A prompt generation method, device and electronic device

Abstract

The present disclosure provides a prompt generation method, device and electronic device, which relates to the field of data processing technology and is used to solve the problem in the prior art that when an electronic device generates a prompt, the generated prompt is often inaccurate and cannot accurately reflect the user's true intention, resulting in a poor user experience. The method includes: receiving a first message sent by an electronic device; when the first message includes operation information, determining a user portrait based on identification information in the first message; determining an actual prompt based on the user portrait and actual location information and actual time information in the first message; and sending a first display message carrying the actual prompt to the electronic device.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a prompt generation method, device and electronic device. Background Art

[0002] Currently, electronic devices generate prompts based on historical voice data input by users, thereby facilitating users to select the functions they need, such as watching movies, watching TV, searching for songs, checking the weather, etc.

[0003] However, when the prompt is generated in the above manner, the generated prompt is often inaccurate and cannot accurately reflect the user's true intention, resulting in a poor user experience. Summary of the invention

[0004] In order to solve the above technical problems, the present disclosure provides a prompt generation method, device and electronic device, which are used to solve the problem in the prior art that when electronic devices generate prompts, the generated prompts are often inaccurate and cannot accurately reflect the user's true intentions, resulting in a poor user experience.

[0005] The technical solution of the present disclosure is as follows:

[0006] In a first aspect, the present disclosure provides a prompt generation method, comprising: receiving first information sent by an electronic device; when the first information includes operation information, determining a user portrait based on identification information in the first information; wherein the operation information includes voice information lacking entity words, and any one of the indication information used to indicate that the electronic device has received the first operation, and the user portrait is generated based on historical voice data, historical operation data, and historical question and answer data corresponding to the identification information; determining an actual prompt based on the user portrait and actual location information and actual time information in the first information; and sending first display information carrying the actual prompt to the electronic device; wherein the first display information is used to instruct the electronic device to display the actual prompt.

[0007] In some feasible examples, the identification information includes a user account, and the prompt generation method provided by the present disclosure also includes: receiving a voice message sent by an electronic device; wherein the voice message includes first voiceprint data; determining whether the second voiceprint data bound to the user account matches the first voiceprint data based on the first voiceprint data; and sending a first indication message to the electronic device when the second voiceprint data matches the first voiceprint data; wherein the first indication message is used to instruct the electronic device to continue logging into the user account.

[0008] In some feasible examples, the prompt generation method provided by the present disclosure also includes: when the second voiceprint data does not match the first voiceprint data, sending a second indication information to the electronic device; wherein the second indication information is used to instruct the electronic device to prompt the user to enter theoretical login information of the user account; receiving actual login information sent by the electronic device; when the theoretical login information is the same as the actual login information, sending the first indication information to the electronic device; when the theoretical login information is different from the actual login information, sending a third indication information to the electronic device; wherein the third indication information is used to instruct the electronic device to prompt the user to perform a target operation, and the target operation includes any one of switching accounts or registering accounts.

[0009] In some feasible examples, before receiving the first information sent by the electronic device, the prompt generation method provided by the present disclosure also includes: obtaining historical voice data, historical operation data and historical question and answer data corresponding to the identification information; analyzing the historical voice data, historical operation data and historical question and answer data to determine at least one portrait data; wherein the portrait data includes the user label weight of each content category in each time period under the historical location information; historical voice data, historical operation data and historical question and answer data; generating a user portrait based on the portrait data.

[0010] In some feasible examples, an actual prompt is determined based on the user portrait and the actual location information and actual time information in the first information, including: determining portrait data corresponding to the actual location information and the actual time information based on the user portrait, the actual location information and the actual time information; determining a content category in which the user tag weight is greater than or equal to a preset weight based on the portrait data corresponding to the actual location information and the actual time information; determining an actual prompt based on the content category in which the user tag weight is greater than or equal to the preset weight; wherein one content category corresponds to at least one actual prompt.

[0011] In some feasible examples, the first information also includes query information, and one content category corresponds to at least one theoretical entity word; the actual prompt is determined based on the user portrait and the actual location information and actual time information in the first information, including: determining the theoretical prompt corresponding to each actual entity word contained in the query information based on a pre-configured knowledge graph and the query information; determining the portrait data corresponding to the actual location information and the actual time information based on the user portrait, the actual location information and the actual time information; determining the content category whose user tag weight is greater than or equal to the preset weight based on the portrait data corresponding to the actual location information and the actual time information; matching the theoretical entity words with the actual entity words of the content category whose user tag weight is greater than or equal to the preset weight; and when the theoretical entity words match the actual entity words, determining the theoretical prompt corresponding to the actual entity word as the actual prompt.

[0012] In some implementable examples, an actual prompt corresponds to an actual control; after sending first display information carrying the actual prompt to the electronic device, the prompt generation method provided by the present disclosure also includes: receiving second information sent by the electronic device; wherein the second information is used to indicate that a selection operation has been performed on a target prompt, and the target prompt is any one of the actual prompts; based on the target prompt, generating display data corresponding to the target prompt; sending second display information carrying the display data to the electronic device; wherein the second display information is used to instruct the electronic device to display the display data.

[0013] In a second aspect, the present disclosure provides a prompt generation method, comprising: sending first information to a server in response to a first operation; wherein the first information includes identification information, actual location information, actual time information and operation information, and the operation information includes voice information lacking entity words, and any one of indication information for indicating that the electronic device has received the first operation; receiving first display information carrying the actual prompt sent by the server; wherein the first display information is used to instruct the electronic device to display the actual prompt, and the actual prompt is determined according to a user portrait, actual location information and actual time information, and the user portrait is generated based on historical voice data, historical operation data and historical question and answer data corresponding to the identification information; and displaying the actual prompt according to the first display information.

[0014] In some feasible examples, the identification information includes a user account, and the prompt generation method provided by the present disclosure also includes: sending a voice message to a server; wherein the voice message includes first voiceprint data; receiving first indication information sent by the server; wherein the first indication information is used to instruct the electronic device to continue to log in to the user account.

[0015] In some feasible examples, the prompt generation method provided by the present disclosure also includes: receiving a second indication information sent by the server; wherein the second indication information is used to instruct the electronic device to prompt the user to enter theoretical login information of the user account; in response to the second operation, sending actual login information to the server; receiving a third indication information sent by the server; wherein the third indication information is used to instruct the electronic device to prompt the user to perform a target operation, and the target operation includes any one of switching accounts or registering accounts.

[0016] In some implementable examples, an actual prompt corresponds to an actual control; after receiving first display information carrying the actual prompt sent by the server, the prompt generation method provided by the present disclosure also includes: sending second information to the server in response to a third operation of the user; wherein the second information is used to indicate that a selection operation has been performed on a target prompt, and the target prompt is any one of the actual prompts; receiving second display information carrying display data sent by the server; wherein the display data is generated based on the target prompt, and the second display information is used to instruct the electronic device to display the display data; and displaying the display data based on the second display information.

[0017] In a third aspect, the present disclosure provides a prompt generating device, comprising: a receiving unit, for receiving first information sent by an electronic device; a processing unit, for determining a user portrait according to identification information in the first information acquired by the acquiring unit when the first information acquired by the acquiring unit includes operation information; wherein the operation information includes voice information lacking entity words, and any one of the indication information for indicating that the electronic device has received the first operation, and the user portrait is generated based on historical voice data, historical operation data, and historical question and answer data corresponding to the identification information; the processing unit is also used to determine the actual prompt based on the user portrait and the actual location information and actual time information in the first information received by the receiving unit; the processing unit is also used to control the sending unit to send first display information carrying the actual prompt to the electronic device; wherein the first display information is used to instruct the electronic device to display the actual prompt.

