smart blood pressure monitor that detects the user's blood pressure to obtain the user's blood pressure value; it can also be a smart body fat scale that detects the user's weight and body fat to obtain the user's weight data and body fat data.

[0050] As a possible example, in response to the type of the interaction data being a non-natural language interaction data type, corresponding natural language text information is generated based on the interaction data.

[0051] Step 104: Generate a corresponding first reply statement based on the natural language text information.

[0052] As a possible example, a first reply statement corresponding to the natural language text information is generated according to the natural language text information, so as to control the intelligent interactive device to interact with the user based on the first reply statement.

[0053] According to the intelligent interaction method of the embodiment of the present application, the interaction data between the object and the intelligent interaction device is obtained, the type of the interaction data is determined, and in response to the type of the interaction data being a non-natural language interaction data type, corresponding natural language text information is generated based on the interaction data, and a corresponding first reply statement is generated based on the natural language text information, thereby realizing the generation of reply statements of the intelligent interaction device based on the non-natural language interaction data, improving the intelligence level of the intelligent interaction device, and at the same time improving the user experience of the user when using the intelligent interaction device.

[0054] In order to ensure that a reply statement can be generated based on non-natural language interaction data, the interaction data is optionally analyzed based on a knowledge base, and natural language text information is obtained according to the analysis results. Figure 2 It is a schematic diagram according to the second embodiment of the present application. It should be noted that the intelligent interaction method of the embodiment of the present application can be executed by the intelligent interaction device in the embodiment of the present application. In some embodiments of the present application, such as Figure 2 As shown, the intelligent interaction method includes:

[0055] Step 201: Acquire interaction data between an object and an intelligent interactive device.

[0056] In the embodiments of the present application, step 201 can be implemented in any of the ways in the embodiments of the present application. The embodiments of the present application do not limit this and will not be described in detail.

[0057] Step 202: Determine the type of the interaction data.

[0058] In the embodiment of the present application, step 202 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0059] Step 203 : In response to the type of the interaction data being a non-natural language interaction data type, knowledge data corresponding to the interaction data is acquired from a knowledge base.

[0060] It should be noted that the above-mentioned knowledge base may be an expert knowledge base in the knowledge field to which the interaction data belongs, and the knowledge base may contain relevant professional knowledge in the knowledge field to which the interaction data belongs.

[0061] As a possible example, in response to the type of the interaction data being a non-natural language interaction data type, the knowledge domain to which the interaction data belongs is determined, and based on the knowledge domain to which the interaction data belongs, the knowledge base corresponding to the interaction data is determined, and the knowledge data corresponding to the interaction data is obtained from the knowledge base.

[0062] Step 204 : Based on the knowledge data, the interaction data is analyzed according to preset analysis rules to obtain analysis results.

[0063] It is understood that the above analysis rules may be pre-set rules based on actual conditions, for example, rules for analyzing the user's physiological state may be pre-set based on the user's physiological parameters.

[0064] As a possible example, based on the above-mentioned knowledge data, the interaction data can be analyzed according to preset analysis rules to obtain analysis results of the interaction data.

[0065] Step 205: Generate corresponding natural language text information based on the analysis results.

[0066] As a possible example, based on the analysis results of the interaction data, natural language text information corresponding to the interaction data is generated.

[0067] As a possible example, for each possible analysis result, natural language text information corresponding to the analysis result is pre-set, and after the analysis result is obtained, the natural language text information corresponding to the analysis result is acquired.

[0068] For example, the user's physiological parameters are analyzed based on the knowledge base to obtain analysis results, and based on the analysis results, natural language text corresponding to the analysis results is found.

[0069] Step 206: Generate a corresponding first reply statement based on the natural language text information.

[0070] In the embodiment of the present application, step 206 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0071] According to the intelligent interaction method of the embodiment of the present application, in response to the type of the interaction data being a non-natural language interaction data type, knowledge data corresponding to the interaction data is obtained from the knowledge base, and based on the knowledge data, the interaction data is analyzed according to preset analysis rules to obtain analysis results, and based on the analysis results, corresponding natural language text information is generated, thereby realizing the conversion of non-natural language interaction data into natural language text information, and then realizing the generation of reply sentences based on the non-natural language interaction data, thereby improving the intelligence level of the intelligent interactive device.

[0072] In order to ensure that the target skill corresponding to the interaction data is determined based on the natural language text information, optionally, the natural language text information is input into a pre-trained skill selection model to obtain the target skill corresponding to the interaction data. Figure 3 It is a schematic diagram according to the third embodiment of the present application. It should be noted that the intelligent interaction method of the embodiment of the present application can be executed by the intelligent interaction device in the embodiment of the present application. In some embodiments of the present application, such as Figure 3 As shown, the intelligent interaction method includes:

[0073] Step 301: Acquire interaction data between an object and an intelligent interactive device.

