WO2020143411A1 - 一种针对视障群体的保险推荐方法和装置 - Google Patents

一种针对视障群体的保险推荐方法和装置 Download PDF

Info

Publication number
WO2020143411A1
WO2020143411A1 PCT/CN2019/125877 CN2019125877W WO2020143411A1 WO 2020143411 A1 WO2020143411 A1 WO 2020143411A1 CN 2019125877 W CN2019125877 W CN 2019125877W WO 2020143411 A1 WO2020143411 A1 WO 2020143411A1
Authority
WO
WIPO (PCT)
Prior art keywords
insurance
information
user
client
server
Prior art date
Application number
PCT/CN2019/125877
Other languages
English (en)
French (fr)
Inventor
唐林华
Original Assignee
阿里巴巴集团控股有限公司
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 阿里巴巴集团控股有限公司 filed Critical 阿里巴巴集团控股有限公司
Publication of WO2020143411A1 publication Critical patent/WO2020143411A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08—Insurance

Definitions

  • This specification relates to the field of Internet technology, and in particular, to an insurance recommendation method and device for visually impaired groups.
  • the general insurance recommendation system is not friendly to the visually impaired, and it is difficult for the visually impaired to interact through the insurance interface.
  • the embodiments of this specification provide an insurance recommendation method and device for visually impaired groups.
  • the technical solutions are as follows:
  • a method for recommending insurance for visually impaired groups includes:
  • the client receives the user's voice information
  • the client inputs the voice information into the insurance voice recognition model, which is an additional training based on local preloaded insurance information, which can be used for speech recognition in the vertical field of insurance, where the preloaded insurance information is from Insurance keyword information pre-loaded by the server to the client;
  • the client determines the user's demand information according to the output recognition result, and sends an insurance recommendation request containing the user's demand information to the server;
  • the client receives insurance recommendation information returned by the server according to the user's demand information, and outputs the insurance recommendation information.
  • an insurance recommendation method for visually impaired groups including:
  • the server receives the insurance recommendation request sent by the client and containing the user's demand information
  • the server side comprehensively determines insurance recommendation information for the user based on the user's demand information, the user's crowd characteristics information and historical recommendation information for the user;
  • the server returns the insurance recommendation information to the client.
  • an insurance recommendation device for visually impaired groups including:
  • Voice receiving module used to enable the client to receive the user's voice information
  • Voice recognition module used to enable the client to input the voice information into the insurance voice recognition model, the insurance voice recognition model is a model that can perform additional training based on local preloaded insurance information and can perform voice recognition in the vertical field of insurance, wherein , Pre-loaded insurance information is insurance keyword information pre-loaded from the server to the client;
  • Information sending module used to enable the client to determine the user's demand information based on the output recognition result, and send an insurance recommendation request containing the user's demand information to the server;
  • Result output module used to enable the client to receive the insurance recommendation information returned by the server according to the user's demand information, and output the insurance recommendation information.
  • an insurance recommendation device for visually impaired groups including:
  • Request receiving module used to enable the server to receive the insurance recommendation request sent by the client and containing user demand information
  • the result determination module used to enable the server to comprehensively determine insurance recommendation information for the user based on the user's demand information, the user's crowd characteristics information and the historical recommendation information for the user;
  • Result return module used to enable the server to return the insurance recommendation information to the client.
  • an insurance recommendation system for visually impaired groups includes: a client and a server;
  • the client is used to receive user's voice information
  • the server is used to receive an insurance recommendation request sent by a client and containing user demand information
  • the server is used for the server to comprehensively determine insurance recommendation information for the user based on the user's demand information, the user's crowd characteristics information and historical recommendation information for the user;
  • the server is used for the server to return the insurance recommendation information to the client;
  • the client is used to receive insurance recommendation information returned by the server according to the user's demand information, and output the insurance recommendation information.
  • a computer device including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements a An insurance recommendation method for visually impaired groups, the method includes:
  • the client receives the user's voice information
  • the client inputs the voice information into the insurance voice recognition model, which is an additional training based on local preloaded insurance information and can be used for speech recognition in the vertical field of insurance, where the preloaded insurance information is from Insurance keyword information pre-loaded by the server to the client;
  • the client determines the user's demand information according to the output recognition result, and sends an insurance recommendation request containing the user's demand information to the server;
  • the client receives insurance recommendation information returned by the server according to the user's demand information, and outputs the insurance recommendation information.
  • a computer device including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the program
  • An insurance recommendation method for visually impaired groups includes:
  • the server receives the insurance recommendation request sent by the client and containing the user's demand information
  • the server side comprehensively determines insurance recommendation information for the user according to the user's demand information, the user's crowd characteristics information and historical recommendation information for the user;
  • the server returns the insurance recommendation information to the client.
  • the technical solutions provided in the embodiments of this specification provide an insurance recommendation method for visually impaired groups. Users can input their needs into the client through voice, so that the client can quickly and accurately recognize the voice in the vertical field of insurance Enter the information to determine the user's demand information. The client preloads the pre-integrated insurance keyword information into the local area and performs additional training on the speech recognition model. Finally, it will perform voice broadcast and interface presentation based on the recommendation results returned by the demand information.
  • the technical solutions provided in this manual enable visually impaired people to interact with the insurance recommendation system without barriers, improving the experience of the visually impaired group.
  • any one of the embodiments of this specification does not need to achieve all the above-mentioned effects.
  • FIG. 1 is a flowchart of an insurance recommendation method for visually impaired groups shown in an exemplary embodiment of this specification
  • FIG. 3 is a schematic diagram of an insurance recommendation device for a visually impaired group shown in an exemplary embodiment of this specification;
  • FIG. 4 is another schematic diagram of an insurance recommendation device for visually impaired groups shown in an exemplary embodiment of this specification
  • FIG. 5 is a schematic diagram of an insurance recommendation system for visually impaired groups shown in an exemplary embodiment of this specification
  • FIG. 6 is a schematic structural diagram of a computer device shown in an exemplary embodiment of this specification.
  • first, second, third, etc. may be used to describe various information in this specification, the information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other.
