Voice response system based on personalized vocabulary and user profile - personalized linguistics AI engine

Abstract

Methods, computer systems, and computer program products for personalized voice responses are provided. The method can include collecting a plurality of user data from an Internet of Things (IoT) connected sensor. The method can include identifying a personalization vocabulary based on the collected plurality of user data. The method can include training a voice response system based on the collected plurality of user data and the identified personalization vocabulary. The method can include receiving a verbal request. The method can include responding to the received verbal request using the trained voice response system.

Description

Background Technology

[0001] This invention generally relates to the field of computing, and more specifically to data management and analysis.

[0002] Humans can have a unique way of interpreting spoken language, which can be based on the stress and / or context of the application, a given personal experience and / or event, and / or on cultural and / or demographic influences. Human language can also be based on pragmatics (e.g., situational context), grammar (e.g., the arrangement of words and phrases in clauses and / or sentences), lexicalities (e.g., grammatical and / or lexical word functions), semantics (e.g., word meaning), phonology (e.g., the classification and / or study of sounds), and articulation (e.g., the study and / or classification of speech sounds), etc. Artificial intelligence (AI) voice response systems can analyze a user's voice requests and respond accordingly using a pre-programmed response generator. Summary of the Invention

[0003] This invention discloses a method, computer system, and computer program product for personalized voice responses. The invention may include collecting multiple user data from sensors connected to the Internet of Things (IoT). The invention may include identifying personalized vocabulary based on the collected user data. The invention may include training a voice response system based on the collected user data and the identified personalized vocabulary. The invention may include receiving verbal requests. The invention may include responding to received verbal requests using the trained voice response system. Attached Figure Description

[0004] These and other objects, features, and advantages of the invention will become apparent from the following detailed description of exemplary embodiments of the invention, which will be read in conjunction with the accompanying drawings. The various features in the drawings are not to scale, as these illustrations are intended to facilitate a clear understanding of the invention by those skilled in the art in conjunction with the specific embodiments. In the drawings:

[0005] Figure 1 The illustration depicts a networked computer environment according to at least one embodiment;

[0006] Figure 2 It is an operational flowchart illustrating a process for personalized voice response according to at least one embodiment;

[0007] Figure 3 It is a block diagram of a personalized voice response program according to at least one embodiment;

[0008] Figure 4 According to at least one embodiment Figure 1 A block diagram depicting the internal and external components of a computer and server;

[0009] Figure 5 Includes embodiments according to this disclosure Figure 1 A block diagram illustrating a cloud computing environment for a computer system; and

[0010] Figure 6 According to embodiments of this disclosure Figure 5 A block diagram illustrating the functional layers of an illustrative cloud computing environment. Detailed Implementation

[0011] This document discloses detailed embodiments of the claimed structures and methods; however, it should be understood that the disclosed embodiments are merely illustrative of the claimed structures and methods, which may be embodied in different forms. The invention can be embodied in many different forms and should not be construed as limited to the exemplary embodiments set forth herein. Rather, these exemplary embodiments are provided so that this disclosure is comprehensive and complete, and fully conveys the scope of the invention to those skilled in the art. In the description, details of well-known features and techniques may be omitted to avoid unnecessarily obscuring the presented embodiments.

[0012] This invention can be a system, method, and / or computer program product at any possible level of technical detail integration. The computer program product may include a computer-readable storage medium (or media) having computer-readable program instructions thereon, wherein the computer-readable program instructions are used to cause a processor to perform various aspects of the invention.

[0013] Computer-readable storage media can be tangible means capable of retaining and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example, but not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer-readable storage media includes: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital universal disc (DVD), memory sticks, floppy disks, mechanical encoding devices such as punched cards or protrusions in slots having instructions recorded thereon, and any suitable combination of the foregoing. As used herein, computer-readable storage media should not be considered as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses passing through fiber optic cables), or electrical signals transmitted through wires.

[0014] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a suitable computing / processing device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network), or to an external computer or external storage device. The network may include copper cables, optical fibers, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards these instructions to a computer-readable storage medium within the suitable computing / processing device.

[0015] Computer-readable program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, configuration data for integrated circuits, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​(such as Smalltalk, C++, etc.) and procedural programming languages ​​(such as the "C" programming language or similar programming languages). The computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as a standalone software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)) or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs) may be personalized by executing computer-readable program instructions using state information to perform aspects of the invention.

[0016] This document describes various aspects of the invention with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0017] These computer-readable program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / actions specified in the blocks or blocks of a flowchart and / or block diagram. These computer-readable program instructions may also be stored in a computer-readable storage medium that directs a computer, programmable data processing apparatus, and / or other device to operate in a particular manner, wherein the computer-readable storage medium storing the instructions comprises an article of manufacture containing instructions that implement aspects of the functions / actions specified in the blocks or blocks of a flowchart and / or block diagram.