[0074] In the embodiments of the present application, step 301 can be implemented in any of the ways in the embodiments of the present application. The embodiments of the present application do not limit this and will not be described in detail.

[0075] Step 302: Determine the type of the interaction data.

[0076] In the embodiment of the present application, step 302 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0077] Step 303: In response to the interaction data being of a non-natural language interaction data type, knowledge data corresponding to the interaction data is acquired from a knowledge base.

[0078] In the embodiment of the present application, step 303 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0079] Step 304: Analyze the interaction data based on the knowledge data and according to preset analysis rules to obtain analysis results.

[0080] In the embodiment of the present application, step 304 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0081] Step 305: Generate corresponding natural language text information based on the analysis results.

[0082] In the embodiment of the present application, step 305 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0083] Step 306: Input the natural language text information into the pre-trained skill selection model to obtain the target skill corresponding to the interaction data.

[0084] It should be noted that the skill selection model can be a pre-trained model. Alternatively, the skill selection model can be a classification model or a generative model. The target skill can be playing audio or controlling a smart device, for example, playing music or turning on a smart water heater.

[0085] It is understood that the sample interaction data can be input into the skill selection model to be trained to obtain the sample target skill as output. The pre-labeled target skill corresponding to the sample interaction data is obtained, and the loss value between the sample target skill and the pre-labeled target skill is calculated. The skill selection model is trained based on the loss value, and finally a trained skill selection model is obtained.

[0086] As a possible example, the above natural language text information is input into a pre-trained skill selection model, the skill selection model determines the target skill corresponding to the interaction data based on the natural language text information, and the skill selection model outputs the target skill corresponding to the interaction data.

[0087] Step 307: Determine the corresponding first reply statement based on the target skill and the analysis result.

[0088] As a possible example, a reply statement corresponding to the target skill and analysis result can be pre-set. In response to determining the target skill and analysis result, a reply statement corresponding to the target skill and analysis result is obtained, and the reply statement is used as the first reply statement for the above-mentioned intelligent interactive device to interact with the user.

[0089] According to the intelligent interaction method of the embodiment of the present application, natural language text information is input into a pre-trained skill selection model to obtain a target skill corresponding to the interaction data. Based on the target skill and the analysis results, the corresponding first reply statement is determined, so that the target skill corresponding to the interaction data can be determined based on the natural language text information, thereby improving the accuracy of the first reply statement.

[0090] In order to ensure that the intelligent interactive device can interact with the user according to the first reply statement, optionally, the first reply statement is sent to the intelligent interactive device. Figure 4 It is a schematic diagram according to the fourth embodiment of the present application. It should be noted that the intelligent interaction method of the embodiment of the present application can be executed by the intelligent interaction device in the embodiment of the present application. In some embodiments of the present application, such as Figure 4 As shown, the intelligent interaction method includes:

[0091] Step 401: Acquire interaction data between the object and the intelligent interactive device.

[0092] In the embodiments of the present application, step 401 can be implemented in any of the ways in the embodiments of the present application. The embodiments of the present application do not limit this and will not be described in detail.

[0093] Step 402: Determine the type of the interaction data.

[0094] In the embodiment of the present application, step 402 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0095] Step 404 : In response to the interaction data being of a non-natural language interaction data type, knowledge data corresponding to the interaction data is acquired from a knowledge base.

[0096] In the embodiment of the present application, step 404 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0097] Step 404 : Based on the knowledge data, the interaction data is analyzed according to preset analysis rules to obtain analysis results.

[0098] In the embodiment of the present application, step 404 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0099] Step 405: Generate corresponding natural language text information based on the analysis results.

[0100] In the embodiment of the present application, step 405 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0101] Step 406: Input the natural language text information into the pre-trained skill selection model to obtain the target skill corresponding to the interaction data.

[0102] In the embodiment of the present application, step 406 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0103] Step 407: Determine the corresponding first reply statement based on the target skill and the analysis result.

[0104] In the embodiment of the present application, step 407 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0105] Step 408: Send the first reply statement to the intelligent interactive device.

[0106] As a possible example, after determining the first reply statement, the server sends the first reply statement to the intelligent interactive device, so that the intelligent interactive device interacts with the user according to the first reply statement.

[0107] According to the intelligent interaction method of the embodiment of the present application, the first reply statement is sent to the intelligent interaction device, so that the intelligent interaction device can interact with the user according to the first reply statement.

[0108] In order to ensure that the intelligent interactive device can play the first reply statement while replying to the interactive information sent by the current user, the first reply statement and the second reply statement are optionally spliced ​​together. Figure 5 It is a schematic diagram according to the fifth embodiment of the present application. It should be noted that the intelligent interaction method of the embodiment of the present application can be executed by the intelligent interaction device in the embodiment of the present application. In some embodiments of the present application, such as Figure 5 As shown, the intelligent interaction method includes:

[0109] Step 501: Acquire interaction data between an object and an intelligent interactive device.