[0018] In some feasible examples, the identification information includes a user account, and the receiving unit is further used to receive voice information sent by the electronic device; wherein the voice information includes first voiceprint data; the processing unit is further used to determine whether the second voiceprint data bound to the user account matches the first voiceprint data received by the receiving unit based on the first voiceprint data received by the receiving unit; the processing unit is further used to control the sending unit to send a first indication information to the electronic device when the second voiceprint data matches the first voiceprint data received by the receiving unit; wherein the first indication information is used to instruct the electronic device to continue logging into the user account.

[0019] In some implementable examples, the processing unit is further used to control the sending unit to send a second indication message to the electronic device when the second voiceprint data does not match the first voiceprint data received by the receiving unit; wherein the second indication message is used to instruct the electronic device to prompt the user to enter theoretical login information of the user account; the receiving unit is further used to receive actual login information sent by the electronic device; the processing unit is further used to control the sending unit to send the first indication message to the electronic device when the theoretical login information is the same as the actual login information received by the receiving unit; the processing unit is further used to control the sending unit to send a third indication message to the electronic device when the theoretical login information is different from the actual login information received by the receiving unit; wherein the third indication message is used to instruct the electronic device to prompt the user to perform a target operation, and the target operation includes any one of switching accounts or registering accounts.

[0020] In some practicable examples, the prompt generating device further includes an acquisition unit. The acquisition unit is used to acquire historical voice data, historical operation data, and historical question and answer data corresponding to the identification information; the historical voice data, historical operation data, and historical question and answer data; the processing unit is also used to analyze the historical voice data acquired by the acquisition unit, the historical operation data acquired by the acquisition unit, and the historical question and answer data acquired by the acquisition unit to determine at least one portrait data; wherein the portrait data includes the user label weight of each content classification in each time period under the historical location information; the processing unit is also used to generate a user portrait based on the portrait data.

[0021] In some implementable examples, the processing unit is specifically used to determine the portrait data corresponding to the actual location information and the actual time information based on the user portrait, the actual location information received by the receiving unit, and the actual time information received by the receiving unit; the processing unit is specifically used to determine the content category in which the user tag weight is greater than or equal to the preset weight based on the portrait data corresponding to the actual location information received by the receiving unit and the actual time information received by the receiving unit; the processing unit is specifically used to determine the actual prompt word based on the content category in which the user tag weight is greater than or equal to the preset weight; wherein, one content category corresponds to at least one actual prompt word.

[0022] In some feasible examples, the first information also includes query information, and one content category corresponds to at least one theoretical entity word; the processing unit is specifically used to determine the theoretical prompt word corresponding to each actual entity word contained in the query information according to a pre-configured knowledge graph and the query information received by the receiving unit; the processing unit is specifically used to determine the portrait data corresponding to the actual location information and the actual time information according to the user portrait, the actual location information received by the receiving unit, and the actual time information received by the receiving unit; the processing unit is specifically used to determine the content category whose user tag weight is greater than or equal to the preset weight according to the portrait data corresponding to the actual location information received by the receiving unit and the actual time information received by the receiving unit; the processing unit is specifically used to match the theoretical entity words and actual entity words of the content category whose user tag weight is greater than or equal to the preset weight; the processing unit is specifically used to determine the theoretical prompt word corresponding to the actual entity word as the actual prompt word when the theoretical entity word matches the actual entity word.

[0023] In some implementable examples, an actual prompt corresponds to an actual control; the receiving unit is further used to receive second information sent by the electronic device; wherein the second information is used to indicate that a selection operation has been performed on the target prompt, and the target prompt is any one of the actual prompts; the processing unit is further used to generate display data corresponding to the target prompt according to the target prompt received by the receiving unit; the processing unit is further used to control the sending unit to send second display information carrying display data to the electronic device; wherein the second display information is used to instruct the electronic device to display the display data.

[0024] In a fourth aspect, the present disclosure provides a prompt generating device, comprising: a processing unit, for controlling a sending unit to send a first information to a server in response to a first operation; wherein the first information comprises identification information, actual location information, actual time information and operation information, and the operation information comprises voice information lacking entity words, and any one of indication information for indicating that the electronic device has received the first operation; a receiving unit, for receiving a first display information carrying the actual prompt sent by the server; wherein the first display information is used to instruct the electronic device to display the actual prompt, and the actual prompt is determined according to a user portrait, actual location information and actual time information, and the user portrait is generated based on historical voice data, historical operation data and historical question and answer data of the identification information; the processing unit is also used to control the display unit to display the actual prompt according to the first display information.

[0025] In some feasible examples, the processing unit is also used to control the sending unit to send a voice message to the server; wherein the voice message includes first voiceprint data; the receiving unit is also used to receive first indication information sent by the server; wherein the first indication information is used to instruct the electronic device to continue to log in to the user account.

[0026] In some implementable examples, the receiving unit is also used to receive a second indication message sent by the server; wherein the second indication message is used to instruct the electronic device to prompt the user to enter theoretical login information of the user account; the processing unit is also used to control the sending unit to send actual login information to the server in response to the second operation; the receiving unit is also used to receive a third indication message sent by the server; wherein the third indication message is used to instruct the electronic device to prompt the user to perform a target operation, and the target operation includes any one of switching accounts or registering accounts.

[0027] In some implementable examples, an actual prompt corresponds to an actual control; the processing unit is further used to control the sending unit to send second information to the server in response to a third operation of the user; wherein the second information is used to indicate that a selection operation has been performed on a target prompt, and the target prompt is any one of the actual prompts; the receiving unit is further used to receive second display information carrying display data sent by the server; wherein the display data is generated based on the target prompt, and the second display information is used to instruct the electronic device to display the display data; the processing unit is further used to control the display unit to display the display data based on the second display information received by the receiving unit.

[0028] In a fifth aspect, the present disclosure provides an electronic device, comprising: a memory and a processor, the memory being used to store a computer program; the processor being used to enable the electronic device to implement any one of the prompt generation methods provided in the first aspect when executing the computer program.

[0029] In a sixth aspect, the present invention provides a computer-readable storage medium, comprising: a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to generate a prompt as provided in any one of the first aspects.

[0030] In a seventh aspect, the present invention provides a computer program product. When the computer program product is run on a computer, the computer executes any one of the prompt generation methods provided in the first aspect.

[0031] In an eighth aspect, the present disclosure provides an electronic device, comprising: a memory and a processor, the memory being used to store a computer program; the processor being used to enable the electronic device to implement any one of the prompt generation methods provided in the second aspect when executing the computer program.

[0032] In a ninth aspect, the present invention provides a computer-readable storage medium, comprising: a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to generate a prompt as provided in any one of the second aspects.

[0033] In a tenth aspect, the present invention provides a computer program product. When the computer program product is run on a computer, the computer executes any one of the prompt generation methods provided in the second aspect.

[0034] It should be noted that the above computer instructions may be stored in whole or in part on a first computer-readable storage medium, wherein the first computer-readable storage medium may be packaged together with the processor of the prompt generating device, or may be packaged separately from the processor of the prompt generating device, which is not limited in the present disclosure.

[0035] The description of the third, fifth, sixth and seventh aspects in the present disclosure can refer to the detailed description of the first aspect; and the beneficial effects of the description of the third, fifth, sixth and seventh aspects can refer to the beneficial effects analysis of the first aspect, which will not be repeated here.

[0036] The descriptions of the fourth, eighth, ninth and tenth aspects of the present disclosure may refer to the detailed description of the first aspect; and the beneficial effects of the descriptions of the fourth, eighth, ninth and tenth aspects may refer to the beneficial effects analysis of the second aspect, which will not be repeated here.

[0037] In the present disclosure, the name of the prompt generating device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear with other names. As long as the functions of each device or functional module are similar to those of the present disclosure, they fall within the scope of the claims of the present disclosure and their equivalent technologies.

