WO2020124453A1 - 信息自动回复的方法及相关装置 - Google Patents

信息自动回复的方法及相关装置 Download PDF

Info

Publication number
WO2020124453A1
WO2020124453A1 PCT/CN2018/122148 CN2018122148W WO2020124453A1 WO 2020124453 A1 WO2020124453 A1 WO 2020124453A1 CN 2018122148 W CN2018122148 W CN 2018122148W WO 2020124453 A1 WO2020124453 A1 WO 2020124453A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
reply
instant messaging
preset
electronic device
Prior art date
Application number
PCT/CN2018/122148
Other languages
English (en)
French (fr)
Inventor
陈岩
Original Assignee
深圳市欢太科技有限公司
Oppo广东移动通信有限公司
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 深圳市欢太科技有限公司, Oppo广东移动通信有限公司 filed Critical 深圳市欢太科技有限公司
Priority to PCT/CN2018/122148 priority Critical patent/WO2020124453A1/zh
Priority to CN201880098601.7A priority patent/CN113039758B/zh
Publication of WO2020124453A1 publication Critical patent/WO2020124453A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
    • H04M1/725—Cordless telephones

Definitions

  • This application relates to the field of communication technology, and in particular, to a method and related device for automatic information reply.
  • the embodiments of the present application provide a method for automatically replying information and related devices, so as to improve the reliability and intelligence of the automatic reply, and enhance the timeliness of user information interaction.
  • an embodiment of the present application provides a method for automatically replying information, which is applied to an electronic device, and the method includes:
  • the instant messaging information When receiving instant messaging information, obtain the display interface content of the electronic device, the instant messaging information includes call information or short message;
  • an embodiment of the present application provides an application control device, which is applied to an electronic device, and the application control device includes a processing unit and a communication unit, wherein,
  • the processing unit is configured to acquire the display interface content of the electronic device when receiving instant communication information through the communication unit, the instant communication information includes caller information or short message; and import the display interface content into the pre A trained scene recognition model, outputting a scene recognition result; and determining whether the electronic device is in a preset scene according to the scene recognition result, the preset scene including a game scene; and when it is determined that the electronic device is in the pre-set When setting the scene, determine whether to activate the automatic reply function according to the instant messaging information; if so, activate the automatic reply function and select a preset reply content for automatic reply.
  • an embodiment of the present application provides an electronic device, including a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be processed by the above
  • the above program includes instructions for performing the steps in any method of the first aspect of the embodiments of the present application.
  • an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program causes the computer to execute the first embodiment of the present application.
  • the computer program causes the computer to execute the first embodiment of the present application.
  • an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium that stores the computer program, and the computer program is operable to cause the computer to execute as implemented in the present application Examples of some or all of the steps described in any method of the first aspect.
  • the computer program product may be a software installation package.
  • the electronic device when the electronic device receives the instant messaging information, it first obtains the display interface content of the electronic device, and the instant messaging information includes caller information or short message information; then, the display interface content is imported into pre-trained scene recognition Model, output scene recognition results; secondly, determine whether the electronic device is in the preset scene according to the scene recognition result, the preset scene includes the game scene; again, when it is determined that the electronic device is in the preset scene, determine whether to start automatic according to instant messaging information Reply function; if yes, finally activate the automatic reply function, select the preset reply content to automatically reply.
  • the electronic device can recognize the current scene through the pre-trained scene recognition model when receiving the instant messaging information, and start the automatic reply function when the preset scene, so the electronic device can determine whether to automatically reply according to the current scene; according to the preset content Automatic reply effectively improves the reliability and intelligence of automatic reply, and enhances the timeliness of user information interaction.
  • FIG. 1 is a schematic flowchart of a method for automatically replying to information provided by an embodiment of the present application
  • FIG. 2 is a schematic flowchart of another method for automatically replying to information provided by an embodiment of the present application
  • FIG. 3 is a schematic flowchart of another method for automatically replying to information provided by an embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • FIG. 5 is a block diagram of functional units of an automatic information reply device provided by an embodiment of the present application.
  • the electronic device involved in the embodiments of the present application may be an electronic device with an information interaction function, and the electronic device may include various handheld devices with communication functions, in-vehicle devices, wearable devices, computing devices, or other devices connected to a wireless modem Processing equipment, and various forms of user equipment (User Equipment, UE), mobile station (Mobile Station, MS), terminal equipment (terminal), etc.
  • UE User Equipment
  • MS Mobile Station
  • terminal terminal
  • FIG. 1 is a schematic flowchart of a method for automatically responding to information provided by an embodiment of the present application, which is applied to an electronic device. As shown in the figure, the method for automatically replying to this information includes:
  • the electronic device can display the instant messaging display interface, and can also prompt through the prompt bar, and can also prompt the user through vibration, light, ring tone, etc.
  • Obtaining the display interface content of the electronic device includes obtaining a screenshot of the display interface and text content displayed on the display interface.
  • the electronic device imports the content of the display interface into a pre-trained scene recognition model, and outputs a scene recognition result;
  • the pre-training scene recognition model is to take a large number of screenshots of the display interface of the electronic device or the text content of the display interface as sample data, and import the sample data into a neural training network for training to create a scene recognition model of a preset scene.
  • a screenshot of the display interface of the display interface of the current scene or text content of the display interface is obtained, and a pre-trained scene recognition model is imported to obtain a scene recognition result of the display interface content of the current electronic device.
  • the electronic device determines whether the electronic device is in a preset scene according to the scene recognition result
  • the electronic device when the electronic device detects that it is in a preset scene, the automatic reply function of the electronic device is activated.
  • the preset scene of the electronic device can be customized according to user needs.
  • the electronic device activates the automatic reply function and selects a preset reply content to automatically reply.
  • an electronic device whenever an electronic device receives an instant messaging message, it immediately determines the current scene. When the current scene is a preset scene, the instant messaging message is analyzed to determine whether an automatic reply and automatic reply content are required.
  • the electronic device when the electronic device receives the instant messaging information, it first obtains the display interface content of the electronic device, and the instant messaging information includes caller information or short message information; then, the display interface content is imported into pre-trained scene recognition Model, output scene recognition results; secondly, determine whether the electronic device is in the preset scene according to the scene recognition result, the preset scene includes the game scene; again, when it is determined that the electronic device is in the preset scene, determine whether to start automatic according to instant messaging information Reply function; if yes, finally activate the automatic reply function, select the preset reply content to automatically reply.
  • the electronic device can recognize the current scene through the pre-trained scene recognition model when receiving the instant messaging information, and start the automatic reply function when the preset scene, so the electronic device can determine whether to automatically reply according to the current scene; according to the preset content Automatic reply effectively improves the reliability and intelligence of automatic reply, and enhances the timeliness of user information interaction.
  • the determining whether the electronic device is in a preset scene further includes: acquiring internal parameters of the electronic device; and determining whether the electronic device is in a preset scene according to the internal parameters.
  • the internal parameters include the amount of load data corresponding to the preset scene in the CPU, the amount of load data corresponding to the preset scene in the GPU, and the module parameters corresponding to the preset scene.
  • the electronic device can determine whether the current scene of the electronic device is a preset scene based on the internal parameters of the electronic device, which simplifies the process of detecting the scene and increases the speed of scene detection.
  • the short message information includes information of the sending end and text information, and it is determined whether to start the automatic reply function according to the information of the sending end and text information.
  • the electronic device can determine whether the short message information can start the automatic reply function by detecting the instant messaging information and determining the short message information, which improves the intelligence and efficiency of information interaction.
  • the determining whether to activate the automatic reply function according to the short message information includes: acquiring information of the sending end of the short message information; according to the information of the sending end and a preset first priority list Determining whether to activate the automatic reply function; or, acquiring text information of the short message information; importing the text information into a pre-trained semantic recognition model to identify the semantics of the short message information; determining whether to activate the text message according to the semantics Automatic reply function.
  • the information of the sending end includes the number of the sending end and the identification of the sending end
  • the identification includes the identification set by the user through the address book and other identifications obtained from the server (promotion, China Mobile, etc.).
  • the electronic device may determine whether to enable the automatic reply function according to the priority of the sender information by acquiring the sender information of the short message.
  • the information about the sending end and the corresponding first priority list of whether to enable the automatic reply function are given in Table 1 below.
  • the text information of the short message information obtained and stored by neural network training is used to create a semantic recognition model; when the short message information is received, the short message information can be imported into the semantic recognition model to determine that the rain of the text information is the same, and then determine Whether to reply automatically. For example, for SMS messages with semantics of "important" and “meeting", the automatic reply is not activated, and a prompt message is output to prompt the user to reply in person; for SMS messages with the semantics of "shopping”, the automatic reply function is not activated. For other semantics, the automatic reply function is activated for automatic reply.
