WO2019192106A1 - 一种提示信息的方法、终端设备及计算机可读存储介质 - Google Patents

一种提示信息的方法、终端设备及计算机可读存储介质 Download PDF

Info

Publication number
WO2019192106A1
WO2019192106A1 PCT/CN2018/097532 CN2018097532W WO2019192106A1 WO 2019192106 A1 WO2019192106 A1 WO 2019192106A1 CN 2018097532 W CN2018097532 W CN 2018097532W WO 2019192106 A1 WO2019192106 A1 WO 2019192106A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
transaction
prompt
prompt information
input
Prior art date
Application number
PCT/CN2018/097532
Other languages
English (en)
French (fr)
Inventor
王培强
刘俊廷
张书源
李洋
陈静
Original Assignee
平安科技(深圳)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技(深圳)有限公司 filed Critical 平安科技(深圳)有限公司
Publication of WO2019192106A1 publication Critical patent/WO2019192106A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/10Office automation; Time management
    • G06Q10/109Time management, e.g. calendars, reminders, meetings or time accounting
    • G06Q10/1093Calendar-based scheduling for persons or groups
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/10Office automation; Time management
    • G06Q10/109Time management, e.g. calendars, reminders, meetings or time accounting
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/044Recurrent networks, e.g. Hopfield networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02ATECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Definitions