  • first information may also be referred to as second information, and similarly, the second information may also be referred to as first information.
  • word “if” as used herein can be interpreted as "when” or “when” or “in response to a determination”.
  • the existing insurance recommendation system is not friendly to the visually impaired.
  • the visually impaired group refers to people whose visual function is impaired to a certain extent. Patients with low visual acuity or impaired visual field cannot reach normal vision. It is difficult for visually impaired groups to interact with the current insurance interface and obtain insurance recommendations. At present, there is a lack of an insurance recommendation method and device for the visually impaired.
  • the embodiments of the present specification provide an insurance recommendation method for the visually impaired group and an insurance recommendation device for the visually impaired group for performing the method.
  • the following describes insurance for the visually impaired group according to this embodiment
  • the recommendation method is described in detail. Referring to FIG. 1, it is an insurance recommendation method applied to the client. The method may include the following steps:
  • the client receives the user's voice information
  • Voice information is the information that the user directly speaks to the client. For the visually impaired, voice is a more convenient way of interaction. Therefore, the insurance recommendation method needs to be applied to clients (such as mobile phones) with voice receiving devices ).
  • the client inputs the voice information into an insurance voice recognition model
  • the insurance voice recognition model is a model that can perform additional training based on local preloaded insurance information and can perform speech recognition in the vertical field of insurance.
  • the preloaded insurance information is insurance keyword information preloaded from the server to the client.
  • the current client voice recognition method may not be able to recognize the voice information. Therefore, it is necessary to preload insurance information locally on the client, and use these preloaded insurance data to perform additional training on the existing voice model.
  • the preloaded insurance information is insurance keyword information that is integrated according to the historical query data of the entire user, insurance product data, and insurance knowledge data, and meets the high-frequency query conditions.
  • the preloaded insurance information can be continuously increased, decreased, and corrected with the increase of insurance products and the expansion of insurance knowledge. For example, when a new insurance product is added to the insurance product database of the server, the insurance name of the insurance product, insurance purchase Conditions, specific insurance regulations, etc. may all become content that users want to know. When the insurance database is updated, the key information needs to be extracted from the updated content, and the server will push the key information as new preloaded information to the client at a predetermined time point, and then the client can be trained by training the speech recognition model Identify the relevant voice information of the new product.
  • the client determines the user's demand information according to the output recognition result, and sends an insurance recommendation request containing the user's demand information to the server;
  • the insurance recommendation request should also include the user's personal information, so that the background recommendation system can make more changes for the user based on the user's age, gender, occupation, interest, and past records in the insurance field. Accurate recommendation.
  • the client receives insurance recommendation information returned by the server according to the user's demand information, and outputs the insurance recommendation information.
  • the client receives insurance recommendation information returned by the server according to the user's demand information, and outputs the insurance recommendation information through voice broadcast and/or interface presentation.
  • the insurance recommendation information may be insurance knowledge information and/or insurance product information
  • this manual can also provide an interactive interface for visually impaired persons.
  • the interactive interface is a customized interface specially designed for visually impaired persons.
  • the number and size of interface buttons should be strictly controlled, focusing on simplicity and practicality. For example, only Back, previous, next, condition screening, product index, detailed reading and other few buttons; and adjust the resolution of the buttons, the layout between the buttons, make the various function buttons of the interface neat and clear, easy to remember, and make the visually impaired Even if the interface details cannot be seen clearly, the interface can be operated by memorizing the interface button layout.
  • the method may include the following steps:
  • the server receives an insurance recommendation request containing user demand information sent by the client;
  • S202 The server side comprehensively determines insurance recommendation information for the user according to the user's demand information, the user's crowd characteristics information, and historical recommendation information for the user;
  • the user's crowd feature information is calculated and matched by the user's personal information, and the overall insurance recommendation of the user's crowd feature can be used as reference information for recommending the user.
  • the server returns the insurance recommendation information to the client.
  • the embodiment of the present specification also provides an insurance recommendation method device for the visually impaired group, which is applied to the client.
  • the device may include: a voice receiving module 310 and a voice recognition module 320.
  • Voice recognition module 320 used to enable the client to input the voice information into the insurance voice recognition model, the insurance voice recognition model is a model that can carry out additional training based on local preloaded insurance information and can perform voice recognition in the vertical field of insurance, Among them, the preloaded insurance information is insurance keyword information preloaded from the server to the client;
  • Information sending module 330 used to enable the client to determine the user's demand information based on the output recognition result, and send an insurance recommendation request containing the user's demand information to the server;
  • Result output module 340 used to enable the client to receive insurance recommendation information returned by the server according to the user's demand information, and output the insurance recommendation information.
  • the embodiments of the present specification also provide an insurance recommendation method device for visually impaired groups, which is applied to the client.
  • the device may include: a request receiving module 410 and a result determination module 420 and the result return module 430.
  • Request receiving module 410 used to enable the server to receive the insurance recommendation request sent by the client and containing user demand information;
  • the result determination module 420 used to enable the server to comprehensively determine insurance recommendation information for the user based on the user's demand information, the user's crowd characteristics information and historical recommendation information for the user;
  • Result return module 430 used to enable the server to return the insurance recommendation information to the client.
  • this specification also provides an insurance recommendation system for visually impaired groups.
  • the system includes: a client and a server;
  • the client is used to receive user's voice information
  • the client is used to input the voice information into an insurance voice recognition model
  • the insurance voice recognition model is a model that can perform additional training based on local pre-loaded insurance information and can perform voice recognition in the vertical field of insurance, where Loading insurance information is insurance keyword information preloaded from the server to the client;
  • the client is used to determine the user's demand information according to the output recognition result, and send an insurance recommendation request containing the user's demand information to the server;
  • the server is used to receive an insurance recommendation request sent by a client and containing user demand information