  • semantic recognition may be performed before the priority judgment shown in Table 1; priority judgment as described in Table 1 may be performed first, and then semantic recognition is performed, for example, in the third priority described in Table 1 Level, semantic recognition of the short message sent by users who are not in the address book, to determine whether to perform automatic reply; two ways to determine whether to activate the automatic reply function can also be set separately.
  • the electronic device can identify the message information text based on the priority of the sender based on the short message information and determine whether to activate the automatic reply function through semantics, it can automatically respond to the user and semantics of the sender and filter the spam , Improve the timeliness and efficiency of information exchange.
  • the instant messaging information includes incoming call information; the determining whether to start the automatic reply function according to the instant messaging information includes: when detecting that the instant messaging information is the incoming call message, according to the The caller information determines whether to activate the automatic reply function.
  • the caller information includes caller information, and it is determined whether to activate the automatic reply function according to the caller information.
  • the electronic device can determine whether the caller of the caller information can start the automatic reply function by detecting the instant messaging information and determining the caller information, which improves the intelligence and efficiency of information exchange.
  • the determining whether to activate the automatic reply function according to the incoming call information includes: acquiring an incoming call identifier of the incoming call information; and determining whether to determine whether to perform the incoming call according to the incoming call identifier and a preset second priority list Start the automatic reply function.
  • the incoming call of the calling end of the incoming call information will carry the incoming call information of the calling end, and the electronic device may obtain the telephone number of the calling end and the incoming call identification of the calling end according to the incoming call information.
  • the caller ID may be the phone number of the calling end, or may be a mark marked on the calling end. The mark includes the name of the caller, the blacklist mark, and other marks (insurance, marketing, etc.) obtained from the network by the electronic device with the corresponding phone number pre-stored.
  • the electronic device can determine whether to enable the automatic reply function through the identification of the calling end in the call information, and can select the calling end user to automatically reply, which improves the timeliness and intelligence of information interaction.
  • the determining whether to start the automatic reply function according to the caller ID and the preset second priority list includes: querying the second priority list using the caller ID as a query identifier, Obtain the priority of the caller ID, and the second priority list includes the correspondence between the caller ID and the priority; when the caller ID is detected as the first priority, output prompt information to prompt the user to answer; When the caller ID is detected as the second priority, the automatic reply function is activated; when the caller ID is detected as the third priority, the automatic reply function is not activated.
  • the electronic device may obtain the caller ID of the caller information, and query the priority corresponding to the caller ID according to the caller ID and the second priority list, according to The priority of the caller ID determines whether to activate the automatic reply function.
  • the caller ID given in Table 2 below and the corresponding second priority list of whether to enable the automatic reply function.
  • the second priority list inquires that the priority is the second priority, and the automatic reply function is activated.
  • the electronic device determines whether to activate the automatic reply function based on the priority of the caller's caller ID in the caller information, and can perform corresponding reply operations for different caller users, thereby improving the timeliness and intelligence of information interaction.
  • the selecting the preset reply content for automatic reply includes: automatically replying according to the preset reply content corresponding to the preset scene; or, obtaining the historical reply content, according to the historical reply The content will automatically reply.
  • the preset reply content may be preset by the user according to different preset scenarios, for example, the user may set different reply content according to the game scenario and video call.
  • the preset reply content may also be set by the electronic device based on the content that the user frequently replies. After selecting the reply content, the electronic device can also store the information so that the user can select, edit, and use it when needed.
  • the electronic device can automatically reply based on the preset reply content or the user's historical reply content, which realizes the targeted reply according to the preset scene, improves the intelligence of the electronic device, and improves the user experience.
  • the acquiring historical reply content and automatically replying based on the historical reply include: acquiring historical instant messaging information and corresponding historical reply content; based on the historical instant messaging information and the historical reply content Generate sample data; use the sample data to train a preset reply content model to obtain a trained reply content model; import the instant messaging information into the trained reply content model to obtain a prediction corresponding to the instant messaging information Reply content; automatically reply according to the predicted reply content.
  • the predicted reply content is a reply content commonly used by users.
  • Generate sample data based on historical instant messaging information and the historical reply content including generating sample data based on the sender information, text information and corresponding historical reply content of historical short message information, call terminal information based on historical call information and the corresponding call
  • the historical reply content of the terminal generates sample data.
  • the instant messaging is imported into the trained reply content model to obtain the reply content commonly used by the user, and an automatic reply is performed according to the predicted reply content. For example, when the message on the sending end or the message on the calling end is "mother", an automatic reply will be made based on the content of the message that is frequently replied to "mother” (for example: Mom, I am busy now, and I will call you back later). For the text information of the short message, you can reply to the semantic historical reply content of the text information, for example, reply "OK”.
  • the electronic device can automatically reply based on the content that the user frequently replies to assist the user in replying information, which improves the intelligence of the electronic device and improves the user experience.
  • FIG. 2 is a schematic flowchart of a method for automatically replying to information provided by an embodiment of the present application, which is applied to an electronic device.
  • this information is automatically Response methods include:
  • the electronic device imports the content of the display interface into a pre-trained scene recognition model, and outputs a scene recognition result;
  • the electronic device determines whether the electronic device is in a preset scene according to the scene recognition result
  • the electronic device when the electronic device receives the instant messaging information, it first obtains the display interface content of the electronic device, and the instant messaging information includes caller information or short message information; then, the display interface content is imported into pre-trained scene recognition Model, output scene recognition results; secondly, determine whether the electronic device is in the preset scene according to the scene recognition result, the preset scene includes the game scene; again, when it is determined that the electronic device is in the preset scene, determine whether to start automatic according to instant messaging information Reply function; if yes, finally activate the automatic reply function, select the preset reply content to automatically reply.
  • the electronic device can recognize the current scene through the pre-trained scene recognition model when receiving the instant messaging information, and start the automatic reply function when the preset scene, so the electronic device can determine whether to automatically reply according to the current scene; according to the preset content Automatic reply effectively improves the reliability and intelligence of automatic reply, and enhances the timeliness of user information interaction.
  • FIG. 3 is a schematic flowchart of a method for automatically replying information provided by an embodiment of the present application. The method is applied to the electronic device.
  • Information automatic reply methods include:
  • the electronic device imports the content of the display interface into a pre-trained scene recognition model, and outputs a scene recognition result;
  • the electronic device determines whether the electronic device is in a preset scene according to the scene recognition result
  • the electronic device when the electronic device receives the instant messaging information, it first obtains the display interface content of the electronic device, and the instant messaging information includes caller information or short message information; then, the display interface content is imported into pre-trained scene recognition Model, output scene recognition results; secondly, determine whether the electronic device is in the preset scene according to the scene recognition result, the preset scene includes the game scene; again, when it is determined that the electronic device is in the preset scene, determine whether to start automatic according to instant messaging information Reply function; if yes, finally activate the automatic reply function, select the preset reply content to automatically reply.
  • the electronic device can recognize the current scene through the pre-trained scene recognition model when receiving the instant messaging information, and start the automatic reply function when the preset scene, so the electronic device can determine whether to automatically reply according to the current scene; according to the preset content Automatic reply effectively improves the reliability and intelligence of automatic reply, and enhances the timeliness of user information interaction.
  • FIG. 4 is a schematic structural diagram of an electronic device 400 provided by an embodiment of the present application.
  • the electronic device 400 includes an application processor 410, a memory 420, a communication interface 430, and one or more programs 421, wherein the one or more programs 421 are stored in the aforementioned memory 420 and are configured to be executed by the aforementioned application processor 410,
  • the one or more programs 421 include instructions for performing the following steps;
  • the instant messaging information When receiving instant messaging information, obtain the display interface content of the electronic device, the instant messaging information includes call information or short message;
  • the electronic device when the electronic device receives the instant messaging information, it first obtains the display interface content of the electronic device, and the instant messaging information includes caller information or short message information; then, the display interface content is imported into pre-trained scene recognition Model, output scene recognition results; secondly, determine whether the electronic device is in the preset scene according to the scene recognition result, the preset scene includes the game scene; again, when it is determined that the electronic device is in the preset scene, determine whether to start automatic according to instant messaging information Reply function; if yes, finally activate the automatic reply function, select the preset reply content to automatically reply.