  • the present application belongs to the field of information processing technologies, and in particular, to a method for prompting information, a terminal device, and a computer readable storage medium.
  • the prompt condition and the transaction content can be obtained from the transaction information input by the user, and when the prompt condition is satisfied, the transaction content is prompted, but the prompt content is only Limited to the transaction content input by the user, it can be seen that there is a problem that the content of the prompt information is too single in the existing prompt information technology.
  • the embodiment of the present application provides a method for prompting information, a terminal device, and a computer readable storage medium, so as to solve the problem that the content of the prompt information is too singular in the existing prompt information technology.
  • a first aspect of the embodiments of the present application provides a method for prompting information, including:
  • the prompt information recommendation model is configured to select, according to the to-do transaction information, a to-be prompted for prompting the second to-do transaction from the preset prompt information database.
  • Information the information in the prompt information base is used to describe a correspondence between the to-do transaction information and the to-be-presented information;
  • the target prompt information is displayed.
  • the method, the terminal device and the computer readable storage medium for implementing the prompt information provided by the embodiment of the present application have the following beneficial effects:
  • the embodiment of the present application obtains the to-do transaction information input by the user for describing the first to-do transaction, and then uses the prompt information recommendation model to select the second information from the preset prompt information library according to the to-do transaction information.
  • the pending information of the to-do transaction based on the input mode of the to-do transaction information, determines the target prompt information from the to-be-presented information for display, and inputs the to-do transaction information under different operation scenarios, respectively, and can prompt various
  • the content associated with the transaction information enriches the content of the prompt information.
  • FIG. 1 is a flowchart of an implementation of a method for prompting information according to an embodiment of the present application
  • FIG. 2 is a flowchart of a specific implementation of a method for prompting information according to another embodiment of the present application
  • FIG. 3 is a flowchart of a specific implementation of a method S13 for prompting information according to another embodiment of the present application
  • FIG. 5 is a structural block diagram of a terminal device according to an embodiment of the present application.
  • FIG. 6 is a schematic diagram of a terminal device according to another embodiment of the present application.
  • the embodiment of the present application obtains the to-do transaction information input by the user for describing the first to-do transaction, and then uses the prompt information recommendation model to select the second information from the preset prompt information library according to the to-do transaction information.
  • the pending information of the to-do transaction based on the input mode of the to-do transaction information, determines the target prompt information from the to-be-presented information for display, and inputs the to-do transaction information under different operation scenarios, respectively, and can prompt various
  • the content associated with the transaction information enriches the content of the prompt information.
  • the execution body of the process is a terminal device.
  • the terminal device includes but is not limited to: a mobile terminal such as a smart phone, a notebook computer, a computer, a tablet computer, and the like.
  • the terminal device may be a seat terminal, and the agent terminal selects the obtained prompt information to the user terminal of each target user.
  • FIG. 1 is a flowchart of an implementation of a method for prompting information provided by a first embodiment of the present application, which is described in detail as follows:
  • S11 Obtain the to-do transaction information input by the user for describing the first to-do transaction.
  • the to-do transaction information may be voice information or text information, wherein the voice information may be entered by calling the microphone of the terminal, or may be obtained by the user by selecting the voice information that has been entered in the application; the text information may be manually input by the user. Or by the user copying a certain piece of text content in the application.
  • the to-do transaction information is used to describe the content of the first to-do transaction, and is also the transaction content that the user wishes to be reminded.
  • the to-do transaction information may include at least two of a transaction reminding condition, a transaction content, and a precaution, wherein the transaction reminding condition may include: time, geographical location, or environmental condition, for example, temperature, humidity, or ultraviolet light. Strength, etc.
  • obtaining the to-do transaction information input by the user for describing the first to-do transaction that is, obtaining the user input for describing "10 am Voice message or text message of meeting in the conference hall.
  • the to-do transaction information may be parsed to determine the condition and transaction content for reminding the first to-do transaction.
  • S12 Enter the to-do transaction information into a prompt information recommendation model, where the prompt information recommendation model is configured to select, according to the to-do transaction information, a second to-do transaction from the preset prompt information database. Pending message.
  • step S12 the information in the preset prompt information base is used to describe the correspondence between the to-do transaction information and the to-be-presented information.
  • the information in the prompt information base can be obtained by counting the historical to-do transaction information input by the user, wherein the to-do transaction described by each historical to-do transaction information includes at least two items, and each item is to be processed.
  • the transaction can be used as the content described in the to-do transaction information in the prompt information library, or the content described in the information to be prompted.
  • each to-do transaction corresponds to a respective transaction reminding condition, or each to-do transaction follows the same transaction reminding condition, for example, the transaction reminding condition is time , each to-do transaction can be executed at the same time, or in succession.
  • the information in the library is used to describe the correspondence between the first to-do transaction and the second to-do transaction, that is, the to-do transaction information used to describe the "afternoon meeting”, and is used to describe "remember to bring coffee”.
  • the information to be presented may be a page connection, in addition to the content for prompting the second to-do transaction, and may distinguish the user from the current operation by distinguishing whether the user is currently convenient to perform further operations on the terminal.
  • the prompt information suitable for the current operation scenario is determined as the target prompt information.
  • S13 Determine target prompt information from the to-be-presented information based on an input manner of the to-do transaction information.
  • the input mode may be text input or voice input
  • the to-be-presented information may include text information, picture information, or an interface link of the application.
  • different input modes may reflect whether the user is currently convenient to perform manual operations on the terminal in the next step, and different input modes may correspond to different target prompt information.
  • the input mode of the to-do transaction information is text input, it indicates that the user is currently convenient to perform the next operation on the terminal, and the current operation interface can be switched according to the interface link to realize the information prompting to the user.
  • the input mode of the to-do transaction information is voice input, it indicates that the user is currently inconvenient to perform the next operation on the terminal, and the user may be prompted to display information by displaying text information or picture information.
  • the input manner of the to-do transaction information it is possible to predict whether the user is currently convenient to perform the next operation on the terminal, and it is convenient to determine the prompt information more suitable for the current use scenario of the user from the prompt information as the target prompt information.
  • the target prompt information is one of the to-be-presented information, and the target prompt information may be: text prompt information, picture prompt information, or web page prompt information.
  • the display target prompt information is to display the target prompt information when it is detected that the current environmental condition satisfies the transaction reminding condition.
  • the target prompt information when the target prompt information is a text prompt information or a picture prompt information, the target prompt information may be displayed by a push system notification.
  • the target prompt information when the target prompt information is the text webpage prompt information, the target prompt information may be displayed by calling the corresponding application to jump to the corresponding page.
  • the method for prompting information obtains the to-do transaction information input by the user for describing the first to-do transaction, and then uses the prompt information recommendation model according to the to-do transaction information.
  • the to-be-prompted information for prompting the second to-do transaction is selected in the prompt information database, and the target prompt information is determined from the to-be-presented information based on the input mode of the to-do transaction information, and the input is performed under different operation scenarios.
  • To-do transaction information respectively, can prompt various content associated with the to-do transaction information, enriching the content of the prompt information.
  • FIG. 2 is a flowchart of a specific implementation of a method for prompting information according to another embodiment of the present application.
  • the method for prompting information provided in this embodiment further includes S21 to S23, which are specifically described as follows:
  • the method before the to-do transaction information is input into the prompt information recommendation model, the method further includes:
  • S21 Acquire template information of the user, and at least two pieces of prompt information corresponding to the template transaction information.
  • the prompt information recommendation model is specifically a long-term and short-term memory LSTM neural network.
  • the template transaction information of the user to the user and at least two pieces of prompt information corresponding to the template transaction information are required to be acquired.
  • the template transaction information is obtained based on the historical agency transaction information.
  • the historical to-do transaction information is “afternoon meeting to remember to bring coffee”, wherein the first prompt information is “afternoon meeting”, the second prompt The message is “Remember to bring coffee” and the third message is the coffee takeaway order page.
  • the content of the at least two pieces of prompt information corresponding to the template transaction information includes the user's past requirements and the user's possible needs, that is, the prompt information displayed by the terminal device is the same as or similar to the user's previous requirements.
  • the template transaction information is used as the input reference value of the LSTM neural network, and the prompt information corresponding to the template transaction information is used as the output reference value of the LSTM neural network, and the LSTM neural network is trained by the above two parameters.
  • ⁇ * is the adjusted learning parameter
  • S is the prompt information
  • I is the template transaction information
  • I 1 , I 2 , I 3 , ..., I n are each of the template transaction information a parameter value of the item transaction
  • n is the number of the transactions
  • the LSTM neural network has N input channels, and each input channel corresponds to each transaction parameter included in the template transaction information.
