Response method and system based on artificial intelligence

Abstract

The present invention discloses an answering method and system based on artificial intelligence, the method comprising: obtaining the voice data of the current user and the sensor data of the current environment through the access control device; determining the visitor scene corresponding to the current user according to the sensor data of the current environment based on the neural network algorithm; screening out a target prediction neural network from a plurality of candidate answer prediction neural networks according to the visitor scene and the voice data; inputting the voice data into the target prediction neural network to generate answering data, and displaying the answering data to the current user through the access control device. It can be seen that the present invention can realize fully automated and realistic visitor answering, improve the intelligence level of visitor answering service, and improve user experience.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an artificial intelligence-based response method and system. Background Art

[0002] With the popularization and development of smart access control equipment, more and more users use smart answering mode to deal with visitors when residents are not at home. However, most of the existing smart answering technologies only use pre-recorded user language and cannot realize intelligent recognition of visitor scenes to make more intelligent and natural answers. Therefore, their intelligence level is not high and the user experience is poor. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide an artificial intelligence-based answering method and system, which can realize fully automated and realistic visitor answering, improve the intelligence level of visitor answering service, and improve user experience.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses an artificial intelligence-based answering method, the method comprising:

[0005] Acquire the current user's voice data and sensor data of the current environment through the access control device;

[0006] Based on a neural network algorithm, determining a visitor scene corresponding to the current user according to the sensor data of the current environment;

[0007] According to the visitor scenario and the voice data, a target prediction neural network is selected from a plurality of candidate response prediction neural networks;

[0008] The voice data is input into the target prediction neural network to generate response data, and the response data is displayed to the current user through the access control device.

[0009] As an optional implementation, in the first aspect of the present invention, the response data is response text and / or response voice.

[0010] As an optional implementation, in the first aspect of the present invention, the sensing data includes temperature data, humidity data, image data, infrared ranging data and light reflection three-dimensional modeling data.

[0011] As an optional implementation, in the first aspect of the present invention, the determining the visitor scene corresponding to the current user based on the sensor data of the current environment based on the neural network algorithm includes:

[0012] Inputting the image data in the sensor data of the current environment into the face image recognition algorithm model to obtain the face recognition result;

[0013] Determine whether the current user is the homeowner user according to the face recognition result, and obtain a first judgment result;

[0014] If the first judgment result is yes, determining that the visitor scene corresponding to the current user is the homeowner scene;

[0015] If the second judgment result is no, the visitor scene corresponding to the current user is determined according to the sensor data of the current environment and a preset algorithm model.

[0016] As an optional implementation, in the first aspect of the present invention, determining the visitor scene corresponding to the current user according to the sensor data of the current environment and a preset algorithm model includes:

[0017] Inputting the image data, infrared ranging data and light reflection three-dimensional modeling data in the sensor data of the current environment into the trained identity recognition neural network to obtain the visitor type of the current user;

[0018] Inputting the temperature data, humidity data and image data in the sensor data of the current environment into the trained weather recognition neural network to obtain the weather type of the current environment;

[0019] According to the visitor type and the weather type, based on a preset scene correspondence relationship, a visitor scene corresponding to the current user is determined.

[0020] As an optional embodiment, in the first aspect of the present invention, the visitor scenario is a rain shelter scenario, a summer escape scenario, a consumption scenario, a dangerous scenario, a home visit scenario, a sales promotion scenario, or a friend or relative visit scenario.

[0021] As an optional implementation, in the first aspect of the present invention, the step of selecting a target prediction neural network from a plurality of candidate response prediction neural networks according to the visitor scenario and the voice data comprises:

[0022] For each candidate response prediction neural network, obtaining a model training record and a model verification record of the response prediction neural network;

[0023] Calculating the scene similarity between the scene annotation of the training data in the model training record and the visitor scene;

[0024] Calculating a verification success rate corresponding to similar voice data corresponding to the voice data in the model verification record;

[0025] Calculating the product of the scene similarity and the verification success rate to obtain a network priority parameter corresponding to the response prediction neural network;

[0026] The response prediction neural network with the highest network priority parameter is determined as the target prediction neural network.