[0038] These and other aspects of the present disclosure will become more apparent from the following description.

[0039] Compared with the prior art, the technical solution provided by the present invention has the following advantages:

[0040] A user image is generated based on historical voice data, historical operation data, and historical question-and-answer data, so that the user's preferences can be analyzed more accurately. Afterwards, after receiving the first information sent by the electronic device, when it is determined that the first information includes operation information, the user portrait is determined according to the identification information in the first information. Afterwards, the actual prompt is determined according to the user portrait and the actual location information and actual time information in the first information. Since the accuracy of the user portrait is improved, the actual prompt can be determined more accurately according to the user portrait and the actual location information and actual time information in the first information to ensure the user experience. Afterwards, by sending the first display information carrying the actual prompt to the electronic device, the user can check the actual prompt that he likes. The problem in the prior art that when an electronic device generates a prompt, the generated prompt is often inaccurate and cannot accurately reflect the user's true intention, resulting in a poor user experience is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0043] Figure 1 A schematic diagram of a scenario of a method for generating a prompt provided in an embodiment of the present application;

[0044] Figure 2 One of the structural schematic diagrams of the display device in the prompt generating method provided in the embodiment of the present application;

[0045] Figure 3 The second structural diagram of the display device in the prompt generating method provided in the embodiment of the present application;

[0046] Figure 4 One of the flowcharts of the prompt generation method provided in the embodiment of the present application;

[0047] Figure 5 The second schematic diagram of the scenario of the prompt generation method provided in the embodiment of the present application;

[0048] Figure 6 The third scenario diagram of the prompt generation method provided in the embodiment of the present application;

[0049] Figure 7A fourth scenario diagram of the method for generating a prompt provided in an embodiment of the present application;

[0050] Figure 8 A fifth scenario diagram of the method for generating prompts provided in an embodiment of the present application;

[0051] Fig. 9 The sixth scenario diagram of the prompt generation method provided in the embodiment of the present application;

[0052] Fig.10 A schematic diagram of the structure of a server provided in an embodiment of the present application;

[0053] Fig.11 One of the schematic diagrams of a chip system provided in an embodiment of the present application;

[0054] Fig.12 A schematic diagram of the structure of a display device provided in an embodiment of the present application;

[0055] Fig.13 The second schematic diagram of a chip system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0057] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0058] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0059] Hive mentioned in the embodiments of the present disclosure is a data warehouse tool based on Hadoop, which is used for data extraction, transformation and loading.

[0060] The HBase mentioned in the embodiments of the present disclosure is a distributed, column-oriented open source database.

[0061] Figure 1 is a schematic diagram of an operation scenario between a display device and a control device according to one or more embodiments of the present application, such as Figure 1 As shown, the user can operate the display device 200 through the mobile terminal 300 and the control device 100. The control device 100 can be a remote controller, and the communication between the remote controller and the display device includes infrared protocol communication, Bluetooth protocol communication, wireless or other wired methods to control the display device 200. The user can input user instructions through buttons on the remote controller, voice input, control panel input, etc. to control the display device 200. In some embodiments, a mobile terminal, a tablet computer, a computer, a laptop computer, and other smart devices can also be used to control the display device 200.

[0062] In some embodiments, the mobile terminal 300 can install software applications with the display device 200, and realize connection communication through the network communication protocol to achieve the purpose of one-to-one control operation and data communication. The audio and video content displayed on the mobile terminal 300 can also be transmitted to the display device 200 to realize the synchronous display function. The display device 200 also communicates data with the electronic device 400 through various communication methods. The display device 200 can be allowed to communicate and connect through a local area network (LAN), a wireless local area network (WLAN) and other networks. The electronic device 400 can provide various content and interactions to the display device 200. The display device 200 can be a liquid crystal display, an OLED display, or a projection display device. In addition to providing a broadcast receiving television function, the display device 200 can also provide an intelligent network TV function that provides a computer support function.

[0063] In some embodiments, the electronic device provided in the embodiment of the present application may be the above-mentioned server 400. Among them, the display device 200 sends the first information to the server 400 in response to the first operation (such as: the user performs a preset operation on the control device 100). The server 400 receives the first information sent by the display device 200. When the first information includes operation information, the server 400 determines the user portrait according to the identification information in the first information. The server 400 determines the actual prompt according to the user portrait and the actual position information and the actual time information in the first information. The server 400 sends the first display information carrying the actual prompt to the display device 200. The display device 200 receives the first display information carrying the actual prompt sent by the server. The display device 200 displays the actual prompt according to the first display information. Since the prompt generation method provided in the embodiment of the present disclosure generates the user portrait through the historical voice data, historical operation data and historical question and answer data of the user account currently logged in by the display device 200, the accuracy of the user portrait can be improved. Therefore, according to the user portrait and the actual position information and the actual time information in the first information, the actual prompt can be determined more accurately to ensure the user experience.

[0064] Figure 2 FIG. 2 shows a hardware configuration block diagram of a display device 200 according to an exemplary embodiment. Figure 2 The display device 200 shown includes at least one of a tuner 210, a communicator 220, a detector 230, an external device interface 240, a controller 250, a display 260, an audio output interface 270, a memory, a power supply, and a user interface 280. The controller includes a central processing unit, a video processor, an audio processor, a graphics processor, a RAM, a ROM, and a first interface to an nth interface for input / output. The display 260 can be a display with a touch function, such as a touch display. The tuner 210 receives broadcast television signals by wired or wireless reception, and demodulates audio and video signals from multiple wireless or wired broadcast television signals, such as and EPG data signals. The detector 230 is used to collect signals of the external environment or interact with the outside. The controller 250 and the tuner 210 can be located in different split devices, that is, the tuner 210 can also be in an external device of the main device where the controller 250 is located, such as an external set-top box.

[0065] In some embodiments, the controller 250 controls the operation of the display device and responds to user operations through various software control programs stored in the memory. The controller 250 controls the overall operation of the display device 200.

[0066] In some examples, the display device 200 of one or more embodiments is a TV set 1, and the operating system of the TV set 1 is an Android system. Figure 3 As shown, the television set 1 can be logically divided into an application layer (“application layer” for short) 21 , a kernel layer 22 and a hardware layer 23 .

[0067] Among them, Figure 3 As shown, the hardware layer may include Figure 2 The communicator 220, the detector 230 and the display 260 shown in the figure. The application layer 21 includes one or more applications. The application can be a system application or a third-party application. For example, the application layer 21 includes a first application, and the first application can provide a prompt recommendation function. The kernel layer 22 is a software middleware between the hardware layer and the application layer 21, which is used to manage and control hardware and software resources.

[0068] In some examples, the kernel layer 22 includes a first driver and a second driver, the first driver is used to send the user operation collected by the detector 230 to the first application, and the second driver is used to control the display 260 to display the information sent by the display module 213. The first application in the TV set 1 is started, and the first application calls the communicator 220 to establish a communication connection with the communication module 301 of the server 400, and the user portrait corresponding to each TV set 1 is stored in the storage module 305 of the server 400. Afterwards, the first driver is used to send the user operation collected by the detector 230 to the first application for identification. Afterwards, the processing module 211 of the first application responds to the first operation received by the acquisition module 210 (such as: the user performs a preset operation on the control device 100), and controls the sending module 212 to send the first information to the server 400. The receiving module 302 of the server 400 receives the first information sent by the first application of the TV set 1. The processing module 303 of the server 400 determines the user portrait according to the identification information in the first information of the receiving module 302 when the first information received by the receiving module 302 includes operation information. The processing module 303 of the server 400 determines the actual prompt according to the user portrait and the actual location information and the actual time information in the first information received by the receiving module 302. The processing module 303 of the server 400 controls the sending module 304 to send the first display information carrying the actual prompt to the first application of the TV set 1. The acquisition module 210 of the first application of the TV set 1 receives the first display information carrying the actual prompt sent by the server 1. The processing module 211 of the first application controls the sending module 212 to send the first display information to the display module 213 according to the first display information received by the acquisition module 210. The display module 213 sends the first display information to the second driver, and the second driver controls the display 260 to display the actual prompt.