  • the template transaction information includes: three transaction parameters: time, location, and transaction content. Then, in the LSTM neural network, three input channels are set, and the input channel corresponding to each transaction information is fixed according to the number of each transaction parameter in the prompt information, thereby ensuring the category of the transaction parameter input by each input channel. Are the same.
  • the output channel of the LSTM neural network is one for outputting prompt information matching the template transaction information.
  • the LSTM neural network includes a plurality of neural layers, each of which is provided with a corresponding learning parameter, and the parameter values of the learning parameters can be adjusted to adapt to different input types and output types.
  • the learning parameter is set to a certain parameter value
  • the user information of the plurality of training users is input to the LSTM neural network, and the target prompt information is output, and the terminal device will at least two prompts corresponding to the target prompt information and the template transaction information.
  • the information is compared to determine whether the current output is correct, and based on the output results of the plurality of training protocols, the probability value that the learning result is correct when the learning parameter takes the parameter value is obtained.
  • the terminal device adjusts the learning parameter so that the probability value takes a maximum value, indicating that the LSTM neural network has been adjusted.
  • the terminal device uses the LSTM neural network adjusted with the learning parameters as the prompt information recommendation model, and improves the accuracy of the candidate protocol recommendation model identification.
  • the corresponding learning parameter with the correct output value is selected as the parameter value of the learning parameter in the LSTM neural network, thereby improving the accuracy of the prompt information recognition and realizing Accurately determine the purpose of the prompt message.
  • the prompt information recommendation model By obtaining the to-do transaction information input by the user for describing the first to-do transaction, and using the prompt information recommendation model to select the second to-do transaction from the preset prompt information database according to the to-do transaction information.
  • the information to be prompted is convenient for selecting the target information suitable for the current use scenario of the user from the information to be presented for display.
  • FIG. 3 is a flowchart showing a specific implementation of a method S13 for prompting information according to another embodiment of the present application.
  • S13 includes S131, S132, and S133, and the details are as follows:
  • the to-be-presented information includes text information and a webpage link.
  • S131 Acquire an input manner of the user inputting the to-do transaction information.
  • the input method can be text input or voice input.
  • the input mode of the user input transaction information is obtained by identifying the information processing port of the to-do transaction information, and the different to-do transaction information input modes correspond to different information processing ports, and the to-do transaction information is determined according to the identifier of the processing port. Input.
  • the different input modes may reflect whether the user is currently convenient to perform the next manual operation on the terminal, and the prompt information that is more suitable for the current use scenario of the user is determined from the prompt information as the target prompt information.
  • the input mode of the to-do transaction information is text input, it indicates that the user is currently convenient to perform the next operation on the terminal, and the current operation interface can be switched according to the interface link to realize the information prompting to the user.
  • the input mode of the to-do transaction information is voice input, it indicates that the user is currently inconvenient to perform the next operation on the terminal, and the user may be prompted to display information by displaying text information or picture information.
  • FIG. 4 is a flowchart showing a specific implementation of a method S14 for prompting information according to a fourth embodiment of the present application. It should be noted that the text information in this embodiment includes a prompt condition.
  • S14 includes S141 and S142.
  • the environment information includes: time information, geographic location information, or weather information, wherein the weather information includes temperature information and/or humidity information.
  • the prompt conditions also include: time information, geographical location information or weather information.
  • the text information configuration prompt condition enables the prompt timing of the text information to match the timing of prompting the pending transaction, thereby realizing accurate display of the prompt information.
  • step S14 may further include: if the target prompt information is the webpage link, invoking a browser to access a webpage pointed by the webpage link.
  • target prompt information In order to improve the accuracy of the display target information, different types of target prompt information correspond to different display strategies.
  • the target prompt information is text information, it indicates that the user is currently inconvenient to perform the next step on the terminal, and therefore, directly displaying the text information. The user can be prevented from performing other redundant operations in a scenario where the user is inconvenient to perform the next step on the terminal.
  • the target prompt information is a webpage link, it indicates that the user is currently convenient to perform the next operation on the terminal. Therefore, by calling the browser to access the webpage pointed by the webpage link, the user is provided with richer prompt information.
  • FIG. 5 is a structural block diagram of a terminal device according to an embodiment of the present application, where each unit included in the terminal device is used to execute each step in the embodiment corresponding to FIG. 2.
  • each unit included in the terminal device is used to execute each step in the embodiment corresponding to FIG. 2.
  • only the parts related to the present embodiment are shown.
  • the terminal device 3 includes a first acquisition unit 31, an input unit 32, a determination unit 33, and a display unit 34. specifically:
  • the first obtaining unit 31 is configured to acquire to-do transaction information input by the user for describing the first to-do transaction.
  • the input unit 32 is configured to input the to-do transaction information into a prompt information recommendation model, where the prompt information recommendation model is configured to select, according to the to-do transaction information, a second prompt for prompting the second Pending information for pending transactions.
  • the determining unit 33 is configured to determine the target prompt information from the to-be-presented information based on the input manner of the to-do transaction information.
  • the display unit 34 is configured to display the target prompt information.
  • the to-be-presented information includes text information and a webpage link.
  • the determining unit 33 is specifically configured to: acquire an input manner of the user inputting the to-do transaction information; if the input mode is voice input, identify the text information as the target prompt information; if the input mode is text Input, the webpage link is identified as the target prompt information.
  • the text information includes a prompt condition.
  • the display unit 34 is specifically configured to: if the target prompt information is the text information, acquire current environmental information; the environmental information includes: time information, geographic location information, or weather information, where the weather information includes temperature information and And/or humidity information; if the environmental information matches the prompt condition, the text information is displayed.
  • the display unit 34 is specifically configured to: if the target prompt information is the webpage link, invoke a browser to access a webpage pointed by the webpage link.
  • the terminal device 3 further includes: a second obtaining unit 301, an adjusting unit 302, and a model generating unit 303. specifically:
  • the second obtaining unit 301 is configured to acquire template transaction information of the user, and at least two pieces of prompt information corresponding to the template transaction information.
  • the adjusting unit 302 is configured to adjust the learning parameter in the long-term and short-term memory LSTM neural network based on the template transaction information and the at least two pieces of the prompt information, so that the learning parameter satisfies the following conditions:
  • ⁇ * is the adjusted learning parameter
  • S is the prompt information
  • I is the template transaction information
  • I 1 , I 2 , I 3 , ..., I n are each of the template transaction information a parameter value of the item transaction
  • n is the number of the transactions
  • the model generating unit 303 is configured to identify the LSTM neural network after adjusting the learning parameter as the prompt information recommendation model.
  • FIG. 6 is a schematic diagram of a terminal device according to another embodiment of the present application.
  • the terminal device 6 of this embodiment includes a processor 60, a memory 61, and a program stored in the memory 61 and executable on the processor 60, such as a program for prompting information.
  • the processor 60 when executing the computer program 62, implements the functions of the various units in the various apparatus embodiments described above, such as the functions of the modules 51-55 shown in FIG.
  • the computer program 62 can be partitioned into one or more units that are stored in the memory 61 and executed by the processor 60 to complete the application.
  • the one or more units may be a series of computer program instruction segments capable of performing a particular function for describing the execution of the computer program 62 in the terminal device 6.
  • the computer program 62 may be divided into a user information acquisition unit, a candidate protocol selection unit, a recommendation coefficient calculation unit, a target protocol determination unit, and a target protocol unit, each of which has a specific function as described above.
  • the terminal device 6 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server.
  • the terminal device may include, but is not limited to, a processor 60 and a memory 61. It will be understood by those skilled in the art that FIG. 6 is only an example of the terminal device 6, and does not constitute a limitation of the terminal device 6, and may include more or less components than those illustrated, or combine some components or different components.
  • the terminal device may further include an input/output device, a network access device, a bus, and the like.
  • the so-called processor 60 may be a central processing unit (CPU), or may be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc.
  • the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
  • the memory 61 may be an internal storage unit of the terminal device 6, such as a hard disk or a memory of the terminal device 6.
  • the memory 61 may also be an external storage device of the terminal device 6, for example, a plug-in hard disk equipped on the terminal device 6, a smart memory card (SMC), and a secure digital (SD). Card, flash card, etc. Further, the memory 61 may also include both an internal storage unit of the terminal device 6 and an external storage device.
  • the memory 61 is used to store the computer program and other programs and data required by the terminal device.
  • the memory 61 can also be used to temporarily store data that has been output or is about to be output.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated modules/units if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, the present application implements all or part of the processes in the foregoing embodiments, and may also be completed by a computer program to instruct related hardware.
  • the computer program may be stored in a computer readable storage medium. The steps of the various method embodiments described above may be implemented when the program is executed by the processor.
  • the computer program comprises computer program code, which may be in the form of source code, object code form, executable file or some intermediate form.
  • the computer readable medium may include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM). , random access memory (RAM, Random Access Memory), electrical carrier signals, telecommunications signals, and software distribution media. It should be noted that the content contained in the computer readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in a jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, computer readable media Does not include electrical carrier signals and telecommunication signals.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

