CN109948155B

CN109948155B - Multi-intention selection method and device and terminal equipment

Info

Publication number: CN109948155B
Application number: CN201910186088.3A
Authority: CN
Inventors: 魏誉荧
Original assignee: Guangdong Genius Technology Co Ltd
Current assignee: Guangdong Genius Technology Co Ltd
Priority date: 2019-03-12
Filing date: 2019-03-12
Publication date: 2023-06-30
Anticipated expiration: 2039-03-12
Also published as: CN109948155A

Abstract

The invention discloses a multi-intention selecting method and device and terminal equipment, and relates to the field of terminal equipment, wherein the multi-intention selecting method comprises the following steps: acquiring corpus of a user; semantic analysis is carried out on the corpus, and keywords representing the intention of the user are extracted; matching corresponding intents according to the keywords; when the keyword corresponds to a plurality of intentions, an intention corresponding to an application program which stays when a corpus is acquired is selected from the plurality of intentions as a target intention. When the terminal equipment matches a plurality of intentions according to the corpus of the user, the terminal equipment can select the target intention according to the application program which stays when the corpus of the user is input, and the accuracy of the target intention is improved according to the use scene, so that the satisfaction degree and the use experience of the user are improved.

Description

Multi-intention selection method and device and terminal equipment

Technical Field

The present invention relates to the field of terminal devices, and in particular, to a multi-purpose selection method and apparatus, and a terminal device.

Background

With the rapid development of voice recognition technology, the control mode of terminal devices (such as mobile phones, tablet computers, home education learning machines and the like) is increased with voice control besides traditional manual control of touch screens, keys and the like, for example: by talking to Siri, the apple iOS system opens a map application, etc.

The current terminal device can only give a corresponding result according to the rule defined by the rule for the voice command of the user, for example: if the user says "I want to watch time", the terminal device will typically call the interface of the clock to the user to watch time.

However, in a specific application scenario, the corpus spoken by the user may correspond to the content of other applications, for example: under the scene that the user uses the terminal equipment to read the text, the corresponding possibility of 'I want to see the time' is a text name, but the current terminal equipment can not give a proper intention judgment result at present, and the matching accuracy is low.

Disclosure of Invention

The invention aims to provide a multi-intention selecting method, a multi-intention selecting device and terminal equipment, which are used for selecting the intention with the highest possibility when a plurality of intentions are matched according to the corpus of a user, so that the use experience and satisfaction of the user are improved.

The technical scheme provided by the invention is as follows:

a multi-purpose selection method, comprising the steps of: acquiring corpus of a user; carrying out semantic analysis on the corpus, and extracting keywords representing the intention of the user; matching corresponding intents according to the keywords; when the keyword corresponds to a plurality of intentions, selecting an intention corresponding to an application program which stays when the corpus is acquired from the plurality of intentions as a target intention.

In the technical scheme, when the terminal equipment matches a plurality of intentions according to the corpus of the user, the terminal equipment can select the target intention according to the application program which stays when the user inputs the corpus, and the accuracy of the target intention is improved according to the use scene, so that the satisfaction degree and the use experience of the user are improved.

Further, the method also comprises the following steps: and after the keyword corresponds to a plurality of intentions and the target intention is selected, sequencing and displaying the rest intentions according to application habit data of the user.

In the technical scheme, other intentions except the target intention can be displayed after being sequenced according to the usual application using habit data of the user, if the target intention is not really wanted by the user, the displayed other intentions can be switched by the user, the operation is simple, convenient and quick, and the using experience and satisfaction of the user are further improved.

Further, the application use habit data refers to the use duration and the use frequency of each application program used by the user.

In the technical scheme, the use duration and the use frequency can clearly reflect the use habit of the user, and the accuracy of intention matching is improved.

Further, the semantic analysis is performed on the corpus, and extracting keywords representing the intention of the user includes: and carrying out semantic analysis on the corpus through the regular expression and the semantic analysis model, and extracting keywords representing the intention of the user.

In the technical scheme, the corpus is subjected to semantic analysis through the regular expression and the semantic analysis model, and the success rate of the semantic analysis is improved through the combination of the regular expression and the semantic analysis model.

Further, the semantic analysis is performed on the corpus through a regular expression and a semantic analysis model, and the keyword for representing the intention of the user is extracted specifically as follows: matching the corpus by using a regular expression, and extracting the keywords after semantic analysis is successful when the matching degree is larger than a preset value; and when the matching degree is not greater than a preset value, analyzing the corpus by using the semantic analysis model, and extracting the keywords.

