CN111552794B - Prompt generation method, device, equipment and storage medium - Google Patents
Prompt generation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN111552794B CN111552794B CN202010400858.2A CN202010400858A CN111552794B CN 111552794 B CN111552794 B CN 111552794B CN 202010400858 A CN202010400858 A CN 202010400858A CN 111552794 B CN111552794 B CN 111552794B
- Authority
- CN
- China
- Prior art keywords
- service type
- user
- service
- prompt
- text information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000006870 function Effects 0.000 claims description 33
- 238000013145 classification model Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 5
- 230000006399 behavior Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 239000013598 vector Substances 0.000 description 7
- 230000000694 effects Effects 0.000 description 4
- 238000011176 pooling Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000000366 juvenile effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The application provides a prompt generation method, a device, equipment and a storage medium. The method comprises the following steps: responding to the operation of a user, and determining a first service type corresponding to a current scene of the electronic equipment; generating a prompt according to the semantic template corresponding to the first service type and the keyword corresponding to the first service type; and displaying the prompt on a display interface of the electronic equipment. According to the embodiment of the application, the prompt is generated aiming at the service type corresponding to the current scene of the equipment, so that the prompt is more targeted, the accuracy of the voice request of the user can be improved, and the user experience is improved.
Description
Technical Field
The present application relates to the field of natural language processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for generating a prompt.
Background
Along with the continuous improvement of the living standard of people and the rapid development of artificial intelligence technology, the demands of people on intelligent household appliances are also increasing, wherein a television is one of the most common household appliances in daily life, and has also changed significantly, and the intelligent television can integrate functions of video, entertainment, games and the like into a whole through the internet technology at present. In order to improve the convenience of television operation, an intelligent voice assistant has been developed, and user experience is improved to a great extent.
In the actual use process of the intelligent voice assistant, many voice requests of the user do not obtain the expected feedback result, generally because the requests of the user are not standard or spoken too much, and the equipment cannot be identified. In order to solve the problems, a voice prompt function is provided on many smart televisions, and when a user uses a voice assistant function, text information similar to "you can say so" is displayed on the television to guide the user to correctly express a voice request. At present, a voice prompt is mainly obtained and generated from a text library, a manufacturer maintains text information of the voice prompt into the text library in advance, and when a user makes a voice request, a plurality of texts are obtained from the text library randomly or fixedly and displayed on an interface. In the above scheme, the displayed prompt may not be wanted by the user, and the prompting effect is poor.
Disclosure of Invention
The application provides a prompt generation method, a device, equipment and a storage medium, so as to generate a prompt closer to the requirements of users and improve the user experience.
In a first aspect, the present application provides a method for generating a prompt, including:
responding to the operation of a user, and determining a first service type corresponding to a current scene of the electronic equipment;
generating a prompt according to the semantic template corresponding to the first service type and the keyword corresponding to the first service type;
and displaying the prompt on a display interface of the electronic equipment.
In a second aspect, the present application provides a cue generation apparatus, including:
the determining module is used for responding to the operation of the user and determining a first service type corresponding to the current scene of the electronic equipment;
the processing module is used for generating a prompt according to the semantic template corresponding to the first service type and the keyword corresponding to the first service type;
and the display module is used for displaying the prompt on a display interface of the electronic equipment.
In a third aspect, embodiments of the present application provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any of the first aspects.
In a fourth aspect, an embodiment of the present application provides an electronic device, including:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the method of any of the first aspects via execution of the executable instructions.
According to the prompt generation method, device, equipment and storage medium provided by the embodiment of the application, when the prompt is generated, the corresponding service type, the semantic template corresponding to the service type and the keyword are selected in combination with the scene where the equipment is currently located, and the generated prompt is closer to the user requirement, so that the user experience is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.
FIG. 1 is an application scenario diagram according to an embodiment of the present application;
FIG. 2 is a flowchart illustrating an embodiment of a method for generating a reminder according to the present application;
FIG. 3 is a schematic illustration of a main page of an embodiment provided by the present application;
FIG. 4 is a schematic diagram of a specific business function scenario according to an embodiment of the present application;
FIG. 5 is a schematic diagram of an embodiment of a method for generating a hint provided by the present application;
FIG. 6 is a schematic diagram of an embodiment of a prompt generation apparatus according to the present application;
fig. 7 is a schematic structural diagram of an embodiment of an electronic device provided by the present application.
Specific embodiments of the present disclosure have been shown by way of the above drawings and will be described in more detail below. These drawings and the written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the disclosed concepts to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.