[0069] Specifically, the storage module 214 of the first application can be used to store the program code for writing the television 1, and can also be used to store data generated during the operation of the television 1, such as data in a write request.

[0070] Specifically, the electronic device provided in the embodiment of the present disclosure may be the above-mentioned server 400 or the above-mentioned display device 200, which is not limited here.

[0071] The user images, voiceprint information, location information, time information, login information, historical voice data, historical operation data and historical question and answer data involved in this application can all be data authorized by the user or fully authorized by all parties.

[0072] In the following embodiments, the method of the embodiment of the present application is described by taking the execution subject of the prompt generating method provided by the embodiment of the present disclosure as the above-mentioned server 400 and the electronic device as the television 1 as an example.

[0073] The present application embodiment provides a method for generating a prompt, such as Figure 4 As shown, the prompt generating method may include S11-S14.

[0074] S11 , receiving first information sent by the TV set 1 .

[0075] In some examples, when using the TV 1, the user usually selects the required function according to the actual prompt recommended by the TV 1, such as watching movies, watching TV, searching for songs, checking the weather, etc. When the user needs the TV 1 to recommend the actual prompt, the user can perform the first operation, such as: the TV 1 supports the touch function, the user presses the prompt function on the TV 1, or presses the voice button of the remote control, or selects the prompt function on the mobile phone that establishes a communication connection with the TV 1, or the user enters the voice information lacking entity words (such as: I want, I want, I want to see) through the voice function of the mobile phone or the remote control. At this time, the TV 1 responds to the first operation and sends the first information to the server 400. In this way, after receiving the first information, the server 400 will generate the corresponding actual prompt when it determines that the first information contains the operation information. After that, the server 400 sends the first display information carrying the actual prompt to the TV 1, so that the TV 1 displays the actual prompt. In this way, the user can select the required function according to the actual prompt displayed by the TV 1 to ensure the user experience.

[0076] S12. When the first information includes operation information, determine a user portrait according to identification information in the first information. The operation information includes any one of voice information lacking entity words and indication information indicating that the electronic device has received the first operation, and the user portrait is generated based on historical voice data, historical operation data, and historical question and answer data corresponding to the identification information.

[0077] In some examples, the identification information includes information used to characterize the TV 1, or information used to characterize the user currently using the TV 1. The user portrait corresponding to the identification information of each TV 1 is pre-stored in the memory of the server 400. For example, when the identification information includes information used to characterize the TV 1, the identification information may be a device identification code, so that the server 400 can query the memory for the user portrait corresponding to the device identification code according to the device identification code in the first information. Alternatively, when the identification information includes information used to characterize the user currently using the TV 1, the identification information may be a user account, so that the server 400 can query the memory for the user portrait corresponding to the currently logged-in user account according to the currently logged-in user account in the first information.

[0078] Specifically, the historical voice data includes the voice data input by the user in history; the historical operation data includes historical search and click data. Among them, the historical search and click data include: data corresponding to the user's manual search and manual click behavior, such as: the user did not get the required content by voice, but got it by manual search, such as: the user could not remember the full name of the song, but knew it was a popular song, so he input voice data through the remote control, such as: "Popular Songs", at this time, the TV 1 prompts "No corresponding song found, recommended songs will be played for you", and randomly plays songs in the recommended list. When the songs in the recommended list are not the songs the user needs, the user's needs cannot be met at this time. Afterwards, the user manually searches for "80s" on the TV 1, and the TV 1 gives "songs from the 80s", and there are songs that the user needs. Then, "songs from the 80s" is used as the data corresponding to the user's manual search and manual click behavior, so that the historical operation data can be continuously updated, thereby improving the accuracy of the user portrait.

[0079] Historical question and answer data include content entity type question and answer response language, such as data of questions and answers between users and TV 1, such as: TV 1 randomly plays a song, the user personally likes it very much, but does not know the name of the song, so the user inputs the voice data "What song is this" through the remote control, and TV 1 gives a recognition result based on the voice data: "This is XX from XX", at this time "This is XX from XX" is used as the content entity type question and answer response language.

[0080] S13. Determine an actual prompt based on the user portrait and the actual location information and the actual time information in the first information.

[0081] S14, sending first display information carrying the actual prompt to the television 1. The first display information is used to instruct the television 1 to display the actual prompt.

[0082] As can be seen from the above, the prompt generation method provided by the embodiment of the present disclosure generates a user image based on historical voice data, historical operation data and historical question and answer data, so that the user's preferences can be analyzed more accurately. Afterwards, after receiving the first information sent by the electronic device, it is determined whether the first information includes operation information. If the first information includes operation information, the user portrait is determined according to the identification information in the first information. Afterwards, the actual prompt is determined according to the user portrait and the actual location information and actual time information in the first information. Since the user portrait can more accurately analyze the user's preferences, the actual prompt can be more accurately determined according to the user portrait and the actual location information and actual time information in the first information to ensure the user experience. Afterwards, by sending the first display information carrying the actual prompt to the electronic device, the user can check the actual prompt that he likes.

[0083] In some feasible examples, the identification information includes a user account, combined with Figure 4 ,like Figure 5 The prompt generation method provided in the embodiment of the present disclosure also includes S15-S17.

[0084] S15, receiving voice information sent by the television 1. The voice information includes first voiceprint data.

[0085] In some examples, when the TV 1 is used for the first time or when a new user uses the TV 1, the user needs to register a user account, and the user needs to set the user image, user age, gender and other attribute information, login information and voiceprint data. In this way, the TV 1 sends the user's registration information to the server 400, and the server 400 creates a user account and saves the user image, user age, gender and other attribute information, login information and voiceprint data corresponding to the user account. In order to give the actual prompt more accurately, the server 400 needs to determine whether the user currently using the TV 1 is the user corresponding to the user account currently logged in by the TV 1 according to the voice information sent by the TV 1. Therefore, the server 400 needs to determine whether the first voiceprint data in the voice information sent by the TV 1 matches the second voiceprint data of the user account currently logged in by the TV 1 stored in the server 400, so as to determine whether the user currently using the TV 1 is the user corresponding to the user account currently logged in by the TV 1.

[0086] S16. Determine, based on the first voiceprint data, whether the second voiceprint data bound to the user account matches the first voiceprint data.

[0087] In some examples, the server 400 extracts the first feature information from the first voiceprint data and the second feature information from the second voiceprint data. Then, the first feature information is processed to obtain the first feature vector; similarly, the second feature information is processed to obtain the second feature vector. Then, the similarity between the first feature vector and the second feature vector is calculated (e.g., by calculating the cosine similarity between the first feature vector and the second feature vector, and using the cosine similarity as the similarity between the first feature vector and the second feature vector. Or, by calculating the target distance between the first feature vector and the second feature vector, and using the target distance as the similarity between the first feature vector and the second feature vector) to determine whether the second voiceprint data matches the first voiceprint data. When the similarity is greater than the similarity threshold, it means that the second voiceprint data matches the first voiceprint data; when the similarity is less than or equal to the similarity threshold, it means that the second voiceprint data does not match the first voiceprint data.

[0088] Specifically, the target distance includes any one of Euclidean distance, Manhattan distance, and Chebyshev distance.

[0089] S17: When the second voiceprint data matches the first voiceprint data, first indication information is sent to the TV 1. The first indication information is used to instruct the TV 1 to continue to log in to the user account.