[0018] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus or other device to enable a series of operational steps to be performed on the computer, other programmable apparatus or other device, so that the instructions executed on the computer, other programmable apparatus or other device perform the functions / actions specified in the blocks or blocks of the flowchart and / or block diagram.

[0019] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, segment, or portion of instructions, including one or more executable instructions for implementing one or more specified logical functions. In some alternative implementations, the functions marked in the blocks may occur in a non-linear order. For example, depending on the functions involved, two consecutively shown blocks may actually be executed substantially simultaneously, or these blocks may sometimes be executed in reverse order. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action or performs a combination of dedicated hardware and computer instructions.

[0020] The exemplary embodiments described below provide a system, method, and program product for personalized voice responses. Thus, this embodiment improves the field of data management and analysis by utilizing a user's personalized vocabulary to formulate responses to voice requests. More specifically, the invention may include collecting multiple user data from sensors connected to the Internet of Things (IoT). The invention may include identifying personalized vocabulary based on the collected multiple user data. The invention may include training a voice response system based on the collected multiple user data and the identified personalized vocabulary. The invention may include receiving a verbal request. The invention may include responding to the received verbal request using the trained voice response system.

[0021] As previously described, humans can have a unique way of interpreting spoken language, which can be based on the stress and / or context of the application, a given personal experience and / or event, and / or on cultural and / or demographic influences. Human language can also be based on pragmatics (e.g., situational context), grammar (e.g., the arrangement of words and phrases in clauses and / or sentences), lexicalities (e.g., grammatical and / or lexical word functions), semantics (e.g., word meaning), phonology (e.g., the classification and / or study of sounds), and articulation (e.g., the study and / or classification of speech sounds), etc. Artificial intelligence (AI) voice response systems can analyze a user's voice requests and can respond accordingly to the user using a pre-programmed response generator.

[0022] In many cases, users may not understand the keywords and / or phrases used by the AI ​​voice response system. Similarly, the AI ​​voice response system may not understand the keywords and / or phrases used by the user. Keywords and / or phrases can be homophones, homographs, location names, smells, lengths, localized spoken language corpora, contextual information, trending words and / or phrases, official and / or scientific words or phrases, and / or complex vocabulary, etc.

[0023] Therefore, it is particularly advantageous that the AI ​​voice response system can utilize the user's personalized vocabulary when responding to the user's voice requests.

[0024] According to at least one embodiment, the present invention can utilize a user's personalized vocabulary to generate a response to a received verbal request.

[0025] According to at least one embodiment, an artificial intelligence (AI) voice response system can analyze one or more attributes of unknown content in a received verbal request, and can verify the unknown content based on relatively known content that may be included in the user's personalized vocabulary.

[0026] Reference Figure 1 An exemplary networked computer environment 100 according to one embodiment is depicted. The networked computer environment 100 may include a computer 102 having a processor 104 and a data storage device 106 capable of running software program 108 and a personalized voice response program 110a. The networked computer environment 100 may also include a server 112 capable of running a personalized voice response program 110b, which can interact with a database 114 and a communication network 116. The networked computer environment 100 may include multiple computers 102 and servers 112, only one of which is shown. The communication network 116 may include different types of communication networks, such as wide area networks (WANs), local area networks (LANs), telecommunications networks, wireless networks, public switched networks, and / or satellite networks. It should be understood that... Figure 1This is merely an illustration of an implementation and does not imply any limitation regarding the environment in which different embodiments may be implemented. Many modifications can be made to the depicted environment based on design and implementation requirements.

[0027] Client computer 102 can communicate with server computer 112 via communication network 116. Communication network 116 may include connections such as wired, wireless communication links, or fiber optic cables. (See reference...) Figure 4 As discussed, server computer 112 may include internal component 902a and external component 904a, and client computer 102 may include internal component 902b and external component 904b. Server computer 112 may also operate in a cloud computing service model (such as Software as a Service (SaaS), Platform as a Service (PaaS), or Infrastructure as a Service (IaaS)). Server 112 may also reside in a cloud computing deployment model, such as a private cloud, community cloud, public cloud, or hybrid cloud. Client computer 102 may be, for example, a mobile device, telephone, personal digital assistant, netbook, laptop computer, tablet computer, desktop computer, or any type of computing device capable of running programs, accessing networks, and accessing database 114. According to various implementations of this embodiment, personalized voice response programs 110a, 110b can interact with database 114, which may be embedded in various storage devices, such as, but not limited to, computer / mobile device 102, networked server 112, or cloud storage service.