[0110] In the embodiments of the present application, step 501 can be implemented in any of the ways in the embodiments of the present application. The embodiments of the present application do not limit this and will not be described in detail.

[0111] Step 502: Determine the type of the interaction data.

[0112] In the embodiment of the present application, step 502 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0113] Step 504 : In response to the interaction data being of a non-natural language interaction data type, knowledge data corresponding to the interaction data is acquired from a knowledge base.

[0114] In the embodiment of the present application, step 504 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0115] Step 504: Based on the knowledge data, the interaction data is analyzed according to preset analysis rules to obtain analysis results.

[0116] In the embodiment of the present application, step 504 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0117] Step 505: Generate corresponding natural language text information based on the analysis results.

[0118] In the embodiment of the present application, step 505 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0119] Step 506: Input the natural language text information into the pre-trained skill selection model to obtain the target skill corresponding to the interaction data.

[0120] In the embodiment of the present application, step 506 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0121] Step 507: Determine the corresponding first reply statement based on the target skill and the analysis result.

[0122] In the embodiment of the present application, step 507 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0123] Step 508: In response to receiving the first voice information from the intelligent interactive device, the first voice information is recognized to obtain a first recognition result.

[0124] It should be noted that the first voice information may be an interactive voice sent by a user to the intelligent interactive device.

[0125] As a possible example, after receiving the first voice information sent by the user, the intelligent interactive device sends the first voice information to the server, and the server recognizes the first voice information to obtain a first recognition result.

[0126] For example, after the user says "I want to listen to music" to the smart speaker, the smart speaker sends the interactive voice to the server. The server recognizes the interactive voice and obtains the recognition result that the user wants to listen to music, that is, the first recognition result.

[0127] Step 509: Based on the first recognition result, generate a second reply sentence corresponding to the first recognition result.

[0128] As a possible example, based on the first recognition result, the server generates a second reply sentence corresponding to the first recognition result. For example, based on the recognition result that the user wants to listen to music, the second reply sentence "OK, play music for you" is generated.

[0129] Step 5010: Concatenate the second reply statement and the first reply statement to obtain a concatenated statement.

[0130] As a possible example, the second reply statement and the first reply statement are concatenated to obtain a concatenated statement.

[0131] For example, the first reply statement is "Based on your recent exercise situation, do you need to recommend music suitable for you to listen to while exercising?", then the spliced ​​statement can be "Okay, play music for you. Based on your recent exercise situation, do you need to recommend music suitable for you to listen to while exercising?".

[0132] Step 5011: Send the concatenated sentence to the intelligent interactive device.

[0133] As one possible example, the server sends the concatenated sentence to the smart interactive device, which then responds to the user's voice message. When the user sends an interactive message to the smart device, the smart interactive device can respond to the interactive message and also provide a corresponding reply sentence based on the non-natural language interaction data obtained from other bound smart devices.

[0134] According to the intelligent interaction method of the embodiment of the present application, in response to receiving a first voice message from the intelligent interaction device, the first voice message is recognized to obtain a first recognition result, based on the first recognition result, a second reply statement corresponding to the first recognition result is generated, the second reply statement and the first reply statement are spliced ​​together to obtain a spliced ​​statement, and the spliced ​​statement is sent to the intelligent interaction device, so that the intelligent interaction device can play the first reply statement while replying to the interaction message sent by the current user, thereby improving the intelligence level of the intelligent interaction device.

[0135] In order to determine whether to execute the target skill, optionally, in response to receiving the second voice information from the intelligent interactive device, the second voice information is recognized to obtain a second recognition result. Figure 6 It is a schematic diagram according to the sixth embodiment of the present application. It should be noted that the intelligent interaction method of the embodiment of the present application can be executed by the intelligent interaction device in the embodiment of the present application. In some embodiments of the present application, such as Figure 6 As shown, the intelligent interaction method includes:

[0136] Step 601: Acquire interaction data between an object and an intelligent interactive device.

[0137] In the embodiment of the present application, step 601 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0138] Step 602: Determine the type of the interaction data.

[0139] In the embodiments of the present application, step 602 can be implemented in any of the ways in the embodiments of the present application. The embodiments of the present application do not limit this and will not be described in detail.

[0140] Step 604 : In response to the interaction data being of a non-natural language interaction data type, knowledge data corresponding to the interaction data is acquired from a knowledge base.

[0141] In the embodiment of the present application, step 604 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0142] Step 604: Based on the knowledge data, the interaction data is analyzed according to preset analysis rules to obtain analysis results.