In the technical scheme, the regular expression is firstly used for analyzing, and then the semantic analysis model is used for analyzing unsuccessfully, so that the speed of semantic analysis can be improved.

The invention also provides a multi-purpose selecting device, which comprises: the corpus acquisition module is used for acquiring the corpus of the user; the semantic analysis module is used for carrying out semantic analysis on the corpus and extracting keywords representing the intention of the user; the intention matching module is used for matching corresponding intention according to the keywords; and the intention selecting module is used for selecting the intention corresponding to the application program which stays when the corpus is acquired from the plurality of intentions as a target intention when the keyword corresponds to the plurality of intentions.

Further, the method further comprises the following steps: and the intention ordering module is used for ordering and displaying the rest intentions according to application habit data of the user after the keyword corresponds to a plurality of intentions and the target intention is selected.

Further, the semantic analysis module is configured to perform semantic analysis on the corpus, and extracting keywords that characterize the intention of the user includes: the semantic analysis module performs semantic analysis on the corpus through a regular expression and a semantic analysis model, and extracts keywords representing user intention.

Further, the semantic analysis module performs semantic analysis on the corpus through a regular expression and a semantic analysis model, and the keyword for representing the intention of the user is extracted specifically as follows: the regular sub-module is used for matching the corpus by using a regular expression, and when the matching degree is larger than a preset value, semantic analysis is successful, and the keywords are extracted; and the model submodule is used for analyzing the corpus by using the semantic analysis model when the matching degree is not greater than a preset value, and extracting the keywords.

The invention also provides a terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the multi-purpose selection method as described in any one of the above when the processor runs the computer program.

Compared with the prior art, the multi-purpose selection method and device and the terminal equipment have the beneficial effects that:

when the terminal equipment matches a plurality of intentions according to the corpus of the user, the terminal equipment can select the target intention according to the application program which stays when the corpus of the user is input, and the accuracy of the target intention is improved according to the use scene, so that the satisfaction degree and the use experience of the user are improved.

Drawings

The above features, technical features, advantages and implementation manners of a multi-purpose selecting method and apparatus, terminal device will be further described below in a clear and understandable manner by describing preferred embodiments with reference to the accompanying drawings.

FIG. 1 is a flow chart of one embodiment of a multi-purpose selection method of the present invention;

FIG. 2 is a flow chart of another embodiment of the multi-purpose selection method of the present invention;

FIG. 3 is a flow chart of yet another embodiment of the multi-purpose selection method of the present invention;

FIG. 4 is a schematic diagram of one embodiment of a multi-purpose selection apparatus of the present invention;

FIG. 5 is a schematic diagram illustrating the construction of one embodiment of a terminal device of the present invention;

fig. 6 is a schematic view of another embodiment of the multi-purpose selection apparatus of the present invention.

Reference numerals illustrate:

4. the multi-intention selecting device comprises a multi-intention selecting device, a corpus acquiring module, a semantic parsing module, a 421 regular sub-module, a 422 model sub-module, a 43 intention matching module, a 44 intention selecting module, a 45 intention sorting module, a 5 terminal device, a 51 memory, a 52 computer program and a 53 processor.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

For the sake of simplicity of the drawing, the parts relevant to the present invention are shown only schematically in the figures, which do not represent the actual structure thereof as a product. Additionally, in order to facilitate a concise understanding of the drawings, components having the same structure or function in some of the drawings are depicted schematically only one of them, or only one of them is labeled. Herein, "a" means not only "only this one" but also "more than one" case.

It should be further understood that the term "and/or" as used in this specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.

In particular implementations, the terminal devices described in embodiments of the present application include, but are not limited to, other portable devices such as mobile phones, laptop computers, home teaching learning machines, or tablet computers having a touch-sensitive surface (e.g., a touch screen display and/or a touch pad). It should also be appreciated that in some embodiments, the terminal device is not a portable communication device, but rather a desktop computer having a touch-sensitive surface (e.g., a touch screen display and/or a touch pad).

In the following discussion, a terminal device including a display and a touch-sensitive surface is described. However, it should be understood that the terminal device may include one or more other physical user interface devices such as a physical keyboard, mouse, and/or joystick.

The terminal device supports various applications, such as one or more of the following: drawing applications, presentation applications, web creation applications, word processing applications, disk burning applications, spreadsheet applications, gaming applications, telephony applications, video conferencing applications, email applications, instant messaging applications, workout support applications, photo management applications, digital camera applications, digital video camera applications, web browsing applications, digital music player applications, and/or digital video player applications.