The terms "comprising" and "having" and any variations thereof in the description and claims of the application and in the drawings are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
The concept of the present application will be described with reference to the accompanying drawings. It should be noted that the following descriptions of the concepts are only for making the content of the present application easier to understand, and do not represent a limitation on the protection scope of the present application.
The term "module" as used in various embodiments of the present application may refer to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and/or software code that is capable of performing the function associated with that element.
The term "remote control" as used in the various embodiments of the present application refers to a component of an electronic device (such as a display device as disclosed herein) that can typically wirelessly control the electronic device over a relatively short distance. The assembly may be connected to the electronic device generally using infrared and/or Radio Frequency (RF) signals and/or bluetooth, and may also include functional modules such as WiFi, wireless USB, bluetooth, motion sensors, etc. For example: the hand-held touch remote controller replaces most of the physical built-in hardware in a general remote control device with a touch screen user interface.
Fig. 1 is an application scenario of an embodiment of the present application. As shown in fig. 1, a user can operate an electronic apparatus 200 through a control device 100. Among other things, the electronic device 200 may include: display devices such as televisions, projectors, etc.
The control device 100 may be a remote controller 100A, which may communicate with the electronic device 200 through infrared protocol communication, bluetooth protocol communication, zigBee protocol communication, or other short-range communication methods, and is used to control the electronic device 200 through wireless or other wired methods. The user may control the electronic device 200 by inputting user instructions through keys, voice input, control panel input, etc. on the remote control 100A. Such as: the user may input corresponding control instructions through volume up-down keys, channel control keys, up/down/left/right movement keys, voice input keys, menu keys, on-off keys, etc. on the remote controller 100A to realize the functions of the control electronic device 200.
The control apparatus 100 may also be an intelligent device, such as a mobile terminal 100B, a tablet computer, a notebook computer, etc., which may communicate with the electronic device 200 through a local area network (LAN, local Area Network), a wide area network (WAN, wide Area Network), a wireless local area network (WLAN, wireless Local Area Network), or other networks, and control the electronic device 200 through an application program corresponding to the electronic device 200. For example, the electronic device 200 is controlled using an application running on a smart device. The application may provide various controls to the User through an intuitive User Interface (UI) on a screen associated with the smart device.
For example, the mobile terminal 100B and the electronic device 200 may each install a software application, so that connection communication between the two may be implemented through a network communication protocol, thereby achieving the purpose of one-to-one control operation and data communication. Such as: the mobile terminal 100B and the electronic device 200 can be made to establish a control instruction protocol, the remote control keyboard is synchronized to the mobile terminal 100B, and the functions of controlling the electronic device 200 are realized by controlling the user interface on the mobile terminal 100B; the audio/video content displayed on the mobile terminal 100B may also be transmitted to the electronic device 200, so as to implement a synchronous display function.
As shown in fig. 1, the electronic device 200 may also be in data communication with the server 300 via a variety of communication means. In various embodiments of the application, the electronic device 200 may be permitted to make a wired or wireless communication connection with the server 300 via a local area network, a wireless local area network, or other network. The server 300 may provide various content and interactions to the electronic device 200.
The electronic device 200, by way of example, receives software program updates by sending and receiving information, and by way of electronic program guide (EPG, electronic Program Guide) interactions, or accesses a remotely stored digital media library. The servers 300 may be one group, may be multiple groups, and may be one or more types of servers. Other web service content such as video on demand and advertising services are provided through the server 300.
The display device of the electronic apparatus 200 may be a liquid crystal display, a OLED (Organic Light Emitting Diode) display, or a projection display; on the other hand, the display device can also be a display system formed by the intelligent television or the display and the set top box. The particular display device type, size, resolution, etc. are not limited, and those skilled in the art will appreciate that the electronic device 200 may be subject to some variations in performance and configuration as desired.
The electronic device 200 may additionally provide an intelligent network television function of a computer support function in addition to the broadcast receiving television function. Examples include web tv, smart tv, internet Protocol Tv (IPTV), etc. In some embodiments, the display device may not have a broadcast receiving television function.
In other examples, more functions may be added or the above functions may be reduced. The function of the electronic device is not particularly limited by the present application.
At present, in order to improve the convenience of electronic equipment such as television operation, an intelligent voice assistant is generated, so that the user experience is improved to a great extent. For example, an intelligent voice assistant is installed on a remote controller of the television, a user presses a key on the remote controller, the remote controller collects voice output by the user, the remote controller sends a voice signal to the television, and the television performs corresponding operation according to the voice signal. Or, the intelligent voice assistant is directly installed on the television, the user triggers the intelligent voice assistant on the television to collect the voice output by the user through the operation of the remote controller, and corresponding operation is carried out according to the voice of the user.