  • the electronic device can recognize the current scene through the pre-trained scene recognition model when receiving the instant messaging information, and start the automatic reply function when the preset scene, so the electronic device can determine whether to automatically reply according to the current scene; according to the preset content Automatic reply effectively improves the reliability and intelligence of automatic reply, and enhances the timeliness of user information interaction.
  • the instant messaging information includes short message information; in terms of determining whether to start the automatic reply function according to the instant messaging information, the instructions in the program are specifically used to perform the following operations:
  • the instant messaging information is the short message, and it is determined whether to activate the automatic reply function according to the short message.
  • the instructions in the program are specifically used to perform the following operations: obtain information on the sending end of the short message information; The sender information and the preset first priority list to determine whether to enable the automatic reply function; or, to obtain the text information of the short message information; import the text information into a pre-trained semantic recognition model to identify the short message Semantics of information; determine whether to activate the automatic reply function according to the semantics.
  • the instant messaging information includes incoming call information; in terms of determining whether to activate the automatic reply function according to the instant messaging information, the instructions in the program are specifically used to perform the following operations:
  • the instant messaging information is the incoming call message, and it is determined whether to activate the automatic reply function according to the incoming call information.
  • the instructions in the program are specifically used to perform the following operations: obtain a caller ID of the caller information; according to the The caller ID and the preset second priority list determine whether to activate the automatic reply function.
  • the instructions in the program are specifically used to perform the following operations: using the caller ID To query the ID, query the second priority list to obtain the priority of the caller ID.
  • the second priority list includes the correspondence between the caller ID and the priority; when the caller ID is detected as When a priority is given, a prompt message is output to prompt the user to answer; when the caller ID is detected as the second priority, the automatic reply function is activated; when the caller ID is detected as the third priority, the automatic reply function is not activated .
  • the instructions in the program are specifically used to perform the following operations: perform automatic reply according to the preset reply content corresponding to the preset scene Or, obtain the historical reply content and automatically reply according to the historical reply content.
  • the instructions in the program are specifically used to perform the following operations: acquire historical instant messaging information and corresponding historical reply content; Generate sample data based on the historical instant messaging information and the historical reply content; use the sample data to train a preset reply content model to obtain a trained reply content model; import the instant messaging information into the trained Reply content model to obtain the predicted reply content corresponding to the instant messaging information; perform an automatic reply according to the predicted reply content.
  • the electronic device includes a hardware structure and/or a software module corresponding to each function.
  • the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is performed by hardware or computer software driven hardware depends on the specific application of the technical solution and design constraints. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered beyond the scope of this application.
  • the embodiments of the present application may divide the functional unit of the electronic device according to the above method example, for example, each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing unit.
  • the above integrated unit can be implemented in the form of hardware or software function unit. It should be noted that the division of the units in the embodiments of the present application is schematic, and is only a division of logical functions, and there may be other division manners in actual implementation.
  • FIG. 5 is a block diagram of the functional units of the application control device 500 involved in the embodiment of the present application.
  • the application control device 500 is applied to electronic equipment, including a processing unit 501 and a communication unit 502, where,
  • the processing unit 501 is configured to acquire display interface content of the electronic device when receiving instant communication information through the communication unit 502, the instant communication information includes caller information or short message; and the display interface content Import a pre-trained scene recognition model and output a scene recognition result; and determine whether the electronic device is in a preset scene based on the scene recognition result, the preset scene includes a game scene; and when it is determined that the electronic device is in a When the preset scene is described, determine whether to activate the automatic reply function according to the instant messaging information; if so, activate the automatic reply function and select a preset reply content to automatically reply.
  • the application control apparatus 500 may further include a storage unit 503 for storing program codes and data of electronic devices.
  • the processing unit 501 may be a processor
  • the communication unit 502 may be a touch screen or a transceiver
  • the storage unit 503 may be a memory.
  • the electronic device when the electronic device receives the instant messaging information, it first obtains the display interface content of the electronic device, and the instant messaging information includes caller information or short message information; then, the display interface content is imported into pre-trained scene recognition Model, output scene recognition results; secondly, determine whether the electronic device is in the preset scene according to the scene recognition result, the preset scene includes the game scene; again, when it is determined that the electronic device is in the preset scene, determine whether to start automatic according to instant messaging information Reply function; if yes, finally activate the automatic reply function, select the preset reply content to automatically reply.
  • the electronic device can recognize the current scene through the pre-trained scene recognition model when receiving the instant messaging information, and start the automatic reply function when the preset scene, so the electronic device can determine whether to automatically reply according to the current scene; according to the preset content Automatic reply effectively improves the reliability and intelligence of automatic reply, and enhances the timeliness of user information interaction.
  • the instant messaging information includes short message information; in terms of determining whether to start the automatic reply function according to the instant messaging information, the processing unit 501 is specifically configured to: when the instant messaging information is detected For the short message, determine whether to activate the automatic reply function according to the short message.
  • the processing unit 501 is specifically configured to: obtain information of the sending end of the short message information; according to the information of the sending end And a pre-set first priority list to determine whether to activate the automatic reply function; or, to obtain text information of the short message information; import the text information into a pre-trained semantic recognition model to identify the semantics of the short message information; Determine whether to activate the automatic reply function according to the semantics.
  • the instant messaging information includes incoming call information; in terms of determining whether to activate the automatic reply function according to the instant messaging information, the processing unit 501 is specifically configured to: when the instant messaging information is detected For the incoming call message, determine whether to activate the automatic reply function according to the incoming call information.
  • the processing unit 501 is specifically configured to: acquire a caller ID of the caller information; according to the caller ID and The set second priority list determines whether to activate the automatic reply function.
  • the processing unit 501 is specifically configured to: use the caller ID as a query ID, Query the second priority list to obtain the priority of the caller ID, the second priority list includes the correspondence between the caller ID and the priority; when the caller ID is detected as the first priority , Output prompt information to prompt the user to answer; when the caller ID is detected as the second priority, the automatic reply function is activated; when the caller ID is detected as the third priority, the automatic reply function is not activated.
  • the processing unit 501 is specifically configured to: automatically reply according to the preset reply content corresponding to the preset scene; or, obtain Historical reply content, according to the historical reply content to automatically reply.
  • the processing unit 501 is specifically configured to: acquire historical reply content; acquire historical instant messaging information and corresponding historical reply content Generate sample data based on the historical instant messaging information and the historical reply content; use the sample data to train a preset reply content model to obtain a trained reply content model; import the instant messaging information into the training Response content model to obtain the predicted reply content corresponding to the instant messaging information; and automatically reply based on the predicted reply content.
  • An embodiment of the present application further provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program causes the computer to perform part or all of the steps of any method described in the foregoing method embodiments ,
  • the above computer includes electronic equipment.
  • Embodiments of the present application also provide a computer program product, where the computer program product includes a non-transitory computer-readable storage medium that stores the computer program, and the computer program is operable to cause the computer to perform any of the methods described in the foregoing method embodiments Some or all steps of the method.
  • the computer program product may be a software installation package, and the computer includes an electronic device.
  • the disclosed device may be implemented in other ways.
  • the device embodiments described above are only schematic.
  • the division of the above-mentioned units is only a division of logical functions.
  • there may be other division methods for example, multiple units or components may be combined or integrated To another system, or some features can be ignored, or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or software function unit.
  • the above integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable memory.
  • the technical solution of the present application may essentially be a part that contributes to the prior art or all or part of the technical solution may be embodied in the form of a software product, and the computer software product is stored in a memory,
  • Several instructions are included to enable a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present application.
  • the aforementioned memory includes: U disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.
  • the program may be stored in a computer-readable memory, and the memory may include: a flash disk , Read-Only Memory (English: Read-Only Memory, abbreviation: ROM), Random Access Device (English: Random Access Memory, abbreviation: RAM), magnetic disk or optical disk, etc.
  • ROM Read-Only Memory
  • RAM Random Access Device
  • magnetic disk or optical disk etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Telephone Function (AREA)