[0028] According to this embodiment, a user using client computer 102 or server computer 112 can use personalized voice response programs 110a and 110b (respectively) to formulate a response to a voice request using the user's personalized vocabulary. See below for further details. Figure 2 and 3 A more detailed explanation of personalized voice response methods.

[0029] Now for reference Figure 2 The document describes an operational flowchart illustrating an exemplary personalized voice response process 200 used by personalized voice response programs 110a and 110b according to at least one embodiment.

[0030] At point 202, user data is collected. Internet of Things (IoT) connected sensors (e.g., those embedded in mobile devices, smartphones, smartwatches, home appliances, and vehicles) can be used to collect various information about the user, including but not limited to user mobility patterns, user travel locations, user preferences, user requests (i.e., requests sent by the user), user responses (i.e., responses received from the user), user identification information, and user activities (i.e., activities performed by the user), if any. IoT-connected sensors (e.g., temperature sensors, pressure sensors, proximity sensors, optical sensors, smoke sensors, and other sensors) can identify details about the user, and the device housing the IoT-connected sensors can store the identified details in a database (e.g., a repository for storing and managing the collected data).

[0031] The identified details may include, but are not limited to, steps taken by the user to perform activities such as driving the vehicle and cooking dinner. For example, IoT-connected sensors embedded in the user's vehicle can identify the user's behavior and habits in relation to the methods the user uses to drive the vehicle (e.g., turning on turn signals a mile before turning, and using a horn to honk at a vehicle entering the lane 100 feet in front of the user's vehicle when that vehicle is entering the road perpendicular to the user's vehicle).

[0032] At point 204, personalized words are identified from the collected user data. The personalized voice response programs 110a and 110b (i.e., the artificial intelligence voice response system) can collect user data as previously described with reference to step 202 above, and can identify activities performed by the user, any requests submitted by the user, and any responses to requests received by the user, etc.

[0033] User language patterns, vocabulary, and / or topics can be analyzed through integration with various external products, including but not limited to social media tools, IoT devices, reading apps, and / or other systems in which users can speak, read, and / or write content. Analyzing communications created, engaged in, and / or consumed by users enables personalized voice response programs 110a and 110b to construct a user's personalized vocabulary.

[0034] Personalized vocabulary can also be identified through contextual understanding of the user's experience. For example, personalized vocabulary can be identified based on integration with calendar systems, GPS systems, and / or health monitoring systems (e.g., systems capable of making observations related to health status and remotely transmitting health-related data).

[0035] The user's IoT-connected sensors can use integrated data collection to gather device content that has already been read by the user. This integration may include, but is not limited to, web browsers, web and / or mobile applications, and social media plugins.

[0036] User-specified topic information can be identified using contextual analysis via Latent Dirichlet Allocation (LDA) (a generative statistical model in Natural Language Processing (NLP)). LDA allows observation sets to be mapped to dynamic topics when language models are similar. LDA can be a method to identify topics within a document and map the document to the identified topics. As here, when speech data is mapped to text by personalized speech response programs 110a, 110b, the mapped text can be classified into dynamic topics.

[0037] A user's social network contributions (including text and image information such as shared images and tagged images) can be analyzed to determine contextual importance and further identify the user's personalized vocabulary. A user's social network profile can be accessed, for example, through authentication via an application programming interface (API) login that connects to their social network account.

[0038] You can also use tone analyzer APIs (e.g., Watson) to identify personalized words. TM Pitch analyzer APIs analyze the context of a user's speech (i.e., voice response). Pitch analyzer APIs can collect patterns in speech and tone. For example, pitch analyzer APIs such as Watson... TM The Tone Analyzer API (Watson and all Watson-based trademarks are trademarks or registered trademarks of International Business Machines Corporation in the U.S. and / or other countries) can utilize a database of historical information (including past interactions between the user and the personalized voice response program 110a, 110b) to determine whether the voice response describes an intense, cheerful, serious, quirky, or humorous tone, as well as many other tones of speech.

[0039] Personalized vocabulary can be used to predict content that a user may know and content that may not know, based on a trained module, as described below with reference to step 206.

[0040] Personalized vocabulary can be identified for each user of the personalized voice response programs 110a and 110b. A user's personalized vocabulary can be stored in a user profile associated with the personalized voice response programs 110a and 110b, in a cloud environment, and / or cached on the user's device, and can be accessed using authenticated credentials (e.g., those set by the user when initiating the personalized voice response program 110a or 110b). A separate knowledge corpus can exist for each user of the personalized voice response programs 110a and 110b, with each user identified from their voice profile.