  • the server is used for the server to comprehensively determine insurance recommendation information for the user based on the user's demand information, the user's crowd characteristics information and historical recommendation information for the user;
  • the server is used for the server to return the insurance recommendation information to the client;
  • the client is used to receive insurance recommendation information returned by the server according to the user's demand information, and output the insurance recommendation information.
  • the schematic diagram of the system including the client and the server can refer to FIG. 5, the client receives the information input by the user through the sound source and the interface operation, and the interactive adapter recognizes the input information to determine the user's demand information, and the The demand information is converted into a recommendation request and sent to the server's back-end recommendation system.
  • the back-end recommendation system calculates the recommendation information and returns it to the client.
  • Embodiments of the present specification also provide a computer device, which includes at least a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the program to implement the foregoing for the visually impaired group
  • the insurance recommendation method is applied to the client.
  • the method at least includes:
  • the client receives the user's voice information
  • the client inputs the voice information into the insurance voice recognition model, which is an additional training based on local preloaded insurance information and can be used for speech recognition in the vertical field of insurance, where the preloaded insurance information is from Insurance keyword information pre-loaded by the server to the client;
  • the client determines the user's demand information according to the output recognition result, and sends an insurance recommendation request containing the user's demand information to the server;
  • the client receives insurance recommendation information returned by the server according to the user's demand information, and outputs the insurance recommendation information.
  • An embodiment of the present specification also provides another computer device, which includes at least a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the program to implement the foregoing for the visually impaired group
  • the recommended method of insurance is applied to the server.
  • the method at least includes:
  • the server receives the insurance recommendation request sent by the client and containing the user's demand information
  • the server side comprehensively determines insurance recommendation information for the user according to the user's demand information, the user's crowd characteristics information and historical recommendation information for the user;
  • the server returns the insurance recommendation information to the client.
  • FIG. 6 shows a schematic diagram of a more specific hardware structure of a computing device provided by an embodiment of the present specification.
  • the device may include: a processor 1110, a memory 1120, an input/output interface 1130, a communication interface 1140, and a bus 1150.
  • the processor 1110, the memory 1120, the input/output interface 1130 and the communication interface 1140 realize the communication connection among the devices through the bus 1150.
  • the processor 1110 may be implemented by a general-purpose CPU (Central Processing Unit, central processing unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, etc. Programs to implement the technical solutions provided by the embodiments of this specification.
  • the memory 1120 may be implemented in the form of ROM (Read Only Memory, Read Only Memory), RAM (Random Access Memory, Random Access Memory), static storage device, dynamic storage device, etc.
  • the memory 1120 may store an operating system and other application programs.
  • related program codes are stored in the memory 1120 and called and executed by the processor 1110.
  • the input/output interface 1130 is used to connect an input/output module to realize information input and output.
  • the input/output/module can be configured as a component in the device (not shown in the figure), or can be externally connected to the device to provide corresponding functions.
  • the input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc.
  • the output device may include a display, a speaker, a vibrator, an indicator light, and the like.
  • the communication interface 1140 is used to connect a communication module (not shown in the figure) to implement communication interaction between the device and other devices.
  • the communication module can realize communication through a wired method (such as USB, network cable, etc.), and can also realize communication through a wireless method (such as mobile network, WIFI, Bluetooth, etc.).
  • the bus 1150 includes a path for transferring information between various components of the device (for example, the processor 1110, the memory 1120, the input/output interface 1130, and the communication interface 1140).
  • the device may also include necessary for normal operation Other components.
  • the above-mentioned device may also include only the components necessary for implementing the solutions of the embodiments of the present specification, rather than including all the components shown in the figures.
  • Embodiments of the present specification also provide a computer-readable storage medium on which a computer program is stored.
  • the program is executed by a processor, the aforementioned insurance recommendation method for a visually impaired group is implemented and applied to a client.
  • the method at least includes :
  • the client inputs the voice information into the insurance voice recognition model, which is an additional training based on local preloaded insurance information and can be used for speech recognition in the vertical field of insurance, where the preloaded insurance information is from Insurance keyword information pre-loaded by the server to the client;
  • the client determines the user's demand information according to the output recognition result, and sends an insurance recommendation request containing the user's demand information to the server;
  • the client receives insurance recommendation information returned by the server according to the user's demand information, and outputs the insurance recommendation information.
  • An embodiment of the present specification also provides another computer-readable storage medium on which a computer program is stored, which when executed by a processor implements the aforementioned insurance recommendation method for the visually impaired group, which is applied to the server, the method at least include:
  • the server receives the insurance recommendation request sent by the client and containing the user's demand information
  • the server side comprehensively determines insurance recommendation information for the user according to the user's demand information, the user's crowd characteristics information and historical recommendation information for the user;
  • the server returns the insurance recommendation information to the client.
  • Computer-readable media including permanent and non-permanent, removable and non-removable media, can store information by any method or technology.
  • the information may be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, Magnetic tape cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices.
  • computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.
  • the relevant part can be referred to the description of the method embodiment.
  • the device embodiments described above are only schematic, wherein 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, may be located One place, or can be distributed to multiple network elements. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solution in this specification. Those of ordinary skill in the art can understand and implement without paying creative labor.
  • the system, device, module or unit explained in the above embodiments may be specifically implemented by a computer chip or entity, or by a product with a certain function.
  • a typical implementation device is a computer, and the specific form of the computer may be a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email sending and receiving device, and a game control Desk, tablet computer, wearable device, or any combination of these devices.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Engineering & Computer Science (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Technology Law (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