[0027] As an optional implementation, in the first aspect of the present invention, the calculating the verification success rate corresponding to the similar voice data corresponding to the voice data in the model verification record includes:

[0028] Inputting the speech data into a trained tone recognition network and a speech rate recognition network to obtain tone type and speech rate information of the speech data;

[0029] Calculating parameter similarity between speech parameters of speech data corresponding to each record in the model verification record and speech parameters of the speech data; the speech parameters include the tone type and the speech speed information;

[0030] Determine the voice data whose parameter similarity is greater than a preset similarity threshold as similar voice data;

[0031] The proportion of successfully predicted records in the verification records corresponding to all the similar voice data in the model verification records is calculated to obtain a verification success rate.

[0032] A second aspect of an embodiment of the present invention discloses an artificial intelligence-based response system, the system comprising:

[0033] The acquisition module is used to acquire the voice data of the current user and the sensor data of the current environment through the access control device;

[0034] A determination module, configured to determine a visitor scene corresponding to the current user based on the sensor data of the current environment based on a neural network algorithm;

[0035] A screening module, used for screening a target prediction neural network from a plurality of candidate answer prediction neural networks according to the visitor scenario and the voice data;

[0036] A display module is used to input the voice data into the target prediction neural network to generate response data, and the response data is displayed to the current user through the access control device.

[0037] As an optional implementation, in the second aspect of the present invention, the response data is response text and / or response voice.

[0038] As an optional implementation, in the second aspect of the present invention, the sensing data includes temperature data, humidity data, image data, infrared ranging data and light reflection three-dimensional modeling data.

[0039] As an optional implementation, in the second aspect of the present invention, the specific manner in which the determination module determines the visitor scene corresponding to the current user based on the sensor data of the current environment based on a neural network algorithm includes:

[0040] Inputting the image data in the sensor data of the current environment into the face image recognition algorithm model to obtain the face recognition result;

[0041] Determine whether the current user is the homeowner user according to the face recognition result, and obtain a first judgment result;

[0042] If the first judgment result is yes, determining that the visitor scene corresponding to the current user is the homeowner scene;

[0043] If the second judgment result is no, the visitor scene corresponding to the current user is determined according to the sensor data of the current environment and a preset algorithm model.

[0044] As an optional implementation, in the second aspect of the present invention, the specific manner in which the determination module determines the visitor scene corresponding to the current user according to the sensor data of the current environment and a preset algorithm model includes:

[0045] Inputting the image data, infrared ranging data and light reflection three-dimensional modeling data in the sensor data of the current environment into the trained identity recognition neural network to obtain the visitor type of the current user;

[0046] Inputting the temperature data, humidity data and image data in the sensor data of the current environment into the trained weather recognition neural network to obtain the weather type of the current environment;

[0047] According to the visitor type and the weather type, based on a preset scene correspondence relationship, a visitor scene corresponding to the current user is determined.

[0048] As an optional implementation, in the second aspect of the present invention, the visitor scenario is a rain shelter scenario, a summer escape scenario, a consumption scenario, a dangerous scenario, a home visit scenario, a sales promotion scenario, or a friend or relative visit scenario.

[0049] As an optional implementation, in the second aspect of the present invention, the specific manner in which the screening module screens out a target prediction neural network from a plurality of candidate answer prediction neural networks according to the visitor scenario and the voice data includes:

[0050] For each candidate response prediction neural network, obtaining a model training record and a model verification record of the response prediction neural network;

[0051] Calculating the scene similarity between the scene annotation of the training data in the model training record and the visitor scene;

[0052] Calculating a verification success rate corresponding to similar voice data corresponding to the voice data in the model verification record;

[0053] Calculating the product of the scene similarity and the verification success rate to obtain a network priority parameter corresponding to the response prediction neural network;

[0054] The response prediction neural network with the highest network priority parameter is determined as the target prediction neural network.