[0041] At point 206, personalized voice response programs 110a and 110b are trained based on the collected user data. A bidirectional long short-term memory (Bi-LSTM) training module with a text- and image-based convolutional neural network (TI-CNN) module can include an AI voice response system trained on the collected user data (i.e., personalized voice response programs 110a and 110b). The Bi-LSTM training module can depict a recurrent neural network (RNN) architecture (e.g., a deep learning module) where signals propagate both backward and forward (e.g., data can be read from start to end and from end to start), which enables faster learning than unidirectional methods. The Bi-LSTM training module can continuously collect user data and can use pattern analysis in conjunction with the text- and image-based convolutional neural network (TI-CNN) module to recognize, classify, and learn based on context.

[0042] LSTM training modules are useful in text and / or speech analysis because they can consider the context of other words within the text and / or speech. Forward LSTM training modules can predict the next part of speech during a speech response session, enabling them to better anticipate the user's needs. Backward LSTM training modules can predict previous parts of speech during a speech response session, allowing them to have more context surrounding the user's current inquiry. Bi-LSTM can do both (e.g., anticipate the user's needs and consider past parts of the user's dialogue), thus better enabling both the user's future intentions and the context of the user's dialogue.

[0043] At point 208, a verbal request is received. As previously described with reference to step 204 above, personalized voice response programs 110a and 110b can deconstruct the received verbal request (e.g., by parsing the received verbal request to determine its semantic structure, etc.) and the content delivered via a previous voice response (i.e., a previous voice response) to formulate a voice response to the received verbal request. Personalized voice response programs 110a and 110b can analyze unknown content of the voice response to be delivered (e.g., the portion of the verbal request that requires a personalized response from the user) and can identify similar content in the user's personalized vocabulary that can be used to respond to the received verbal request. Here, personalized voice response programs 110a and 110b can formulate a response to the verbal request based on one or more identified patterns in the user's personalized vocabulary.

[0044] Personalized voice response programs 110a and 110b can use K-means clustering to perform similarity analysis using the user's personalized vocabulary. K-means clustering can be an unsupervised machine learning algorithm that can group data together based on determined similarities. For example, a received user request may be related to the current weather, and personalized voice response programs 110a and 110b can determine how to communicate "the weather will be cold in the morning" based on the user's personalized vocabulary (e.g., using "cold" instead of "chilly" and "morning" instead of "AM").

[0045] If similar and / or equivalent content is not available in the user's personalized vocabulary, the personalized voice response programs 110a, 110b may then employ external assistance functions and / or search for the personalized vocabulary of other users (e.g., similar users and / or users located near a determined GPS location, etc.) discovered using local storage and / or databases, and / or utilize a regional language corpus of merged vocabulary, phrases, and / or vocalizations that can be applied to a cultural or regional subset of a specific user and / or local group.

[0046] Semantic similarity can be estimated by defining topological similarity, using ontology to define the differences between terms and / or concepts. Ontology can be used to orthogonalize groups of definitions, categories, attributes, and entities to better group data into and out of groups. For example, a native metric for comparing concepts ordered in a partially ordered set and represented as a directed acyclic graph (e.g., a taxonomy) could be the shortest path linking two concept nodes.

[0047] IBM's Watson for document stemming TMThe Ground Truth Editor (Watson and all Watson-based trademarks are trademarks or registered trademarks of IBM, Inc. in the U.S. and / or other countries) can also be used to build user-understandable ontology. This can enhance the utilization of synonyms and the understanding of user content, thereby improving the relevance of the user's knowledge space to unknown content.

[0048] via IBM's Watson TM The ground truth editor's documentation annotations and classifications of the target domain can include manual classification and / or annotation of some training and / or service data from the personalized voice response programs 110a and 110b. TM The ground truth editor can obtain ground truth, or can be used to make Watson... TM A collection of examined data adapted to a specific domain. Human users can help classify ground truth.

[0049] If similar and / or equivalent content is unavailable in a user’s personalized vocabulary, or in the personalized vocabulary of other (e.g., similar) users, then the personalized voice response procedures 110a, 110b can then trace back to the individual who made the verbal request (e.g., by verbal request for information from the original requester) to explain the verbal request in more detail.

[0050] For example, personalized voice response programs 110a and 110b can verbally ask the original requester whether the type of "package" mentioned by the user is related to paper (e.g., wrapping paper) or to a music genre (e.g., rap music).

[0051] At point 210, the voice response system responds to the received verbal request. Personalized voice response programs 110a and 110b can construct a response to the received verbal request using information collected from personalized vocabulary and / or personalized vocabulary from similar users, and can verbally deliver it to the user.

[0052] In response to a received verbal request, personalized voice response programs 110a and 110b can analyze historical information about the user (e.g., travel location, activities performed, content read, known words, etc.) to identify the knowledge possessed by the user. In doing so, personalized voice response programs 110a and 110b can use the identified personalized vocabulary of the user to generate a verbal response to the received verbal request that can be understood by the user.