[0143] In the embodiment of the present application, step 604 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0144] Step 605: Generate corresponding natural language text information based on the analysis results.

[0145] In the embodiments of the present application, step 605 can be implemented in any of the ways in the embodiments of the present application. The embodiments of the present application do not limit this and will not be described in detail.

[0146] Step 606: Input the natural language text information into the pre-trained skill selection model to obtain the target skill corresponding to the interaction data.

[0147] In the embodiment of the present application, step 606 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0148] Step 607: Determine the corresponding first reply statement based on the target skill and the analysis result.

[0149] In the embodiment of the present application, step 607 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0150] Step 608: In response to receiving the second voice information from the intelligent interactive device, the second voice information is recognized to obtain a second recognition result.

[0151] It can be understood that after the intelligent interactive device receives the first reply statement sent by the server, it converts the first reply statement into voice for playback. The user gives a second voice message to reply to the first reply statement based on the voice. The intelligent interactive device sends the received second voice message to the server. The server recognizes the second voice message and obtains a second recognition result.

[0152] For example, the smart speaker plays the message "Based on your recent exercise, do you need to recommend music suitable for exercise?", and the user replies with the second voice message "OK". The smart speaker sends the second voice message to the server, and the server recognizes the second voice message, determines that the user accepts the music suitable for exercise, and uses this as the second recognition result.

[0153] Step 609 : In response to the second recognition result being acceptance of the target skill, executing the target skill.

[0154] As a possible example, in response to the server's second recognition result of the second voice information being acceptance of the target skill, the intelligent interactive device executes the above target skill.

[0155] Step 6010: In response to the second recognition result being rejection of the target skill, stop executing the target skill.

[0156] As a possible example, in response to the server's second recognition result of the second voice information being a rejection of the target skill, the intelligent interactive device stops executing the target skill.

[0157] According to the intelligent interaction method of the embodiment of the present application, in response to receiving a second voice information from the intelligent interaction device, the second voice information is recognized to obtain a second recognition result. In response to accepting the target skill as a result of the second recognition, the target skill is executed. In response to rejecting the target skill as a result of the second recognition, the execution of the target skill is stopped. This makes it possible to judge the user's intention based on the recognition result, and then determine whether to execute the target skill.

[0158] In order to ensure interaction with the user based on voice interaction data, optionally, the interaction data is recognized to obtain a third recognition result, and based on the third recognition result, a corresponding third reply statement is generated. Figure 7 It is a schematic diagram according to the seventh embodiment of the present application. It should be noted that the intelligent interaction method of the embodiment of the present application can be executed by the intelligent interaction device in the embodiment of the present application. In some embodiments of the present application, such as Figure 7 As shown, the intelligent interaction method includes:

[0159] Step 701: Acquire interaction data between an object and an intelligent interactive device.

[0160] In the embodiment of the present application, step 701 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0161] Step 702: Determine the type of the interaction data.

[0162] In the embodiment of the present application, step 702 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0163] Step 703: In response to the interaction data being of a non-natural language interaction data type, corresponding natural language text information is generated based on the interaction data, and a corresponding first reply statement is generated according to the natural language text information, and the first reply statement is sent to the intelligent interaction device.

[0164] In the embodiment of the present application, step 703 can be implemented in any of the ways in the embodiments of the present application. The embodiment of the present application does not limit this and will not be described in detail.

[0165] Step 704: In response to the interaction data being of a voice interaction data type, identify the interaction data to obtain a third recognition result.

[0166] It should be noted that the interaction data of the voice interaction data type described above can be interaction data generated by a user interacting with an intelligent interactive device through a conversation. For example, a user initiates a conversation with a smart speaker, "I want to listen to music," and the smart speaker responds with "OK, I'll play music for you," and then plays the music. The conversation content during this interaction process is interaction data of the voice interaction data type.

[0167] As a possible example, in response to the interaction data being of a voice interaction data type, the voice interaction data is converted into natural language text data, and the natural language text data is recognized to obtain a third recognition result. Optionally, the voice interaction data can be recognized as natural language text data by a voice recognition engine.

[0168] Step 705: Generate a corresponding third reply statement based on the third recognition result.

[0169] As one possible example, the third recognition result is input into a target skill selection model to obtain a target skill, and based on the target skill, a third response statement corresponding to the target skill is found. As one possible implementation example, the third response statement can be a pre-set response statement.

[0170] Step 706: Send the third reply statement to the intelligent interactive device.

[0171] As a possible example, the server sends the third reply statement to the intelligent interactive device, so as to enable the intelligent interactive device to play the third reply statement to interact with the user.