In the actual use process of the intelligent voice assistant, many voice requests of the user do not obtain the expected feedback result, generally because the requests of the user are not standard or spoken too much, and the equipment cannot be identified. In order to solve the problems, a voice prompt function is provided on many smart televisions, and when a user uses a voice assistant function, text information similar to "you can say so" is displayed on the television to guide the user to correctly express a voice request. At present, a voice prompt is mainly obtained and generated from a text library, a manufacturer maintains text information of the voice prompt into the text library in advance, and when a user makes a voice request, a plurality of texts are obtained from the text library randomly or fixedly and displayed on an interface. In the above scheme, the displayed prompt may not be wanted by the user, and the prompting effect is poor.
The inventors found during the course of the study that: the prompt information generated in the scheme does not distinguish specific application scenes, the content of the prompt is always unchanged, and the prompt is not carried out aiming at the content which is the most concerned by the user, so that when the user operates the television according to the voice request of the prompt, the user can not obtain the expected feedback result, and the experience is poor.
According to the method provided by the embodiment of the application, the service type corresponding to the current scene of the equipment and the semantic template and the keyword corresponding to the service type are selected, the prompt is generated, the current scene of the equipment is considered, the prompt is closer to the user requirement, and the user experience is improved.
The method provided by the application can be realized by the execution of the corresponding software code by the electronic equipment such as a processor, or can be realized by the execution of the corresponding software code by the electronic equipment and the data interaction with a server, for example, the execution of partial operation by the server, so as to control the electronic equipment to execute the prompt generation method.
The technical scheme of the application is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
Fig. 2 is a flowchart of an embodiment of a method for generating a prompt in the present application. As shown in fig. 2, the method provided in this embodiment includes:
step 101, responding to the operation of a user, and determining a first service type corresponding to a scene where the electronic equipment is currently located.
Specifically, the operation of the user is received, for example, by pressing a key of the remote controller, the electronic device is triggered to display a prompt of the voice request of the user.
The electronic device first determines a current scene of the device, for example, as shown in fig. 3, if the television is in a home page scene of starting up; or as shown in fig. 4, the television is positioned on the front page of a certain video APP and is positioned in a video service function scene; or a page at a certain weather app, in a weather service function scenario, etc.
The corresponding first service type is determined according to the current scene, for example, the first service type corresponding to the main page scene may be video service, weather service, etc., and the service types may be more frequently used service types by the user, or service types used in the last period of time by the user, or service types used more by other users, namely popular service types, etc.
In an embodiment, the first service type corresponding to the current scene of the electronic device is obtained according to historical behavior data of the user.
Step 102, generating a prompt according to the semantic template corresponding to the first service type and the keyword corresponding to the first service type.
Step 103, displaying a prompt on a display interface of the electronic equipment.
Specifically, before the semantic templates are selected, templates of different service types need to be configured correspondingly in the device. Semantic templates under different service types may be different, such as the weather of the weather service's template "[ place name ] [ date ]," the television control service's template "[ action ] [ device ]. However, for some more complex services, such as "video", a unified semantic template may not be used, and further differentiation according to a slot rule is required, and a plurality of slot rules may be preset, which is exemplified as follows.
TABLE 1 film and television service semantic template partitioning
For example, the determined first service type is a movie service, the corresponding semantic templates under the movie service are matched, for example, the intention information of the user obtained by analysis by using a machine learning model (the intention information of the user can be obtained according to historical behavior data, for example, the historical behavior data comprises text information of a voice request before the user) is matched with the corresponding semantic templates under the movie service and keywords corresponding to the movie service, for example, keywords frequently searched by the user or hot keywords searched by other users, and the keywords can be hot content from persistence into a text library.
And matching the keywords with the semantic templates, generating prompt languages, and displaying the prompt languages on a display interface of the electronic equipment so as to prompt a user to send a voice request by referring to the prompt languages.
For example, the following prompts are displayed on the television: you can say as such "a television show suitable for [ whole family ]; [ national celebration section ] is suitable to see [ domestic ] [ film ]; [ celebration for the rest of the year ] [ group 2 ].
According to the method, when the prompt is generated, the corresponding service type is selected in combination with the scene where the equipment is currently located, and the semantic templates and keywords corresponding to the service type, so that the generated prompt is closer to the user requirements, and the user experience is improved.