[0090] In some examples, the second voiceprint data matches the first voiceprint data, indicating that the user currently using TV 1 is the user corresponding to the user account currently logged in to TV 1. In this way, when TV 1 generates actual prompts based on the user portrait and the first information, it can accurately generate actual prompts that are consistent with the user, thereby ensuring the user experience.

[0091] In some possible implementation examples, combined with Figure 4 ,like Figure 5 In the prompt generation method provided in the embodiment of the present disclosure, before executing S11, it is also necessary to execute S18-S21.

[0092] S18: When the second voiceprint data does not match the first voiceprint data, second indication information is sent to the TV 1. The second indication information is used to instruct the TV 1 to prompt the user to enter theoretical login information of the user account.

[0093] In some examples, the second voiceprint data does not match the first voiceprint data, indicating that the user currently using the TV set 1 is not the user corresponding to the user account currently logged in by the TV set 1. At this time, when the TV set 1 generates the actual prompt according to the user portrait corresponding to the user account and the first information, since the user currently using the TV set 1 is not the user corresponding to the user account currently logged in by the TV set 1, the actual prompt generated by the TV set 1 is not what the user currently using the TV set 1 needs, causing the user to search manually. To solve the above problem, the prompt generation method provided in the embodiment of the present disclosure needs to confirm the identity of the user currently using the TV set 1 again, such as: the server 400 sends the second indication information to the TV set 1. Afterwards, the TV set 1 responds to the second operation (such as: the operation of the user inputting the actual login information) and sends the actual login information (such as: login password) to the server 400. In this way, the server 400 can match the actual login information with the theoretical login information of the user account to determine whether the user currently using the TV set 1 is the user corresponding to the user account currently logged in by the TV set 1.

[0094] S19, receiving actual login information sent by TV set 1.

[0095] S20. When the theoretical login information is the same as the actual login information, send first indication information to the TV 1.

[0096] In some examples, when the theoretical login information is the same as the actual login information, it means that the user currently using the TV 1 is the user corresponding to the user account currently logged in to the TV 1. In this way, when the TV 1 generates actual prompts based on the user portrait and the first information, it can accurately generate actual prompts that are consistent with the user, thereby ensuring the user experience.

[0097] S21. When the theoretical login information is different from the actual login information, third instruction information is sent to the TV 1. The third instruction information is used to instruct the TV 1 to prompt the user to perform a target operation, where the target operation includes switching an account or registering an account.

[0098] In some examples, when the theoretical login information is different from the actual login information, it means that the user currently using the TV 1 is not the user corresponding to the user account currently logged in by the TV 1. In order to avoid the problem that the actual prompt generated by the TV 1 is not what the user currently using the TV 1 needs, causing the user to search manually. The server 1 sends the third indication information to the TV 1. In this way, after receiving the third indication information sent by the server 400, the TV 1 will prompt the user currently using the TV 1 to switch accounts or register an account, thereby ensuring that when each user uses the TV 1, the TV 1 can accurately generate the actual prompt required by each user, thereby ensuring the user experience.

[0099] It should be noted that the above example is explained by taking the example that the server 400 determines whether the user currently using the TV 1 is the user corresponding to the user account currently logged in on the TV 1 by verifying the voiceprint data and login information. In some other examples, the TV 1 is provided with an image acquisition device for collecting user images. When the user uses the TV 1, the image acquisition device collects the user image of the user and sends the user image to the server 400. The server 400 searches the memory for the user portrait corresponding to the user image according to the user image. In this way, no matter which user uses the TV 1, the server 400 can determine the user portrait corresponding to the user image according to the user image of the current user collected by the TV 1. Afterwards, the actual prompt required by the user can be generated in real time according to the user portrait to ensure the user experience.

[0100] In some possible implementation examples, combined with Figure 4 ,like Figure 6 In the prompt generation method provided in the embodiment of the present disclosure, before executing S11, it is also necessary to execute S22-S24.

[0101] S22. Acquire historical voice data, historical operation data, and historical question-and-answer data corresponding to the identification information.

[0102] In some examples, when analyzing historical voice data, historical operation data, and historical question-and-answer data, it is necessary to process the historical voice data, historical operation data, and historical question-and-answer data, such as using data warehouse technology (Extract, transform, load, ETL) to extract, clean, transform, and load the historical voice data, historical operation data, and historical question-and-answer data, so as to obtain historical voice data, historical operation data, and historical question-and-answer data that meet the requirements. Afterwards, by analyzing the processed historical voice data, historical operation data, and historical question-and-answer data, it is possible to determine the user's portrait data in different time periods (such as morning, noon, and afternoon on weekdays, or morning, noon, and afternoon on non-working days) with the same location information. In this way, a user portrait of the user can be generated based on the portrait data.

[0103] S23: Analyze the historical voice data, historical operation data, and historical question-and-answer data to determine at least one piece of portrait data, wherein the portrait data includes the user tag weight of each content category in each time period under the historical location information.

[0104] In some examples, the server 400 analyzes the historical voice data, historical operation data, and historical question-and-answer data to determine the access probability of the user accessing each content category in each time period under the historical location information, such as: the access probability is equal to a represents the first total number of visits to the target category in the historical voice data, historical operation data, and historical question and answer data in any time period under the historical position information, and b represents the second total number of visits to the target category in the historical voice data, historical operation data, and historical question and answer data under the historical position information, where the target category is any content category.

[0105] Afterwards, the server 400 determines the user tag weight according to the access probability and the first total number of times. For example, the user tag weight is equal to (α×γ)×(ω×a), where α represents the behavior type weight, γ represents the time decay coefficient, ω represents the access probability, and a represents the first total number of times.

[0106] Among them, the behavior type weight refers to the different importance of different behaviors such as user search and click to users, and the weights of different behaviors are also different. The behavior type weight is generally pre-set by the operation and maintenance personnel after analyzing the historical voice data, historical operation data and historical question and answer data. The time decay coefficient means that some behaviors are constantly weakened by the actual influence, so it is necessary to adjust the objectivity of the behavior through the time decay coefficient to ensure the accuracy of the user label weight.

[0107] For example, if the time information adopts the 24-hour format, the content classification includes 5 categories, namely music / radio, hot news, movies, shopping and beauty, the user tag weight of each content classification in each time period under the same historical location information is shown in Table 1.

[0108] Table 1

[0109]

[0110] S24. Generate a user portrait based on the portrait data.

[0111] In some possible implementation examples, combined with Figure 4 ,like Figure 7 As shown, the above S13 can be specifically implemented through the following S130-S132.

[0112] S130. Determine the portrait data corresponding to the actual location information and the actual time information according to the user portrait, the actual location information and the actual time information.

[0113] In some examples, combined with Table 1 given in S23 above, when the actual location information is "Xi'an" and the actual time information is "Monday, 8:05", it can be known by querying Table 1 that the portrait data corresponding to the actual location information and the actual time information are as shown in Table 2.

[0114] Table 2

[0115]

[0116] S131. Determine a content category whose user tag weight is greater than or equal to a preset weight based on the portrait data corresponding to the actual location information and the actual time information.

[0117] In some examples, combined with the example given in S130 above, the user tag weight corresponding to each content category in the same time period of the same historical location information is different. Therefore, the content category that the user is interested in can be determined by the relationship between the user tag weight and the preset weight, and then the actual prompt for the content category that the user is interested in is generated, thereby improving the accuracy of the actual prompt and ensuring the user experience.

[0118] S132: Determine an actual prompt word according to the content category whose user tag weight is greater than or equal to the preset weight, wherein one content category corresponds to at least one actual prompt word.

[0119] In some examples, combined with the example given in S131 above, when the user tag weight is greater than or equal to the preset weight, it means that the user is more interested in the content category corresponding to the user tag weight. Therefore, by generating actual prompts for the content categories that the user is more interested in, the accuracy of the actual prompts can be improved to ensure the user experience.