Abstract

本申请实施例公开了一种信息自动回复的方法及相关装置，应用于电子设备，方法包括：当接收即时通讯信息时，获取电子设备的显示界面内容，即时通讯信息包括来电信息或短信消息；将显示界面内容导入预训练的场景识别模型，输出场景识别结果；根据场景识别结果确定电子设备是否处于预设场景，预设场景包括游戏场景；当电子设备处于预设场景时，根据即时通讯信息确定是否启动自动回复功能；若是，启动自动回复功能，选择预设回复内容进行自动回复。本申请实施例有利于提高自动回复的可靠性和智能性，且增强用户信息交互的及时性。

Description

信息自动回复的方法及相关装置 技术领域
本申请涉及通信技术领域，具体涉及一种信息自动回复的方法及相关装置。
背景技术
随着通信技术发展，用户的信息交互方式越来越多样化。最初，用户借助终端仅能进行简单的语音通话，后来发展到可以进行文字通信、视频通话等多种方式。虽然这些信息交互的方式提高了用户之间的信息传递。但人们对于信息交互的互动性和及时性要求也越来越高，但有时候用户无法及时回复信息。
发明内容
本申请实施例提供了一种信息自动回复的方法及相关装置，以期提高自动回复的可靠性和智能性，且增强了用户信息交互的及时性。
第一方面，本申请实施例提供一种信息自动回复的方法，应用于电子设备，所述方法包括：
当接收即时通讯信息时，获取所述电子设备的显示界面内容，所述即时通讯信息包括来电信息或短信消息；
将所述显示界面内容导入预训练的场景识别模型，输出场景识别结果；
根据所述场景识别结果确定所述电子设备是否处于预设场景，所述预设场景包括游戏场景；
当确定出所述电子设备处于所述预设场景时，根据所述即时通讯信息确定是否启动自动回复功能；
若是，启动所述自动回复功能，选择预设回复内容进行自动回复。
第二方面，本申请实施例提供一种应用控制装置，应用于电子设备，所述应用控制装置包括处理单元和通信单元，其中，
所述处理单元，用于当通过所述通信单元接收即时通讯信息时，获取所述电子设备的显示界面内容，所述即时通讯信息包括来电信息或短信消息；以及将所述显示界面内容导入预训练的场景识别模型，输出场景识别结果；以及根据所述场景识别结果确定所述电子设备是否处于预设场景，所述预设场景包括游戏场景；以及当确定出所述电子设备处于所述预设场景时，根据所述即时通讯信息确定是否启动自动回复功能；若是，启动所述自动回复功能，选择预设回复内容进行自动回复。
第三方面，本申请实施例提供一种电子设备，包括处理器、存储器、通信接口以及一个或多个程序，其中，上述一个或多个程序被存储在上述存储器中，并且被配置由上述处理器执行，上述程序包括用于执行本申请实施例第一方面任一方法中的步骤的指令。
第四方面，本申请实施例提供了一种计算机可读存储介质，其中，上述计算机可读存储介质存储用于电子数据交换的计算机程序，其中，上述计算机程序使得计算机执行如本申请实施例第一方面任一方法中所描述的部分或全部步骤。
第五方面，本申请实施例提供了一种计算机程序产品，其中，上述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，上述计算机程序可操作来使计算机执行如本申请实施例第一方面任一方法中所描述的部分或全部步骤。该计算机程序产品可以为一个软件安装包。
可以看出，本申请实施例中，电子设备接收到即时通讯信息时，首先获取电子设备的显示界面内容，即时通讯信息包括来电信息或短信信息；然后，将显示界面内容导入预训练的场景识别模型，输出场景识别结果；其次，根据场景识别结果确定电子设备是否处于预设场景，预设场景包括游戏场景；再次，当确定出电子设备处于预设场景时，根据即时通讯信息确定是否启动自动回复功能；若是，最后启动自动回复功能，选择预设回复内容进行自动回复。可见，电子设备能够在接收到即时通讯信息时通过预训练的场景识别模型识别当前场景，在预设场景时启动自动回复功能，因此电子设备可以根据当前场景确定是否自动回复；根据预设内容进行自动回复，有效提高自动回复的可靠性和智能性，且增强了用户信息交互的及时性。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的一种信息自动回复的方法的流程示意图；
图2是本申请实施例提供的另一种信息自动回复的方法的流程示意图；
图3是本申请实施例提供的另一种信息自动回复的方法的流程示意图；
图4是本申请实施例提供的一种电子设备的结构示意图；
图5是本申请实施例提供的一种信息自动回复装置的功能单元组成框图。
具体实施方式
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其他步骤或单元。
在本文中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本申请的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本文所描述的实施例可以与其它实施例相结合。
本申请实施例所涉及到的电子设备可以是具备信息交互功能的电子设备，该电子设备可以包括各种具有通信功能的手持设备、车载设备、可穿戴设备、计算设备或连接到无线调制解调器的其他处理设备，以及各种形式的用户设备(User Equipment，UE)，移动台(Mobile Station，MS)，终端设备(terminal device)等等。
下面对本申请实施例进行详细介绍。
请参阅图1，图1是本申请实施例提供了一种信息自动回复的方法的流程示意图，应用于电子设备，如图所示，本信息自动回复的方法包括：
S101，当电子设备接收即时通讯信息时，获取所述电子设备的显示界面内容；
其中，电子设备接收到即时通讯信息后，可以显示即时通讯显示界面，还可以通过提示栏提示，同时可以通过振动、灯光、铃声等方式提示用户。获取所述电子设备的显示界面内容包括获取显示界面截图、显示界面显示的文本内容。
S102，所述电子设备将所述显示界面内容导入预训练的场景识别模型，输出场景识别结果；
其中，预训练场景识别模型是将截取大量的电子设备显示界面截图或显示界面的文本内容作为样本数据，将所述样本数据导入神经训练网络进行训练，创建预设场景的场景识别模型。
具体实现中，获取当前场景的显示界面的显示界面截图或显示界面的文本内容，并导入预训练的场景识别模型，得到当前电子设备的显示界面内容的场景识别结果。
S103，所述电子设备根据所述场景识别结果确定所述电子设备是否处于预设场景；
其中，根据S102得到的当前显示界面的场景识别结果识别当前场景是否为预设场景。
S104，当确定出所述电子设备处于所述预设场景时，根据所述即时通讯信息确定是否启动自动回复功能；
其中，电子设备检测到处于预设场景时，启动电子设备的自动回复功能。具体的，电子设备的预设场景可以根据用户需要自定义设置。
S105，若是，所述电子设备启动所述自动回复功能，选择预设回复内容进行自动回复。
具体实现中，每当电子设备接收到即时通讯消息时，立即判断当前场景，当前场景为预设场景时，对该即时通讯消息进行分析，判断是否需要进行自动回复以及自动回复内容。
可以看出，本申请实施例中，电子设备接收到即时通讯信息时，首先获取电子设备的显示界面内容，即时通讯信息包括来电信息或短信信息；然后，将显示界面内容导入预训练的场景识别模型，输出场景识别结果；其次，根据场景识别结果确定电子设备是否处于预设场景，预设场景包括游戏场景；再次，当确定出电子设备处于预设场景时，根据即时通讯信息确定是否启动自动回复功能；若是，最后启动自动回复功能，选择预设回复内容进行自动回复。可见，电子设备能够在接收到即时通讯信息时通过预训练的场景识别模型识别当前场景，在预设场景时启动自动回复功能，因此电子设备可以根据当前场景确定是否自动回复；根据预设内容进行自动回复，有效提高自动回复的可靠性和智能性，且增强了用户信息交互的及时性。
在一个可能的示例中，所述确定所述电子设备是否处于预设场景，还包括：获取电子设备的内部参数；根据所述内部参数确定所述电子设备是否处于预设场景。
其中，内部参数包括CPU中与所述预设场景对应的负载数据量，GPU中与所述预设场景对应的负载数据量以及预设场景对应的模块参数。
可见，本示例中，电子设备能够基于电子设备内部参数确定电子设备的当前场景是否为预设场景，简化了检测场景的过程，提高场景检测的速度。
在一个可能的示例中，所述即时通讯信息包括短信信息；所述根据所述即时通讯信息确定是否启动自动回复功能，包括：当检测到所述即时通讯信息为所述短信消息，根据所述短信信息确定是否启动所述自动回复功能。
其中，短信信息包括发送端信息和文本信息，根据所述发送端信息和文本信息确定是否启动所述自动回复功能。
可见，本示例中，电子设备能够通过检测即时通讯信息，确定为短信信息时，判断所述短信信息是否能够启动自动回复功能，提高了信息交互的智能性性和效率。
在一个可能的示例中，所述根据所述短信信息确定是否启动所述自动回复功能，包括：获取所述短信信息的发送端信息；根据所述发送端信息和预设置的第一优先级列表确定是 否启动所述自动回复功能；或，获取所述短信信息的文本信息；将所述文本信息导入预训练的语义识别模型，识别所述短信信息的语义；根据所述语义确定是否启动所述自动回复功能。
其中，所述发送端信息包括发送端号码、以及发送端的标识，所述标识包括用户通过通讯录自定义设置的标识和从服务器获取的其他标识(推销、中国移动等)。
具体实现中，当所述即时通讯信息为短信信息时，电子设备可以通过获取所述短信消息的发送端信息，根据发送端信息的优先级确定是否开启自动回复功能。示例性地，如下表1给出的发送端信息以及对应的是否开启自动回复功能的第一优先级列表。
表1
优先级 发送端信息 是否启动自动回复功能
第一优先级 通讯录内需亲自回复的用户 否，输出提示信息
第二优先级 通讯录内需自动回复的用户 是
第三优先级 不在通讯录的用户以及黑名单用户 否