On the basis of the above embodiment, further, step 101 may be implemented as follows:
acquiring the search probability of each second service type corresponding to the user; the second service type comprises the first service type;
and determining the first service type corresponding to the current scene of the electronic equipment according to the search probability of each second service type.
Specifically, the first service type corresponding to the current scene of the electronic device may be determined according to the use condition of the user, for example, the frequency of the user requesting each second service type through voice in the preset duration range may be obtained, for example, the frequency may also be represented by searching probability.
For example, the number of voice requests of the user in a week is 30, the frequency of weather service is 7, and the corresponding search probability is 23%; the frequency of the control service is 6 times, and the corresponding search probability is 20%; the frequency of video traffic was 17 times, corresponding to a search probability of 57%.
Wherein, the frequency of the video service is 8 times, and the corresponding searching probability is 47%; the frequency of the variety service is 6 times, and the corresponding searching probability is 35%; the frequency of the child animation service is 3 times, and the corresponding searching probability is 18%.
If the current scene is a main page scene, the corresponding first service types include a plurality of service types with high probability or the service types with top search probability, such as video service and weather service;
if the current scene is a video service functional scene, the corresponding first service types include a plurality of service types with high probability, such as video service, variety service, and the like.
In an embodiment, if the current scene of the electronic device is a main page scene, taking at least one second service type with a search probability corresponding to the user being greater than or equal to a first preset value as the first service type;
and if the current scene of the electronic equipment is a service function scene, taking at least one second service type with the searching probability larger than or equal to a second preset value in the service function scene as the first service type.
Specifically, if the current scene of the electronic device is a main page scene, one or more second service types with larger searching probability corresponding to the user in the second service types are selected as the first service types, for example, one or more service types with searching probability larger than a certain preset value. The second service types may be ranked according to a search probability, for example, in descending order, and when determining a service type corresponding to a current scene, the first service types may be selected directly, or one or more service types with a search probability greater than a certain preset value may be selected.
For example, 39% of film and television service, 28% of variety service, 18% of weather service and 15% of control service, and determining that the first service type corresponding to the current scene comprises film and television service and variety service.
If the current scene of the electronic device is a service function scene, selecting one or more second service types with larger searching probability corresponding to the user from the second service types under the service function scene as the first service type, for example, one or more service types with searching probability larger than a certain preset value.
For example, the current scene of the electronic device is a service function scene and is a video service function scene, under the video service function scene, 39% of video service, 28% of child animation, 18% of variety service and 15% of sports, and then the first service type corresponding to the current scene is determined to include video service and child animation.
In the above embodiment, the result of the analysis of the user behavior, that is, the search probability of the service type corresponding to the user is used to select the service type in the current scene, and then the corresponding prompt is generated by combining with the configured semantic template. The prompt can meet the requirement of standardization of the voice request, and can give personalized recommended content by combining the preference and habit of the user.
In one embodiment, step 102 may be implemented as follows:
acquiring a semantic template and a keyword corresponding to a first service type;
and matching the keywords corresponding to the first service type with the semantic templates corresponding to the first service type to generate prompt.
Specifically, when the user uses the voice request function, the service types with the top ranking (with higher probability) and the hot content, such as keywords, focused by the user are automatically acquired. And reading the corresponding semantic templates from the semantic templates through the service types, and filling the hot content serving as a keyword into the slots of the semantic templates to generate the prompt finally displayed on the television.
The semantic template corresponding to a certain service type is selected by the following method:
and selecting at least one semantic template with the use probability larger than or equal to a third preset value corresponding to the first service type.
Specifically, different service types may have multiple semantic simulations, and may further obtain, in advance, use probabilities of respective semantic templates corresponding to respective service types, for example, obtain text information of a voice request of a user in a period of time (for example, half a year, a month, half a month, etc.), determine service types to which the text information belongs, and semantic templates corresponding to the text information, and may further obtain search probabilities of respective service types, and use probabilities of respective semantic templates under each service type. Such as by the user behavior analysis model process of fig. 5.
And selecting a semantic template with larger use probability under the first service type, for example, using one or more service types with probability larger than a certain preset value. The semantic templates under the first service type may be ranked according to the use probability, for example, in descending order, and when the semantic templates corresponding to the first service type are selected, the first few semantic templates may be selected directly, or one or more semantic templates with use probabilities greater than a certain preset value may be selected.