一种针对视障群体的保险推荐方法和装置。用户可通过语音将自己的需求信息输入客户端，为使客户端能迅速准确地识别保险垂直领域的语音输入信息，进而确定用户的需求信息，客户端将预先整合的保险关键词信息预加载到本地并对语音识别模型进行附加训练，最后将根据需求信息返回的推荐结果进行语音播报和界面呈现。该技术方案使视障人士无障碍地与保险推荐系统进行交互，改善了视障群体的使用体验度。

Description

一种针对视障群体的保险推荐方法和装置 技术领域
本说明书涉及互联网技术领域，尤其涉及一种针对视障群体的保险推荐方法和装置。
背景技术
目前，随着人们生活水平的提高，越来越多的人开始重视保障类服务产品，而购买保险是首选的保障类服务之一。随着保险业务市场的活跃，出现了很多线上保险推荐系统，用户可以使用互联网提出需求，并被推荐相应的保险产品。
但一般保险推荐系统对视障人士不友好，视障人士难以通过保险界面进行交互。目前缺乏一种针对视障群体的保险推荐方法和装置。
发明内容
针对上述技术问题，本说明书实施例提供一种针对视障群体的保险推荐方法和装置，技术方案如下：
根据本说明书实施例的第一方面，提供一种针对视障群体的保险推荐方法，该方法包括：
客户端接收用户的语音信息；
客户端将所述语音信息输入保险语音识别模型，所述保险语音识别模型为根据本地预加载保险信息进行附加训练的、可针对保险垂直领域进行语音识别的模型，其中，预加载保险信息为从服务器预先加载到客户端的保险关键词信息；
客户端根据输出的识别结果确定所述用户的需求信息，并将包含所述用户需求信息的保险推荐请求发送给服务端；
客户端接收服务端根据所述用户的需求信息返回的保险推荐信息，并输出所述保险推荐信息。
根据本说明书实施例的第二方面，还提供一种针对视障群体的保险推荐方法，该方法包括：
服务端接收客户端发送的包含用户需求信息的保险推荐请求；
服务端根据所述用户的需求信息，所述用户的人群特征信息与对所述用户的历史推荐信息综合确定对所述用户的保险推荐信息；
服务端将所述保险推荐信息返回给客户端。
根据本说明书实施例的第三方面，提供一种针对视障群体的保险推荐装置，该装置包括：
语音接收模块：用于使客户端接收用户的语音信息；
语音识别模块：用于使客户端将所述语音信息输入保险语音识别模型，所述保险语音识别模型为根据本地预加载保险信息进行附加训练的、可针对保险垂直领域进行语音识别的模型，其中，预加载保险信息为从服务器预先加载到客户端的保险关键词信息；
信息发送模块：用于使客户端根据输出的识别结果确定所述用户的需求信息，并将包含所述用户需求信息的保险推荐请求发送给服务端；
结果输出模块：用于使客户端接收服务端根据所述用户的需求信息返回的保险推荐信息，并输出所述保险推荐信息。
根据本说明书实施例的第四方面，还提供一种针对视障群体的保险推荐装置，该装置包括：
请求接收模块：用于使服务端接收客户端发送的包含用户需求信息的保险推荐请求；
结果确定模块：用于使服务端根据所述用户的需求信息，所述用户的人群特征信息与对所述用户的历史推荐信息综合确定对所述用户的保险推荐信息；
结果返回模块：用于使服务端将所述保险推荐信息返回给客户端。
根据本说明书实施例的第五方面，提供一种针对视障群体的保险推荐系统，该系统包括：客户端、服务端；
所述客户端，用于接收用户的语音信息；
所述客户端，用于将所述语音信息输入保险语音识别模型，所述保险语音识别模型为根据本地预加载保险信息进行附加训练的、可针对保险垂直领域进行语音识别的模型，其中，预加载保险信息为从服务器预先加载到客户端的保险关键词信息；
所述客户端，用于根据输出的识别结果确定所述用户的需求信息，并将包含所述用户需求信息的保险推荐请求发送给服务端；
所述服务端，用于接收客户端发送的包含用户需求信息的保险推荐请求；
所述服务端，用于服务端根据所述用户的需求信息，所述用户的人群特征信息与对所述用户的历史推荐信息综合确定对所述用户的保险推荐信息；
所述服务端，用于服务端将所述保险推荐信息返回给客户端；
所述客户端，用于接收服务端根据所述用户的需求信息返回的保险推荐信息，并输出所述保险推荐信息。
根据本说明书实施例的第六方面，提供一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，所述处理器执行所述程序时实现一种针对视障群体的保险推荐方法，所述方法包括：
客户端接收用户的语音信息；
客户端将所述语音信息输入保险语音识别模型，所述保险语音识别模型为根据本地预加载保险信息进行附加训练的、可针对保险垂直领域进行语音识别的模型，其中，预加载保险信息为从服务器预先加载到客户端的保险关键词信息；
客户端根据输出的识别结果确定所述用户的需求信息，并将包含所述用户需求信息的保险推荐请求发送给服务端；
客户端接收服务端根据所述用户的需求信息返回的保险推荐信息，并输出所述保险推荐信息。
根据本说明书实施例的第七方面，还提供一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，所述处理器执行所述程序时实现一种针对视障群体的保险推荐方法，所述方法包括：
服务端接收客户端发送的包含用户需求信息的保险推荐请求；
服务端根据所述用户的需求信息，所述用户的人群特征信息与对所述用户的历史推荐信息综合确定对所述用户的保险推荐信息；
服务端将所述保险推荐信息返回给客户端。
本说明书实施例所提供的技术方案，提供了一种针对视障群体的保险推荐方法， 用户可通过语音将自己的需求信息输入客户端，为使客户端能迅速准确地识别保险垂直领域的语音输入信息，进而确定用户的需求信息，客户端将预先整合的保险关键词信息预加载到本地并对语音识别模型进行附加训练，最后将根据需求信息返回的推荐结果进行语音播报和界面呈现。本说明书提供的技术方案使视障人士无障碍地与保险推荐系统进行交互，改善了视障群体的使用体验度。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本说明书实施例。
此外，本说明书实施例中的任一实施例并不需要达到上述的全部效果。
附图说明
为了更清楚地说明本说明书实施例中的技术方案，下面将对实施例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说明书实施例中记载的一些实施例，对于本领域普通技术人员来讲，还可以根据这些附图获得其他的附图。
图1是本说明书一示例性实施例示出的针对视障群体的保险推荐方法的一种流程图；
图2是本说明书一示例性实施例示出的针对视障群体的保险推荐方法的另一种流程图；
图3是本说明书一示例性实施例示出的针对视障群体的保险推荐装置的一种示意图；
图4是本说明书一示例性实施例示出的针对视障群体的保险推荐装置的另一种示意图；
图5是本说明书一示例性实施例示出的针对视障群体的保险推荐系统的一种示意图；
图6是本说明书一示例性实施例示出的一种计算机设备的结构示意图。
具体实施方式
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实 施例中所描述的实施方式并不代表与本说明书相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本说明书的一些方面相一致的装置和方法的例子。
在本说明书使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本说明书。在本说明书和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。还应当理解，本文中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。