[0172] According to the intelligent interaction method of the embodiment of the present application, in response to the type of the interaction data being a voice interaction data type, the interaction data is identified, a third recognition result is obtained, and based on the third recognition result, a corresponding third reply statement is generated, and the third reply statement is sent to the intelligent interaction device, thereby realizing interaction with the user based on voice interaction data.

[0173] In order to implement the above embodiments, the present application proposes an intelligent interactive device.

[0174] Figure 8 Schematic diagram of the eighth embodiment of the present application. Figure 8 As shown, the device includes: an acquisition module 801, a determination module 802, a first generation module 803 and a second generation module 804.

[0175] An acquisition module 801 is used to acquire interaction data between an object and an intelligent interactive device;

[0176] Determination module 802, used to determine the type of interaction data;

[0177] A first generating module 803 is configured to generate corresponding natural language text information based on the interaction data in response to the interaction data belonging to a non-natural language interaction data type;

[0178] The second generating module 804 is used to generate a corresponding first reply statement according to the natural language text information.

[0179] According to the intelligent interaction device of the embodiment of the present application, the interaction data between the object and the intelligent interaction device is obtained, the type of the interaction data is determined, and in response to the type of the interaction data being a non-natural language interaction data type, corresponding natural language text information is generated based on the interaction data, and a corresponding first reply statement is generated based on the natural language text information, thereby realizing the generation of a reply statement of the intelligent interaction device based on the non-natural language interaction data, improving the intelligence level of the intelligent interaction device, and at the same time improving the user experience of the user when using the intelligent interaction device.

[0180] In order to implement the above embodiments, the present application proposes an intelligent interactive device.

[0181] Figure 9 Schematic diagram of the ninth embodiment of the present application. Figure 9As shown, the apparatus includes: an acquisition module 910 , a determination module 920 , a first generation module 930 and a second generation module 940 , wherein the first generation module 930 includes an acquisition submodule 931 , an analysis submodule 932 and a first generation submodule 933 .

[0182] An acquisition module 910 is used to acquire interaction data between an object and an intelligent interactive device;

[0183] Determination module 920, used to determine the type of interaction data;

[0184] A first generating module 930 is configured to generate corresponding natural language text information based on the interaction data in response to the interaction data belonging to a non-natural language interaction data type;

[0185] The first generation module 930 includes:

[0186] The acquisition submodule 931 is used to acquire knowledge data corresponding to the interaction data from the knowledge base;

[0187] The analysis submodule 932 is used to analyze the interaction data based on the knowledge data and according to the preset analysis rules to obtain the analysis results;

[0188] The first generating submodule 933 is used to generate corresponding natural language text information based on the analysis result.

[0189] The second generating module 940 is used to generate a corresponding first reply sentence according to the natural language text information.

[0190] According to the intelligent interactive device of the embodiment of the present application, in response to the type of the interactive data being a non-natural language interactive data type, knowledge data corresponding to the interactive data is obtained from the knowledge base, and based on the knowledge data, the interactive data is analyzed according to preset analysis rules to obtain analysis results, and based on the analysis results, corresponding natural language text information is generated, thereby realizing the conversion of non-natural language interactive data into natural language text information, and then realizing the generation of reply sentences based on the non-natural language interactive data, thereby improving the intelligence level of the intelligent interactive device.

[0191] In order to implement the above embodiments, the present application proposes an intelligent interactive device.

[0192] Figure 10 1 is a schematic diagram according to the tenth embodiment of the present application. Figure 10As shown, the device includes: an acquisition module 1010, a determination module 1020, a first generation module 1030 and a second generation module 1040, wherein the first generation module 1030 includes an acquisition submodule 1031, an analysis submodule 1032 and a first generation submodule 1033; wherein the second generation module 1040 includes an input submodule 1041 and a determination submodule 1042.

[0193] An acquisition module 1010 is used to acquire interaction data between an object and an intelligent interactive device;

[0194] Determining module 1020, used to determine the type of interaction data;

[0195] A first generating module 1030 is configured to generate corresponding natural language text information based on the interaction data in response to the interaction data belonging to a non-natural language interaction data type;

[0196] The first generation module 1030 includes:

[0197] The acquisition submodule 1031 is used to acquire knowledge data corresponding to the interaction data from the knowledge base;

[0198] The analysis submodule 1032 is used to analyze the interaction data based on the knowledge data and according to the preset analysis rules to obtain the analysis results;

[0199] The first generating submodule 1033 is used to generate corresponding natural language text information based on the analysis result.

[0200] The second generating module 1040 is used to generate a corresponding first reply sentence according to the natural language text information.

[0201] The second generation module 1040 includes:

[0202] Input submodule 1041, for inputting natural language text information into a pre-trained skill selection model to obtain a target skill corresponding to the interaction data;

[0203] The determination submodule 1042 is configured to determine the corresponding first reply statement according to the target skill and the analysis result.

