Interaction optimization method and system based on large language model

Abstract

The invention discloses an interaction optimization method and system based on a large language model. The method comprises the following steps: receiving a user instruction in a voice or character form; performing semantic understanding on the user instruction to obtain a semantic understanding result; and generating a robot action instruction according to the semantic understanding result. According to the scheme provided by the embodiment of the invention, the natural language text of the user can be automatically converted into the command which can be understood and executed by a machine, so that real two-way communication is realized. In addition, in some cases, a reply message can be generated by using a preset answer template, so that the requirements in different scenes can be better met. Through the scheme provided by the embodiment of the invention, the man-machine interaction efficiency and quality are improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an interactive optimization method and system based on a large language model. Background Art

[0002] With the development and progress of science and technology, people's living standards are gradually improving, and the demand for intelligent products is also getting higher and higher. Many products on the market have begun to have the function of human-computer interaction, but most of them are achieved through simple mechanical methods such as buttons and touch screens, lacking the real "communication". Moreover, when processing the user's natural language input, the existing robots cannot accurately understand the user's intention and give an appropriate response, resulting in a poor user experience.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present invention provide an interaction optimization method and system based on a large language model, so as to at least solve the technical problem in the related art that it is difficult for robots to accurately understand user intentions.

[0005] According to a first aspect, there is provided an artificial intelligence interaction method for an industrial robot, the method comprising:

[0006] Receive user instructions in voice or text form;

[0007] Performing semantic understanding on the user instruction to obtain a semantic understanding result;

[0008] Generate robot action instructions according to the semantic understanding results.

[0009] Furthermore, voice recognition is performed on the user instruction to obtain a voice recognition result.

[0010] Furthermore, a reply message is generated according to the user instruction.

[0011] Furthermore, a robot action instruction is generated according to the semantic understanding result and a preset action template.

[0012] Furthermore, a reply message is generated according to the semantic understanding result and a preset answer template.

[0013] Furthermore, generating robot action instructions according to the semantic understanding result includes: generating robot action instructions according to the semantic understanding result and a preset dialogue state transition model.

[0014] According to a second aspect, an artificial intelligence interaction device is provided, the device comprising:

[0015] A semantic understanding unit, configured to receive a user instruction in voice or text form, and perform semantic understanding on the user instruction to obtain a semantic understanding result;

[0016] A robot action instruction generating unit is used to generate a robot action instruction according to the semantic understanding result.

[0017] Furthermore, it also includes: a speech recognition unit, which is used to perform speech recognition on the user instruction to obtain a speech recognition result.

[0018] Furthermore, it also includes: a reply message generating unit, which is used to generate a reply message according to the user instruction.

[0019] According to a third aspect, an electronic device is provided, comprising: one or more processors; and one or more computer-readable media having one or more computer-executable instructions thereon, wherein the one or more computer-executable instructions are configured to enable the one or more processors to execute the method described in the first aspect.

[0020] According to a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0021] According to a fifth aspect, a computer program product is provided. When the computer program product is executed, the computer is caused to execute the method as described in the first aspect.

[0022] The solution provided by the embodiment of the present invention can automatically convert the user's natural language text into commands that can be understood and executed by the machine, thereby realizing true two-way communication. In addition, in some cases, a preset answer template can be used to generate a reply message to better meet the needs in different scenarios. The solution provided by the embodiment of the present application improves the efficiency and quality of human-computer interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0024] Figure 1 This is a first flow chart of an artificial intelligence interaction method provided by an embodiment of the present invention;

[0025] Figure 2 is a second flow chart of an artificial intelligence interaction method provided by an embodiment of the present invention;

[0026] Figure 3is a structural block diagram of an artificial intelligence interaction device provided by an embodiment of the present invention;

[0027] Figure 4 It is a structural block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] The embodiment of the present invention provides a specific implementation of an artificial intelligence interaction method, such as Figure 1 As shown, the following steps are included:

[0031] S201: receiving a user instruction in voice or text form;

[0032] S202: Perform semantic understanding on the user instruction to obtain a semantic understanding result;

[0033] S203: Generate robot action instructions based on the semantic understanding results.

[0034] Specifically, the sound signal emitted by the user can be collected through a microphone or other recording device, and then converted into a digital signal after a series of processing, and then processed by the speech recognition module to obtain the corresponding text information. After that, the next step can be entered - the semantic understanding stage. In this process, the input text needs to be segmented first, and then the sentence is parsed and semantically analyzed using natural language processing technology to finally obtain the actual meaning that is intended to be expressed.

[0035] The next stage is the conversation management stage. In this stage, we need to determine the current conversation state based on the information collected previously, and decide how to respond to the user based on this state. For example, if the user asks about the price of a certain product, we need to query the corresponding product information from the database and reply to the other party. Of course, in some special cases, you can directly tell the user that you don’t know the answer, but you need to pay attention to being polite and friendly.