其中，通过神经网络训练获取并存储的短信信息的文本信息，创建语义识别模型；在接收到短信信息时，可以将所述短信信息导入语义识别模型，确定所述文本信息的雨一样，进而确定是否进行自动回复。例如，针对识别到语义为“重要”“会议”的短信信息，不启动自动回复，输出提示信息提示用户亲自回复；针对识别到的语义为“购物”的短信信息，不启动自动回复功能，对于其他语义，则启动自动回复功能进行自动回复。
具体实现中，语义识别可以在如表1所示的优先级判断之前进行；也可以先进行如表1所述的优先级判断，再进行语义识别，例如在如表1所述的第三优先级，对不在通讯录的用户发来的短信信息进行语义识别，判断是否进行自动回复；还可以将两个判断是否启动自动回复功能的方式分别设置。
可见，本示例中，由于电子设备能够基于短信信息发送端信息的优先级，以及通过语义识别短信信息文本，确定是否启动自动回复功能，能够针对发送端用户和语义进行自动回复，过滤了垃圾信息，提高了信息交互的及时性和效率。
在一个可能的示例中，所述即时通讯信息包括来电信息；所述根据所述即时通讯信息确定是否启动自动回复功能，包括：当检测到所述即时通讯信息为所述来电消息，根据所述来电信息确定是否启动所述自动回复功能。
其中，来电信息包括呼叫端信息，根据所述呼叫端信息确定是否启动所述自动回复功能。
可见，本示例中，电子设备能够通过检测即时通讯信息，确定为来电信息时，判断所述来电信息的呼叫端是否能够启动自动回复功能，提高了信息交互的智能性性和效率。
在一个可能的示例中，所述根据所述来电信息确定是否启动所述自动回复功能，包括：获取所述来电信息的来电标识；根据所述来电标识和预设置的第二优先级列表确定是否启动自动回复功能。
其中，来电信息的呼叫端的来电会携带呼叫端的来电信息，电子设备根据所述来电信息可以获取呼叫端的电话号码、呼叫端的来电标识。其中，该来电标识可以是呼叫端的电话号码，也可以是呼叫端被标注的标记。标记包括电子设备预存对应电话号码的来电用户名称、黑名单标记、以及从网络获取的其他标记(保险、推销等)。
可见，本示例中，电子设备能够通过来电信息中呼叫端的标识确定是否启动自动回复功能，能够选择呼叫端用户进行自动回复，提高了信息交互的及时性和智能性。
在一个可能的示例中，所述根据所述来电标识和预设置的第二优先级列表确定是否启动自动回复功能，包括：以所述来电标识为查询标识，查询所述第二优先级列表，获取所 述来电标识的优先级，所述第二优先级列表包括来电标识与优先级之间的对应关系；当检测到所述来电标识为第一优先级时，输出提示信息提示用户接听；当检测到所述来电标识为第二优先级时，启动自动回复功能；当检测到所述来电标识为第三优先级时，不启动自动回复功能。
具体实现中，当所述即时通讯信息为来电信息时，电子设备可以通过获取所述来电信息的来电标识，根据所述来电标识和第二优先级列表查询所述来电标识对应的优先级，根据来电标识的优先级确定是否启动自动回复功能。示例性地，如下表2给出的来电标识以及对应的是否启动自动回复功能的第二优先级列表。
表2
Figure PCTCN2018122148-appb-000001
例如，当所述来电标识为不在通讯录内的用户标识，通过第二优先级列表查询到其优先级为第二优先级，启动自动回复功能。
可见，本示例中，电子设备基于来电信息中呼叫端的来电标识的优先级确定是否启动自动回复功能，能够针对不同呼叫端用户执行对应的回复操作，提高了信息交互的及时性和智能性。
在一个可能的示例中，所述选择预设回复内容进行自动回复，包括：根据预设置的针对所述预设场景对应的回复内容进行自动回复；或者，获取历史回复内容，根据所述历史回复内容进行自动回复。
具体实现中，预设的回复内容可以是用户根据不同的预设场景预先设置的，例如用户可以根据游戏场景和视频通话设置不同的回复内容。预设的回复内容还可以是电子设备基于用户经常回复的内容进行设置的。电子设备在选择回复内容后，还可以储存该信息，以便用户在需要时进行选择、编辑、使用。
可见，本示例中，电子设备可以基于预设置的回复内容或用户的历史回复内容进行自动回复，实现了根据预设场景的针对性回复，提高了电子设备的智能性，提高了用户体验。
在一个可能的示例中，所述获取历史回复内容，根据所述历史回复进行自动回复，包括：获取历史即时通讯信息和对应的历史回复内容；根据所述历史即时通讯信息和所述历史回复内容生成样本数据；利用所述样本数据训练预设置的回复内容模型，得到训练后的回复内容模型；将所述即时通讯信息导入所述训练后的回复内容模型，得到所述即时通讯信息对应的预测回复内容；根据所述预测回复内容进行自动回复。
其中，预测回复内容为用户常用的回复内容。根据历史即时通讯信息和所述历史回复内容生成样本数据，包括根据历史短信信息的发送端信息、文本信息和对应的历史回复内容生成样本数据，根据历史来电信息的呼叫端信息和对应所述呼叫端的历史回复内容生成样本数据。
具体实现中，将所述即时通讯导入训练后的回复内容模型，得到用户常用的回复内容，根据所述预测回复内容进行自动回复。例如，针对发送端信息或呼叫端信息为“母亲”时，根据经常回复给“母亲”的信息内容(例如：妈妈，我现在在忙，待会给你回电话。)进行自动回复。针对短信信息的文本信息，可以针对文本信息的语义的历史回复内容进行回复，例如回复“好的”等。
可见，本示例中，电子设备可以基于用户经常回复的内容进行自动回复，辅助用户回 复信息，提高了电子设备的智能性提高了用户体验。
与上述图1所示的实施例一致的，请参阅图2，图2是本申请实施例提供的一种信息自动回复的方法的流程示意图，应用于电子设备，如图所示，本信息自动回复方法包括：
S201，当电子设备接收即时通讯信息时，获取所述电子设备的显示界面内容；
S202，所述电子设备将所述显示界面内容导入预训练的场景识别模型，输出场景识别结果；
S203，所述电子设备根据所述场景识别结果确定所述电子设备是否处于预设场景；
S204，当确定出所述电子设备处于所述预设场景时，检测到所述即时通讯信息为所述短信消息，根据所述短信信息确定是否启动所述自动回复功能。
可以看出，本申请实施例中，电子设备接收到即时通讯信息时，首先获取电子设备的显示界面内容，即时通讯信息包括来电信息或短信信息；然后，将显示界面内容导入预训练的场景识别模型，输出场景识别结果；其次，根据场景识别结果确定电子设备是否处于预设场景，预设场景包括游戏场景；再次，当确定出电子设备处于预设场景时，根据即时通讯信息确定是否启动自动回复功能；若是，最后启动自动回复功能，选择预设回复内容进行自动回复。可见，电子设备能够在接收到即时通讯信息时通过预训练的场景识别模型识别当前场景，在预设场景时启动自动回复功能，因此电子设备可以根据当前场景确定是否自动回复；根据预设内容进行自动回复，有效提高自动回复的可靠性和智能性，且增强了用户信息交互的及时性。
与上述图1所示的实施例一致的，请参阅图3，图3是本申请实施例提供的一种信息自动回复的方法的流程示意图，应用于所述电子设备，如图所示，本信息自动回复方法包括：
S301，当电子设备接收即时通讯信息时，获取所述电子设备的显示界面内容；
S302，所述电子设备将所述显示界面内容导入预训练的场景识别模型，输出场景识别结果；
S303，所述电子设备根据所述场景识别结果确定所述电子设备是否处于预设场景；
S304，当确定出所述电子设备处于所述预设场景时，检测到所述即时通讯信息为所述来电消息，获取所述来电信息的来电标识；
S305，当所述电子设备根据所述来电标识和预设置的第二优先级列表确定是否启动自动回复功能。
可以看出，本申请实施例中，电子设备接收到即时通讯信息时，首先获取电子设备的显示界面内容，即时通讯信息包括来电信息或短信信息；然后，将显示界面内容导入预训练的场景识别模型，输出场景识别结果；其次，根据场景识别结果确定电子设备是否处于预设场景，预设场景包括游戏场景；再次，当确定出电子设备处于预设场景时，根据即时通讯信息确定是否启动自动回复功能；若是，最后启动自动回复功能，选择预设回复内容进行自动回复。可见，电子设备能够在接收到即时通讯信息时通过预训练的场景识别模型识别当前场景，在预设场景时启动自动回复功能，因此电子设备可以根据当前场景确定是否自动回复；根据预设内容进行自动回复，有效提高自动回复的可靠性和智能性，且增强了用户信息交互的及时性。
与上述图1、图2、图3所示的实施例一致的，请参阅图4，图4是本申请实施例提供的一种电子设备400的结构示意图，如图所示，所述电子设备400包括应用处理器410、存储器420、通信接口430以及一个或多个程序421，其中，所述一个或多个程序421被存储在上述存储器420中，并且被配置由上述应用处理器410执行，所述一个或多个程序421包括用于执行以下步骤的指令；
当接收即时通讯信息时，获取所述电子设备的显示界面内容，所述即时通讯信息包括来电信息或短信消息；
将所述显示界面内容导入预训练的场景识别模型，输出场景识别结果；
根据所述场景识别结果确定所述电子设备是否处于预设场景，所述预设场景包括游戏场景；
当确定出所述电子设备处于所述预设场景时，根据所述即时通讯信息确定是否启动自动回复功能；
若是，启动所述自动回复功能，选择预设回复内容进行自动回复。
可以看出，本申请实施例中，电子设备接收到即时通讯信息时，首先获取电子设备的显示界面内容，即时通讯信息包括来电信息或短信信息；然后，将显示界面内容导入预训练的场景识别模型，输出场景识别结果；其次，根据场景识别结果确定电子设备是否处于预设场景，预设场景包括游戏场景；再次，当确定出电子设备处于预设场景时，根据即时通讯信息确定是否启动自动回复功能；若是，最后启动自动回复功能，选择预设回复内容进行自动回复。可见，电子设备能够在接收到即时通讯信息时通过预训练的场景识别模型识别当前场景，在预设场景时启动自动回复功能，因此电子设备可以根据当前场景确定是否自动回复；根据预设内容进行自动回复，有效提高自动回复的可靠性和智能性，且增强了用户信息交互的及时性。
在一个可能的示例中，所述即时通讯信息包括短信信息；在所述根据所述即时通讯信息确定是否启动自动回复功能方面，所述程序中的指令具体用于执行以下操作：当检测到所述即时通讯信息为所述短信消息，根据所述短信信息确定是否启动所述自动回复功能。