[0204] According to the intelligent interactive device of the embodiment of the present application, natural language text information is input into a pre-trained skill selection model to obtain a target skill corresponding to the interaction data. Based on the target skill and the analysis result, the corresponding first reply statement is determined, so that the target skill corresponding to the interaction data can be determined based on the natural language text information, thereby improving the accuracy of the first reply statement.

[0205] In order to implement the above embodiments, the present application proposes an intelligent interactive device.

[0206] Figure 11 Schematic diagram of the eleventh embodiment of the present application. Figure 11 As shown, the device includes: an acquisition module 1110, a determination module 1120, a first generation module 1130 and a second generation module 1140, wherein the first generation module 1130 includes an acquisition submodule 1131, an analysis submodule 1132 and a first generation submodule 1133; the second generation module 1140 includes an input submodule 1141 and a determination submodule 1142; the first sending module 1150 includes a first identification submodule 1151, a second generation submodule 1152, a splicing submodule 1153 and a sending submodule 1154.

[0207] An acquisition module 1110 is configured to acquire interaction data between an object and an intelligent interactive device;

[0208] A determination module 1120 is configured to determine the type of the interaction data.

[0209] A first generating module 1130 is configured to generate corresponding natural language text information based on the interaction data in response to the interaction data belonging to a non-natural language interaction data type;

[0210] The first generation module 1130 includes:

[0211] The acquisition submodule 1131 is used to acquire knowledge data corresponding to the interaction data from the knowledge base;

[0212] The analysis submodule 1132 is used to analyze the interaction data based on the knowledge data and according to the preset analysis rules to obtain the analysis results;

[0213] The first generating submodule 1133 is used to generate corresponding natural language text information based on the analysis result.

[0214] The second generating module 1140 is used to generate a corresponding first reply sentence according to the natural language text information.

[0215] The second generation module 1140 includes:

[0216] An input submodule 1141 is used to input natural language text information into a pre-trained skill selection model to obtain a target skill corresponding to the interaction data;

[0217] The determination submodule 1142 is configured to determine the corresponding first reply statement according to the target skill and the analysis result.

[0218] The first sending module 1150 is configured to send the first reply statement to the intelligent interactive device.

[0219] The first sending module 1150 includes:

[0220] The first recognition submodule 1151 is configured to, in response to receiving the first voice information from the intelligent interactive device, recognize the first voice information and obtain a first recognition result;

[0221] The second generation submodule 1152 is configured to generate a second reply statement corresponding to the first recognition result based on the first recognition result;

[0222] The splicing submodule 1153 is used to splice the second reply statement with the first reply statement to obtain a spliced ​​statement;

[0223] The sending submodule 1154 is configured to send the concatenated sentence to the intelligent interactive device.

[0224] According to the intelligent interactive device of the embodiment of the present application, in response to receiving a first voice message from the intelligent interactive device, the first voice message is recognized to obtain a first recognition result, based on the first recognition result, a second reply statement corresponding to the first recognition result is generated, the second reply statement and the first reply statement are spliced ​​together to obtain a spliced ​​statement, and the spliced ​​statement is sent to the intelligent interactive device, so that the intelligent interactive device can play the first reply statement while replying to the interactive message sent by the current user, thereby improving the intelligence level of the intelligent interactive device.

[0225] In order to implement the above embodiments, the present application proposes an intelligent interactive device.

[0226] Figure 12 Schematic diagram of the twelfth embodiment of the present application. Figure 12 As shown, the device includes: an acquisition module 1210, a determination module 1220, a first generation module 1230 and a second generation module 1240, wherein the first generation module 1230 includes an acquisition submodule 1231, an analysis submodule 1232 and a first generation submodule 1233; wherein the second generation module 1240 includes an input submodule 1241 and a determination submodule 1242; the first sending module 1250 includes a second identification submodule 1251, a first execution submodule 1252 and a second execution submodule 1253.

[0227] An acquisition module 1210 is configured to acquire interaction data between an object and an intelligent interactive device;

[0228] Determining module 1220, used to determine the type of interaction data;

[0229] A first generating module 1230 is configured to generate corresponding natural language text information based on the interaction data in response to the interaction data belonging to a non-natural language interaction data type;

[0230] The first generation module 1230 includes:

[0231] The acquisition submodule 1231 is used to acquire knowledge data corresponding to the interaction data from the knowledge base;

[0232] The analysis submodule 1232 is used to analyze the interaction data based on the knowledge data and according to the preset analysis rules to obtain the analysis results;

[0233] The first generating submodule 1233 is used to generate corresponding natural language text information based on the analysis result.

[0234] The second generating module 1240 is used to generate a corresponding first reply sentence according to the natural language text information.