本申请适用于信息处理技术领域,提供了一种提示信息的方法、终端设备及计算机可读存储介质,其中,一种提示信息的方法,通过获取用户输入的用于描述第一待办事务的待办事务信息,再利用提示信息推荐模型根据待办事务信息,从预设的提示信息库中选取出用于提示第二待办事务的待提示信息,基于待办事务信息的输入方式,从待提示信息中确定目标提示信息进行显示,实现在不同的操作场景下输入待办事务信息,分别可以提示出各种与待办事务信息相关联的内容,丰富了提示信息的内容。

Description

一种提示信息的方法、终端设备及计算机可读存储介质
本申请申明享有2017年04月2日递交的申请号为201810281391.7、名称为“一种提示信息的方法、终端设备及计算机可读存储介质”中国专利申请的优先权,该中国专利申请的整体内容以参考的方式结合在本申请中。
技术领域
本申请属于信息处理技术领域,尤其涉及一种提示信息的方法、终端设备及计算机可读存储介质。
背景技术
随着终端的智能化水平越来越高,人们在日常工作或生活中,对终端的依赖程度也越来越深,例如,线上购物、路线规划以及代办事务提示等,都需要依赖终端。
在现有技术中,依赖终端为进行代办事务的提示时,虽然可以从用户输入的事务信息中获取到提示条件和事务内容,并在满足提示条件时,进行事务内容的提示,但是提示内容仅限于用户输入的事务内容,可见,现有的提示信息技术中存在提示信息内容过于单一的问题。
技术问题
有鉴于此,本申请实施例提供了一种提示信息的方法、终端设备及计算机可读存储介质,以解决现有的提示信息技术中存在提示信息内容过于单一的问题。
技术解决方案
本申请实施例的第一方面提供了一种提示信息的方法,包括:
获取用户输入的用于描述第一待办事务的待办事务信息;
将所述待办事务信息输入提示信息推荐模型,所述提示信息推荐模型用于根据所述待办事务信息,从预设的提示信息库中选取出用于提示第二待办事务的待提示信息,所述提示信息库中的信息用于描述所述待办事务信息与所述待提示信息之间的对应关系;
基于所述待办事务信息的输入方式,从所述待提示信息中确定目标提示信息;
显示所述目标提示信息。
有益效果
实施本申请实施例提供的一种提示信息的方法、终端设备及计算机可读存储介质具有以下有益效果:
本申请实施例通过获取用户输入的用于描述第一待办事务的待办事务信息,再利用提 示信息推荐模型根据待办事务信息,从预设的提示信息库中选取出用于提示第二待办事务的待提示信息,基于待办事务信息的输入方式,从待提示信息中确定目标提示信息进行显示,实现在不同的操作场景下输入待办事务信息,分别可以提示出各种与待办事务信息相关联的内容,丰富了提示信息的内容。
附图说明
图1是本申请实施例提供的一种提示信息的方法的实现流程图;
图2是本申请另一实施例提供的一种提示信息的方法具体实现流程图;
图3是本申请另一实施例提供的一种提示信息的方法S13具体实现流程图;
图4是本申请另一实施例提供的一种提示信息的方法S14具体实现流程图;
图5是本申请一实施例提供的一种终端设备的结构框图;
图6是本申请另一实施例提供的一种终端设备的示意图。
本发明的实施方式
为了使本申请的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本申请进行进一步详细说明。应当理解,此处所描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。
本申请实施例通过获取用户输入的用于描述第一待办事务的待办事务信息,再利用提示信息推荐模型根据待办事务信息,从预设的提示信息库中选取出用于提示第二待办事务的待提示信息,基于待办事务信息的输入方式,从待提示信息中确定目标提示信息进行显示,实现在不同的操作场景下输入待办事务信息,分别可以提示出各种与待办事务信息相关联的内容,丰富了提示信息的内容。
在本申请实施例中,流程的执行主体为终端设备。该终端设备包括但不限于:智能手机、笔记本电脑、计算机、平板电脑等移动终端。特别地,该终端设备可以为一坐席终端,坐席终端将选取得到的提示信息给各个目标用户的用户终端。图1示出了本申请第一实施例提供的提示信息的方法的实现流程图,详述如下:
S11:获取用户输入的用于描述第一待办事务的待办事务信息。
在步骤S11中,待办事务信息可以为语音信息或者文字信息,其中,语音信息可以通过调用终端的麦克风录入,或者由用户通过选取应用中已录入的语音信息得到;文字信息可以由用户手动输入,或者由用户在应用中对某段文字内容进行复制得到。
在本实施例中,待办事务信息用于描述第一待办事务的内容,同时还是用户希望被提醒的事务内容。
需要说明的是,待办事务信息可以包括:事务提醒条件、事务内容以及注意事项中的至少两项,其中,事务提醒条件可以包括:时间、地理位置或者环境条件,例如,温度、湿度或者紫外线强度等。
以第一待办事务为“上午十点在会议厅开会”为例,获取用户输入的用于描述第一待办事务的待办事务信息,也即获取用户输入的用于描述“上午十点在会议厅开会”的语音信息或者文字信息。
可以理解的是,在实际应用中,当终端获取到用户输入的待办事务信息,可以通过对该待办事务信息进行解析,进而确定对第一待办事务进行提醒的条件和事务内容。
S12:将所述待办事务信息输入提示信息推荐模型,所述提示信息推荐模型用于根据所述待办事务信息,从预设的提示信息库中选取出用于提示第二待办事务的待提示信息。
在步骤S12中,预设的提示信息库中的信息,用于描述待办事务信息与待提示信息之间的对应关系。
在本实施例中,提示信息库中的信息可以通过统计用户输入的历史待办事务信息得到,其中,每项历史待办事务信息所描述的待办事务至少包括两项,且每项待办事务均可作为提示信息库中待办事务信息所描述的内容,或者待提示信息所描述的内容。每项历史待办事务信息所描述的至少两项待办事务中,每项待办事务对应有各自的事务提醒条件,或者每项待办事务遵循同一事务提醒条件,例如,事务提醒条件为时间,则每项待办事务可以同时执行,或者分先后执行。
以历史待办事务信息“下午开会记住带咖啡”为例,其中,第一项待办事务为“下午开会”,第二项待办事务为“记住带咖啡”,预设的提示信息库中信息用于描述第一项待办事务与第二项待办事务之间的对应关系,也即用于描述“下午开会”的待办事务信息,与用于描述“记住带咖啡”待提示信息之间的对应关系,或者是用于描述“记住带咖啡”的待办事务信息,与用于描述“下午开会”待提示信息之间的对应关系。
为了进一步丰富提示信息的内容,待提示信息除了可以是用于提示第二待办事务的内容以外,还可以是页面连接,可以通过区分用户当前是否便于对终端进行进一步操作,进而从待提示信息中确定出合适当前操作场景的提示信息,作为目标提示信息。
S13:基于所述待办事务信息的输入方式,从所述待提示信息中确定目标提示信息。
在步骤S13中,输入方式可以为文字输入或者语音输入,待提示信息可以包括文字信息、图片信息或者应用的界面链接。
需要说明的是,不同的输入方式可以反映用户当前是否便于对终端进行下一步的手动操作,不同的输入方式可以对应不同的目标提示信息。
例如,当待办事务信息的输入方式为文本输入时,则表示用户当前便于对终端进行下一步操作,可通过启动相关应用,并根据界面链接切换当前操作界面,实现对用户进行信息提示。
再例如,当待办事务信息的输入方式为语音输入时,则表示用户当前不便于对终端进行下一步操作,可通过显示文字信息或者图片信息,实现对用户进行信息提示。
在本实施例中,根据待办事务信息的输入方式,可以预测用户当前是否便于对终端进行下一步操作,便于从提示信息中确定出更适合用户当前使用场景的提示信息,作为目标提示信息。