在一个可能的示例中，在所述根据所述短信信息确定是否启动所述自动回复功能方面，所述程序中的指令具体用于执行以下操作：获取所述短信信息的发送端信息；根据所述发送端信息和预设置的第一优先级列表确定是否启动所述自动回复功能；或，获取所述短信信息的文本信息；将所述文本信息导入预训练的语义识别模型，识别所述短信信息的语义；根据所述语义确定是否启动所述自动回复功能。
在一个可能的示例中，所述即时通讯信息包括来电信息；在所述根据所述即时通讯信息确定是否启动自动回复功能方面，所述程序中的指令具体用于执行以下操作：当检测到所述即时通讯信息为所述来电消息，根据所述来电信息确定是否启动所述自动回复功能。
在一个可能的示例中，在所述根据所述来电信息确定是否启动所述自动回复功能方面，所述程序中的指令具体用于执行以下操作：获取所述来电信息的来电标识；根据所述来电标识和预设置的第二优先级列表确定是否启动自动回复功能。
在一个可能的示例中，在所述根据所述来电标识和预设置的第二优先级列表确定是否启动自动回复功能方面，所述程序中的指令具体用于执行以下操作：以所述来电标识为查询标识，查询所述第二优先级列表，获取所述来电标识的优先级，所述第二优先级列表包括来电标识与优先级之间的对应关系；当检测到所述来电标识为第一优先级时，输出提示信息提示用户接听；当检测到所述来电标识为第二优先级时，启动自动回复功能；当检测到所述来电标识为第三优先级时，不启动自动回复功能。
在一个可能的示例中，在所述选择预设回复内容进行自动回复方面，所述程序中的指令具体用于执行以下操作：根据预设置的针对所述预设场景对应的回复内容进行自动回复；或者，获取历史回复内容，根据所述历史回复内容进行自动回复。
在一个可能的示例中，在所述获取历史回复内容，根据所述历史回复进行自动回复方面，所述程序中的指令具体用于执行以下操作：获取历史即时通讯信息和对应的历史回复内容；根据所述历史即时通讯信息和所述历史回复内容生成样本数据；利用所述样本数据 训练预设置的回复内容模型，得到训练后的回复内容模型；将所述即时通讯信息导入所述训练后的回复内容模型，得到所述即时通讯信息对应的预测回复内容；根据所述预测回复内容进行自动回复。
上述主要从方法侧执行过程的角度对本申请实施例的方案进行了介绍。可以理解的是，电子设备为了实现上述功能，其包含了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本文中所提供的实施例描述的各示例的单元及算法步骤，本申请能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
本申请实施例可以根据上述方法示例对电子设备进行功能单元的划分，例如，可以对应各个功能划分各个功能单元，也可以将两个或两个以上的功能集成在一个处理单元中。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。需要说明的是，本申请实施例中对单元的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
图5是本申请实施例中所涉及的应用控制装置500的功能单元组成框图。该应用控制装置500应用于电子设备，包括处理单元501和通信单元502，其中，
所述处理单元501，用于当通过所述通信单元502接收即时通讯信息时，获取所述电子设备的显示界面内容，所述即时通讯信息包括来电信息或短信消息；以及将所述显示界面内容导入预训练的场景识别模型，输出场景识别结果；以及根据所述场景识别结果确定所述电子设备是否处于预设场景，所述预设场景包括游戏场景；以及当确定出所述电子设备处于所述预设场景时，根据所述即时通讯信息确定是否启动自动回复功能；若是，启动所述自动回复功能，选择预设回复内容进行自动回复。
其中，所述应用控制装置500还可以包括存储单元503，用于存储电子设备的程序代码和数据。所述处理单元501可以是处理器，所述通信单元502可以是触控显示屏或者收发器，存储单元503可以是存储器。
可以看出，本申请实施例中，电子设备接收到即时通讯信息时，首先获取电子设备的显示界面内容，即时通讯信息包括来电信息或短信信息；然后，将显示界面内容导入预训练的场景识别模型，输出场景识别结果；其次，根据场景识别结果确定电子设备是否处于预设场景，预设场景包括游戏场景；再次，当确定出电子设备处于预设场景时，根据即时通讯信息确定是否启动自动回复功能；若是，最后启动自动回复功能，选择预设回复内容进行自动回复。可见，电子设备能够在接收到即时通讯信息时通过预训练的场景识别模型识别当前场景，在预设场景时启动自动回复功能，因此电子设备可以根据当前场景确定是否自动回复；根据预设内容进行自动回复，有效提高自动回复的可靠性和智能性，且增强了用户信息交互的及时性。
在一个可能的示例中，所述即时通讯信息包括短信信息；在所述根据所述即时通讯信息确定是否启动自动回复功能方面，所述处理单元501具体用于：当检测到所述即时通讯信息为所述短信消息，根据所述短信信息确定是否启动所述自动回复功能。
在一个可能的示例中，在所述根据所述短信信息确定是否启动所述自动回复功能方面，所述处理单元501具体用于：获取所述短信信息的发送端信息；根据所述发送端信息和预设置的第一优先级列表确定是否启动所述自动回复功能；或，获取所述短信信息的文本信息；将所述文本信息导入预训练的语义识别模型，识别所述短信信息的语义；根据所述语义确定是否启动所述自动回复功能。
在一个可能的示例中，所述即时通讯信息包括来电信息；在所述根据所述即时通讯信息确定是否启动自动回复功能方面，所述处理单元501具体用于：当检测到所述即时通讯信息为所述来电消息，根据所述来电信息确定是否启动所述自动回复功能。
在一个可能的示例中，在所述根据所述来电信息确定是否启动所述自动回复功能方面，所述处理单元501具体用于：获取所述来电信息的来电标识；根据所述来电标识和预设置的第二优先级列表确定是否启动自动回复功能。
在一个可能的示例中，在所述根据所述来电标识和预设置的第二优先级列表确定是否启动自动回复功能方面，所述处理单元501具体用于：以所述来电标识为查询标识，查询所述第二优先级列表，获取所述来电标识的优先级，所述第二优先级列表包括来电标识与优先级之间的对应关系；当检测到所述来电标识为第一优先级时，输出提示信息提示用户接听；当检测到所述来电标识为第二优先级时，启动自动回复功能；当检测到所述来电标识为第三优先级时，不启动自动回复功能。
在一个可能的示例中，在所述选择预设回复内容进行自动回复方面，所述处理单元501具体用于：根据预设置的针对所述预设场景对应的回复内容进行自动回复；或者，获取历史回复内容，根据所述历史回复内容进行自动回复。
在一个可能的示例中，在所述获取历史回复内容，根据所述历史回复进行自动回复方面，所述处理单元501具体用于：获取历史回复内容；获取历史即时通讯信息和对应的历史回复内容；根据所述历史即时通讯信息和所述历史回复内容生成样本数据；利用所述样本数据训练预设置的回复内容模型，得到训练后的回复内容模型；将所述即时通讯信息导入所述训练后的回复内容模型，得到所述即时通讯信息对应的预测回复内容；根据所述预测回复内容进行自动回复。
本申请实施例还提供一种计算机存储介质，其中，该计算机存储介质存储用于电子数据交换的计算机程序，该计算机程序使得计算机执行如上述方法实施例中记载的任一方法的部分或全部步骤，上述计算机包括电子设备。
本申请实施例还提供一种计算机程序产品，上述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，上述计算机程序可操作来使计算机执行如上述方法实施例中记载的任一方法的部分或全部步骤。该计算机程序产品可以为一个软件安装包，上述计算机包括电子设备。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本申请所必须的。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置，可通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如上述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性或其它的形式。
上述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络 单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
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。
上述集成的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器中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储器中，包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本申请各个实施例上述方法的全部或部分步骤。而前述的存储器包括：U盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储器中，存储器可以包括：闪存盘、只读存储器(英文：Read-Only Memory，简称：ROM)、随机存取器(英文：Random Access Memory，简称：RAM)、磁盘或光盘等。
以上对本申请实施例进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的一般技术人员，依据本申请的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本申请的限制。