[0055] As an optional implementation, in the second aspect of the present invention, the specific manner in which the screening module calculates the verification success rate corresponding to the similar voice data corresponding to the voice data in the model verification record includes:

[0056] Inputting the speech data into a trained tone recognition network and a speech rate recognition network to obtain tone type and speech rate information of the speech data;

[0057] Calculating parameter similarity between speech parameters of speech data corresponding to each record in the model verification record and speech parameters of the speech data; the speech parameters include the tone type and the speech speed information;

[0058] Determine the voice data whose parameter similarity is greater than a preset similarity threshold as similar voice data;

[0059] The proportion of successfully predicted records in the verification records corresponding to all the similar voice data in the model verification records is calculated to obtain a verification success rate.

[0060] The third aspect of the present invention discloses another artificial intelligence-based response system, the system comprising:

[0061] A memory storing executable program code;

[0062] a processor coupled to the memory;

[0063] The processor calls the executable program code stored in the memory to execute part or all of the steps in the artificial intelligence-based answering method disclosed in the first aspect of the present invention.

[0064] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the artificial intelligence-based response method disclosed in the first aspect of the present invention.

[0065] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0066] The present invention can determine the visitor scene corresponding to the current user according to the sensor data of the current environment based on the neural network algorithm, and then screen out the target prediction neural network from multiple candidate response prediction neural networks based on the visitor scene and voice data to realize the prediction and display of response data for user voice data, thereby realizing fully automated and realistic visitor response, improving the intelligence level of visitor response service, and improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0068] Figure 1 It is a flow chart of an artificial intelligence-based answering method disclosed in an embodiment of the present invention.

[0069] Figure 2 It is a structural diagram of an artificial intelligence-based response system disclosed in an embodiment of the present invention.

[0070] Figure 3 It is a structural diagram of another artificial intelligence-based response system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0071] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0072] The terms "first", "second", etc. in the specification and claims of the present invention 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, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0073] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0074] The present invention discloses an artificial intelligence-based answering method and system, which can determine the visitor scene corresponding to the current user according to the sensor data of the current environment based on the neural network algorithm, and then select a target prediction neural network from multiple candidate answer prediction neural networks based on the visitor scene and voice data to predict and display the answer data of the user's voice data, thereby realizing fully automated and realistic visitor answering, improving the intelligence level of visitor answering services, and improving user experience. The following are detailed descriptions.

[0075] Embodiment 1

[0076] See also Figure 1 , Figure 1 : is a flow chart of an artificial intelligence-based answering method disclosed in an embodiment of the present invention. Figure 1 The described artificial intelligence-based answering method can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the artificial intelligence-based answering method may include the following operations:

[0077] 101. Acquire the voice data of the current user and the sensor data of the current environment through the access control device.

[0078] 102. Based on the neural network algorithm, the visitor scene corresponding to the current user is determined according to the sensor data of the current environment.

[0079] 103. According to the visitor scenario and voice data, a target prediction neural network is selected from multiple candidate response prediction neural networks.

[0080] 104. Input the voice data into the target prediction neural network to generate response data, and display the response data to the current user through the access control device.

[0081] It can be seen that the above-mentioned embodiments of the invention can determine the visitor scene corresponding to the current user according to the sensor data of the current environment based on the neural network algorithm, and then screen out the target prediction neural network from multiple candidate response prediction neural networks based on the visitor scene and voice data to realize the prediction and display of the response data of the user's voice data, thereby realizing fully automated and realistic visitor responses, improving the intelligence level of visitor response services, and improving user experience.

[0082] As an optional embodiment, in the above steps, the response data is response text and / or response voice.

[0083] It can be seen that through the above optional embodiments, the type of response data is limited, which is convenient for providing users with a variety of response display options, assisting in achieving fully automated and realistic visitor responses, improving the intelligence level of visitor response services, and improving user experience.

[0084] As an optional embodiment, in the above steps, the sensing data includes temperature data, humidity data, image data, infrared ranging data and light reflection three-dimensional modeling data.

[0085] It can be seen that through the above optional embodiments, the content of the sensor data is limited, which facilitates the subsequent accurate prediction of visitor scenarios, assists in achieving fully automated and realistic visitor responses, improves the intelligence level of visitor response services, and improves user experience.