S14:显示所述目标提示信息。
在步骤S14中,目标提示信息为待提示信息中的一种,目标提示信息具体可以为:文字提示信息、图片提示信息或者网页提示信息。
在本实施例中,显示目标提示信息是在检测到当前环境条件满足事务提醒条件时,显示目标提示信息。
需要说明的是,不同的目标提示信息,显示方式可以不同。
例如,当目标提示信息为文字提示信息或图片提示信息时,可以通过推送系统通知的方式显示目标提示信息。
再例如,当目标提示信息为文字网页提示信息时,可以通过调用相应的应用跳转到对应的页面显示该目标提示信息。
以上可以看出,本申请实施例提供的一种提示信息的方法通过获取用户输入的用于描述第一待办事务的待办事务信息,再利用提示信息推荐模型根据待办事务信息,从预设的提示信息库中选取出用于提示第二待办事务的待提示信息,基于待办事务信息的输入方式,从待提示信息中确定目标提示信息进行显示,实现在不同的操作场景下输入待办事务信息,分别可以提示出各种与待办事务信息相关联的内容,丰富了提示信息的内容。
图2示出了本申请另一实施例提供的一种提示信息的方法的具体实现流程图。参见图2所示,相对于图1所述实施例,本实施例提供的一种提示信息的方法中还包括S21~S23,具体详述如下:
进一步地,作为本申请另一实施例,在将所述待办事务信息输入提示信息推荐模型之前,还包括:
S21:获取所述用户的模版事务信息,以及与所述模版事务信息对应的至少两项提示信息。
在本实施例中,提示信息推荐模型具体为一长短期记忆LSTM神经网络,为了提高该 LSTM神经网络输出候选协议的正确率,需要输入训练数据对该神经网络进行学习训练。因此,在S21中,需要终端对用户的模版事务信息,以及与模版事务信息对应的至少两项提示信息进行获取。其中,模版事务信息基于历史代办事务信息得到。具体地,基于某一类历史待办事务信息的内容,通过调用预先配置的响应服务工具,根据历史待办事务信息确定相应的消费应用或资讯应用,使其对应的至少两项提示信息中,不仅包括历史待办事务信息的内容,还包括历史待办事务信息的内容相关的应用界面连接。
以模版事务信息为包含两项事务的历史待办事务信息为例,历史待办事务信息为“下午开会记住带咖啡”,其中,第一项提示信息为“下午开会”,第二项提示信息为“记住带咖啡”,第三项提示信息为咖啡外卖订购页面。
在本实施例中,模版事务信息对应的至少两项提示信息的内容中,包含了用户以往的需求和用户可能存在的需求,即终端设备显示的提示信息,与用户以往的需求相同或相近,把模版事务信息作为LSTM神经网络的输入参考值,把模版事务信息对应的提示信息作为LSTM神经网络的输出参考值,通过上述两个参数对LSTM神经网络进行训练。
S22:基于所述模版事务信息与至少两项所述提示信息,调整长短期记忆LSTM神经网络中的学习参数,以使所述学习参数满足以下条件:
Figure PCTCN2018097532-appb-000001
其中,θ *为调整后的所述学习参数;S为所述提示信息;I为所述模版事务信息;I 1,I 2,I 3,…,I n为所述模版事务信息包含的各项事务的参数值;n为所述事务的个数;p(S|I 1,I 2,I 3,…,I n;θ)为当所述学习参数的值为θ时,将所述模版事务信息输入到所述LSTM神经网络,输出结果为所述提示信息的概率值;max θ(I,S)logp(S|I 1,I 2,I 3,…,I n;θ)为所述概率值取最大值时所述学习参数的取值。
在本实施例中,LSTM神经网络有N个输入通道,每个输入通道对应于模版事务信息中包含的各项事务参数,例如模版事务信息中包含:时间、地点、事务内容3个事务参数,则LSTM神经网络中则会设置有3个输入通道,依据各个事务参数在提示信息中的编号,为每个事务信息固定与之对应的输入通道,从而保证每个输入通道输入的事务参数的类别是相同的。该LSTM神经网络的输出通道为一个,用于输出与模版事务信息相匹配的提示信息。
在本实施例中,LSTM神经网络中包含多个神经层,每个神经层设置有相应的学习参数,通过调整学习参数的参数值能够适应不同输入类型以及输出类型。当学习参数设置为 某一参数值时,将多个训练用户的用户信息输入到该LSTM神经网络,将对应输出目标提示信息,终端设备会将目标提示信息与模版事务信息对应的至少两项提示信息进行比对,确定本次输出是否正确,并且基于多个训练协议的输出结果,得到该学习参数取该参数值时输出结果正确的概率值。终端设备会调整该学习参数,以使该概率值取最大值,则表示该LSTM神经网络已经调整完毕。
S23:将调整学习参数后的所述LSTM神经网络识别为所述提示信息推荐模型。
在本实施例中,终端设备将调整了学习参数后的LSTM神经网络作为提示信息推荐模型,提高了候选协议推荐模型识别的准确率。
在本申请实施例中,通过对LSTM神经网络进行训练,选取输出结果正确的概率值最大时对应的学习参数作为LSTM神经网络中学习参数的参数值,从而提高了提示信息识别的准确性,实现精准确定提示信息的目的。
通过获取用户输入的用于描述第一待办事务的待办事务信息,再利用提示信息推荐模型根据待办事务信息,从预设的提示信息库中选取出用于提示第二待办事务的待提示信息,便于从待提示信息中选取适合用户当前使用场景的目标信息进行显示。
图3示出了本申请另一实施例提供的一种提示信息的方法S13的具体实现流程图。参见图3所示,相对于图1所述实施例,本实施例提供的一种提示信息的方法中S13包括S131、S132以及S133,具体详述如下:
作为本申请另一实施例,待提示信息包括文本信息和网页链接。
S131:获取用户输入所述待办事务信息的输入方式。
S132:若所述输入方式为语音输入,则将所述文本信息识别为所述目标提示信息。
S133:若所述输入方式为文本输入,则将所述网页链接识别为所述目标提示信息。
需要说的是,输入方式可以为文字输入或者语音输入。获取用户输入代办事务信息的输入方式,可以通过识别该待办事务信息的信息处理端口,不同的待办事务信息输入方式对应不同的信息处理端口,根据该处理端口的标识确定待办事务信息的输入方式。
在本实施例中,不同的输入方式可以反映用户当前是否便于对终端进行下一步的手动操作,便于从提示信息中确定出更适合用户当前使用场景的提示信息,作为目标提示信息。
例如,当待办事务信息的输入方式为文本输入时,则表示用户当前便于对终端进行下一步操作,可通过启动相关应用,并根据界面链接切换当前操作界面,实现对用户进行信息提示。
再例如,当待办事务信息的输入方式为语音输入时,则表示用户当前不便于对终端进行下一步操作,可通过显示文字信息或者图片信息,实现对用户进行信息提示。
图4示出了本申请第四实施例提供的一种提示信息的方法S14的具体实现流程图。需要说明的是,本实施例中的文本信息中包括提示条件。
参见图4所示,相对于图1所述实施例,本实施例提供的一种提示信息的方法中S14包括S141和S142。
S141:若所述目标提示信息为所述文本信息,则获取当前的环境信息。
S142:若所述环境信息与所述提示条件相匹配,则显示所述文本信息。
在本实施例中,环境信息包括:时间信息、地理位置信息或者天气信息,其中,天气信息包括温度信息和/或湿度信息。相应的,提示条件也包括:时间信息、地理位置信息或者天气信息。
在实际中,许多待办事务并非用户当前需要及时办理的事务,而是用户希望终端能够在满足某种条件下,向用户进行提醒的事务,因此,当目标提示信息为文本信息时,为该文本信息配置提示条件,使得该文本信息的提示时机能够与提示待办事务的时机相匹配,实现提示信息的准确显示。