Claims (11)

  1. 一种信息自动回复的方法，其特征在于，应用于电子设备，所述方法包括：
    当接收即时通讯信息时，获取所述电子设备的显示界面内容，所述即时通讯信息包括来电信息或短信消息；
    将所述显示界面内容导入预训练的场景识别模型，输出场景识别结果；
    根据所述场景识别结果确定所述电子设备是否处于预设场景；
    当确定出所述电子设备处于所述预设场景时，根据所述即时通讯信息确定是否启动自动回复功能；
    若是，启动所述自动回复功能，选择预设回复内容进行自动回复。
  2. 根据权利要求1所述的方法，其特征在于，所述即时通讯信息包括短信信息和来电信息；所述根据所述即时通讯信息确定是否启动自动回复功能，包括：
    当检测到所述即时通讯信息为所述短信消息，根据所述短信信息确定是否启动所述自动回复功能。
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述短信信息确定是否启动所述自动回复功能，包括：
    获取所述短信信息的发送端信息；
    根据所述发送端信息和预设置的第一优先级列表确定是否启动所述自动回复功能；或，
    获取所述短信信息的文本信息；
    将所述文本信息导入预训练的语义识别神经网络模型，识别所述短信信息的语义；
    根据所述语义确定是否启动所述自动回复功能。
  4. 根据权利要求1所述的方法，其特征在于，所述即时通讯信息包括短信信息和来电信息；所述根据所述即时通讯信息确定是否启动自动回复功能，包括：
    当检测到所述即时通讯信息为所述来电消息，根据所述来电信息确定是否启动所述自动回复功能。
  5. 根据权利要求4所述的方法，其特征在于，所述根据所述来电信息确定是否启动所述自动回复功能，包括：
    获取所述来电信息的来电标识；
    根据所述来电标识和预设置的第二优先级列表确定是否启动自动回复功能。
  6. 根据权利要求5所述的方法，其特征在于，所述根据所述来电标识和预设置的第二优先级列表确定是否启动自动回复功能，包括：
    以所述来电标识为查询标识，查询所述第二优先级列表，获取所述来电标识的优先级，所述第二优先级列表包括来电标识与优先级之间的对应关系；
    当检测到所述来电标识为第一优先级时，输出提示信息提示用户接听；
    当检测到所述来电标识为第二优先级时，启动自动回复功能；
    当检测到所述来电标识为第三优先级时，不启动自动回复功能。
  7. 根据权利要求1-6所述的方法，其特征在于，所述选择预设回复内容进行自动回复，包括：
    根据预设置的针对所述预设场景对应的回复内容进行自动回复；或者，
    获取历史回复内容，根据所述历史回复内容进行自动回复。
  8. 根据权利要求7所述的方法，其特征在于，所述获取历史回复内容，根据所述历史回复进行自动回复，包括：
    获取历史即时通讯信息和对应的历史回复内容；
    根据所述历史即时通讯信息和所述历史回复内容生成样本数据；
    利用所述样本数据训练预设置的回复内容模型，得到训练后的回复内容模型；
    将所述即时通讯信息导入所述训练后的回复内容模型，得到所述即时通讯信息对应的预测回复内容；
    根据所述预测回复内容进行自动回复。
  9. 一种应用控制装置，其特征在于，应用于电子设备，所述应用控制装置包括处理单元和通信单元，其中，
    所述处理单元，用于当通过所述通信单元接收即时通讯信息时，获取所述电子设备的显示界面内容，所述即时通讯信息包括来电信息或短信消息；以及将所述显示界面内容导入预训练的场景识别模型，输出场景识别结果；以及根据所述场景识别结果确定所述电子设备是否处于预设场景，所述预设场景包括游戏场景；以及当确定出所述电子设备处于所述预设场景时，根据所述即时通讯信息确定是否启动自动回复功能；若是，启动所述自动回复功能，选择预设回复内容进行自动回复。
  10. 一种电子设备，其特征在于，包括处理器、存储器、通信接口，以及一个或多个程序，所述一个或多个程序被存储在所述存储器中，并且被配置由所述处理器执行，所述程序包括用于执行如权利要求1-8任一项所述的方法中的步骤的指令。
  11. 一种计算机可读存储介质，其特征在于，存储用于电子数据交换的计算机程序，其中，所述计算机程序使得计算机执行如权利要求1-8任一项所述的方法。
PCT/CN2018/122148 2018-12-19 2018-12-19 信息自动回复的方法及相关装置 WO2020124453A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2018/122148 WO2020124453A1 (zh) 2018-12-19 2018-12-19 信息自动回复的方法及相关装置
CN201880098601.7A CN113039758B (zh) 2018-12-19 2018-12-19 信息自动回复的方法及相关装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/122148 WO2020124453A1 (zh) 2018-12-19 2018-12-19 信息自动回复的方法及相关装置