Various applications that may be executed on the terminal device may use at least one common physical user interface device such as a touch sensitive surface. One or more functions of the touch-sensitive surface and corresponding information displayed on the terminal may be adjusted and/or changed between applications and/or within the corresponding applications. In this way, the common physical architecture (e.g., touch-sensitive surface) of the terminal may support various applications with user interfaces that are intuitive and transparent to the user.

In addition, in the description of the present application, the terms "first," "second," and the like are used merely to distinguish between descriptions and are not to be construed as indicating or implying relative importance.

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description will explain the specific embodiments of the present invention with reference to the accompanying drawings. It is evident that the drawings in the following description are only examples of the invention, from which other drawings and other embodiments can be obtained by a person skilled in the art without inventive effort.

Fig. 1 shows a flowchart of an implementation of a multi-intent selection method of the present invention, which can be applied to a terminal device (e.g., a tablet computer, a home education learning machine, etc., all of which are explained by using the home education learning machine as a main language for convenience of understanding in this embodiment, but those skilled in the art understand that the multi-intent selection method can also be applied to other terminal devices as long as corresponding functions can be implemented), and the multi-intent selection method includes the following steps:

s101, acquiring corpus of a user.

Specifically, corpus is language material, and popular understanding is what the user speaks. For example: the user speaks a sentence "telephone to reddish" to his terminal device, and the content of the sentence is the corpus of the user.

The terminal equipment is provided with a microphone, can be internally arranged or externally arranged, and is determined according to the actual product design and the actual use condition. And acquiring the corpus of the user through a microphone, and enabling the terminal equipment to perform subsequent semantic analysis and intention selection.

S102, carrying out semantic analysis on the corpus, and extracting keywords representing the intention of the user.

Specifically, the meaning of the language can be understood by the meaning of the language, meaning analysis is performed on the language, namely, the meaning of the language is understood by understanding the content of the language, and the meaning of the language is analyzed.

In this embodiment, the semantic parsing of the material may use the existing semantic parsing method to extract the keywords. For example: semantic parsing of the material using regular expressions, etc.

S103, matching corresponding intents according to the keywords.

Specifically, after extracting the keywords, the terminal device matches with each application program and the content thereof in its own database, thereby obtaining the intentions corresponding to the keywords.

For example: the user says "one plus equal to several", and if the extracted keyword is also "one plus equal to several", the terminal device is related to the application program a for doing the job and also related to the application program B for laughter, and this keyword corresponds to both 1) the mathematics questions in the application program a and 2) one laughter in the application program B, so the keyword matches the corresponding intention to be the two.

And S104, when the keyword corresponds to a plurality of intentions, selecting the intentions corresponding to the application program which stays when the corpus is acquired from the intentions as target intentions.

Specifically, if the keyword matches only one intent, then this intent is the target intent. If a situation occurs in which the keyword corresponds to a plurality of intents, it is necessary to select an intention that the user most likely wants to show to the client.

The application program corresponding to the interface when the corpus is acquired is considered, and when the user uses the terminal equipment conventionally, the corpus emitted by the terminal equipment is related to the application program in use at present, so that the corresponding intention is used as the preferential intention, the actual requirement of the user is more easily closed, and the satisfaction degree of the user is improved.

For example: when the user says "one adds and equals several", the terminal device stays on the interface of the application program B related to the small joke, after the corpus is obtained and the keyword "one adds and equals several" is extracted, the terminal device matches two intentions corresponding to the keyword, namely: 1) Math questions in application A, 2) a small joke in application B, because the terminal device stays on the interface of application B when acquiring corpus, the probability of the user wanting to hear the small joke is higher, and therefore the small joke of "one plus equal to a few" in application B is taken as the target intention.

After selecting the target intention, the target intention is displayed to the user in various modes, for example: displaying characters and/or pictures; and displaying characters and/or pictures, and adding voice broadcasting and the like. If the specific display mode is defined by the user in the corpus, the user will be taken as the main choice.

For example: the user speaks "make phone call to" and the extracted keywords are "make phone call" and "small bright", only one intention is matched, namely the application program corresponding to "make phone call" is the application program C related to the phone, and when the intention is displayed, the terminal equipment directly jumps to the application program C to dial the "small bright" and wait for the interface of the terminal equipment to be connected.