应当理解，尽管在本说明书可能采用术语第一、第二、第三等来描述各种信息，但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区分开。例如，在不脱离本说明书范围的情况下，第一信息也可以被称为第二信息，类似地，第二信息也可以被称为第一信息。取决于语境，如在此所使用的词语“如果”可以被解释成为“在……时”或“当……时”或“响应于确定”。
目前，随着人们生活水平的提高，越来越多的人开始重视保障类服务产品，而购买保险是首选的保障类服务之一。随着保险业务市场的活跃，出现了很多线上保险推荐系统，用户可以使用互联网提出需求，并被推荐相应的保险产品。
但现有保险推荐系统对视障人士不友好，视障群体指的是视觉功能受到一定程度的损害，患者因为视觉敏锐度低或视野受损，以致无法达到正常视力的人群。视障群体难与目前的保险界面进行交互，进而获取保险推荐方案。目前缺乏一种针对视障群体的保险推荐方法和装置。
针对以上问题，本说明书实施例提供一种针对视障群体的保险推荐方法，以及一种用于执行该方法的针对视障群体的保险推荐装置，下面对本实施例涉及的针对视障群体的保险推荐方法进行详细说明，参见图1所示，为应用于客户端的保险推荐方法，该方法可以包括以下步骤：
S101，客户端接收用户的语音信息；
语音信息即用户端直接对客户端说出的信息，对于视障人士来说，语音是一种更加方便的交互方式，因此该保险推荐方法需要应用于具备语音接收装置的客户端(如手机等)。
S102，客户端将所述语音信息输入保险语音识别模型；
其中，该保险语音识别模型为根据本地预加载保险信息进行附加训练的、可针对保险垂直领域进行语音识别的模型，预加载保险信息为从服务器预先加载到客户端的保 险关键词信息。
为了使客户端更加快捷准确地识别用户输入的语音信息的具体含义，需要对现有的语音识别模型进行额外的训练，使其能够针对保险垂直领域做出更好的识别。
举例说明，当用户对客户端说出一种保险产品名称时，目前的客户端语音识别方式很可能无法识别该语音信息。因此，需要在客户端本地预加载保险信息，使用这些预加载保险数据对现有的语音模型进行额外训练。
具体地，预加载保险信息为根据整体用户的历史查询数据，保险产品数据和保险知识数据进行整合的，符合高频查询条件的保险关键词信息。
预加载保险信息可以随着保险产品的增加和保险知识的扩充不断增减和更正，例如，当服务器的保险产品数据库中增加了一种新的保险产品时，该保险产品的保险名称，保险购买条件，保险具体条例等均可能成为给用户想要了解的内容。当保险数据库出现更新时，需要从更新内容中提取出关键信息，并由服务器在预定的时间点将该关键信息作为新的预加载信息推送到客户端，进而通过训练语音识别模型使得客户端能识别该新产品的相关语音信息。
S103，客户端根据输出的识别结果确定所述用户的需求信息，并将包含所述用户需求信息的保险推荐请求发送给服务端；
保险推荐请求中除了包含用户输入的需求信息外，还应包含用户的个人信息，以便后台推荐系统能够根据用户的年龄、性别、职业、兴趣以及在保险领域的过往记录等信息为用户做出更加精准的推荐。
进一步地，在用户授权的情况下，还可将用户在其他领域的信息加入保险推荐请求中，从而做出更加个性化的保险推荐，例如：通过账单发现，用户有较频繁的长途出行(旅行/出差)行为，则可对应为用户推荐相关的出行保险。
S104，客户端接收服务端根据所述用户的需求信息返回的保险推荐信息，并输出所述保险推荐信息。
客户端接收服务端根据所述用户的需求信息返回的保险推荐信息，并通过语音播报和/或界面呈现的方式输出所述保险推荐信息。该保险推荐信息可以是保险知识信息和/或保险产品信息
进一步地，本说明书还可提供一种针对视障人士交互界面，该交互界面为专为视 障人士设计的定制化界面，应严格控制住界面按钮的数量和大小，专注简洁和实用，例如只有返回、上一个、下一个、条件筛选、产品指数、详情阅读等少数几个按钮；并调整按钮的分辨率，按钮间的布局，使界面的各个功能按钮整齐明了，便于记忆，使视障人士即使无法看清界面细节，也可通过记忆界面按钮布局的方式操作界面。
当用户对该界面上的按钮进行点击等操作后，交互界面将针对该用户操作呈现出对应的内容。进一步地，当客户端界面按钮接收到点击等操作后，通过语音播放该按钮名称的方式，使视障人士确定点击的按钮未出现错误。且在界面呈现内容的同时，使用语音播放呈现出的内容，以帮助视障人士了解内容。
具体地，可为普通交互界面和视障人士交互界面设计切换接口。当用户为视障人士，需要使用定制化界面时。可通过输入语音，如对客户端说出“简洁界面”，或操作切换按钮等方式。使客户端界面在普通交互界面和视障人士交互界面之间相互切换。
参见图2所示，为应用于服务端的保险推荐方法，该方法可以包括以下步骤：
S201，服务端接收客户端发送的包含用户需求信息的保险推荐请求；
S202，服务端根据所述用户的需求信息，所述用户的人群特征信息与对所述用户的历史推荐信息综合确定对所述用户的保险推荐信息；
其中，用户地人群特征信息是通过用户的个人信息计算匹配得出的，用户所属的人群特征的整体保险推荐情况可以作为对该用户进行推荐的参考信息。
S203，服务端将所述保险推荐信息返回给客户端。
相应于上述方法实施例，本说明书实施例还提供一种针对视障群体的保险推荐方法装置，应用于客户端，参见图3所示，所述装置可以包括：语音接收模块310、语音识别模块320、信息发送模块330和结果输出模块340。
语音接收模块310：用于使客户端接收用户的语音信息；
语音识别模块320：用于使客户端将所述语音信息输入保险语音识别模型，所述保险语音识别模型为根据本地预加载保险信息进行附加训练的、可针对保险垂直领域进行语音识别的模型，其中，预加载保险信息为从服务器预先加载到客户端的保险关键词信息；
信息发送模块330：用于使客户端根据输出的识别结果确定所述用户的需求信息，并将包含所述用户需求信息的保险推荐请求发送给服务端；
结果输出模块340：用于使客户端接收服务端根据所述用户的需求信息返回的保险推荐信息，并输出所述保险推荐信息。
相应于上述方法实施例，本说明书实施例还提供一种针对视障群体的保险推荐方法装置，应用于客户端，参见图4所示，所述装置可以包括：请求接收模块410、结果确定模块420和结果返回模块430。
请求接收模块410：用于使服务端接收客户端发送的包含用户需求信息的保险推荐请求；
结果确定模块420：用于使服务端根据所述用户的需求信息，所述用户的人群特征信息与对所述用户的历史推荐信息综合确定对所述用户的保险推荐信息；
结果返回模块430：用于使服务端将所述保险推荐信息返回给客户端。
参见图5，本说明书还提供一种针对视障群体的保险推荐系统，所述系统包括：客户端、服务端；
所述客户端，用于接收用户的语音信息；
所述客户端，用于将所述语音信息输入保险语音识别模型，所述保险语音识别模型为根据本地预加载保险信息进行附加训练的、可针对保险垂直领域进行语音识别的模型，其中，预加载保险信息为从服务器预先加载到客户端的保险关键词信息；
所述客户端，用于根据输出的识别结果确定所述用户的需求信息，并将包含所述用户需求信息的保险推荐请求发送给服务端；
所述服务端，用于接收客户端发送的包含用户需求信息的保险推荐请求；
所述服务端，用于服务端根据所述用户的需求信息，所述用户的人群特征信息与对所述用户的历史推荐信息综合确定对所述用户的保险推荐信息；
所述服务端，用于服务端将所述保险推荐信息返回给客户端；