作为本申请另一实施例,步骤S14还可以包括:若所述目标提示信息为所述网页链接,则调用浏览器访问所述网页链接所指向的网页。
为了提高显示目标信息的准确性,不同类型的目标提示信息对应不同的显示策略,当目标提示信息为文本信息时,则表示用户当前不便于对终端进行下一步,因此,直接通过显示文本信息,可以在用户不便于对终端进行下一步操作的场景下,避免用户进行其他多余的操作。对应的,当目标提示信息为网页链接时,则表示用户当前便于对终端进行下一步操作,因此,通过调用浏览器访问网页链接所指向的网页,进而为用户提供更丰富的提示信息。
图5示出了本申请一实施例提供的一种终端设备的结构框图,该终端设备包括的各单元用于执行图2对应的实施例中的各步骤。具体请参阅图2与图2所对应的实施例中的相关描述。为了便于说明,仅示出了与本实施例相关的部分。
参见图5,终端设备3包括:第一获取单元31、输入单元32、确定单元33以及显示单元34。具体地:
第一获取单元31,用于获取用户输入的用于描述第一待办事务的待办事务信息。
输入单元32,用于将所述待办事务信息输入提示信息推荐模型,所述提示信息推荐模型用于根据所述待办事务信息,从预设的提示信息库中选取出用于提示第二待办事务的待提示信息。
确定单元33,用于基于所述待办事务信息的输入方式,从所述待提示信息中确定目标 提示信息。
显示单元34,用于显示所述目标提示信息。
进一步地,作为本实施例一种可能实现的方式,所述待提示信息包括文本信息和网页链接。
确定单元33具体用于,获取用户输入所述待办事务信息的输入方式;若所述输入方式为语音输入,则将所述文本信息识别为所述目标提示信息;若所述输入方式为文本输入,则将所述网页链接识别为所述目标提示信息。
进一步地,作为本实施例一种可能实现的方式,所述文本信息中包括提示条件。
显示单元34具体用于,若所述目标提示信息为所述文本信息,则获取当前的环境信息;所述环境信息包括:时间信息、地理位置信息或者天气信息,其中,天气信息包括温度信息和/或湿度信息;若所述环境信息与所述提示条件相匹配,则显示所述文本信息。
进一步地,作为本实施例一种可能实现的方式,显示单元34具体用于,若所述目标提示信息为所述网页链接,则调用浏览器访问所述网页链接所指向的网页。
进一步地,作为本实施例一种可能实现的方式,终端设备3还包括:第二获取单元301、调整单元302以及模型生成单元303。具体地:
第二获取单元301,用于获取所述用户的模版事务信息,以及与所述模版事务信息对应的至少两项提示信息。
调整单元302,用于基于所述模版事务信息与至少两项所述提示信息,调整长短期记忆LSTM神经网络中的学习参数,以使所述学习参数满足以下条件:
Figure PCTCN2018097532-appb-000002
其中,θ *为调整后的所述学习参数;S为所述提示信息;I为所述模版事务信息;I 1,I 2,I 3,…,I n为所述模版事务信息包含的各项事务的参数值;n为所述事务的个数;p(S|I 1,I 2,I 3,…,I n;θ)为当所述学习参数的值为θ时,将所述模版事务信息输入到所述LSTM神经网络,输出结果为所述提示信息的概率值;max θ(I,S)logp(S|I 1,I 2,I 3,…,I n;θ)为所述概率值取最大值时所述学习参数的取值。
模型生成单元303,用于将调整学习参数后的所述LSTM神经网络识别为所述提示信息推荐模型。
图6是本申请另一实施例提供的一种终端设备的示意图。如图6所示,该实施例的终端设备6包括:处理器60、存储器61以及存储在所述存储器61中并可在所述处理器60 上运行的计算机程序62,例如提示信息的程序。所述处理器60执行所述计算机程序62时实现上述各个提示信息的方法实施例中的步骤,例如图1所示的S101至S105。或者,所述处理器60执行所述计算机程序62时实现上述各装置实施例中各单元的功能,例如图5所示模块51至55功能。
示例性的,所述计算机程序62可以被分割成一个或多个单元,所述一个或者多个单元被存储在所述存储器61中,并由所述处理器60执行,以完成本申请。所述一个或多个单元可以是能够完成特定功能的一系列计算机程序指令段,该指令段用于描述所述计算机程序62在所述终端设备6中的执行过程。例如,所述计算机程序62可以被分割成用户信息获取单元、候选协议选取单元、推荐系数计算单元、目标协议确定单元以及目标协议单元,各单元具体功能如上所述。
所述终端设备6可以是桌上型计算机、笔记本、掌上电脑及云端服务器等计算设备。所述终端设备可包括,但不仅限于,处理器60、存储器61。本领域技术人员可以理解,图6仅仅是终端设备6的示例,并不构成对终端设备6的限定,可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件,例如所述终端设备还可以包括输入输出设备、网络接入设备、总线等。
所称处理器60可以是中央处理单元(Central Processing Unit,CPU),还可以是其他通用处理器、数字信号处理器(Digital Signal Processor,DSP)、专用集成电路(Application Specific Integrated Circuit,ASIC)、现成可编程门阵列(Field-Programmable Gate Array,FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
所述存储器61可以是所述终端设备6的内部存储单元,例如终端设备6的硬盘或内存。所述存储器61也可以是所述终端设备6的外部存储设备,例如所述终端设备6上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。进一步地,所述存储器61还可以既包括所述终端设备6的内部存储单元也包括外部存储设备。所述存储器61用于存储所述计算机程序以及所述终端设备所需的其他程序和数据。所述存储器61还可以用于暂时地存储已经输出或者将要输出的数据。
另外,在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。
所述集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用 时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本申请实现上述实施例方法中的全部或部分流程,也可以通过计算机程序来指令相关的硬件来完成,所述的计算机程序可存储于一计算机可读存储介质中,该计算机程序在被处理器执行时,可实现上述各个方法实施例的步骤。其中,所述计算机程序包括计算机程序代码,所述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。所述计算机可读介质可以包括:能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、电载波信号、电信信号以及软件分发介质等。需要说明的是,所述计算机可读介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减,例如在某些司法管辖区,根据立法和专利实践,计算机可读介质不包括电载波信号和电信信号。
以上所述实施例仅用以说明本申请的技术方案,而非对其限制;尽管参照前述实施例对本申请进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围,均应包含在本申请的保护范围之内。