Optionally, the multi-purpose selection method in this embodiment further includes the following steps:

s105, after the keyword corresponds to a plurality of intentions and the target intention is selected, sequencing and displaying the rest intentions according to application habit data of the user.

Specifically, considering that the target intention selected by the terminal device may not be really wanted by the user, the terminal device may display the matched other intentions for the user to select.

The ordered other intentions are displayed in various ways, and the specific display way is not limited, so long as the user can be prompted to have other intentions besides the target intention.

Examples of ordered intent displays are as follows: icons of other intentions are displayed at corners of an interface for displaying target intentions according to the sequence, and a user can switch the intentions by clicking the related icons; the exclamation mark may be displayed at a corner of the interface for displaying the target intention, after the user clicks the exclamation mark, the text or icon of other intention after the sorting is displayed, after the user clicks the related text or icon, the terminal device switches the intention, etc.

The application usage habit data refers to the usage duration and the usage frequency of each application program used by the user. When the user uses each application program, the terminal equipment updates the corresponding use duration and use frequency of each application program in real time for use in intention sorting.

In the priority determination, the priority between the use period and the use frequency may be set according to the need, for example: the priority of the use period is higher than the priority of the use frequency, or the priority of the use frequency is higher than the priority of the use period.

For example: the corpus of the user obtained by the terminal equipment is 'I want to hear the sun', the keywords which are extracted after semantic analysis and represent the intention of the user are 'hear' and 'sun', the terminal equipment finds that the terminal equipment corresponds to 3 intentions after matching, namely 1) sun is a new poem, and the user wants to hear the poem in an application program D related to poem; 2) The sun is a song that the user wants to listen to in the application E for music playing; 3) The user wants to hear the sun's introduction in the application F on common sense. The duration and frequency of use data of the application D, E, F are as follows, and it is assumed that the terminal device stays at the interface of the application D when the corpus of the user is obtained, so 1) the user wants to listen to the poem of "sun" as the target intention in the application D about poem; the priority of the use period is higher than the use frequency in this example, and thus, the priority of fig. 2) is higher than the priority of fig. 3).

When the terminal equipment plays the poem of Sun in the application program D, a small icon of the application program E and the application program F is displayed at the upper left corner of the interface, the application program E is arranged on the upper side, and the application program F is arranged below the application program E.

List one

In this embodiment, when a plurality of intentions are matched according to the corpus of the user, the terminal device may select the target intention according to the application program that the user stays when inputting the corpus, and improve the accuracy of the target intention according to the usage scenario, thereby improving the satisfaction and the usage experience of the user.

In addition, other intentions except the target intention can be displayed after being sequenced according to the usual application using habit data of the user, if the target intention is not really wanted by the user, the displayed other intentions can be switched by the user, the operation is simple, convenient and quick, and the using experience and satisfaction of the user are further improved.

Fig. 2 shows a flowchart of another multi-purpose selecting method of the present invention, which can be applied to a terminal device (for example, a tablet computer, a home education learning machine, etc., all of which are explained by using the home education learning machine as a subject for convenience of understanding in this embodiment, but those skilled in the art understand that the multi-purpose selecting method can also be applied to other terminal devices as long as the corresponding functions can be implemented), and the multi-purpose selecting method includes the following steps:

S201, corpus of users is obtained.

S202, carrying out semantic analysis on the corpus, wherein extracting keywords representing the intention of the user comprises the following steps: s212, carrying out semantic analysis on the corpus through the regular expression and the semantic analysis model, and extracting keywords representing the intention of the user.

Specifically, a regular expression can be understood as: by acquiring a large amount of corpus information and then generating a large amount of regular expressions according to the acquired corpus information, the regular expressions are used for describing or matching a series of character strings conforming to a certain syntax rule.

For example, the current corpus information is "why whale will spray water", the extracted sentence pattern main body is "whale sprays water", "whale" is the subject, and "spray water" is the predicate. The words of the sentence pattern main body are converted into corresponding semantic slots, and the semantic slots can be all words of the word part corresponding to the words, or can be words with the same semantic as the words. For example, the sentence-based body is "whale water spray", where "whale" is a noun, "water spray" is a verb, "semantic slot corresponding to" whale "is a noun library, and" semantic slot corresponding to "water spray" is a word stock.

After the sentence-based main body and the semantic slots corresponding to the words of the sentence-based main body are obtained, a regular expression corresponding to the current corpus information can be generated according to the sentence-based main body, the semantic slots and the rest non-main body parts in the current corpus information.