In the above embodiment, the result of the analysis on the user behavior is used to select the service type in the current scene, and select the semantic template corresponding to the service type to generate the corresponding prompt. The prompt can meet the requirement of standardization of the voice request, and can give personalized recommended content by combining the preference and habit of the user.
In one embodiment, text information of a voice request of a user in a preset duration range is acquired;
and extracting characteristic information of the text information, and acquiring search probability of each second service type corresponding to the text information according to the characteristic information of the text information.
Specifically, determining the search probability of each second service type may be implemented by a server, where the server obtains text information of a voice request of a user within a preset duration range, for example, as shown in fig. 5, processes the text information by a user behavior analysis model (e.g., obtained by training a machine learning model) to obtain the search probability of each second service type corresponding to the text information, and sends the search probability of each second service type to an electronic device. Meanwhile, the user behavior analysis model can also obtain keywords under each service type.
The results obtained by the user behavior analysis model may form corresponding statistical results to be stored, for example, in a database.
The keywords may also be obtained by analyzing text information of a user voice request in a preset duration range by the server, for example, may be implemented in the following manner:
acquiring words with occurrence probability larger than or equal to a third preset value in text information corresponding to the second service type;
and taking the words as keywords corresponding to the second service type.
In other embodiments, the keywords may also be keywords when other users request the service type through voice.
In one embodiment, determining the search probabilities for the respective traffic types may be accomplished by:
extracting characteristic information of the text information by using a text classification model obtained by training in advance;
and acquiring the search probability of each second service type corresponding to the text information by utilizing the text classification model according to the characteristic information of the text information.
In one embodiment, the text information of the user's voice request may be processed through a text classification model, such as a textCNN model, that includes, for example, a word embedding layer, a convolution layer, a pooling layer, and a classification layer.
The following is an example of the processing of text information of a voice request from a user: firstly, word segmentation processing is carried out on text information of a voice request of a user through a word embedding layer, a plurality of meaningless symbols or texts are removed to obtain segmented words such as play, celebration rest years and back ancient poems, then each word is mapped into a multidimensional word vector through word2vec, GLOV and other word embedding empedding modes for digitizing natural language, after the word vector is built, all word vectors are spliced into a two-dimensional vector and input into a convolution layer and a pooling layer, the convolution layer can comprise multiple layers, the pooling layer carries out maximum pooling processing for example, a vector is output, the vector represents characteristic information of the extracted text information, and finally the vector is input into a classification layer and processed through a softmax classifier for obtaining a service type corresponding to the text information, for example, the service belongs to video services.
In addition, the text classification model is used for processing the plurality of text information to obtain the search probability of each service type, for example, the text information has 100 pieces, the service type corresponding to 30 pieces of text information is video service, the service type corresponding to 20 pieces of text information is weather service, the service type corresponding to 15 pieces of text information is control service, and the service type corresponding to 35 pieces of text information is music service.
The video service may be further subdivided, such as a movie service, a variety service, a juvenile animation service, etc. For example, "play celebration afteryear ancient poems" belong to the movie and television service in video services.
In addition, word frequency information can be obtained through a text classification model, and the occurrence frequency of different words is obtained. And finally, storing the analyzed service type and the analyzed hot word frequency into a database, and storing the analyzed service type and the analyzed hot word frequency into electronic equipment.
The process can also be adopted, and the pre-established text classification model is trained through the collected training data to obtain the text classification model. The pre-established text classification model is established by an algorithm model such as a neural network.
The server extracts text information of all voice requests in the last half month or one month on the device through the MAC address of the television, analyzes the service type (video, music, weather, encyclopedia, etc.) to which the text information of each voice request belongs and the occurrence frequency of the service type by using a textCNN model, for example, when the text of the voice request of the user is 'weather today of the martial arts', determines that the service type corresponding to the text is 'weather' through iterative analysis of a text classification model, and the keyword is 'martial arts'.
By the method, the text information of all voice requests is classified according to the service types, the occurrence probability of each service type is calculated, and meanwhile, the keywords which appear under the service types are extracted and stored through the following statistical table.
Table 2 voice search statistics
As shown in fig. 5, the electronic device determines, in response to the operation of the user, whether the current scene corresponds to a specific service function scene, and if not, indicates that the current scene is a main page scene (as shown in fig. 3), then selects a plurality of service types with top ranking as a first service type, that is, selects a plurality of service types with high searching probability as the first service type, that is, selects a service type corresponding to the current scene according to the intention of the user (such as the intention of the user obtained by speculating according to the historical behavior data of the user); if yes, selecting the service type ranked at the top in the service function scene as a first service type; furthermore, selecting a semantic template corresponding to the first service type, for example, selecting a semantic template frequently used by the user under the first service type from a semantic template library; and matching the keyword corresponding to the first service type with the semantic template to generate a prompt. For example, i want to see the last phase of the third season of the limit challenge (keywords such as limit challenge).