Claims (20)

  1. 一种提示信息的方法,其特征在于,包括:
    获取用户输入的用于描述第一待办事务的待办事务信息;
    将所述待办事务信息输入提示信息推荐模型,所述提示信息推荐模型用于根据所述待办事务信息,从预设的提示信息库中选取出用于提示第二待办事务的待提示信息,所述提示信息库中的信息用于描述所述待办事务信息与所述待提示信息之间的对应关系;
    基于所述待办事务信息的输入方式,从所述待提示信息中确定目标提示信息;
    显示所述目标提示信息。
  2. 根据权利要求1所述的方法,其特征在于,所述将所述待办事务信息输入提示信息推荐模型之前,还包括:
    获取所述用户的模版事务信息,以及与所述模版事务信息对应的至少两项提示信息;所述模版事务信息基于历史待办事务信息得到;
    基于所述模版事务信息与至少两项所述提示信息,调整长短期记忆LSTM神经网络中的学习参数,以使所述学习参数满足以下条件:
    Figure PCTCN2018097532-appb-100001
    其中,θ *为调整后的所述学习参数;S为所述提示信息;I为所述模版事务信息;I 1,I 2,I 3,…,I n为所述模版事务信息包含的各项事务的参数值;n为所述事务的个数;p(S|I 1,I 2,I 3,…,I n;θ)为当所述学习参数的值为θ时,将所述模版事务信息输入到所述LSTM神经网络,输出结果为所述提示信息的概率值;max θ(I,S)logp(S|I 1,I 2,I 3,…,I n;θ)为所述概率值取最大值时所述学习参数的取值;
    将调整学习参数后的所述LSTM神经网络识别为所述提示信息推荐模型。
  3. 根据权利要求1所述的方法,其特征在于,所述待提示信息包括文本信息和网页链接;
    所述基于所述待办事务信息的输入方式,从所述待提示信息中确定目标提示信息,包括:
    获取用户输入所述待办事务信息的输入方式;
    若所述输入方式为语音输入,则将所述文本信息识别为所述目标提示信息;
    若所述输入方式为文本输入,则将所述网页链接识别为所述目标提示信息。
  4. 根据权利要求3所述的方法,其特征在于,所述文本信息中包括提示条件;所述显示所述目标提示信息,包括:
    若所述目标提示信息为所述文本信息,则获取当前的环境信息;所述环境信息包括:时间信息、地理位置信息或者天气信息,其中,天气信息包括温度信息和/或湿度信息;
    若所述环境信息与所述提示条件相匹配,则显示所述文本信息。
  5. 根据权利要求3所述的方法,其特征在于,所述显示所述目标提示信息,包括:
    若所述目标提示信息为所述网页链接,则调用浏览器访问所述网页链接所指向的网页。
  6. 一种提示信息的装置,其特征在于,包括:
    第一获取单元,用于获取用户输入的用于描述第一待办事务的待办事务信息;
    输入单元,用于将所述待办事务信息输入提示信息推荐模型,所述提示信息推荐模型用于根据所述待办事务信息,从预设的提示信息库中选取出用于提示第二待办事务的待提示信息;
    确定单元,用于基于所述待办事务信息的输入方式,从所述待提示信息中确定目标提示信息;
    显示单元,用于显示所述目标提示信息。
  7. 如权利要求6所述的装置,其特征在于,所述
    第二获取单元,用于获取所述用户的模版事务信息,以及与所述模版事务信息对应的至少两项提示信息;所述模版事务信息基于历史待办事务信息得到;
    调整单元,用于基于所述模版事务信息与至少两项所述提示信息,调整长短期记忆LSTM神经网络中的学习参数,以使所述学习参数满足以下条件:
    Figure PCTCN2018097532-appb-100002
    其中,θ *为调整后的所述学习参数;S为所述提示信息;I为所述模版事务信息;I 1,I 2,I 3,…,I n为所述模版事务信息包含的各项事务的参数值;n为所述事务的个数;p(S|I 1,I 2,I 3,…,I n;θ)为当所述学习参数的值为θ时,将所述模版事务信息输入到所述LSTM神经网络,输出结果为所述提示信息的概率值;max θ(I,S)logp(S|I 1,I 2,I 3,…,I n;θ)为所述概率值取最大值时所述学习参数的取值;
    模型生成单元,用于将调整学习参数后的所述LSTM神经网络识别为所述提示信息推荐模型。
  8. 如权利要求6所述的装置,其特征在于,所述待提示信息包括文本信息和网页链接;
    所述确定单元具体用于,获取用户输入所述待办事务信息的输入方式;若所述输入方式为语音输入,则将所述文本信息识别为所述目标提示信息;若所述输入方式为文本输入,则将所述网页链接识别为所述目标提示信息。
  9. 如权利要求8所述的装置,其特征在于,所述文本信息中包括提示条件;
    所述显示单元具体用于,若所述目标提示信息为所述文本信息,则获取当前的环境信息;所述环境信息包括:时间信息、地理位置信息或者天气信息,其中,天气信息包括温度信息和/或湿度信息;若所述环境信息与所述提示条件相匹配,则显示所述文本信息。
  10. 如权利要求8所述的装置,其特征在于,所述显示单元具体用于,若所述目标提示信息为所述网页链接,则调用浏览器访问所述网页链接所指向的网页。
  11. 一种终端设备,包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机可读指令,其特征在于,所述处理器执行所述计算机可读指令时实现如下步骤:
    获取用户输入的用于描述第一待办事务的待办事务信息;
    将所述待办事务信息输入提示信息推荐模型,所述提示信息推荐模型用于根据所述待办事务信息,从预设的提示信息库中选取出用于提示第二待办事务的待提示信息,所述提示信息库中的信息用于描述所述待办事务信息与所述待提示信息之间的对应关系;
    基于所述待办事务信息的输入方式,从所述待提示信息中确定目标提示信息;
    显示所述目标提示信息。
  12. 如权利要求11所述的终端设备,其特征在于,所述将所述待办事务信息输入提示信息推荐模型之前,还包括:
    获取所述用户的模版事务信息,以及与所述模版事务信息对应的至少两项提示信息;所述模版事务信息基于历史待办事务信息得到;
    基于所述模版事务信息与至少两项所述提示信息,调整长短期记忆LSTM神经网络中的学习参数,以使所述学习参数满足以下条件:
    Figure PCTCN2018097532-appb-100003
    其中,θ *为调整后的所述学习参数;S为所述提示信息;I为所述模版事务信息;I 1,I 2,I 3,…,I n为所述模版事务信息包含的各项事务的参数值;n为所述事务的个数;p(S|I 1,I 2,I 3,…,I n;θ)为当所述学习参数的值为θ时,将所述模版事务信息输入到所述LSTM 神经网络,输出结果为所述提示信息的概率值;max θ(I,S)logp(S|I 1,I 2,I 3,…,I n;θ)为所述概率值取最大值时所述学习参数的取值;
    将调整学习参数后的所述LSTM神经网络识别为所述提示信息推荐模型。
  13. 如权利要求11所述的终端设备,其特征在于,所述待提示信息包括文本信息和网页链接;
    所述基于所述待办事务信息的输入方式,从所述待提示信息中确定目标提示信息,包括:
    获取用户输入所述待办事务信息的输入方式;
    若所述输入方式为语音输入,则将所述文本信息识别为所述目标提示信息;
    若所述输入方式为文本输入,则将所述网页链接识别为所述目标提示信息。
  14. 如权利要求13所述的终端设备,其特征在于,所述文本信息中包括提示条件;所述显示所述目标提示信息,包括:
    若所述目标提示信息为所述文本信息,则获取当前的环境信息;所述环境信息包括:时间信息、地理位置信息或者天气信息,其中,天气信息包括温度信息和/或湿度信息;
    若所述环境信息与所述提示条件相匹配,则显示所述文本信息。
  15. 如权利要求13所述的终端设备,其特征在于,所述显示所述目标提示信息,包括:
    若所述目标提示信息为所述网页链接,则调用浏览器访问所述网页链接所指向的网页。
  16. 一种计算机可读存储介质,所述计算机可读存储介质存储有计算机可读指令,其特征在于,所述计算机可读指令被处理器执行时实现如下步骤:
    获取用户输入的用于描述第一待办事务的待办事务信息;
    将所述待办事务信息输入提示信息推荐模型,所述提示信息推荐模型用于根据所述待办事务信息,从预设的提示信息库中选取出用于提示第二待办事务的待提示信息,所述提示信息库中的信息用于描述所述待办事务信息与所述待提示信息之间的对应关系;
    基于所述待办事务信息的输入方式,从所述待提示信息中确定目标提示信息;
    显示所述目标提示信息。
  17. 如权利要求16所述的计算机可读存储介质,其特征在于,所述将所述待办事务信息输入提示信息推荐模型之前,还包括:
    获取所述用户的模版事务信息,以及与所述模版事务信息对应的至少两项提示信息;所述模版事务信息基于历史待办事务信息得到;
    基于所述模版事务信息与至少两项所述提示信息,调整长短期记忆LSTM神经网络中 的学习参数,以使所述学习参数满足以下条件:
    Figure PCTCN2018097532-appb-100004
    其中,θ *为调整后的所述学习参数;S为所述提示信息;I为所述模版事务信息;I 1,I 2,I 3,…,I n为所述模版事务信息包含的各项事务的参数值;n为所述事务的个数;p(S|I 1,I 2,I 3,…,I n;θ)为当所述学习参数的值为θ时,将所述模版事务信息输入到所述LSTM神经网络,输出结果为所述提示信息的概率值;max θ(I,S)logp(S|I 1,I 2,I 3,…,I n;θ)为所述概率值取最大值时所述学习参数的取值;
    将调整学习参数后的所述LSTM神经网络识别为所述提示信息推荐模型。
  18. 如权利要求16所述的计算机可读存储介质,其特征在于,所述待提示信息包括文本信息和网页链接;
    所述基于所述待办事务信息的输入方式,从所述待提示信息中确定目标提示信息,包括:
    获取用户输入所述待办事务信息的输入方式;
    若所述输入方式为语音输入,则将所述文本信息识别为所述目标提示信息;
    若所述输入方式为文本输入,则将所述网页链接识别为所述目标提示信息。
  19. 如权利要求18所述的计算机可读存储介质,其特征在于,所述文本信息中包括提示条件;所述显示所述目标提示信息,包括:
    若所述目标提示信息为所述文本信息,则获取当前的环境信息;所述环境信息包括:时间信息、地理位置信息或者天气信息,其中,天气信息包括温度信息和/或湿度信息;
    若所述环境信息与所述提示条件相匹配,则显示所述文本信息。
  20. 根据权利要求18所述的计算机可读存储介质,其特征在于,所述显示所述目标提示信息,包括:
    若所述目标提示信息为所述网页链接,则调用浏览器访问所述网页链接所指向的网页。
PCT/CN2018/097532 2018-04-02 2018-07-27 一种提示信息的方法、终端设备及计算机可读存储介质 WO2019192106A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810281391.7 2018-04-02
CN201810281391.7A CN108681871B (zh) 2018-04-02 2018-04-02 一种提示信息的方法、终端设备及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2019192106A1 true WO2019192106A1 (zh) 2019-10-10