[0120] In some feasible examples, the first information also includes query information, a content classification corresponds to at least one theoretical entity word; Figure 4 ,like Figure 8 As shown, the above S13 can be specifically implemented through the following S130, S131, S133-S135.

[0121] S130. Determine the portrait data corresponding to the actual location information and the actual time information according to the user portrait, the actual location information and the actual time information.

[0122] S131. Determine a content category whose user tag weight is greater than or equal to a preset weight based on the portrait data corresponding to the actual location information and the actual time information.

[0123] S133. Determine, based on a pre-configured knowledge graph and query information, a theoretical prompt corresponding to each actual entity word included in the query information.

[0124] In some examples, when the server 400 determines that the first information includes query information, it is necessary to perform recognition processing on the query information, such as optical character recognition (OCR) or natural language processing (NLP), so that at least one actual entity word contained in the query information can be identified. Afterwards, based on the pre-configured knowledge graph, the theoretical prompt related to each actual entity word is calculated. For example, if the query information is "AA's TV series", the server 400 performs recognition processing on "AA's TV series" and determines that the actual entity words contained in "AA's TV series" are "AA" and "TV series", respectively. Afterwards, based on the pre-configured knowledge graph, at least one theoretical prompt for "AA" and at least one theoretical prompt for "TV series" are determined.

[0125] S134: Match theoretical entity words of content categories whose user tag weights are greater than or equal to preset weights with actual entity words.

[0126] In some examples, since the server 400 cannot identify the theoretical entity word or the actual entity word. Therefore, when matching the theoretical entity word with the actual entity word, it is necessary to match the word vector corresponding to the theoretical entity word with the word vector corresponding to the actual entity word, such as: by calculating the similarity between the word vector corresponding to the theoretical entity word and the word vector corresponding to the actual entity word, determine whether the theoretical entity word matches the actual entity word. Specifically, the process of calculating the similarity between the word vector corresponding to the theoretical entity word and the word vector corresponding to the actual entity word is the same as the process of calculating the similarity between the first feature vector and the second feature vector, which will not be repeated here.

[0127] Since each content classification corresponds to one or more theoretical entity words, by matching the theoretical entity words with the actual entity words, the actual prompt words that the user is interested in can be found. For example, in combination with the example given in S130 above, it is determined that the content classification with a user tag weight greater than or equal to the preset weight is "music / radio", and the similarity between the theoretical entity word corresponding to "music / radio" and the actual entity word "AA" is greater than the similarity threshold, which means that the theoretical entity word matches the actual entity word "AA". Therefore, the actual prompt words related to "music / radio" can be found in the theoretical prompt words corresponding to "AA".

[0128] S135. When the theoretical entity word matches the actual entity word, determine the theoretical prompt word corresponding to the actual entity word as the actual prompt word.

[0129] In some examples, a theoretical prompt word corresponds to a content category. Combined with the example given in S134 above, when the theoretical entity word matches the actual entity word, it means that the user is interested in "AA". Therefore, the theoretical prompt word corresponding to "AA" can be recommended to the user as the actual prompt word, thereby ensuring that the user can select the actual prompt word he needs.

[0130] In some other examples, in order to improve the accuracy of the actual prompts, it is necessary to filter the theoretical prompts corresponding to the content categories whose user tag weights are greater than or equal to the preset weights among the theoretical prompts corresponding to "AA". This can greatly improve the accuracy of the actual prompts.

[0131] In some feasible examples, an actual prompt corresponds to an actual control; Figure 4 ,like Fig. 9 As shown, the prompt generating method provided in the embodiment of the present disclosure can further execute S25-S27 after executing S14.

[0132] S25, receiving the second information sent by the television 1. The second information is used to indicate that a selection operation has been performed on a target prompt, and the target prompt is any one of the actual prompts.

[0133] S26. Generate display data corresponding to the target prompt according to the target prompt.

[0134] S27, sending second display information carrying display data to the television set 1. The second display information is used to instruct the television set 1 to display the display data.

[0135] In some examples, in order to facilitate the user to select the actual prompt required, the server 400 assigns an actual control to each actual prompt when sending the first display information to the TV 1. In this way, when the TV 1 displays the actual prompt, each actual prompt corresponds to a control, and the user can select the control corresponding to the actual prompt, such as: the user selects the control corresponding to the required actual prompt through the "OK" key in the remote control, or the user selects the control corresponding to the required actual prompt through semantic information (such as: selecting the first one), thereby improving the media resource reach rate and improving the user experience. In this way, the TV 1 responds to the third operation and sends the second information to the server 400. Afterwards, after receiving the second information sent by the TV 1, the server 400 needs to generate the display data of the target prompt contained in the second information. Afterwards, the server 400 sends the second display information carrying the display data to the TV 1, so that the user can check the required display content to ensure the user experience.

[0136] Specifically, in the prompt generation method provided by the embodiment of the present disclosure, the TV 1 uses a computing engine (Apache Spark) to synchronize the user's voice data and operation data to the server 400 in real time. After receiving the voice data and operation data sent by the TV 1, the server 400 stores the voice data, operation data, and user portrait in a database, such as HBase. The server 400 can read the data user portrait, historical voice data, historical operation data, and historical question and answer data in HBase through Hive.

[0137] It should be noted that the above example is described by taking the execution subject of the prompt generation method provided by the embodiment of the present disclosure as the server 400. In some other examples, the execution subject of the prompt generation method provided by the embodiment of the present disclosure may also be the display device 200, which is not limited here.

[0138] In the following embodiments, the method of the embodiment of the present application is described by taking the television 1 as the executing subject of the prompt generating method provided by the embodiment of the present disclosure and the server as the server 400 as an example.

[0139] The present application embodiment provides a method for generating a prompt, such as Figure 4As shown, the prompt generating method may include S31-S33.

[0140] S31. In response to a first operation, first information is sent to a server, wherein the first information includes identification information, actual location information, actual time information, and operation information, and the operation information includes any one of voice information lacking entity words and indication information indicating that the electronic device has received the first operation.

[0141] S32, receiving first display information carrying actual prompts sent by the server, wherein the first display information is used to instruct the electronic device to display actual prompts, the actual prompts are determined according to the user portrait, actual location information and actual time information, and the user portrait is generated based on historical voice data, historical operation data and historical question and answer data corresponding to the identification information.

[0142] S33. Display the actual prompt according to the first display information.

[0143] In some feasible examples, the identification information includes a user account, combined with Figure 4 ,like Figure 5 As shown, the prompt generation method provided by the embodiment of the present disclosure also includes S34 and S35.

[0144] S34: Send a voice message to the server, wherein the voice message includes the first voiceprint data.

[0145] S35, receiving first instruction information sent by the server, wherein the first instruction information is used to instruct the electronic device to continue to log in to the user account.

[0146] In some possible implementation examples, combined with Figure 4 ,like Figure 5 As shown, the prompt generation method provided by the embodiment of the present disclosure also includes: S36-S38.

[0147] S36, receiving the second indication information sent by the server, wherein the second indication information is used to instruct the electronic device to prompt the user to input theoretical login information of the user account.

[0148] S37. In response to the second operation, actual login information is sent to the server.

[0149] S38: Receive the third instruction information sent by the server, wherein the third instruction information is used to instruct the electronic device to prompt the user to perform a target operation, where the target operation includes switching an account or registering an account.

[0150] In some feasible examples, an actual prompt corresponds to an actual control; Figure 4 ,like Fig. 9As shown, the prompt generation method provided by the embodiment of the present disclosure also includes: S39-S41.

[0151] S39: In response to the user's third operation, send second information to the server, wherein the second information is used to indicate that a selection operation has been performed on a target prompt, and the target prompt is any one of the actual prompts.

[0152] S40, receiving second display information carrying display data sent by the server, wherein the display data is generated according to the target prompt, and the second display information is used to instruct the electronic device to display the display data.