In the scheme, the text classification model is utilized to determine focus of attention in a last period of time of a user, wherein the focus comprises a service type and keywords, and a corresponding prompt is generated by combining with the configured semantic template. The prompt can meet the requirement of standardization of the voice request, and can give personalized recommended content by combining the preference and habit of the user.
According to the scheme, the personalized prompt can be automatically generated by analyzing the voice request of the user, the user is guided to learn various voice speaking methods, the habit of using voice to operate the television by the user is cultivated, and the user experience is improved.
Fig. 6 is a schematic structural diagram of an embodiment of a prompt generating device provided by the present application, as shown in fig. 6, where the prompt generating device of the present embodiment includes:
the determining module is used for responding to the operation of the user and determining a first service type corresponding to the current scene of the electronic equipment;
the processing module is used for generating a prompt according to the semantic template corresponding to the first service type and the keyword corresponding to the first service type;
and the display module is used for displaying the prompt on a display interface of the electronic equipment.
In one possible implementation manner, the determining module is specifically configured to:
acquiring the search probability of each second service type corresponding to the user; the second service type comprises the first service type;
and determining the first service type corresponding to the current scene of the electronic equipment according to the search probability of each second service type.
In one possible implementation manner, the determining module is specifically configured to:
if the current scene of the electronic equipment is a main page scene, taking at least one second service type with the searching probability corresponding to the user being greater than or equal to a first preset value as the first service type;
and if the current scene of the electronic equipment is a service function scene, taking at least one second service type with the searching probability larger than or equal to a second preset value in the service function scene as the first service type.
In one possible implementation manner, the determining module is specifically configured to:
acquiring text information of a voice request of the user within a preset duration range;
extracting characteristic information of the text information, and acquiring search probability of each second service type corresponding to the text information according to the characteristic information of the text information.
In one possible implementation manner, the determining module is specifically configured to:
extracting characteristic information of the text information by using a text classification model obtained by training in advance;
and acquiring the search probability of each second service type corresponding to the text information by utilizing the text classification model according to the characteristic information of the text information.
In one possible implementation, the processing module is specifically configured to:
acquiring a semantic template and a keyword corresponding to the first service type;
and matching the keywords corresponding to the first service type with the semantic templates corresponding to the first service type to generate the prompt.
In one possible implementation, the processing module is specifically configured to:
and selecting at least one semantic template with the use probability larger than or equal to a third preset value corresponding to the first service type.
The device of the present embodiment may be used to execute the technical solution of the foregoing method embodiment, and its implementation principle and technical effects are similar, and are not described herein again.
Fig. 7 is a block diagram of an embodiment of an electronic device according to the present application, as shown in fig. 7, where the electronic device includes:
a processor 701, and a memory 702 for storing executable instructions of the processor 701.
Optionally, the method may further include: a display screen 703 for displaying the generated prompt.
The components may communicate via one or more buses.
The processor 701 is configured to execute the corresponding method in the foregoing method embodiment by executing the executable instruction, and the specific implementation process of the processor may refer to the foregoing method embodiment and will not be described herein.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, the computer program when executed by a processor implements a method corresponding to the foregoing method embodiment, and the specific implementation process of the computer program may refer to the foregoing method embodiment, and its implementation principle and technical effect are similar, and will not be repeated herein.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (9)
1. A cue generation method, comprising:
responding to the operation of a user, and determining a first service type corresponding to a current scene of the electronic equipment;
generating a prompt according to the semantic template corresponding to the first service type and the keyword corresponding to the first service type;
displaying the prompt on a display interface of the electronic equipment;
the determining the first service type corresponding to the current scene of the electronic device includes:
acquiring the search probability of each second service type corresponding to the user; the second service type comprises the first service type;
and determining the first service type corresponding to the current scene of the electronic equipment according to the search probability of each second service type.
2. The method of claim 1, wherein determining the first service type corresponding to the current scene of the electronic device according to the search probability of each of the second service categories comprises:
if the current scene of the electronic equipment is a main page scene, taking at least one second service type with the searching probability corresponding to the user being greater than or equal to a first preset value as the first service type;
and if the current scene of the electronic equipment is a service function scene, taking at least one second service type with the searching probability larger than or equal to a second preset value in the service function scene as the first service type.