[0036] The last step is the work of the robot controller. It is mainly responsible for coordinating the work between various subsystems and responding appropriately to the external environment. For example, when we receive messages from users, we need to pass them to the corresponding modules for processing; after completing the task, we need to promptly notify the user that the request has been completed, etc.

[0037] In addition, in the solution provided by the embodiment of the present invention, a reply message can be generated according to the user instruction. Specifically, a reply message in a fixed format can be used, or different reply messages can be dynamically generated according to actual conditions. For example, "Thank you for your feedback!", "We will reply to you as soon as possible.", etc.

[0038] It should also be noted that in some cases, different strategies may be needed to deal with different user inputs. This requires us to set up corresponding rules and conditional judgment mechanisms in advance so that we can flexibly adjust our behavior patterns.

[0039] In some embodiments, generating robot action instructions according to the semantic understanding results includes: generating robot action instructions according to the semantic understanding results and a pre-set action template. Specifically, the corresponding action template can be matched according to the semantic understanding results to generate the action instructions that the robot needs to execute. The action template can be in the form of a string or a function call, and its specific content can be defined according to the actual application scenario.

[0040] In other embodiments, generating robot action instructions according to the semantic understanding results includes: generating robot action instructions according to the semantic understanding results and a preset dialogue state transition model. Specifically, a deep reinforcement learning method can be used to train the dialogue state transition model, so that the robot can gradually learn how to correctly handle various complex situations in the process of continuous interaction with the user.

[0041] In some other embodiments, a reply message is generated based on the semantic understanding result and a preset answer template. Specifically, various types of answer templates can be designed according to different scenarios and purposes, and the reply message is generated by matching the most suitable template according to the semantic understanding result. The advantage of this method is that it can quickly generate answers that meet the specifications, and it is also easier to maintain and expand.

[0042] In summary, the solution provided by the embodiment of the present invention can automatically convert the user's natural language text into commands that can be understood and executed by the machine, thereby achieving true two-way communication. In addition, in some cases, a preset answer template can also be used to generate a reply message to better meet the needs in different scenarios. The solution provided by the embodiment of the present application improves the efficiency and quality of human-computer interaction.

[0043] The embodiment of the present invention also provides another specific implementation of an artificial intelligence interaction method, such as Figure 2 As shown, the following steps are included:

[0044] S301: receiving a user instruction in voice or text form;

[0045] S302: Perform voice recognition on the user's instruction to obtain a voice recognition result;

[0046] S303: Performing semantic understanding on the speech recognition result to obtain a semantic understanding result;

[0047] S304: Generate robot action instructions based on the semantic understanding results.

[0048] Specifically, the sound signal emitted by the user can be collected through a microphone or other recording device, and then converted into a digital signal after a series of processing, and then processed by the speech recognition module to obtain the corresponding text information. After that, the next step can be entered - the semantic understanding stage. In this process, the input text needs to be segmented first, and then the sentence is parsed and semantically analyzed using natural language processing technology to finally obtain the actual meaning that is intended to be expressed.

[0049] The next stage is the conversation management stage. In this stage, we need to determine the current conversation state based on the information collected previously, and decide how to respond to the user based on this state. For example, if the user asks about the price of a certain product, we need to query the corresponding product information from the database and reply to the other party. Of course, in some special cases, you can directly tell the user that you don’t know the answer, but you need to pay attention to being polite and friendly.

[0050] The last step is the work of the robot controller. It is mainly responsible for coordinating the work between various subsystems and responding appropriately to the external environment. For example, when we receive messages from users, we need to pass them to the corresponding modules for processing; after completing the task, we need to promptly notify the user that the request has been completed, etc.

[0051] In addition, in the solution provided by the embodiment of the present invention, a reply message can be generated according to the user instruction. Specifically, a reply message in a fixed format can be used, or different reply messages can be dynamically generated according to actual conditions. For example, "Thank you for your feedback!", "We will reply to you as soon as possible.", etc.

[0052] It should also be noted that in some cases, different strategies may be needed to deal with different user inputs. This requires us to set up corresponding rules and conditional judgment mechanisms in advance so that we can flexibly adjust our behavior patterns.

[0053] In some embodiments, generating robot action instructions according to the semantic understanding results includes: generating robot action instructions according to the semantic understanding results and a pre-set action template. Specifically, the corresponding action template can be matched according to the semantic understanding results to generate the action instructions that the robot needs to execute. The action template can be in the form of a string or a function call, and its specific content can be defined according to the actual application scenario.

[0054] In other embodiments, generating robot action instructions according to the semantic understanding results includes: generating robot action instructions according to the semantic understanding results and a preset dialogue state transition model. Specifically, a deep reinforcement learning method can be used to train the dialogue state transition model, so that the robot can gradually learn how to correctly handle various complex situations in the process of continuous interaction with the user.

[0055] In some other embodiments, a reply message is generated based on the semantic understanding result and a preset answer template. Specifically, various types of answer templates can be designed according to different scenarios and purposes, and the reply message is generated by matching the most suitable template according to the semantic understanding result. The advantage of this method is that it can quickly generate answers that meet the specifications, and it is also easier to maintain and expand.