[0153] S41. Display display data according to the second display information.

[0154] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to realize the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0155] The embodiment of the present application can divide the functional modules of the electronic device according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0156] like Fig.10 As shown, an embodiment of the present application provides a structural diagram of a server 400 , which includes a communicator 101 and a processor 102 .

[0157] The communicator 101 is used to receive a first message sent by an electronic device; the processor 102 is used to determine a user portrait according to identification information in the first message received by the communicator 101 when the first message received by the communicator 101 includes operation information; wherein the operation information includes voice information lacking entity words and any one of the indication information used to indicate that the electronic device has received a first operation, and the user portrait is generated based on historical voice data, historical operation data, and historical question and answer data corresponding to the identification information; the processor 102 is also used to determine an actual prompt based on the user portrait and actual location information and actual time information in the first message received by the communicator 101; the processor 102 is also used to control the sending unit to send first display information carrying the actual prompt to the electronic device; wherein the first display information is used to instruct the electronic device to display the actual prompt.

[0158] In some feasible examples, the identification information includes a user account, and the communicator 101 is further used to receive a voice message sent by an electronic device; wherein the voice message includes a first voiceprint data; the processor 102 is further used to determine whether the second voiceprint data bound to the user account matches the first voiceprint data received by the communicator 101 based on the first voiceprint data received by the communicator 101; the processor 102 is further used to control the sending unit to send a first indication message to the electronic device when the second voiceprint data matches the first voiceprint data received by the communicator 101; wherein the first indication message is used to instruct the electronic device to continue logging into the user account.

[0159] In some implementable examples, the processor 102 is also used to control the sending unit to send a second indication message to the electronic device when the second voiceprint data does not match the first voiceprint data received by the communicator 101; wherein the second indication message is used to instruct the electronic device to prompt the user to enter theoretical login information of the user account; the communicator 101 is also used to receive actual login information sent by the electronic device; the processor 102 is also used to control the sending unit to send the first indication message to the electronic device when the theoretical login information is the same as the actual login information received by the communicator 101; the processor 102 is also used to control the sending unit to send a third indication message to the electronic device when the theoretical login information is different from the actual login information received by the communicator 101; wherein the third indication message is used to instruct the electronic device to prompt the user to perform a target operation, and the target operation includes any one of switching accounts or registering accounts.

[0160] In some feasible examples, the communicator 101 is used to obtain historical voice data, historical operation data and historical question and answer data corresponding to the identification information; the processor 102 is also used to analyze the historical voice data obtained by the communicator 101, the historical operation data obtained by the communicator 101 and the historical question and answer data obtained by the communicator 101 to determine at least one portrait data; wherein the portrait data includes the user label weight of each content category in each time period under the historical location information; the processor 102 is also used to generate a user portrait based on the portrait data.

[0161] In some implementable examples, the processor 102 is specifically used to determine the portrait data corresponding to the actual location information and the actual time information based on the user portrait, the actual location information received by the communicator 101, and the actual time information received by the communicator 101; the processor 102 is specifically used to determine the content category with a user tag weight greater than or equal to a preset weight based on the portrait data corresponding to the actual location information received by the communicator 101 and the actual time information received by the communicator 101; the processor 102 is specifically used to determine the actual prompt word based on the content category with a user tag weight greater than or equal to the preset weight; wherein, one content category corresponds to at least one actual prompt word.

[0162] In some feasible examples, the first information also includes query information, and one content classification corresponds to at least one theoretical entity word; the processor 102 is specifically used to determine the theoretical prompt corresponding to each actual entity word contained in the query information according to the pre-configured knowledge graph and the query information received by the communicator 101; the processor 102 is specifically used to determine the portrait data corresponding to the actual location information and the actual time information according to the user portrait, the actual location information received by the communicator 101, and the actual time information received by the communicator 101; the processor 102 is specifically used to determine the content classification whose user tag weight is greater than or equal to the preset weight according to the portrait data corresponding to the actual location information received by the communicator 101 and the actual time information received by the communicator 101; the processor 102 is specifically used to match the theoretical entity words and the actual entity words of the content classification whose user tag weight is greater than or equal to the preset weight; the processor 102 is specifically used to determine the theoretical prompt corresponding to the actual entity word as the actual prompt when the theoretical entity word matches the actual entity word.

[0163] In some implementable examples, an actual prompt corresponds to an actual control; the communicator 101 is further used to receive second information sent by the electronic device; wherein the second information is used to indicate that a selection operation has been performed on a target prompt, and the target prompt is any one of the actual prompts; the processor 102 is further used to generate display data corresponding to the target prompt according to the target prompt received by the communicator 101; the processor 102 is further used to control the sending unit to send second display information carrying display data to the electronic device; wherein the second display information is used to instruct the electronic device to display the display data.

[0164] Among them, all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and its role will not be repeated here.

[0165] Of course, the server 400 provided in the embodiment of the present application includes but is not limited to the above modules, for example, the server 400 may also include a memory 103. The memory 103 may be used to store the program code of the write server 400, and may also be used to store data generated by the write server 400 during operation, such as data in a write request.

[0166] As an example, combining Figure 3 The functions implemented by the communication module 301, the receiving module 302 and the sending module 304 in the server 400 are the same as Fig.10 The function of the communicator 101 in FIG. 1 is the same as that of the processing module 303. Fig.10 The functions of the processor 102 in the embodiment are the same as those of the storage module 305. Fig.10 The function of the memory 103 in is the same.

[0167] The present application also provides a chip system, which can be applied to the server 400 in the above embodiment. Fig.11 As shown, the chip system includes at least one processor 1501 and at least one interface circuit 1502. The processor 1501 may be the processor in the above-mentioned server 400. The processor 1501 and the interface circuit 1502 may be interconnected via a line. The processor 1501 may receive and execute computer instructions from the memory of the above-mentioned server 400 via the interface circuit 1502. When the computer instructions are executed by the processor 1501, the server 400 may execute the various steps executed by the server 400 in the above-mentioned embodiment. Of course, the chip system may also include other discrete devices, which are not specifically limited in the embodiments of the present application.

[0168] The embodiment of the present application also provides a computer-readable storage medium for storing computer instructions executed by the above-mentioned server 400.

[0169] The embodiment of the present application also provides a computer program product, including computer instructions executed by the above-mentioned server 400.

[0170] like Fig.12 As shown, an embodiment of the present application provides a structural schematic diagram of a display device 200 , which includes a processor 201 , a communicator 202 , and a display 203 .

[0171] Processor 201 is used to control the sending unit to send first information to the server in response to a first operation; wherein the first information includes identification information, actual location information, actual time information and operation information, and the operation information includes voice information lacking entity words, and any one of the indication information used to indicate that the electronic device has received the first operation; communicator 202 is used to receive first display information carrying actual prompt words sent by the server; wherein the first display information is used to instruct the electronic device to display actual prompt words, and the actual prompt words are determined according to the user portrait, actual location information and actual time information, and the user portrait is generated based on historical voice data, historical operation data and historical question and answer data corresponding to the identification information; processor 201 is also used to control the display 203 to display the actual prompt words according to the first display information.

[0172] In some feasible examples, the identification information includes a user account, and the processor 201 is also used to control the sending unit to send a voice message to the server; wherein the voice message includes first voiceprint data; the communicator 202 is also used to receive a first indication message sent by the server; wherein the first indication message is used to instruct the electronic device to continue to log in to the user account.

[0173] In some implementable examples, the communicator 202 is also used to receive a second indication message sent by the server; wherein the second indication message is used to instruct the electronic device to prompt the user to enter theoretical login information of the user account; the processor 201 is also used to control the sending unit to send actual login information to the server in response to the second operation; the communicator 202 is also used to receive a third indication message sent by the server; wherein the third indication message is used to instruct the electronic device to prompt the user to perform a target operation, and the target operation includes any one of switching accounts or registering accounts.