Illustratively, the current corpus information is "why whale will spray water", the extracted sentence-like body is "whale sprays water", the semantic slot corresponding to whale "is a noun library, the semantic slot corresponding to" spray water "is a verb library, the rest of non-body parts are" why meeting ", and the regular expression generated according to the obtained information is" # "word library# # [ why ] [ meeting ] # verb library# #").

The semantic analysis model is to train and correct some sentences with unobvious characteristics and sentences incapable of converting regular expressions (the sentences may be caused by unclear user expression, disordered word order logic or other things during corpus input) by using some open-source model algorithms and weight settings, so as to obtain the semantic analysis model, wherein the model training process is determined according to the adopted open-source algorithm, and the training method is the prior art and is not repeated here.

Examples of sentences with insignificant features, sentences that cannot convert regular expressions are as follows:

1. fifteen years, what part the radical word-finding method should find;

2. the division of the addition in the middle brackets in the upper brackets is finally recalculated with the multiplication outside the brackets.

Examples of semantic parsing model training are as follows: the semantic analysis model is formed by training a large number of corpora which cannot be analyzed by the regular expressions through a machine learning algorithm.

And carrying out semantic analysis on the corpus through the regular expression and the semantic analysis model, and improving the success rate of the semantic analysis by combining the regular expression and the semantic analysis model.

Preferably, S212 performs semantic analysis on the corpus through a regular expression and a semantic analysis model, and extracting keywords that characterize the intention of the user specifically includes:

s2121, matching the corpus by using a regular expression, and when the matching degree is larger than a preset value, successfully analyzing the semantics and extracting the keywords;

s2122, when the matching degree is not greater than a preset value, analyzing the corpus by using the semantic analysis model, and extracting the keywords.

Specifically, when semantic analysis is performed on the language materials, the regular expressions are used for matching, and the process of matching the language materials with the corresponding regular expressions can be understood as equivalent to sentence pattern matching, and whether the regular expressions are successfully matched or whether the analysis is successful is confirmed according to the matching degree (also understood as similarity) of the language materials.

The preset value can be set according to the requirement of matching precision, for example: 50%,60%, etc.

For example: the user says ' I want to see time ', the matching degree of the ' I want to see time ' and the ' I want to see time ' of the ' I want to see ' is 100% with the ' I want to see ' of the regular expression ' # ' and the ' I want to see ' of the verb library, # # and the ' noun library, # # ', and the corpus of the sentence is successfully analyzed by the regular expression, and the keyword is extracted as ' see ' time '.

For another example: the user explains why the weather is sunny, the logical sequence of the corpus is obviously wrong, the sentences are not feasible, when the corpus is matched with each regular expression, the matching degree is 20-30%, if the preset value is 50%, the corpus cannot be successfully analyzed by the regular expressions, so that the corpus is input into a trained semantic analysis model for semantic analysis, and keywords of the weather, the sunny and the sunny are extracted. It should be noted that this example is merely illustrative of the keywords extracted using the semantic parsing model, and the actual semantic parsing model may be different from this example.

S203, matching corresponding intents according to the keywords.

S204, when the keyword corresponds to a plurality of intentions, selecting an intention corresponding to an application program which stays when the corpus is acquired from the intentions as a target intention.

s205, after the keyword corresponds to a plurality of intentions and the target intention has been selected, sequencing and displaying the rest intentions according to application habit data of the user.

Specifically, considering that the target intention selected by the terminal device may not be really desired by the user, the terminal device may display the matched intention for the user to select.

The ordered other intentions can be displayed in various ways, so long as the user can be prompted to have other intentions besides the target intention.

In the priority judgment, the priority between the use time period and the use frequency can be set according to the requirement. For example: the priority of the use period is higher than the priority of the use frequency, or the priority of the use frequency is higher than the priority of the use period.

In the embodiment, the terminal equipment uses the combination of the regular expression and the semantic analysis model when extracting the keywords, so that the success rate of semantic analysis is improved, the terminal equipment is more flexible and changeable when the user uses the language to control the terminal equipment, and the use experience of the user is improved.