[0056] In summary, the solution provided by the embodiment of the present invention can automatically convert the user's natural language text into commands that can be understood and executed by the machine, thereby achieving true two-way communication. In addition, in some cases, a preset answer template can also be used to generate a reply message to better meet the needs in different scenarios. The solution provided by the embodiment of the present application improves the efficiency and quality of human-computer interaction.

[0057] Based on the same concept, an embodiment of the present invention provides an artificial intelligence interaction system, such as Figure 3 As shown, including:

[0058] The semantic understanding unit 401 is used to receive a user instruction in voice or text form, and perform semantic understanding on the user instruction to obtain a semantic understanding result;

[0059] The robot action instruction generating unit 402 is used to generate the robot action instruction according to the semantic understanding result.

[0060] Furthermore, it also includes: a speech recognition unit 403, which is used to perform speech recognition on user instructions to obtain speech recognition results.

[0061] Furthermore, it also includes: a reply message generating unit 404, which is used to generate a reply message according to a user instruction.

[0062] In some embodiments, generating robot motion instructions according to semantic understanding results includes: generating robot motion instructions according to semantic understanding results and a preset motion template.

[0063] In other embodiments, generating robot action instructions according to the semantic understanding results includes: generating robot action instructions according to the semantic understanding results and a preset dialogue state transition model.

[0064] In still other embodiments, a reply message is generated based on the semantic understanding result and a preset answer template.

[0065] Regarding the system in the above embodiment, the specific manner in which each unit performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0066] As shown in 4, Figure 4 A schematic diagram of an electronic device 20 that can implement an embodiment of the present invention is shown, and the electronic device is intended to represent various forms of control devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0067] The electronic device 20 includes at least one processor 21, and a memory connected to the at least one processor 21, such as a read-only memory (ROM) 22, a random access memory (RAM) 23, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 22 or the computer program loaded from the storage unit 28 to the random access memory (RAM) 13. In the RAM 23, various programs and data required for the operation of the electronic device 20 can also be stored. The processor 21, ROM 22 and RAM 23 are connected to each other through a bus 24. An input / output (I / O) interface 25 is also connected to the bus 24.

[0068] A number of components in the electronic device 20 are connected to the I / O interface 25, including: an input unit 26, such as a keyboard, a mouse, etc.; an output unit 27, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 29, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 29 allows the electronic device 20 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0069] The processor 21 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 21 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 21 performs the various methods and processes described above.

[0070] In some embodiments, the method of the above embodiment may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 28. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 20 via the ROM 22 and / or the communication unit 29. When the computer program is loaded into the RAM 23 and executed by the processor 21, one or more steps in the method described above may be performed. Alternatively, in other embodiments, the processor 21 may be configured to perform the method of the above embodiment in any other appropriate manner (e.g., by means of firmware).

[0071] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), 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 including 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.

[0072] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0073] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0074] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device 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 electronic device. 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

[0075] Input from the user may be received in any form, including acoustic input, voice input, or tactile input.

[0076] The systems and techniques described herein may be implemented in a computing system that includes backend 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 frontend components (e.g., a user computer with 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 backend components, middleware components, or frontend components. The components of the system may 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), a blockchain network, and the Internet.

[0077] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0078] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0079] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An artificial intelligence interaction method for an industrial robot, the method comprising: Receiving a user instruction in voice or text form; performing semantic understanding on the user instruction to obtain a semantic understanding result; Generate robot action instructions according to the semantic understanding results.

2. The method according to claim 1, further comprising: Performing voice recognition on the user instruction to obtain a voice recognition result.

3. The method according to claim 1 or 2, further comprising: A reply message is generated according to the user instruction.

4. The method according to any one of claims 1 to 3, wherein: The generating robot action instructions according to the semantic understanding result includes: generating robot action instructions according to the semantic understanding result and a preset action template.

5. The method according to any one of claims 1 to 4, wherein: The method further includes: generating a reply message according to the semantic understanding result and a preset answer template.

6. The method according to any one of claims 1 to 5, wherein: The generating robot action instructions according to the semantic understanding result includes: generating robot action instructions according to the semantic understanding result and a preset dialogue state transition model.

7. An artificial intelligence interaction device, comprising: A semantic understanding unit, configured to receive a user instruction in voice or text form, and perform semantic understanding on the user instruction to obtain a semantic understanding result; A robot action instruction generating unit is used to generate a robot action instruction according to the semantic understanding result.

8. The apparatus according to claim 7, further comprising: The speech recognition unit is used to perform speech recognition on the user instruction to obtain a speech recognition result.

9. The device according to claim 7 or 8, further comprising: A reply message generating unit is used to generate a reply message according to the user instruction.

10. A computer-readable storage medium storing a computer program, wherein the computer program implements the method according to any one of claims 1 to 6 when executed by a processor.

Images