Family

ID=63800571

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/097532 WO2019192106A1 (zh) 2018-04-02 2018-07-27 一种提示信息的方法、终端设备及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN108681871B (zh)
WO (1) WO2019192106A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113313454A (zh) * 2020-02-26 2021-08-27 阿里巴巴集团控股有限公司 时间提醒方法、装置及设备
CN113781205A (zh) * 2021-09-10 2021-12-10 平安普惠企业管理有限公司 事项进度智能跟进提示方法、装置、设备及介质

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111198641A (zh) * 2018-11-19 2020-05-26 珠海格力电器股份有限公司 一种消息推送方法及终端设备
CN116629810B (zh) * 2023-07-24 2023-10-20 中建五局第三建设有限公司 基于建筑办公系统的操作推荐方法、装置、设备和介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120052889A1 (en) * 2005-11-08 2012-03-01 David Clark Wireless Messaging Using Notification Messages in a Wireless Communication Network
CN104820918A (zh) * 2015-05-19 2015-08-05 李霈 智能事务处理方法、装置以及系统
CN104954560A (zh) * 2015-05-26 2015-09-30 深圳市万普拉斯科技有限公司 事件提示方法、装置及移动终端
US20170091819A1 (en) * 2015-09-30 2017-03-30 Newstore Inc. Mobile Communication Device Awareness and Guidance for Customer Assistance Applications
CN106791068A (zh) * 2016-12-14 2017-05-31 深圳市金立通信设备有限公司 一种待办事项的提醒方法和终端

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10701014B2 (en) * 2013-03-15 2020-06-30 Companyons, Inc. Contextual messaging systems and methods
CN106296116A (zh) * 2016-08-03 2017-01-04 北京小米移动软件有限公司 生成提示信息的方法及装置
CN107580128A (zh) * 2017-08-31 2018-01-12 珠海市魅族科技有限公司 待办事项处理方法及装置、终端及可读存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120052889A1 (en) * 2005-11-08 2012-03-01 David Clark Wireless Messaging Using Notification Messages in a Wireless Communication Network
CN104820918A (zh) * 2015-05-19 2015-08-05 李霈 智能事务处理方法、装置以及系统
CN104954560A (zh) * 2015-05-26 2015-09-30 深圳市万普拉斯科技有限公司 事件提示方法、装置及移动终端
US20170091819A1 (en) * 2015-09-30 2017-03-30 Newstore Inc. Mobile Communication Device Awareness and Guidance for Customer Assistance Applications
CN106791068A (zh) * 2016-12-14 2017-05-31 深圳市金立通信设备有限公司 一种待办事项的提醒方法和终端

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113313454A (zh) * 2020-02-26 2021-08-27 阿里巴巴集团控股有限公司 时间提醒方法、装置及设备
CN113781205A (zh) * 2021-09-10 2021-12-10 平安普惠企业管理有限公司 事项进度智能跟进提示方法、装置、设备及介质
CN113781205B (zh) * 2021-09-10 2023-08-15 平安普惠企业管理有限公司 事项进度智能跟进提示方法、装置、设备及介质

Also Published As

Publication number Publication date
CN108681871A (zh) 2018-10-19
CN108681871B (zh) 2023-04-18

Similar Documents

Publication Publication Date Title
WO2019192106A1 (zh) 一种提示信息的方法、终端设备及计算机可读存储介质
US10936672B2 (en) Automatic document negotiation
US9582757B1 (en) Scalable curation system
CN106686339B (zh) 电子会议智能
US20210224832A1 (en) Method and apparatus for predicting customer purchase intention, electronic device and medium
US9299041B2 (en) Obtaining data from unstructured data for a structured data collection
CN109522397B (zh) 信息处理方法及装置
US20160189103A1 (en) Apparatus and method for automatically creating and recording minutes of meeting
CN111223015B (zh) 课程推荐方法、装置及终端设备
EP3690673A1 (en) Method, apparatus, electronic device, and storage medium for image-based data processing
WO2020024417A1 (zh) 企业财务账单生成方法、装置、电子设备及存储介质
CN111985857A (zh) 审核方法以及装置
US11922929B2 (en) Presentation support system
US20200125796A1 (en) Displaying and Editing an Electronic Document
CN112233669A (zh) 一种演讲内容提示方法及系统
JP2016524733A (ja) カレンダアプリケーションの入力ストリームを処理するシステムおよび方法
CN110750626A (zh) 一种基于场景的任务驱动的多轮对话方法及系统
CN115905497A (zh) 确定答复语句的方法、装置、电子设备和存储介质
WO2022267168A1 (zh) 语音识别方法、装置、计算机设备及存储介质
CN111540358B (zh) 人机交互方法、装置、设备和存储介质
US9503504B2 (en) System and method for generating visual identifiers from user input associated with perceived stimuli
CN112367494A (zh) 基于ai的在线会议通讯方法、装置及计算机设备
CN111782776A (zh) 一种通过填槽实现意图识别的方法和装置
CN113127058A (zh) 数据标注方法、相关装置及计算机程序产品
CN112765331B (zh) 对话知识模板构建方法、装置、计算机设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18913819

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 19/01/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18913819

Country of ref document: EP

Kind code of ref document: A1