Publications (1)

Publication Number Publication Date
WO2020124453A1 true WO2020124453A1 (zh) 2020-06-25

Family

ID=71102561

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/122148 WO2020124453A1 (zh) 2018-12-19 2018-12-19 信息自动回复的方法及相关装置

Country Status (2)

Country Link
CN (1) CN113039758B (zh)
WO (1) WO2020124453A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111782061A (zh) * 2020-06-30 2020-10-16 北京百度网讯科技有限公司 用于推荐智能手表的输入方式的方法和装置

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113905001B (zh) * 2021-09-15 2023-06-06 深圳市六度人和科技有限公司 一种自动回复方法、装置、计算机设备及可读存储介质
CN114172856B (zh) * 2021-11-30 2023-05-30 中国平安财产保险股份有限公司 消息自动回复方法、装置、设备及存储介质
CN114356173A (zh) * 2021-12-06 2022-04-15 科大讯飞股份有限公司 消息回复方法及相关装置、电子设备和存储介质
CN116708647B (zh) * 2022-09-14 2024-04-19 荣耀终端有限公司 通知消息回复方法及电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101237641A (zh) * 2007-11-08 2008-08-06 宇龙计算机通信科技(深圳)有限公司 一种业务终端处理方法及通信装置
CN104125322A (zh) * 2013-04-24 2014-10-29 腾讯科技（深圳）有限公司 来电和短信控制方法及移动终端
US20150201313A1 (en) * 2014-01-10 2015-07-16 Onepin, Inc. Automated messaging
CN105204852A (zh) * 2015-09-14 2015-12-30 联想(北京)有限公司 信息处理方法及电子设备
CN106845549A (zh) * 2017-01-22 2017-06-13 珠海习悦信息技术有限公司 一种基于多任务学习的场景与目标识别的方法及装置

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101568083A (zh) * 2008-04-25 2009-10-28 中兴通讯股份有限公司 短消息自动回复方法以及移动终端
CN103780734A (zh) * 2012-10-23 2014-05-07 江南大学 一种手机自动应答的系统和方法
US20140372896A1 (en) * 2013-06-14 2014-12-18 Microsoft Corporation User-defined shortcuts for actions above the lock screen
CN105245724A (zh) * 2015-10-29 2016-01-13 努比亚技术有限公司 一种移动终端及其处理来电的方法
CN105959474A (zh) * 2016-05-04 2016-09-21 廖建强 一种短信编辑方法和终端
CN107018229A (zh) * 2016-05-26 2017-08-04 周兰兰 短信发送方法
CN106506782A (zh) * 2016-09-30 2017-03-15 北京珠穆朗玛移动通信有限公司 来电处理方法及移动终端
CN108803993B (zh) * 2018-06-13 2022-02-11 南昌黑鲨科技有限公司 应用程序的交互方法、智能终端及计算机可读存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101237641A (zh) * 2007-11-08 2008-08-06 宇龙计算机通信科技(深圳)有限公司 一种业务终端处理方法及通信装置
CN104125322A (zh) * 2013-04-24 2014-10-29 腾讯科技（深圳）有限公司 来电和短信控制方法及移动终端
US20150201313A1 (en) * 2014-01-10 2015-07-16 Onepin, Inc. Automated messaging
CN105204852A (zh) * 2015-09-14 2015-12-30 联想(北京)有限公司 信息处理方法及电子设备
CN106845549A (zh) * 2017-01-22 2017-06-13 珠海习悦信息技术有限公司 一种基于多任务学习的场景与目标识别的方法及装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111782061A (zh) * 2020-06-30 2020-10-16 北京百度网讯科技有限公司 用于推荐智能手表的输入方式的方法和装置
CN111782061B (zh) * 2020-06-30 2024-05-07 北京百度网讯科技有限公司 用于推荐智能手表的输入方式的方法和装置

Also Published As

Publication number Publication date
CN113039758A (zh) 2021-06-25
CN113039758B (zh) 2023-01-10

Similar Documents

Publication Publication Date Title
WO2020124453A1 (zh) 信息自动回复的方法及相关装置
US11451657B2 (en) Call method of mobile terminal, mobile terminal control method, and related device
CN110459221B (zh) 多设备协同语音交互的方法和装置
CN104135563B (zh) 一种通信处理方法和系统
WO2017185862A1 (zh) 识别恶意电话及建立识别模型的方法、装置、设备
CN104113626B (zh) 一种通信处理方法和系统
US9686506B2 (en) Method, apparatus, system, and storage medium for video call and video call control
JP2019533915A (ja) 着呼管理方法及び装置
US20170064084A1 (en) Method and Apparatus for Implementing Voice Mailbox
CN104935500B (zh) 基于网络通话的好友推荐方法和装置
CN110708430A (zh) 一种通话管理方法、通信终端及存储介质
CN106782604A (zh) 语音消息的处理方法、装置及其电子设备
CN110971984B (zh) 一种连麦方法、装置、系统、设备及存储介质
CN107613091A (zh) 一种建立通信的方法及终端
WO2018166367A1 (zh) 一种实时对话中的实时提醒方法、装置、存储介质及电子装置
CN104394169A (zh) 双方采用匿名方式发送私信方法及服务器
KR20220157472A (ko) 호출 설정들에 기반한 착신 호출들의 제어
US20140181687A1 (en) Method and Apparatus for Processing Contact Information
CN105491223B (zh) 一种信息处理方法、相关设备及系统
CN103813031A (zh) 呼叫处理方法及装置
WO2014101413A1 (zh) 联系人信息处理方法和装置
CN106209583A (zh) 一种消息输入方法、装置及其用户终端
CN103179550A (zh) 查询通话相对方信息的方法和装置
CN110650249A (zh) 通话接听方法、装置、计算机设备及存储介质
WO2020258553A1 (zh) 一种呼叫应答的方法、装置及终端

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: 18943397

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 03/11/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18943397

Country of ref document: EP

Kind code of ref document: A1