[0235] The second generation module 1240 includes:

[0236] An input submodule 1241 is used to input natural language text information into a pre-trained skill selection model to obtain a target skill corresponding to the interaction data;

[0237] The determination submodule 1242 is configured to determine the corresponding first reply statement according to the target skill and the analysis result.

[0238] The first sending module 1250 is configured to send the first reply statement to the intelligent interactive device.

[0239] The first sending module 1250 includes:

[0240] The second recognition submodule 1251 is configured to, in response to receiving the second voice information from the intelligent interactive device, recognize the second voice information and obtain a second recognition result;

[0241] The first execution submodule 1252 is configured to execute the target skill in response to the second recognition result being acceptance of the target skill;

[0242] The second execution submodule 1253 is configured to stop executing the target skill in response to the second recognition result being rejection of the target skill.

[0243] According to the intelligent interactive device of the embodiment of the present application, in response to receiving the second voice information from the intelligent interactive device, the second voice information is recognized to obtain a second recognition result. In response to accepting the target skill as a result of the second recognition, the target skill is executed. In response to rejecting the target skill as a result of the second recognition, the execution of the target skill is stopped. In this way, the user's intention can be judged according to the recognition result, and then it is determined whether to execute the target skill.

[0244] In order to implement the above embodiments, the present application proposes an intelligent interactive device.

[0245] Figure 13 Schematic diagram of the thirteenth embodiment of the present application. Figure 13 As shown, the apparatus includes: an acquisition module 1301 , a determination module 1302 , a first generation module 1303 and a second generation module 1304 .

[0246] An acquisition module 1301 is used to acquire interaction data between an object and an intelligent interactive device;

[0247] Determining module 1302, used to determine the type of interaction data;

[0248] A first generating module 1303 is configured to generate corresponding natural language text information based on the interaction data in response to the interaction data belonging to a non-natural language interaction data type;

[0249] The second generating module 1304 is used to generate a corresponding first reply sentence according to the natural language text information.

[0250] An identification module 1305 is configured to identify the interaction data in response to the interaction data being of a voice interaction data type, and obtain a third recognition result;

[0251] A third generating module 1306 is configured to generate a corresponding third reply statement based on the third recognition result;

[0252] The second sending module 1307 is configured to send the third reply statement to the intelligent interactive device.

[0253] According to the intelligent interaction device of the embodiment of the present application, in response to the type of the interaction data being a voice interaction data type, the interaction data is identified to obtain a third recognition result, and based on the third recognition result, a corresponding third reply statement is generated, and the third reply statement is sent to the intelligent interaction device, thereby realizing interaction with the user based on voice interaction data.

[0254] It should be noted that the acquisition, storage and application of user personal information involved in the technical solution of this application are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0255] According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.

[0256] like Figure 14, is a block diagram of an electronic device according to a method of intelligent interaction according to an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0257] like Figure 14 As shown, the electronic device includes: one or more processors 1401, a memory 1402, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the electronic device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 14 A processor 1401 is taken as an example.

[0258] Memory 1402 is the non-transitory computer-readable storage medium provided in this application. The memory stores instructions executable by at least one processor to cause the at least one processor to perform the intelligent interaction method provided in this application. The non-transitory computer-readable storage medium of this application stores computer instructions for causing a computer to perform the intelligent interaction method provided in this application.

[0259] The memory 1402 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as the program instructions / modules corresponding to the intelligent interaction method in the embodiment of the present application (for example, the attached Figure 8 The processor 1401 executes the non-transient software programs, instructions, and modules stored in the memory 1402 to execute various functional applications and data processing of the server, that is, to implement the intelligent interaction method in the above method embodiment.

[0260] The memory 1402 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store data created based on the use of the intelligent interactive electronic device, etc. In addition, the memory 1402 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 1402 may optionally include a memory remotely located relative to the processor 1401, and these remote memories may be connected to the intelligent interactive electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0261] The electronic device of the intelligent interaction method may further include: an input device 1403 and an output device 1404. The processor 1401, the memory 1402, the input device 1403 and the output device 1404 may be connected via a bus or other means. Figure 14 The bus connection is taken as an example.

[0262] The input device 1403 can receive input digital or character information and generate key signal input related to user settings and function control of the intelligent interactive electronic device, such as input devices such as a touch screen, a keypad, a mouse, a trackpad, a touch pad, an indicator stick, one or more mouse buttons, a trackball, and a joystick. The output device 1404 may include a display device, an auxiliary lighting device (e.g., an LED), and a tactile feedback device (e.g., a vibration motor). The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some embodiments, the display device may be a touch screen.

[0263] Various implementations of the systems and techniques described herein can be realized in digital electronic circuit systems, integrated circuit systems, dedicated ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0264] These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for a programmable processor and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and / or device (e.g., a magnetic disk, an optical disk, a memory, a programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0265] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0266] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0267] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. The client-server relationship is established by computer programs running on the respective computers and establishing a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, a host product within a cloud computing service ecosystem that addresses the management difficulties and limited business scalability of traditional physical hosts and VPS services ("Virtual Private Servers" or "VPS").