[0053] Now for reference Figure 3Block diagram 300 depicts personalized voice response programs 110a and 110b according to at least one embodiment. A user speaks a voice request to an AI voice response device 302 equipped with an embedded microphone. As depicted in diagram 304, the voice request received by the AI ​​voice response device 302 can be connected to the personalized voice response programs 110a and 110b, which can process the received voice request. The personalized voice response programs 110a and 110b depicted in diagram 304 can be capable of performing natural language processing (NLP) and natural language understanding (NLU) technologies, and these technologies can be used to analyze collected data (e.g., spoken voice requests). Additional data collected by the AI ​​voice response device 302 and / or other connected Internet of Things (IoT) devices can be stored in the data collection module of the personalized voice response programs 110a and 110b depicted in diagram 304.

[0054] The embedded deep neural network (also depicted by 304) within the personalized voice response programs 110a and 110b can utilize a training module to analyze the user's previous voice responses and, optionally, those similar to the user's voice responses, to generate a personalized response to the user's request. As depicted by 304, the corpus of data contained in the personalized voice response programs 110a and 110b can be the user's personalized linguistic corpus (i.e., personalized vocabulary), which can include pragmatic, grammatical, lexical, semantic, phonological, and / or phonetic information specific to a given user.

[0055] Optionally, the two-way feed can be utilized by personalized voice response programs 110a, 110b (described by 304) to access regional and / or cultural linguistic corpora, which may include language data that is not present in the user's personalized corpus but is useful in responding to received voice requests.

[0056] Understandable. Figure 2 and 3 The illustration provides only one embodiment and does not imply any limitation on how different embodiments may be implemented. Many modifications may be made to the depicted embodiment(s) based on design and implementation requirements.

[0057] According to at least one alternative embodiment, an iterative feedback learning module can be included in the personalized voice response program. This module enables monitoring of the user's reactions to the responses provided by the personalized voice response program via a close-range camera and / or IoT sensor that can help determine the user's satisfaction level. For example, the iterative feedback learning module can employ facial scanning technology and / or a tone analyzer to find indicators of user satisfaction, ranging from confusion and / or frustration to happiness. Depending on the content and satisfaction level, the iterative feedback learning module can refine and / or modify the corpus of user data to improve the accuracy of the user's personalized vocabulary, improve the accuracy of responses to received verbal requests, and optimize user satisfaction with the personalized voice response program.

[0058] Figure 4 This is an illustrative embodiment of the present invention. Figure 1 Block diagram 900 depicts the internal and external components of a computer. It should be understood that... Figure 4 This is merely an illustration of an implementation and does not imply any limitation regarding the environment in which different embodiments may be implemented. Many modifications can be made to the depicted environment based on design and implementation requirements.

[0059] Data processing systems 902 and 904 represent any electronic device capable of executing machine-readable program instructions. Data processing systems 902 and 904 can represent smartphones, computer systems, PDAs, or other electronic devices. Examples of computing systems, environments, and / or configurations that data processing systems 902 and 904 can represent include, but are not limited to, personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, multiprocessor systems, microprocessor-based systems, network PCs, minicomputer systems, and distributed cloud computing environments that include any of the above systems or devices.

[0060] The user client computer 102 and the network server 112 may include Figure 4The diagram illustrates corresponding groups of internal components 902a, b and external components 904a, b. Each group of internal components 902a, b includes one or more processors 906, one or more computer-readable RAMs 908 and one or more computer-readable ROMs 910 on one or more buses 912, as well as one or more operating systems 914 and one or more computer-readable tangible storage devices 916. One or more operating systems 914, software programs 108, and personalized voice response programs 110a in client computer 102 and personalized voice response programs 110b in network server 112 may be stored on one or more computer-readable tangible storage devices 916 for execution by one or more processors 906 via one or more RAMs 908 (which typically include cache memory). Figure 4 In the illustrated embodiment, each of the computer-readable tangible storage devices 916 is a disk storage device of an internal hard disk drive. Alternatively, each of the computer-readable tangible storage devices 916 is a semiconductor storage device, such as ROM 910, EPROM, flash memory, or any other computer-readable tangible storage device capable of storing computer programs and digital information.

[0061] Each set of internal components 902a, b also includes an R / W drive or interface 918 for reading from and writing to one or more portable computer-readable tangible storage devices 920, such as CD-ROM, DVD, Memory Stick, magnetic tape, disk, optical disc, or semiconductor storage devices. Software programs such as software program 108 and personalized voice response programs 110a and 110b can be stored on one or more corresponding portable computer-readable tangible storage devices 920, read from and loaded into corresponding hard disk drives 916 via the corresponding R / W drive or interface 918.