[0086] As an optional embodiment, in the above steps, based on the neural network algorithm, according to the sensor data of the current environment, determining the visitor scene corresponding to the current user includes:

[0087] Input the image data in the sensor data of the current environment into the face image recognition algorithm model to obtain the face recognition result;

[0088] According to the face recognition result, determine whether the current user is the homeowner user, and obtain a first judgment result;

[0089] If the first judgment result is yes, it is determined that the visitor scene corresponding to the current user is the homeowner scene;

[0090] If the second judgment result is no, the visitor scene corresponding to the current user is determined based on the sensor data of the current environment and the preset algorithm model.

[0091] It can be seen that through the above-mentioned optional embodiments, the face recognition result can be obtained based on the image data in the sensor data of the current environment and the face image recognition algorithm model to determine whether the current user is the homeowner. If not, more complex scene predictions can be further performed to achieve low-cost and high-efficiency scene judgment, so as to facilitate the subsequent screening of suitable target prediction neural networks to realize response prediction, assist in realizing fully automated and realistic visitor responses, improve the intelligence level of visitor response services, and improve user experience.

[0092] As an optional embodiment, in the above steps, determining the visitor scene corresponding to the current user according to the sensor data of the current environment and a preset algorithm model includes:

[0093] Input the image data, infrared ranging data and light reflection 3D modeling data in the current environment sensor data into the trained identity recognition neural network to obtain the visitor type of the current user;

[0094] Input the temperature data, humidity data and image data in the current environment sensor data into the trained weather recognition neural network to obtain the weather type of the current environment;

[0095] According to the visitor type and weather type, based on the preset scene correspondence, the visitor scene corresponding to the current user is determined.

[0096] It can be seen that through the above-mentioned optional embodiments, the visitor type and weather type can be determined through neural networks based on the sensor data of the current environment, so as to comprehensively and accurately determine the visitor scene, so as to facilitate the subsequent screening of suitable target prediction neural networks to realize response prediction, assist in realizing fully automated and realistic visitor responses, improve the intelligence level of visitor response services, and improve user experience.

[0097] As an optional embodiment, in the above steps, the visitor scenario is a rain shelter scenario, a summer vacation scenario, a consumption scenario, a dangerous scenario, a home visit scenario, a sales promotion scenario, or a friend or relative visit scenario.

[0098] It can be seen that through the above optional embodiments, the types of visitor scenarios are limited, and the scene characteristics are better characterized, so as to facilitate the subsequent screening of suitable target prediction neural networks to realize response prediction, assist in realizing fully automated and realistic visitor responses, improve the intelligence level of visitor response services, and improve user experience.

[0099] As an optional embodiment, in the above steps, selecting a target prediction neural network from a plurality of candidate answer prediction neural networks according to the visitor scenario and voice data includes:

[0100] For each candidate response prediction neural network, obtaining a model training record and a model verification record of the response prediction neural network;

[0101] Calculate the scene similarity between the scene annotations of the training data in the model training record and the visitor scene;

[0102] Calculate the verification success rate of similar voice data corresponding to the voice data in the model verification record;

[0103] Calculate the product of the scene similarity and the verification success rate to obtain the network priority parameters corresponding to the response prediction neural network;

[0104] The answer prediction neural network with the highest network priority parameter is determined as the target prediction neural network.

[0105] It can be seen that through the above-mentioned optional embodiments, it is possible to screen out a more suitable network through the scene similarity in the training of the model and the verification success rate of more similar voice data in the verification record, realize fully automated and realistic visitor response, improve the intelligence level of the visitor response service, and improve the user experience.

[0106] As an optional embodiment, in the above step, calculating the verification success rate of similar voice data corresponding to the voice data in the model verification record includes:

[0107] Input the speech data into the trained tone recognition network and speech rate recognition network to obtain the tone type and speech rate information of the speech data;

[0108] Calculating the parameter similarity between the voice parameters of the voice data corresponding to each record in the model verification record and the voice parameters of the voice data; optionally, the voice parameters include tone type and speech speed information;

[0109] Determine the speech data whose parameter similarity is greater than a preset similarity threshold as similar speech data;

[0110] The verification success rate is obtained by calculating the proportion of successfully predicted records in the verification records corresponding to all similar speech data in the model verification records.