Fig. 3 shows a flowchart of another multi-purpose selecting method of the present invention, which can be applied to a terminal device (e.g., a tablet computer, a home education learning machine, etc., all of which are explained by using the home education learning machine as a main language for convenience of understanding in this embodiment, but those skilled in the art understand that the multi-purpose selecting method can also be applied to other terminal devices as long as the corresponding functions can be implemented), and the multi-purpose selecting method includes the following steps:

S301, acquiring corpus of a user;

s302, carrying out semantic analysis on the corpus, and extracting keywords representing the intention of a user;

s303, matching corresponding intents according to the keywords;

s304, when the keyword corresponds to a plurality of intentions and no intention related to the application program stayed when the corpus is acquired exists in the corresponding intentions, sequencing the intentions according to the application habit data of the user by priority, and taking the intention with the highest priority as a target intention;

s305, when the keyword corresponds to a plurality of intentions, selecting an intention corresponding to an application program which stays when the corpus is acquired from the plurality of intentions as a target intention.

Specifically, in this embodiment, comprehensive consideration is performed for the situation of matching multiple intentions, so that the multi-intention selecting method in the present invention is ensured to be applicable in various scenes, and the general applicability of the method is improved. If the keyword matches only one intent, then this intent is the target intent.

The application usage habit data refers to the usage duration and the usage frequency of each application program used by the user. When the intents are ranked according to the priority of the application using habit data of the user, the intents are ranked according to the priority of the using duration and the using frequency. The priority between the use period and the use frequency can be set according to the requirement.

For example: the keyword is matched with 3 intentions, the 3 intentions respectively correspond to 3 application programs D, E, F, the using time and the using frequency of the 3 application programs are shown in a table one, the terminal equipment stays at the interface of the application program A when the corpus of the user is obtained, the using frequency in the example is higher than the using time, and the ordered priority is as follows: application E > application F > application D, and thus the intent corresponding to application E is the target intent.

s306, after the keyword corresponds to a plurality of intentions and the target intention is selected, sequencing and displaying the rest intentions according to application habit data of the user.

In other embodiments, if the target intention is selected according to the ranking of the intents, the remaining other intents may follow the previously ranked order, and may not be reordered once, thereby increasing the processing speed.

Optionally, S302 performs semantic parsing on the corpus, and extracting keywords that characterize the intention of the user includes: s312, carrying out semantic analysis on the corpus through the regular expression and the semantic analysis model, and extracting keywords representing the intention of the user.

Preferably, S312 performs semantic analysis on the corpus through a regular expression and a semantic analysis model, and extracting keywords that characterize the intention of the user specifically includes:

s3121, matching the corpus by using a regular expression, and when the matching degree is larger than a preset value, successfully analyzing the semantics and extracting the keywords;

and S3122, when the matching degree is not more than a preset value, analyzing the corpus by using the semantic analysis model, and extracting the keywords.

The same parts of this embodiment as those of the above embodiments will not be explained again, and reference will be made to the corresponding embodiments.

In the embodiment, various situations matched with multiple intentions are considered, corresponding processing modes are provided for the various situations, universality of a multi-intention selection method is improved, and use experience and satisfaction of users are further improved.

It should be understood that, in the foregoing embodiment, the size of the sequence number of each step does not mean that the execution sequence of each step should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention in any way.

Fig. 4 is a schematic view of the multi-purpose selection apparatus 4 provided in the present application, and only the portions relevant to the embodiments of the present application are shown for convenience of explanation.

The multi-purpose selecting means 4 may be a software unit, a hardware unit or a combination of both a hardware unit and a software unit built in the terminal device, or may be integrated into the terminal device as a separate pendant.

The multi-purpose selecting device 4 includes:

the corpus acquisition module 41 is configured to acquire a corpus of a user.

The semantic analysis module 42 is configured to perform semantic analysis on the corpus, and extract keywords that characterize the intention of the user.

And the intention matching module 43 is used for matching corresponding intention according to the keyword.

Specifically, after extracting the keywords, the multi-intention selecting device matches with each application program and the content thereof in the database, thereby obtaining the intention corresponding to the keywords.

An intention selecting module 44, configured to select, when the keyword corresponds to a plurality of intentions, an intention corresponding to an application program that stays when the corpus is acquired from the plurality of intentions as a target intention.

Optionally, the multi-purpose selecting apparatus 4 in the present embodiment further includes: the intention sorting module 45 is configured to sort and display the rest intents according to application habit data of the user after the keyword corresponds to a plurality of intents and the target intention has been selected.

Specifically, considering that the target intention selected by the multi-intention selecting device may not be really wanted by the user, the multi-intention selecting device may display other intents matched for the user to select by himself.

In the priority determination, the priority between the use period and the use frequency may be set according to the need, for example: the priority of the use period is higher than the priority of the use frequency, or the priority of the use frequency is higher than the priority of the use period. Specific examples may refer to corresponding method embodiments, and are not described herein.