3. The method according to claim 1 or 2, wherein the obtaining the search probability of each second service type corresponding to the user includes:
acquiring text information of a voice request of the user within a preset duration range;
extracting characteristic information of the text information, and acquiring search probability of each second service type corresponding to the text information according to the characteristic information of the text information.
4. The method of claim 3, wherein the extracting feature information of the text information and obtaining the search probability of each second service type corresponding to the text information according to the feature information of the text information comprises:
extracting characteristic information of the text information by using a text classification model obtained by training in advance;
and acquiring the search probability of each second service type corresponding to the text information by utilizing the text classification model according to the characteristic information of the text information.
5. The method according to claim 1 or 2, wherein the generating a prompt according to the semantic template corresponding to the first service type and the keyword corresponding to the first service type includes:
acquiring a semantic template and a keyword corresponding to the first service type;
and matching the keywords corresponding to the first service type with the semantic templates corresponding to the first service type to generate the prompt.
6. The method of claim 3, wherein the obtaining the semantic template corresponding to the first service type comprises:
and selecting at least one semantic template with the use probability larger than or equal to a third preset value corresponding to the first service type.
7. A cue generation apparatus, comprising:
the determining module is used for responding to the operation of the user and determining a first service type corresponding to the current scene of the electronic equipment;
the processing module is used for generating a prompt according to the semantic template corresponding to the first service type and the keyword corresponding to the first service type;
the display module is used for displaying the prompt on a display interface of the electronic equipment;
the determining module is specifically configured to obtain a search probability of each second service type corresponding to the user; the second service type comprises the first service type; and determining the first service type corresponding to the current scene of the electronic equipment according to the search probability of each second service type.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method of any of claims 1-6.
9. An electronic device, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the method of any of claims 1-6 via execution of the executable instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010400858.2A CN111552794B (en) | 2020-05-13 | 2020-05-13 | Prompt generation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010400858.2A CN111552794B (en) | 2020-05-13 | 2020-05-13 | Prompt generation method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111552794A CN111552794A (en) | 2020-08-18 |
| CN111552794B true CN111552794B (en) | 2023-09-19 |
Family
ID=72001563
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010400858.2A Active CN111552794B (en) | 2020-05-13 | 2020-05-13 | Prompt generation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111552794B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112927686A (en) * | 2021-01-20 | 2021-06-08 | 北京奇艺世纪科技有限公司 | Voice recommendation language display method, device and system and electronic equipment |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008153625A2 (en) * | 2007-05-25 | 2008-12-18 | Peerset Inc. | Recommendation systems and methods |
| CN107277225A (en) * | 2017-05-04 | 2017-10-20 | 北京奇虎科技有限公司 | Method, device and the smart machine of Voice command smart machine |
| CN108206883A (en) * | 2016-12-20 | 2018-06-26 | 北京小米移动软件有限公司 | The method and device of terminal notifying |
| CN108428450A (en) * | 2017-02-15 | 2018-08-21 | 阿里巴巴集团控股有限公司 | A kind of operational order processing method and processing device |
| WO2019007245A1 (en) * | 2017-07-04 | 2019-01-10 | 阿里巴巴集团控股有限公司 | Processing method, control method and recognition method, and apparatus and electronic device therefor |
| CN109325097A (en) * | 2018-07-13 | 2019-02-12 | 海信集团有限公司 | A kind of voice guide method and device, electronic equipment, storage medium |
| WO2019119771A1 (en) * | 2017-12-20 | 2019-06-27 | 深圳Tcl新技术有限公司 | Voice interaction method, device and computer readable storage medium |
| CN110046230A (en) * | 2018-12-18 | 2019-07-23 | 阿里巴巴集团控股有限公司 | Generate the method for recommending words art set, the method and apparatus for recommending words art |