[0111] It can be seen that through the above-mentioned optional embodiments, it is possible to compare and calculate the similarity in tone and speaking speed between the voice data in the verification record of the model and the current voice data to screen out more similar voice data, and further calculate the verification success rate of the more similar voice data to screen out a more suitable network, thereby realizing fully automated and realistic visitor responses, improving the intelligence level of visitor response services, and improving user experience.

[0112] Embodiment 2

[0113] See also Figure 2 , Figure 2 : is a schematic diagram of a structure of an artificial intelligence-based response system disclosed in an embodiment of the present invention. Figure 2 The described artificial intelligence-based response system can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the artificial intelligence-based response system may include:

[0114] The acquisition module 201 is used to acquire the voice data of the current user and the sensor data of the current environment through the access control device.

[0115] The determination module 202 is used to determine the visitor scene corresponding to the current user based on the neural network algorithm and the sensor data of the current environment.

[0116] The screening module 203 is used to screen out a target prediction neural network from multiple candidate answer prediction neural networks according to the visitor scenario and voice data.

[0117] The display module 204 is used to input the voice data into the target prediction neural network to generate response data, and the response data is displayed to the current user through the access control device.

[0118] It can be seen that the above-mentioned embodiments of the invention can determine the visitor scene corresponding to the current user according to the sensor data of the current environment based on the neural network algorithm, and then screen out the target prediction neural network from multiple candidate response prediction neural networks based on the visitor scene and voice data to realize the prediction and display of the response data of the user's voice data, thereby realizing fully automated and realistic visitor responses, improving the intelligence level of visitor response services, and improving user experience.

[0119] As an optional embodiment, the response data is response text and / or response voice.

[0120] It can be seen that through the above optional embodiments, the type of response data is limited, which is convenient for providing users with a variety of response display options, assisting in achieving fully automated and realistic visitor responses, improving the intelligence level of visitor response services, and improving user experience.

[0121] As an optional embodiment, the sensing data includes temperature data, humidity data, image data, infrared ranging data and light reflection three-dimensional modeling data.

[0122] It can be seen that through the above optional embodiments, the content of the sensor data is limited, which facilitates the subsequent accurate prediction of visitor scenarios, assists in achieving fully automated and realistic visitor responses, improves the intelligence level of visitor response services, and improves user experience.

[0123] As an optional embodiment, the determination module determines the specific manner of the visitor scene corresponding to the current user based on the neural network algorithm and the sensor data of the current environment, including:

[0124] Input the image data in the sensor data of the current environment into the face image recognition algorithm model to obtain the face recognition result;

[0125] According to the face recognition result, determine whether the current user is the homeowner user, and obtain a first judgment result;

[0126] If the first judgment result is yes, it is determined that the visitor scene corresponding to the current user is the homeowner scene;

[0127] If the second judgment result is no, the visitor scene corresponding to the current user is determined based on the sensor data of the current environment and the preset algorithm model.

[0128] It can be seen that through the above-mentioned optional embodiments, the face recognition result can be obtained based on the image data in the sensor data of the current environment and the face image recognition algorithm model to determine whether the current user is the homeowner. If not, more complex scene predictions can be further performed to achieve low-cost and high-efficiency scene judgment, so as to facilitate the subsequent screening of suitable target prediction neural networks to realize response prediction, assist in realizing fully automated and realistic visitor responses, improve the intelligence level of visitor response services, and improve user experience.

[0129] As an optional embodiment, the determination module determines the specific manner of the visitor scene corresponding to the current user according to the sensor data of the current environment and the preset algorithm model, including:

[0130] Input the image data, infrared ranging data and light reflection 3D modeling data in the current environment sensor data into the trained identity recognition neural network to obtain the visitor type of the current user;

[0131] Input the temperature data, humidity data and image data in the current environment sensor data into the trained weather recognition neural network to obtain the weather type of the current environment;

[0132] According to the visitor type and weather type, based on the preset scene correspondence, the visitor scene corresponding to the current user is determined.