[0268] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this application can be achieved. This is not a limitation herein.

[0269] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the scope of protection of this application.

Claims

1. An intelligent interaction method, comprising: Acquiring interaction data between the subject and the intelligent interactive device, the interaction data including voice interaction data and non-natural language interaction data, the non-natural language interaction data being physiological parameter data obtained by the intelligent detection device detecting the user's physiological state; Determining the type of the interaction data; In response to the type of the interaction data being a non-natural language interaction data type, Acquire knowledge data corresponding to the interaction data from a knowledge base, where the knowledge base is an expert knowledge base in the knowledge field to which the interaction data belongs; Based on the knowledge data, analyzing the interaction data according to preset analysis rules to obtain analysis results; Based on the analysis results, generating corresponding natural language text information; Inputting the natural language text information into a pre-trained skill selection model to obtain a target skill corresponding to the interaction data; Determine a corresponding first reply statement according to the target skill and the analysis result.

2. The method according to claim 1, wherein Also includes: The first reply statement is sent to the intelligent interactive device.

3. The method according to claim 2, wherein: The sending the first reply statement to the intelligent interactive device includes: In response to receiving a first voice message from the intelligent interactive device, recognizing the first voice message to obtain a first recognition result; Based on the first recognition result, generating a second reply sentence corresponding to the first recognition result; concatenating the second reply statement with the first reply statement to obtain a concatenated statement; The concatenated sentence is sent to the intelligent interactive device.

4. The method according to claim 2, wherein: The sending of the first reply statement to the intelligent interactive device further includes: In response to receiving a second voice message from the intelligent interactive device, recognizing the second voice message to obtain a second recognition result; In response to the second recognition result being acceptance of the target skill, executing the target skill; In response to the second recognition result being rejection of the target skill, execution of the target skill is stopped.

5. The method according to claim 1, wherein Also includes: In response to the type of the interaction data being a voice interaction data type, identifying the interaction data to obtain a third recognition result; Based on the third recognition result, generating a corresponding third reply statement; The third reply statement is sent to the intelligent interactive device.

6. An intelligent interactive device, comprising: An acquisition module is used to acquire interaction data between the object and the intelligent interactive device, wherein the interaction data includes voice interaction data and non-natural language interaction data. The non-natural language interaction data is physiological parameter data obtained by the intelligent detection device detecting the physiological state of the user; A determination module, configured to determine the type of the interaction data; a first generating module, configured to generate corresponding natural language text information based on the interaction data in response to the interaction data belonging to a non-natural language interaction data type; A second generating module is used to generate a corresponding first reply sentence according to the natural language text information; Wherein, the first generation module includes: An acquisition submodule, configured to acquire knowledge data corresponding to the interaction data from a knowledge base; An analysis submodule, configured to analyze the interaction data based on the knowledge data and in accordance with preset analysis rules to obtain analysis results; A first generating submodule, configured to generate corresponding natural language text information based on the analysis result; The second generation module includes: An input submodule, configured to input the natural language text information into a pre-trained skill selection model to obtain a target skill corresponding to the interaction data; The determination submodule is used to determine the corresponding first reply statement according to the target skill and the analysis result.

7. The device according to claim 6, wherein Also includes: The first sending module is used to send the first reply statement to the intelligent interactive device.

8. The device according to claim 7, wherein The first sending module includes: a first recognition submodule, configured to, in response to receiving first voice information from the intelligent interactive device, recognize the first voice information and obtain a first recognition result; A second generation submodule, configured to generate a second reply statement corresponding to the first recognition result based on the first recognition result; a concatenation submodule, configured to concatenate the second reply statement and the first reply statement to obtain a concatenated statement; The sending submodule is used to send the spliced ​​sentence to the intelligent interactive device.

9. The device according to claim 7, wherein The first sending module further includes: a second recognition submodule, configured to, in response to receiving second voice information from the intelligent interactive device, recognize the second voice information to obtain a second recognition result; a first execution submodule, configured to execute the target skill in response to the second recognition result being acceptance of the target skill; The second execution submodule is configured to stop executing the target skill in response to the second recognition result being a rejection of the target skill.

10. The device according to claim 6, wherein Also includes: an identification module, configured to identify the interaction data in response to the interaction data being of a voice interaction data type, and obtain a third identification result; A third generating module, configured to generate a corresponding third reply statement based on the third recognition result; The second sending module is used to send the third reply statement to the intelligent interactive device.

11. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 5.

13. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the steps of the intelligent interaction method according to any one of claims 1 to 5.

Images