In this embodiment, when multiple intentions are matched according to the corpus of the user, the multi-intention selecting device may select the target intention according to the application program that the user stays when inputting the corpus, and improve the accuracy of the target intention according to the use scenario, thereby improving the satisfaction and use experience of the user.

Fig. 6 is another schematic view of the multi-purpose selection apparatus 4 provided herein, and for ease of illustration, only portions relevant to embodiments of the present application are shown. The multi-purpose selecting means 4 may be a software unit, a hardware unit or a combination of both a hardware unit and a software unit built in the terminal device, or may be integrated into the terminal device as a separate pendant.

The multi-purpose selecting means 4 comprises:

the corpus acquisition module 41 is configured to acquire a corpus of a user.

The semantic parsing module 42 is configured to perform semantic parsing on the corpus, and extracting keywords that characterize the intention of the user includes: the semantic analysis module 42 performs semantic analysis on the corpus through the regular expression and the semantic analysis model, and extracts keywords representing the intention of the user.

1. fifteen years, what part the radical word-finding method should find;

Preferably, the semantic analysis module 42 performs semantic analysis on the corpus through a regular expression and a semantic analysis model, and extracting keywords representing the intention of the user specifically includes:

A regular sub-module 421, configured to match the corpus using a regular expression, and when the matching degree is greater than a preset value, the semantic analysis is successful, and the keyword is extracted;

and a model submodule 422, configured to parse the corpus using the semantic parsing model when the matching degree is not greater than a preset value, and extract the keyword.

In this embodiment, the multi-intent selecting device uses a combination of a regular expression and a semantic analysis model when extracting keywords, so as to improve the success rate of semantic analysis, and the user uses the speech control terminal device more flexibly and variably, so as to improve the use experience of the user.

In a further embodiment of the multi-purpose selection means 4 of the invention, the multi-purpose selection means 4 comprises:

the corpus acquisition module 41 is configured to acquire a corpus of a user.

An intention selecting module 44, configured to select, when the keyword corresponds to a plurality of intentions, an intention corresponding to an application program that stays when the corpus is acquired from among the plurality of intentions as a target intention; and when the keyword corresponds to a plurality of intentions and no intention related to the application program stayed when the corpus is acquired is in the corresponding intentions, sequencing the intentions according to the application habit data of the user by priority, and taking the intention with the highest priority as the target intention.

The application usage habit data refers to the usage duration and the usage frequency of each application program used by the user. When the intents are ranked according to the priority of the application using habit data of the user, the intents are ranked according to the priority of the using duration and the using frequency. The priority between the use period and the use frequency can be set according to the requirement. Specific examples are the same as corresponding method embodiments, please refer to corresponding method embodiments, and detailed descriptions thereof are omitted herein.

Optionally, the semantic parsing module 42 is configured to perform semantic parsing on the corpus, and extracting keywords that characterize the intention of the user includes: the semantic analysis module 42 performs semantic analysis on the corpus through the regular expression and the semantic analysis model, and extracts keywords representing the intention of the user.

The same parts as those of the above-mentioned device embodiments in this embodiment are not repeated, and please refer to corresponding device embodiments.

In the embodiment, various situations matched with multiple intentions are considered, corresponding processing modes are provided for the various situations, universality of the multi-intention selecting device is improved, and use experience and satisfaction of users are further improved.

It will be apparent to those skilled in the art that the above-described program modules are only illustrated in the division of the above-described program modules for convenience and brevity, and that in practical applications, the above-described functional allocation may be performed by different program modules, i.e., the internal structure of the apparatus is divided into different program units or modules, to perform all or part of the above-described functions. The program modules in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one processing unit, where the integrated units may be implemented in a form of hardware or in a form of a software program unit. In addition, the specific names of the program modules are also only for distinguishing from each other, and are not used to limit the protection scope of the present application.

Fig. 5 is a schematic structural diagram of a terminal device 5 provided in an embodiment of the present invention. As shown in fig. 5, the terminal device 5 of the present embodiment includes: a processor 53, a memory 51 and a computer program 52 stored in the memory 51 and executable on the processor 53, for example: multi-purpose selection procedure. The steps of the above-described embodiments of the multi-purpose selection method are implemented by the processor 53 when the computer program 52 is executed, or the functions of the modules of the above-described embodiments of the multi-purpose selection apparatus are implemented by the processor 53 when the computer program 52 is executed.