[0133] It can be seen that through the above-mentioned optional embodiments, the visitor type and weather type can be determined through neural networks based on the sensor data of the current environment, so as to comprehensively and accurately determine the visitor scene, so as to facilitate the subsequent screening of suitable target prediction neural networks to realize response prediction, assist in realizing fully automated and realistic visitor responses, improve the intelligence level of visitor response services, and improve user experience.

[0134] As an optional embodiment, the visitor scenario is a rain shelter scenario, a summer vacation scenario, a consumption scenario, a dangerous scenario, a home visit scenario, a sales promotion scenario, or a friend or relative visit scenario.

[0135] It can be seen that through the above optional embodiments, the types of visitor scenarios are limited, and the scene characteristics are better characterized, so as to facilitate the subsequent screening of suitable target prediction neural networks to realize response prediction, assist in realizing fully automated and realistic visitor responses, improve the intelligence level of visitor response services, and improve user experience.

[0136] As an optional embodiment, the specific method of the screening module screening out the target prediction neural network from multiple candidate answer prediction neural networks according to the visitor scenario and voice data includes:

[0137] For each candidate response prediction neural network, obtaining a model training record and a model verification record of the response prediction neural network;

[0138] Calculate the scene similarity between the scene annotations of the training data in the model training record and the visitor scene;

[0139] Calculate the verification success rate of similar voice data corresponding to the voice data in the model verification record;

[0140] Calculate the product of the scene similarity and the verification success rate to obtain the network priority parameters corresponding to the response prediction neural network;

[0141] The answer prediction neural network with the highest network priority parameter is determined as the target prediction neural network.

[0142] It can be seen that through the above-mentioned optional embodiments, it is possible to screen out a more suitable network through the scene similarity in the training of the model and the verification success rate of more similar voice data in the verification record, realize fully automated and realistic visitor response, improve the intelligence level of the visitor response service, and improve the user experience.

[0143] As an optional embodiment, the specific manner in which the screening module calculates the verification success rate of the similar voice data corresponding to the voice data in the model verification record includes:

[0144] Input the speech data into the trained tone recognition network and speech rate recognition network to obtain the tone type and speech rate information of the speech data;

[0145] Calculating the parameter similarity between the voice parameters of the voice data corresponding to each record in the model verification record and the voice parameters of the voice data; optionally, the voice parameters include tone type and speech speed information;

[0146] Determine the speech data whose parameter similarity is greater than a preset similarity threshold as similar speech data;

[0147] The verification success rate is obtained by calculating the proportion of successfully predicted records in the verification records corresponding to all similar speech data in the model verification records.

[0148] It can be seen that through the above-mentioned optional embodiments, it is possible to compare and calculate the similarity in tone and speaking speed between the voice data in the verification record of the model and the current voice data to screen out more similar voice data, and further calculate the verification success rate of the more similar voice data to screen out a more suitable network, thereby realizing fully automated and realistic visitor responses, improving the intelligence level of visitor response services, and improving user experience.

[0149] Embodiment 3

[0150] See also Figure 3 , Figure 3 It is another artificial intelligence-based response system disclosed in the embodiment of the present invention. Figure 3 The described artificial intelligence-based response system is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the artificial intelligence-based response system may include:

[0151] A memory 301 storing executable program codes;

[0152] a processor 302 coupled to the memory 301;

[0153] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the artificial intelligence-based answering method described in the first embodiment.

[0154] Embodiment 4

[0155] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the artificial intelligence-based response method described in the first embodiment.

[0156] Embodiment 5

[0157] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the artificial intelligence-based response method described in Example 1.