所述客户端，用于接收服务端根据所述用户的需求信息返回的保险推荐信息，并输出所述保险推荐信息。
其中，该包含客户端与服务端的系统的示意图可参考图5，客户端接收用户通过声源和界面操作输入的信息，由交互适配器对输入的信息进行识别进而确定用户的需求信息，并将该需求信息转换成推荐请求发送给服务器的后端推荐系统，由后端推荐系统计算后确定推荐信息并返回给客户端。
本说明书实施例还提供一种计算机设备，其至少包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，处理器执行所述程序时实现前述针对视障群体的保险推荐方法，应用于客户端，所述方法至少包括：
客户端接收用户的语音信息；
客户端将所述语音信息输入保险语音识别模型，所述保险语音识别模型为根据本地预加载保险信息进行附加训练的、可针对保险垂直领域进行语音识别的模型，其中，预加载保险信息为从服务器预先加载到客户端的保险关键词信息；
客户端根据输出的识别结果确定所述用户的需求信息，并将包含所述用户需求信息的保险推荐请求发送给服务端；
客户端接收服务端根据所述用户的需求信息返回的保险推荐信息，并输出所述保险推荐信息。
本说明书实施例还提供另一种计算机设备，其至少包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，处理器执行所述程序时实现前述针对视障群体的保险推荐方法，应用于服务端，所述方法至少包括：
服务端接收客户端发送的包含用户需求信息的保险推荐请求；
服务端根据所述用户的需求信息，所述用户的人群特征信息与对所述用户的历史推荐信息综合确定对所述用户的保险推荐信息；
服务端将所述保险推荐信息返回给客户端。
图6示出了本说明书实施例所提供的一种更为具体的计算设备硬件结构示意图，该设备可以包括：处理器1110、存储器1120、输入/输出接口1130、通信接口1140和总线1150。其中处理器1110、存储器1120、输入/输出接口1130和通信接口1140通过总线1150实现彼此之间在设备内部的通信连接。
处理器1110可以采用通用的CPU(Central Processing Unit，中央处理器)、微处理器、应用专用集成电路(Application Specific Integrated Circuit，ASIC)、或者一个或多个集成电路等方式实现，用于执行相关程序，以实现本说明书实施例所提供的技术方案。
存储器1120可以采用ROM(Read Only Memory，只读存储器)、RAM(Random Access Memory，随机存取存储器)、静态存储设备、动态存储设备等形式实现。存储 器1120可以存储操作系统和其他应用程序，在通过软件或者固件来实现本说明书实施例所提供的技术方案时，相关的程序代码保存在存储器1120中，并由处理器1110来调用执行。
输入/输出接口1130用于连接输入/输出模块，以实现信息输入及输出。输入输出/模块可以作为组件配置在设备中(图中未示出)，也可以外接于设备以提供相应功能。其中输入设备可以包括键盘、鼠标、触摸屏、麦克风、各类传感器等，输出设备可以包括显示器、扬声器、振动器、指示灯等。
通信接口1140用于连接通信模块(图中未示出)，以实现本设备与其他设备的通信交互。其中通信模块可以通过有线方式(例如USB、网线等)实现通信，也可以通过无线方式(例如移动网络、WIFI、蓝牙等)实现通信。
总线1150包括一通路，在设备的各个组件(例如处理器1110、存储器1120、输入/输出接口1130和通信接口1140)之间传输信息。
需要说明的是，尽管上述设备仅示出了处理器1110、存储器1120、输入/输出接口1130、通信接口1140以及总线1150，但是在具体实施过程中，该设备还可以包括实现正常运行所必需的其他组件。此外，本领域的技术人员可以理解的是，上述设备中也可以仅包含实现本说明书实施例方案所必需的组件，而不必包含图中所示的全部组件。
本说明书实施例还提供一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现前述的针对视障群体的保险推荐方法，应用于客户端，所述方法至少包括：
客户端接收用户的语音信息；
客户端将所述语音信息输入保险语音识别模型，所述保险语音识别模型为根据本地预加载保险信息进行附加训练的、可针对保险垂直领域进行语音识别的模型，其中，预加载保险信息为从服务器预先加载到客户端的保险关键词信息；
客户端根据输出的识别结果确定所述用户的需求信息，并将包含所述用户需求信息的保险推荐请求发送给服务端；
客户端接收服务端根据所述用户的需求信息返回的保险推荐信息，并输出所述保险推荐信息。
本说明书实施例还提供另一种计算机可读存储介质，其上存储有计算机程序，该 程序被处理器执行时实现前述的针对视障群体的保险推荐方法，应用于服务端，所述方法至少包括：
服务端接收客户端发送的包含用户需求信息的保险推荐请求；
服务端根据所述用户的需求信息，所述用户的人群特征信息与对所述用户的历史推荐信息综合确定对所述用户的保险推荐信息；
服务端将所述保险推荐信息返回给客户端。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
对于装置实施例而言，由于其基本对应于方法实施例，所以相关之处参见方法实施例的部分说明即可。以上所描述的装置实施例仅仅是示意性的，其中所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模块来实现本说明书方案的目的。本领域普通技术人员在不付出创造性劳动的情况下，即可以理解并实施。
通过以上的实施方式的描述可知，本领域的技术人员可以清楚地了解到本说明书实施例可借助软件加必需的通用硬件平台的方式来实现。基于这样的理解，本说明书实施例的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在存储介质中，如ROM/RAM、磁碟、光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本说明书实施例各个实施例或者实施例的某些部分所述的方法。
上述实施例阐明的系统、装置、模块或单元，具体可以由计算机芯片或实体实现，或者由具有某种功能的产品来实现。一种典型的实现设备为计算机，计算机的具体形式 可以是个人计算机、膝上型计算机、蜂窝电话、相机电话、智能电话、个人数字助理、媒体播放器、导航设备、电子邮件收发设备、游戏控制台、平板计算机、可穿戴设备或者这些设备中的任意几种设备的组合。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于装置实施例而言，由于其基本相似于方法实施例，所以描述得比较简单，相关之处参见方法实施例的部分说明即可。以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，在实施本说明书实施例方案时可以把各模块的功能在同一个或多个软件和/或硬件中实现。也可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性劳动的情况下，即可以理解并实施。
以上所述仅是本说明书实施例的具体实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本说明书实施例原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视为本说明书实施例的保护范围。