The terminal device 5 may be a desktop computer, a notebook computer, a palm computer, a tablet computer, a mobile phone, a home education learning machine, or the like. The terminal device 5 may include, but is not limited to, a processor 53, a memory 51. It will be appreciated by those skilled in the art that fig. 5 is merely an example of a terminal device and does not constitute a limitation of the terminal device 5, and may include more or fewer components than shown, or may combine certain components, or different components, such as: the terminal devices may also include input and output devices, display devices, network access devices, buses, and the like.

The processor 53 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 51 may be an internal storage unit of the terminal device 5, for example: a hard disk or a memory of the terminal equipment. The memory may also be an external storage device of the terminal device, for example: a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) and the like, which are provided on the terminal device. Further, the memory 51 may also include both an internal storage unit and an external storage device of the terminal device 5. The memory 51 is used for storing the computer program 52 and other programs and data required by the terminal device 5. The memory may also be used to temporarily store data that has been output or is to be output.

In the foregoing embodiments, the descriptions of the embodiments are focused on, and the parts of a certain embodiment that are not described or depicted in detail may be referred to in the related descriptions of other embodiments.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other manners. For example, the apparatus/terminal device embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical function division, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on this understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by sending instructions to related hardware by a computer program, where the computer program may be stored in a computer readable storage medium, and the computer program may implement the steps of each of the method embodiments described above when executed by a processor. Wherein the computer program comprises: computer program code may be in the form of source code, object code, executable files, or in some intermediate form, etc. The computer readable storage medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable storage medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in jurisdictions, for example: in some jurisdictions, computer-readable media do not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.

It should be noted that the above embodiments can be freely combined as needed. The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention.

Claims

1. A method of multi-purpose selection, comprising the steps of:

acquiring corpus of a user;

carrying out semantic analysis on the corpus, and extracting keywords representing the intention of the user;

matching corresponding intents according to the keywords;

when the keyword corresponds to a plurality of intentions, selecting an intention corresponding to an application program which stays when the corpus is acquired from the intentions as a target intention;

the semantic analysis is carried out on the corpus, and the extracting of the keywords representing the intention of the user comprises the following steps:

carrying out semantic analysis on the corpus through a regular expression and a semantic analysis model, and extracting keywords representing the intention of a user;

the corpus is subjected to semantic analysis through a regular expression and a semantic analysis model, and the keyword for representing the intention of the user is extracted specifically as follows:

Matching the corpus by using a regular expression, and extracting the keywords after semantic analysis is successful when the matching degree is larger than a preset value;

and when the matching degree is not greater than a preset value, analyzing the corpus by using the semantic analysis model, and extracting the keywords.

2. The multi-purpose selection method as claimed in claim 1, further comprising the steps of:

and after the keyword corresponds to a plurality of intentions and the target intention is selected, sequencing and displaying the rest intentions according to application habit data of the user.

3. The multi-purpose selecting method as claimed in claim 2, wherein the application usage habit data refers to a usage duration and a usage frequency of each application program used by the user.

4. A multi-purpose selection device, comprising:

the corpus acquisition module is used for acquiring the corpus of the user;

the semantic analysis module is used for carrying out semantic analysis on the corpus and extracting keywords representing the intention of the user;

the intention matching module is used for matching corresponding intention according to the keywords;

the intention selecting module is used for selecting the intention corresponding to the application program which stays when the corpus is acquired from a plurality of intentions as a target intention when the keyword corresponds to the plurality of intentions;

The semantic analysis module is configured to perform semantic analysis on the corpus, and extracting keywords that characterize the intention of the user includes:

the semantic analysis module performs semantic analysis on the corpus through a regular expression and a semantic analysis model, and extracts keywords representing user intention;

the semantic analysis module performs semantic analysis on the corpus through a regular expression and a semantic analysis model, and the keyword for representing the intention of the user is extracted specifically as follows:

the regular sub-module is used for matching the corpus by using a regular expression, and when the matching degree is larger than a preset value, semantic analysis is successful, and the keywords are extracted;

and the model submodule is used for analyzing the corpus by using the semantic analysis model when the matching degree is not greater than a preset value, and extracting the keywords.

5. The multi-intent selection device as recited in claim 4, further comprising:

and the intention ordering module is used for ordering and displaying the rest intentions according to application habit data of the user after the keyword corresponds to a plurality of intentions and the target intention is selected.

6. Terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the multi-purpose selection method according to any one of claims 1-3 when the computer program is run.