[0158] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0159] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0160] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0161] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0162] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0163] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0164] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0165] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0166] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0167] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0168] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0169] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0170] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0171] Finally, it should be noted that the artificial intelligence-based response method and system disclosed in the embodiments of the present invention only disclose the preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A response method based on artificial intelligence, characterized in that: The method comprises: Acquire the current user's voice data and sensor data of the current environment through the access control device; Based on a neural network algorithm, determining a visitor scene corresponding to the current user according to the sensor data of the current environment; According to the visitor scenario and the voice data, a target prediction neural network is selected from a plurality of candidate answer prediction neural networks, including: For each candidate response prediction neural network, obtaining a model training record and a model verification record of the response prediction neural network; Calculating the scene similarity between the scene annotation of the training data in the model training record and the visitor scene; Inputting the speech data into a trained tone recognition network and a speech rate recognition network to obtain tone type and speech rate information of the speech data; Calculating parameter similarity between speech parameters of speech data corresponding to each record in the model verification record and speech parameters of the speech data; the speech parameters include the tone type and the speech speed information; Determine the voice data whose parameter similarity is greater than a preset similarity threshold as similar voice data; Calculate the proportion of successfully predicted records in the verification records corresponding to all the similar voice data in the model verification records to obtain a verification success rate; Calculating the product of the scene similarity and the verification success rate to obtain a network priority parameter corresponding to the response prediction neural network; Determine the response prediction neural network with the highest network priority parameter as the target prediction neural network; The voice data is input into the target prediction neural network to generate response data, and the response data is displayed to the current user through the access control device.

2. The artificial intelligence-based answering method according to claim 1, characterized in that: The response data is a response text and / or a response voice.

3. The artificial intelligence-based answering method according to claim 1, characterized in that: The sensing data includes temperature data, humidity data, image data, infrared ranging data and light reflection three-dimensional modeling data.

4. The artificial intelligence-based answering method according to claim 3, characterized in that: The determining, based on the neural network algorithm and according to the sensor data of the current environment, the visitor scene corresponding to the current user includes: Inputting the image data in the sensor data of the current environment into the face image recognition algorithm model to obtain the face recognition result; Determine whether the current user is a homeowner user according to the face recognition result, and obtain a first judgment result; If the first judgment result is yes, determining that the visitor scene corresponding to the current user is the homeowner scene; If the first judgment result is no, the visitor scene corresponding to the current user is determined according to the sensor data of the current environment and a preset algorithm model.

5. The artificial intelligence-based answering method according to claim 4, characterized in that: Determining the visitor scene corresponding to the current user according to the sensor data of the current environment and a preset algorithm model includes: Inputting the image data, infrared ranging data and light reflection three-dimensional modeling data in the sensor data of the current environment into the trained identity recognition neural network to obtain the visitor type of the current user; Inputting the temperature data, humidity data and image data in the sensor data of the current environment into the trained weather recognition neural network to obtain the weather type of the current environment; According to the visitor type and the weather type, based on a preset scene correspondence relationship, a visitor scene corresponding to the current user is determined.

6. The artificial intelligence-based answering method according to claim 5, characterized in that: The visitor scenario is a rain shelter scenario, a summer vacation scenario, a consumption scenario, a dangerous scenario, a home visit scenario, a sales promotion scenario, or a visit scenario by relatives and friends.

7. An artificial intelligence-based response system, characterized in that: The system comprises: The acquisition module is used to acquire the voice data of the current user and the sensor data of the current environment through the access control device; A determination module, configured to determine a visitor scene corresponding to the current user based on the sensor data of the current environment based on a neural network algorithm; A screening module, used to screen out a target prediction neural network from a plurality of candidate answer prediction neural networks according to the visitor scenario and the voice data, including: For each candidate response prediction neural network, obtaining a model training record and a model verification record of the response prediction neural network; Calculating the scene similarity between the scene annotation of the training data in the model training record and the visitor scene; Inputting the speech data into a trained tone recognition network and a speech rate recognition network to obtain tone type and speech rate information of the speech data; Calculating parameter similarity between speech parameters of speech data corresponding to each record in the model verification record and speech parameters of the speech data; the speech parameters include the tone type and the speech speed information; Determine the voice data whose parameter similarity is greater than a preset similarity threshold as similar voice data; Calculate the proportion of successfully predicted records in the verification records corresponding to all the similar voice data in the model verification records to obtain a verification success rate; Calculating the product of the scene similarity and the verification success rate to obtain a network priority parameter corresponding to the response prediction neural network; Determine the response prediction neural network with the highest network priority parameter as the target prediction neural network; A display module is used to input the voice data into the target prediction neural network to generate response data, and the response data is displayed to the current user through the access control device.

8. An artificial intelligence-based response system, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the artificial intelligence-based response method as described in any one of claims 1-6.

Images