[0062] Each set of internal components 902a, b may also include a network adapter (or switch port card) or interface 922, such as a TCP / IP adapter card, a wireless Wi-Fi interface card, or a 3G or 4G wireless interface card, or other wired or wireless communication links. The software program 108 and personalized voice response program 110a in the client computer 102 and the personalized voice response program 110b in the network server computer 112 may be downloaded from an external computer (e.g., a server) via a network (e.g., the Internet, a local area network, or other, wide area network) and the corresponding network adapter or interface 922. The software program 108 and personalized voice response program 110a in the client computer 102 and the personalized voice response program 110b in the network server computer 112 are loaded into the corresponding hard disk drive 916 from the network adapter (or switch port adapter) or interface 922. The network may include copper wire, fiber optic, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers.

[0063] Each set of external components 904a, b may include a computer display monitor 924, a keyboard 926, and a computer mouse 928. External components 904a, b may also include a touchscreen, virtual keyboard, touchpad, pointing device, and other human interface devices. Each set of internal components 902a, b also includes a device driver 930 that interfaces to the computer display monitor 924, keyboard 926, and computer mouse 928. The device driver 930, R / W driver or interface 918, and network adapter or interface 922 include hardware and software (stored in storage device 916 and / or ROM 910).

[0064] It should be understood in advance that while this disclosure includes a detailed description of cloud computing, the implementation of the teachings illustrated herein is not limited to cloud computing environments. Rather, embodiments of the invention can be implemented in conjunction with any other type of computing environment now known or developed hereafter.

[0065] Cloud computing is a service delivery model that enables convenient, on-demand network access to a shared pool of configurable computing resources (such as networks, network bandwidth, servers, processing power, storage devices, applications, virtual machines, and services) that can be rapidly provisioned and released with minimal management effort or interaction with service providers. This cloud model may include at least five features, at least three service models, and at least four deployment models.

[0066] The features are as follows:

[0067] On-demand self-service: Cloud consumers can unilaterally and automatically provide computing power, such as server time and network storage, as needed, without requiring human interaction with the service provider.

[0068] Extensive network access: Capabilities are available through networks and accessed via standard mechanisms that facilitate the use of heterogeneous thin client platforms or thick client platforms (e.g., mobile phones, laptops, and PDAs).

[0069] Resource pooling: A provider's computing resources are pooled to serve multiple consumers using a multi-tenant model, where different physical and virtual resources are dynamically allocated and reallocated as needed. There is a sense of location independence here, as consumers typically do not have control or knowledge of the exact location of the resources provided, but may be able to specify the location at a higher level of abstraction (e.g., country, state, or data center).

[0070] Rapid flexibility: Capacity can be automatically and flexibly provided in certain situations to shrink rapidly and expand rapidly. For consumers, the capacity available for supply often appears unlimited and can be purchased at any time and in any quantity.

[0071] Measuring services: Cloud systems automate and optimize resource usage by leveraging metering capabilities at some level of abstraction appropriate to service types (e.g., storage, processing, bandwidth, and active user accounts). Resource usage can be monitored, controlled, and reported to provide transparency for both service providers and consumers.

[0072] The service model is as follows:

[0073] Software as a Service (SaaS): This provides consumers with the ability to use a provider's applications running on cloud infrastructure. These applications can be accessed from different client devices via thin client interfaces such as web browsers (e.g., web-based email). Consumers do not manage or control the underlying cloud infrastructure, including the network, servers, operating system, storage devices, or even individual application capabilities, with possible exceptions of limited user-specific application configuration settings.

[0074] Platform as a Service (PaaS): This provides consumers with the ability to deploy applications created by the consumer or acquired using programming languages ​​and tools supported by the provider onto cloud infrastructure. Consumers do not manage or control the underlying cloud infrastructure, including networks, servers, operating systems, or storage devices, but they have control over the deployed applications and the configuration of the potentially hosted environments.

[0075] Infrastructure as a Service (IaaS): This provides consumers with the capability to offer processing, storage, networking, and other basic computing resources that enable them to deploy and run arbitrary software, which may include operating systems and applications. Consumers do not manage or control the underlying cloud infrastructure, but they do have control over the operating system, storage devices, deployed applications, and potentially limited control over chosen networking components (e.g., host firewalls).

[0076] The deployment model is as follows:

[0077] Private cloud: A cloud infrastructure designed solely for organizational operations. It can be managed by the organization or a third party and can exist either on-site or off-site.

[0078] Community cloud: A cloud infrastructure shared by several organizations and supporting a specific community with shared concerns (e.g., tasks, security requirements, policies, and compliance considerations). It can be managed by an organization or a third party and can exist on-site or off-site.

[0079] Public cloud: Makes cloud infrastructure available to the general public or large industry organizations and is owned by the organization that sells cloud services.

[0080] Hybrid cloud: A cloud infrastructure is a combination of two or more clouds (private, community, or public) that remain a single entity but are bound together by standardized or proprietary technologies that enable data and application portability (e.g., cloud bursts for load balancing between clouds).

[0081] Cloud computing environments are service-oriented, emphasizing statelessness, loose coupling, modularity, and semantic interoperability. At the heart of cloud computing is the infrastructure that includes a network of interconnected nodes.

[0082] Now for reference Figure 5 The illustration depicts a cloud computing environment 1000. As shown, the cloud computing environment 1000 includes one or more cloud computing nodes 100 that can communicate with local computing devices used by cloud consumers, such as, for example, personal digital assistants (PDAs) or cellular phones 1000A, desktop computers 1000B, laptop computers 1000C, and / or automotive computer systems 1000N. The nodes 100 can communicate with each other. They can be physically or virtually grouped (not shown) in one or more networks, such as private clouds, community clouds, public clouds, or hybrid clouds, or combinations thereof, as described above. This allows the cloud computing environment 1000 to provide Infrastructure as a Service, Platform as a Service, and / or Software as a Service, without requiring cloud consumers to maintain resources for them on their local computing devices. It should be understood that in Figure 5The types of computing devices 1000A-1000N shown are intended to be illustrative only, and computing node 100 and cloud computing environment 1000 can communicate with any type of computerized device via any type of network and / or network-addressable connection (e.g., using a web browser).

[0083] Now for reference Figure 6 This illustrates a set of functional abstraction layers 1100 provided by the cloud computing environment 1000. It should be understood in advance that... Figure 6 The components, layers, and functions shown are intended to be illustrative only, and embodiments of the invention are not limited thereto. As depicted, the following layers and corresponding functions are provided:

[0084] The hardware and software layer 1102 includes hardware and software components. Examples of hardware components include: a mainframe 1104; a server 1106 based on a RISC (Reduced Instruction Set Computer) architecture; a server 1108; a blade server 1110; a storage device 1112; and network and networking components 1114. In some embodiments, software components include network application server software 1116 and database software 1118.

[0085] The virtualization layer 1120 provides an abstraction layer from which the following examples of virtual entities can be provided: virtual server 1122; virtual storage device 1124; virtual network 1126 including virtual private network; virtual application and operating system 1128; and virtual client 1130.

[0086] In one example, management layer 1132 may provide the functionality described below. Resource Provisioning 1134 provides dynamic procurement of computing resources and other resources used to perform tasks within the cloud computing environment. Metering and Pricing 1136 provides cost tracking as resources are utilized within the cloud computing environment and bills or invoices for the consumption of these resources. In one example, these resources may include application software licenses. Security provides authentication for cloud consumers and tasks, as well as protection for data and other resources. User Portal 1138 provides access to the cloud computing environment for consumers and system administrators. Service Level Management 1140 provides cloud resource allocation and management to ensure that required service levels are met. Service Level Agreement (SLA) Planning and Fulfillment 1142 provides pre-scheduling and procurement of cloud resources for anticipated future needs according to the SLA.

[0087] Workload layer 1144 provides examples of functionalities that can leverage a cloud computing environment. Examples of workloads and functionalities that can be provided from this layer include: mapping and navigation 1146; software development and lifecycle management 1148; virtual classroom education delivery 1150; data analytics and processing 1152; transaction processing 1154; and personalized voice responses 1156. Personalized voice response programs 110a and 110b provide a way to tailor responses to voice requests using the user's personalized vocabulary.

[0088] Various embodiments of the invention have been described for illustrative purposes, but are not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope of the described embodiments. The terminology used herein has been chosen to best explain the principles of the embodiments, their practical application, or technical improvements to technologies found in the market, or to enable those skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for personalized voice response, the method comprising: Collect data from multiple users from sensors connected to the Internet of Things (IoT); Personalized vocabulary is identified based on multiple user data sets collected. Based on the collected user data and the identified personalized vocabulary, a bidirectional long short-term memory (Bi-LSTM) training module is used to train the speech response system. The Bi-LSTM training module uses pattern analysis and a text and image-based convolutional neural network (TI-CNN) module to recognize, classify and learn based on context. Receiving verbal requests; and The system uses a trained speech response system to respond to received verbal requests and, as needed, uses personalized vocabulary from similarly and closely located users, wherein the similarly and closely located users are identified using a regional language corpus employing an ontology for lexical similarity.

2. The method according to claim 1, wherein, The collected user data is selected from groups consisting of user travel locations, user preferences, user requests, user responses, user identification information, and user activities.

3. The method according to claim 1, wherein, Identifying the personalized vocabulary based on multiple user data sets collected also includes: Using contextual analysis via Potential Dirichlet Allocation (LDA), topic information from multiple user data sets collected was identified; and The contextual importance of multiple user data collected is determined based on contributions from social networks.

4. The method according to claim 1, wherein, Receiving the verbal request also includes: Deconstruct the received verbal requests; K-means clustering was used to identify content in the personalized vocabulary similar to the received verbal request; and If no content similar to the received verbal request is identified, personalized words for similar and nearby users are searched based on Global Positioning System (GPS) location.

5. The method according to claim 4, further comprising: By leveraging merged corpora of vocabulary, phrases, and pronunciation-personalized regional language corpora, content similar to the received verbal requests can be found.

6. The method according to claim 4, wherein, Responding to received verbal requests using the trained voice response system also includes: Use the identified information to construct a response to the received verbal request.

7. A computer system for personalized voice response, comprising: One or more processors, one or more computer-readable memories, one or more computer-readable tangible storage media, and program instructions stored on at least one of the one or more tangible storage media for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising: Collect data from multiple users from sensors connected to the Internet of Things (IoT); Personalized vocabulary is identified based on multiple user data sets collected. Based on the collected user data and the identified personalized vocabulary, a bidirectional long short-term memory (Bi-LSTM) training module is used to train the speech response system. The Bi-LSTM training module uses pattern analysis and a text and image-based convolutional neural network (TI-CNN) module to recognize, classify and learn based on context. Receiving verbal requests; and The system uses a trained speech response system to respond to received verbal requests and, as needed, uses personalized vocabulary from similarly and closely located users, wherein the similarly and closely located users are identified using a regional language corpus employing an ontology for lexical similarity.

8. The computer system according to claim 7, wherein, The collected user data is selected from groups consisting of user travel locations, user preferences, user requests, user responses, user identification information, and user activities.

9. The computer system according to claim 7, wherein, Identifying the personalized vocabulary based on multiple user data sets collected also includes: Using contextual analysis via Potential Dirichlet Allocation (LDA), topic information from multiple user data sets collected was identified; and The contextual importance of multiple user data collected is determined based on contributions from social networks.

10. The computer system according to claim 7, wherein, Receiving the verbal request also includes: Deconstruct the received verbal requests; K-means clustering was used to identify content in the personalized vocabulary similar to the received verbal request; and If no content similar to the received verbal request is identified, personalized words for similar and nearby users are searched based on Global Positioning System (GPS) location.

11. The computer system according to claim 10, further comprising: By leveraging merged corpora of vocabulary, phrases, and pronunciation-personalized regional language corpora, content similar to the received verbal requests can be found.

12. The computer system according to claim 10, wherein, Responding to received verbal requests using a trained voice response system also includes: Use the identified information to construct a response to the received verbal request.

13. A computer program product for personalized voice response, comprising program instructions executable by a processor to cause the processor to perform a method, the method comprising: Collect data from multiple users from sensors connected to the Internet of Things (IoT); Personalized vocabulary is identified based on multiple user data sets collected. Based on the collected user data and the identified personalized vocabulary, a bidirectional long short-term memory (Bi-LSTM) training module is used to train the speech response system. The Bi-LSTM training module uses pattern analysis and a text and image-based convolutional neural network (TI-CNN) module to recognize, classify and learn based on context. Receiving verbal requests; and The system uses a trained speech response system to respond to received verbal requests and, as needed, uses personalized vocabulary from similarly and closely located users, wherein the similarly and closely located users are identified using a regional language corpus employing an ontology for lexical similarity.

14. The computer program product according to claim 13, wherein, The collected user data is selected from groups consisting of user travel locations, user preferences, user requests, user responses, user identification information, and user activities.

15. The computer program product according to claim 13, wherein, Identifying the personalized vocabulary based on multiple user data sets collected also includes: Using contextual analysis via Potential Dirichlet Allocation (LDA), topic information from multiple user data sets collected was identified; and The contextual importance of multiple user data collected is determined based on contributions from social networks.

16. The computer program product according to claim 13, wherein, Receiving the verbal request also includes: Deconstruct the received verbal requests; K-means clustering was used to identify content in the personalized vocabulary similar to the received verbal request; and If no content similar to the received verbal request is identified, personalized words for similar and nearby users are searched based on Global Positioning System (GPS) location.

17. The computer program product according to claim 16, further comprising: By leveraging merged corpora of vocabulary, phrases, and pronunciation-personalized regional language corpora, content similar to the received verbal requests can be found.

Images