[0174] In some implementable examples, an actual prompt corresponds to an actual control; the processor 201 is further used to control the sending unit to send a second message to the server in response to a third operation of the user; wherein the second information is used to indicate that a selection operation has been performed on a target prompt, and the target prompt is any one of the actual prompts; the communicator 202 is further used to receive second display information carrying display data sent by the server; wherein the display data is generated according to the target prompt, and the second display information is used to instruct the electronic device to display the display data; the processor 201 is further used to control the display 203 to display the display data according to the second display information received by the communicator 202.

[0175] Among them, all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and its role will not be repeated here.

[0176] Of course, the display device 200 provided in the embodiment of the present application includes but is not limited to the above modules, for example, the display device 200 may also include a memory 204. The memory 204 may be used to store the program code of the display device 200, and may also be used to store data generated by the display device 200 during operation, such as data in a write request.

[0177] As an example, combining Figure 3 The functions implemented by the acquisition module 210 and the sending module 212 in the display device 200 are the same as Fig.12 The function of the communicator 202 is the same as that of the processing module 211. Fig.12 The functions of the processor 201 are the same as those of the display module 213. Fig.12 The function of the display 203 in FIG. 1 is the same as that of the display 203 in FIG. 1 , and the function implemented by the storage module 214 is the same as that of the display 203 in FIG. Fig.12 The function of the memory 204 is the same as that of the memory 204 in FIG.

[0178] The present application also provides a chip system, which can be applied to the display device 200 in the above embodiment. Fig.13 As shown, the chip system includes at least one processor 2501 and at least one interface circuit 2502. The processor 2501 may be the processor in the display device 200. The processor 2501 and the interface circuit 2502 may be interconnected via a line. The processor 2501 may receive and execute computer instructions from the memory of the display device 200 via the interface circuit 2502. When the computer instructions are executed by the processor 2501, the display device 200 may execute the various steps executed by the display device 200 in the above-mentioned embodiment. Of course, the chip system may also include other discrete devices, which are not specifically limited in the embodiments of the present application.

[0179] The embodiment of the present application also provides a computer-readable storage medium for storing computer instructions executed by the above-mentioned display device 200.

[0180] The embodiment of the present application also provides a computer program product, including computer instructions executed by the above-mentioned display device 200.

[0181] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for generating a prompt, characterized in that: include: Receiving first information sent by an electronic device; In the case where the first information includes operation information, determining a user portrait according to identification information in the first information; wherein the operation information includes any one of voice information lacking entity words and indication information for indicating that the electronic device has received the first operation, and the user portrait is generated based on historical voice data, historical operation data, and historical question and answer data corresponding to the identification information; Determine, according to the user portrait, the actual location information and the actual time information, portrait data corresponding to the actual location information and the actual time information; Determine, based on the portrait data corresponding to the actual location information and the actual time information, a content category in which the user tag weight is greater than or equal to a preset weight; Determine an actual prompt word according to the content category whose user tag weight is greater than or equal to a preset weight; wherein one content category corresponds to at least one actual prompt word; Sending first display information carrying the actual prompt to the electronic device; wherein the first display information is used to instruct the electronic device to display the actual prompt.

2. The method for generating a prompt according to claim 1, characterized in that: The identification information includes a user account, and the method further includes: Receiving voice information sent by the electronic device; wherein the voice information includes first voiceprint data; Determining, based on the first voiceprint data, whether the second voiceprint data bound to the user account matches the first voiceprint data; When the second voiceprint data matches the first voiceprint data, first indication information is sent to the electronic device; wherein the first indication information is used to instruct the electronic device to continue to log in to the user account.

3. The method for generating a prompt according to claim 2, characterized in that: The method further comprises: In the case where the second voiceprint data does not match the first voiceprint data, sending second indication information to the electronic device; wherein the second indication information is used to instruct the electronic device to prompt the user to enter theoretical login information of the user account; Receiving actual login information sent by the electronic device; When the theoretical login information is the same as the actual login information, sending the first indication information to the electronic device; When the theoretical login information is different from the actual login information, a third indication information is sent to the electronic device; wherein the third indication information is used to instruct the electronic device to prompt the user to perform a target operation, and the target operation includes switching accounts or registering accounts.

4. The method for generating a prompt according to claim 1, characterized in that: Before receiving the first information sent by the electronic device, the method further includes: Acquire historical voice data, historical operation data, and historical question-and-answer data corresponding to the identification information; Analyze the historical voice data, the historical operation data, and the historical question-and-answer data to determine at least one piece of portrait data; wherein the portrait data includes a user tag weight for each content category in each time period under the historical location information; The user portrait is generated according to the portrait data.

5. A method for generating a prompt, characterized in that: include: In response to the first operation, sending first information to the server; wherein the first information includes identification information, actual location information, actual time information and operation information, and the operation information includes any one of voice information lacking entity words and indication information for indicating that the electronic device has received the first operation; Receive first display information carrying an actual prompt sent by the server; wherein the first display information is used to instruct the electronic device to display the actual prompt, and the process of determining the actual prompt includes: determining the portrait data corresponding to the actual location information and the actual time information according to the user portrait, the actual location information and the actual time information; determining a content category whose user tag weight is greater than or equal to a preset weight according to the portrait data corresponding to the actual location information and the actual time information; determining the actual prompt according to the content category whose user tag weight is greater than or equal to the preset weight; wherein one content category corresponds to at least one actual prompt; The actual prompt is displayed according to the first display information.

6. A prompt generating device, characterized in that: include: A receiving unit, configured to receive first information sent by an electronic device; a processing unit, configured to determine a user portrait according to identification information in the first information obtained by the receiving unit, when the first information obtained by the receiving unit includes operation information; wherein the operation information includes any one of voice information lacking entity words and indication information indicating that the electronic device has received a first operation, and the user portrait is generated based on historical voice data, historical operation data, and historical question and answer data corresponding to the identification information; The processing unit is further used to determine the portrait data corresponding to the actual location information and the actual time information according to the user portrait, the actual location information and the actual time information; The processing unit is further used to determine a content classification whose user tag weight is greater than or equal to a preset weight based on the portrait data corresponding to the actual location information and the actual time information; The processing unit is further used to determine the actual prompt word according to the content category whose user tag weight is greater than or equal to the preset weight; wherein one content category corresponds to at least one actual prompt word; The processing unit is further used to control the sending unit to send first display information carrying the actual prompt to the electronic device; wherein the first display information is used to instruct the electronic device to display the actual prompt.

7. A prompt generating device, characterized in that: include: a processing unit, configured to control the sending unit to send first information to the server in response to the first operation; wherein the first information includes identification information, actual location information, actual time information, and operation information, and the operation information includes any one of voice information lacking entity words and indication information indicating that the electronic device has received the first operation; A receiving unit is used to receive a first display message carrying an actual prompt sent by the server; wherein, the first display message is used to instruct the electronic device to display the actual prompt, and the process of determining the actual prompt includes: determining the portrait data corresponding to the actual location information and the actual time information based on the user portrait, the actual location information and the actual time information; determining a content category whose user tag weight is greater than or equal to a preset weight based on the portrait data corresponding to the actual location information and the actual time information; determining the actual prompt based on the content category whose user tag weight is greater than or equal to the preset weight; wherein one content category corresponds to at least one actual prompt.

8. An electronic device, characterized in that: include: A memory and a processor, wherein the memory is used to store a computer program; and the processor is used to, when executing the computer program, enable the electronic device to execute the prompt generation method described in any one of claims 1 to 4, or enable the electronic device to execute the prompt generation method described in claim 5.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a computing device, the computing device executes the prompt generation method described in any one of claims 1 to 4, or the computing device executes the prompt generation method described in claim 5.

Images