Claims (15)

  1. 一种针对视障群体的保险推荐方法，所述方法包括：
    客户端接收用户的语音信息；
    客户端将所述语音信息输入保险语音识别模型，所述保险语音识别模型为根据本地预加载保险信息进行附加训练的、可针对保险垂直领域进行语音识别的模型，其中，预加载保险信息为从服务器预先加载到客户端的保险关键词信息；
    客户端根据输出的识别结果确定所述用户的需求信息，并将包含所述用户需求信息的保险推荐请求发送给服务端；
    客户端接收服务端根据所述用户的需求信息返回的保险推荐信息，并输出所述保险推荐信息。
  2. 如权利要求1所述的方法，所述客户端接收服务端根据所述用户的需求信息返回的保险推荐信息，并输出所述保险推荐信息，包括：
    客户端接收服务端根据所述用户的需求信息返回的保险推荐信息，并通过语音播报和/或界面呈现的方式输出所述保险推荐信息。
  3. 如权利要求1所述的方法，所述保险推荐信息包括保险知识信息和/或保险产品信息。
  4. 如权利要求1所述的方法，所述预加载保险信息根据服务端保险数据库的更新而更新。
  5. 如权利要求1所述的方法，所述预加载保险信息为根据整体用户的历史查询数据，保险产品数据和保险知识数据进行整合的，符合高频查询条件的保险关键词信息。
  6. 一种针对视障群体的保险推荐方法，所述方法包括：
    服务端接收客户端发送的包含用户需求信息的保险推荐请求；
    服务端根据所述用户的需求信息，所述用户的人群特征信息与对所述用户的历史推荐信息综合确定对所述用户的保险推荐信息；
    服务端将所述保险推荐信息返回给客户端。
  7. 一种针对视障群体的保险推荐装置，所述装置包括：
    语音接收模块：用于使客户端接收用户的语音信息；
    语音识别模块：用于使客户端将所述语音信息输入保险语音识别模型，所述保险语音识别模型为根据本地预加载保险信息进行附加训练的、可针对保险垂直领域进行语音识别的模型，其中，预加载保险信息为从服务器预先加载到客户端的保险关键词信息；
    信息发送模块：用于使客户端根据输出的识别结果确定所述用户的需求信息，并将 包含所述用户需求信息的保险推荐请求发送给服务端；
    结果输出模块：用于使客户端接收服务端根据所述用户的需求信息返回的保险推荐信息，并输出所述保险推荐信息。
  8. 如权利要求7所述的装置，所述结果输出模块，具体用于：
    使客户端接收服务端根据所述用户的需求信息返回的保险推荐信息，并通过语音播报和/或界面呈现的方式输出所述保险推荐信息。
  9. 如权利要求7所述的装置，所述保险推荐信息包括保险知识信息和/或保险产品信息。
  10. 如权利要求7所述的装置，所述预加载保险信息根据服务端保险数据库的更新而更新。
  11. 如权利要求7所述的装置，所述预加载保险信息为服务器根据整体用户的历史查询数据，保险产品数据和保险知识数据进行整合的，符合高频查询条件的保险关键词信息。
  12. 一种针对视障群体的保险推荐装置，所述装置包括：
    请求接收模块：用于使服务端接收客户端发送的包含用户需求信息的保险推荐请求；
    结果确定模块：用于使服务端根据所述用户的需求信息，所述用户的人群特征信息与对所述用户的历史推荐信息综合确定对所述用户的保险推荐信息；
    结果返回模块：用于使服务端将所述保险推荐信息返回给客户端。
  13. 一种针对视障群体的保险推荐系统，所述系统包括：客户端、服务端；
    所述客户端，用于接收用户的语音信息；
    所述客户端，用于将所述语音信息输入保险语音识别模型，所述保险语音识别模型为根据本地预加载保险信息进行附加训练的、可针对保险垂直领域进行语音识别的模型，其中，预加载保险信息为从服务器预先加载到客户端的保险关键词信息；
    所述客户端，用于根据输出的识别结果确定所述用户的需求信息，并将包含所述用户需求信息的保险推荐请求发送给服务端；
    所述服务端，用于接收客户端发送的包含用户需求信息的保险推荐请求；
    所述服务端，用于服务端根据所述用户的需求信息，所述用户的人群特征信息与对所述用户的历史推荐信息综合确定对所述用户的保险推荐信息；
    所述服务端，用于服务端将所述保险推荐信息返回给客户端；
    所述客户端，用于接收服务端根据所述用户的需求信息返回的保险推荐信息，并输出所述保险推荐信息。
  14. 一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，所述处理器执行所述程序时实现如权利要求1所述的方法。
  15. 一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，所述处理器执行所述程序时实现如权利要求6所述的方法。
PCT/CN2019/125877 2019-01-11 2019-12-17 一种针对视障群体的保险推荐方法和装置 WO2020143411A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910027469.7 2019-01-11
CN201910027469.7A CN110033381A (zh) 2019-01-11 2019-01-11 一种针对视障群体的保险推荐方法和装置

Publications (1)

Publication Number Publication Date
WO2020143411A1 true WO2020143411A1 (zh) 2020-07-16

Family

ID=67235547

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/125877 WO2020143411A1 (zh) 2019-01-11 2019-12-17 一种针对视障群体的保险推荐方法和装置

Country Status (3)

Country Link
CN (1) CN110033381A (zh)
TW (1) TW202032482A (zh)
WO (1) WO2020143411A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110033381A (zh) * 2019-01-11 2019-07-19 阿里巴巴集团控股有限公司 一种针对视障群体的保险推荐方法和装置
CN113190323A (zh) * 2021-06-02 2021-07-30 口碑(上海)信息技术有限公司 一种信息播放方法、装置、电子设备及存储介质
CN114997948A (zh) * 2022-05-24 2022-09-02 拉扎斯网络科技（上海）有限公司 信息展示方法、装置、设备和计算机可读存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110225046A1 (en) * 1998-12-03 2011-09-15 Prime Research Alliance E., Inc. Method and System for Presenting Targeted Advertisements
CN107330719A (zh) * 2017-06-09 2017-11-07 上海新概念保险经纪有限公司 一种保险产品推荐方法及系统
CN108629697A (zh) * 2018-03-30 2018-10-09 平安科技（深圳）有限公司 保险产品配置方法、装置、计算机设备及存储介质
CN108765043A (zh) * 2018-03-28 2018-11-06 平安科技（深圳）有限公司 产品推荐方法、电子设备及存储介质
CN108921708A (zh) * 2018-06-05 2018-11-30 沈烨 保险服务优化方法、装置和存储介质
CN109146610A (zh) * 2018-07-16 2019-01-04 众安在线财产保险股份有限公司 一种智能保险推荐方法、装置及智能保险机器人设备
CN110033381A (zh) * 2019-01-11 2019-07-19 阿里巴巴集团控股有限公司 一种针对视障群体的保险推荐方法和装置

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108364160A (zh) * 2017-01-26 2018-08-03 樊少霞 一种智能人事工作处理方法及装置
CN107705793B (zh) * 2017-09-22 2023-01-31 百度在线网络技术（北京）有限公司 基于声纹识别的信息推送方法、系统及其设备
CN108335177A (zh) * 2018-03-09 2018-07-27 京东方科技集团股份有限公司 购物推荐方法、用户端、服务端、设备和存储介质

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110225046A1 (en) * 1998-12-03 2011-09-15 Prime Research Alliance E., Inc. Method and System for Presenting Targeted Advertisements
CN107330719A (zh) * 2017-06-09 2017-11-07 上海新概念保险经纪有限公司 一种保险产品推荐方法及系统
CN108765043A (zh) * 2018-03-28 2018-11-06 平安科技（深圳）有限公司 产品推荐方法、电子设备及存储介质
CN108629697A (zh) * 2018-03-30 2018-10-09 平安科技（深圳）有限公司 保险产品配置方法、装置、计算机设备及存储介质
CN108921708A (zh) * 2018-06-05 2018-11-30 沈烨 保险服务优化方法、装置和存储介质
CN109146610A (zh) * 2018-07-16 2019-01-04 众安在线财产保险股份有限公司 一种智能保险推荐方法、装置及智能保险机器人设备
CN110033381A (zh) * 2019-01-11 2019-07-19 阿里巴巴集团控股有限公司 一种针对视障群体的保险推荐方法和装置

Also Published As

Publication number Publication date
CN110033381A (zh) 2019-07-19
TW202032482A (zh) 2020-09-01

Similar Documents

Publication Publication Date Title
US11960694B2 (en) Method of using a virtual assistant
DK180653B1 (en) Digital assistant hardware abstraction
US11638059B2 (en) Content playback on multiple devices
CN109844855B (zh) 任务的多重计算代理执行
JP7121052B2 (ja) イメージデータに少なくとも部分的に基づく、アクションを実行するためのエージェントの決定
CN105701254B (zh) 一种信息处理方法和装置、一种用于信息处理的装置
US10360265B1 (en) Using a voice communications device to answer unstructured questions
US9026941B1 (en) Suggesting activities
US20180349755A1 (en) Modeling an action completion conversation using a knowledge graph
US9058563B1 (en) Suggesting activities
US20220237486A1 (en) Suggesting activities
WO2020143411A1 (zh) 一种针对视障群体的保险推荐方法和装置
KR20170078768A (ko) 예측성 타이핑을 위한 문맥 관련 온톨로지의 동적 로딩
WO2013059906A1 (en) Electronic device management using interdomain profile-based inferences
CN112292675A (zh) 利用实体和任务的显著性排名辅助计算机解译自然语言输入
JP2023520483A (ja) 検索コンテンツ表示方法、装置、電子機器及び記憶媒体
JP2022547598A (ja) コンテキストデータを使用した対話処理のための技術
US20090150341A1 (en) Generation of alternative phrasings for short descriptions
US20240146776A1 (en) Digital assistant hardware abstraction
US20150278907A1 (en) User Inactivity Aware Recommendation System
US11005993B2 (en) Computational assistant extension device
US20190163450A1 (en) Systems and methds of developments, testing, and distribution of applications in a computer network
US11416686B2 (en) Natural language processing based on user context
JP6509364B2 (ja) 検索サービス提供装置、方法及びコンピュータプログラム
CN113781084A (zh) 一种调查问卷展示方法和装置

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: 19908856

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19908856

Country of ref document: EP

Kind code of ref document: A1