| CN110377195A (en) * | 2019-07-15 | 2019-10-25 | 腾讯科技（深圳）有限公司 | The method and apparatus for showing interactive function |
| CN110737840A (en) * | 2019-10-22 | 2020-01-31 | 青岛海信电器股份有限公司 | Voice control method and display device |
| CN110910872A (en) * | 2019-09-30 | 2020-03-24 | 华为终端有限公司 | Voice interaction method and device |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140115456A1 (en) * | 2012-09-28 | 2014-04-24 | Oracle International Corporation | System for accessing software functionality |
| KR20140089861A (en) * | 2013-01-07 | 2014-07-16 | 삼성전자주식회사 | display apparatus and method for controlling the display apparatus |
| CN106557461B (en) * | 2016-10-31 | 2019-03-12 | 百度在线网络技术（北京）有限公司 | Semantic analyzing and processing method and device based on artificial intelligence |
| CN108347646B (en) * | 2018-03-20 | 2019-07-02 | 百度在线网络技术（北京）有限公司 | Multimedia content playing method and device |
-
2020
- 2020-05-13 CN CN202010400858.2A patent/CN111552794B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008153625A2 (en) * | 2007-05-25 | 2008-12-18 | Peerset Inc. | Recommendation systems and methods |
| CN108206883A (en) * | 2016-12-20 | 2018-06-26 | 北京小米移动软件有限公司 | The method and device of terminal notifying |
| CN108428450A (en) * | 2017-02-15 | 2018-08-21 | 阿里巴巴集团控股有限公司 | A kind of operational order processing method and processing device |
| CN107277225A (en) * | 2017-05-04 | 2017-10-20 | 北京奇虎科技有限公司 | Method, device and the smart machine of Voice command smart machine |
| WO2019007245A1 (en) * | 2017-07-04 | 2019-01-10 | 阿里巴巴集团控股有限公司 | Processing method, control method and recognition method, and apparatus and electronic device therefor |
| WO2019119771A1 (en) * | 2017-12-20 | 2019-06-27 | 深圳Tcl新技术有限公司 | Voice interaction method, device and computer readable storage medium |
| CN109325097A (en) * | 2018-07-13 | 2019-02-12 | 海信集团有限公司 | A kind of voice guide method and device, electronic equipment, storage medium |
| CN110046230A (en) * | 2018-12-18 | 2019-07-23 | 阿里巴巴集团控股有限公司 | Generate the method for recommending words art set, the method and apparatus for recommending words art |
| CN110377195A (en) * | 2019-07-15 | 2019-10-25 | 腾讯科技（深圳）有限公司 | The method and apparatus for showing interactive function |
| CN110910872A (en) * | 2019-09-30 | 2020-03-24 | 华为终端有限公司 | Voice interaction method and device |
| CN110737840A (en) * | 2019-10-22 | 2020-01-31 | 青岛海信电器股份有限公司 | Voice control method and display device |
Non-Patent Citations (3)
| Title |
|---|
| WWW上基于概念的智能搜索;张琳;上海海运学院学报(04);全文 * |
| 基于用户场景理念下的语音交互设计研究;黄升;靳文奎;;设计(09);全文 * |
| 有线网络智能语音搜索能力***建设与应用;何晓峰;丁浩;;广播与电视技术(05);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111552794A (en) | 2020-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110737840B (en) | Voice control method and display device | |
| CN109325097B (en) | Voice guide method and device, electronic equipment and storage medium | |
| CN111372109B (en) | Intelligent television and information interaction method | |
| US11409817B2 (en) | Display apparatus and method of controlling the same | |
| JP6272553B2 (en) | Smart TV interaction control system and method based on image recognition | |
| CN112163086B (en) | Multi-intention recognition method and display device | |
| CN112000820A (en) | Media asset recommendation method and display device | |
| WO2022032916A1 (en) | Display system | |
| CN111901656B (en) | Media data searching method, display equipment and server | |
| CN106412713B (en) | Interactive information publishing method and device | |
| CN109144285A (en) | A kind of input method and device | |
| CN109600646B (en) | Voice positioning method and device, smart television and storage medium | |
| CN116261857A (en) | Display equipment and application program interface display method | |
| CN111984763A (en) | Question answering processing method and intelligent equipment | |
| CN111625716A (en) | Media asset recommendation method, server and display device | |
| CN111552794B (en) | Prompt generation method, device, equipment and storage medium | |
| CN106060641A (en) | Display apparatus for searching and control method thereof | |
| CN103248942B (en) | Visualize the update method and updating device of the rendition list | |
| CN115240665A (en) | Display apparatus, control method, and storage medium | |
| CN111950288B (en) | Entity labeling method in named entity recognition and intelligent device | |
| CN111344664B (en) | Electronic apparatus and control method thereof | |
| CN114627864A (en) | Display device and voice interaction method | |
| CN111858856A (en) | Multi-round search type chatting method and display equipment | |
| CN111159467A (en) | Method and equipment for processing information interaction | |
| CN112883144A (en) | Information interaction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |