CN115392253A - Control method and device and electronic equipment - Google Patents

Control method and device and electronic equipment Download PDF

Info

Publication number
CN115392253A
CN115392253A CN202211020026.3A CN202211020026A CN115392253A CN 115392253 A CN115392253 A CN 115392253A CN 202211020026 A CN202211020026 A CN 202211020026A CN 115392253 A CN115392253 A CN 115392253A
Authority
CN
China
Prior art keywords
keywords
basic
voice data
menu item
keyword
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.)
Pending
Application number
CN202211020026.3A
Other languages
Chinese (zh)
Inventor
申亚坤
刘烨敏
谭莹坤
陶威
周慧婷
程璐
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Bank of China Ltd
Original Assignee
Bank of China Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Bank of China Ltd filed Critical Bank of China Ltd
Priority to CN202211020026.3A priority Critical patent/CN115392253A/en
Publication of CN115392253A publication Critical patent/CN115392253A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • 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
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • 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
    • G10L15/26—Speech to text systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

The application discloses a control method, a control device and electronic equipment, which can be applied to the field of artificial intelligence or the field of finance, wherein the method comprises the following steps: obtaining current voice data; splitting the current voice data to obtain a plurality of basic voice data; obtaining basic keywords in each basic voice data; comparing the basic keywords with a keyword list corresponding to each menu item to obtain target menu items matched with the basic keywords; and outputting a display page corresponding to the corresponding target menu item according to the target sequence among the basic keywords.

Description

Control method and device and electronic equipment
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a control method and apparatus, and an electronic device.
Background
With the development of technology, at present, an intelligent counter is mostly adopted to provide services such as business handling and the like for a user. The user can click the corresponding control on the counter page, and after the counter page outputs the corresponding page for the user, the user can conduct business transaction on the page.
However, this process requires the user to operate the counter page many times, which results in a high complexity of operation for the user.
Disclosure of Invention
In view of this, the present application provides a control method, an apparatus and an electronic device, so as to solve the technical problem of high complexity of user operation. The following:
a method of controlling, the method comprising:
obtaining current voice data;
splitting the current voice data to obtain a plurality of basic voice data;
obtaining basic keywords in each basic voice data;
comparing the basic keywords with a keyword list corresponding to each menu item to obtain target menu items matched with the basic keywords;
and outputting a display page corresponding to the corresponding target menu item according to the target sequence among the basic keywords.
Preferably, before splitting the current voice data to obtain a plurality of basic voice data, the method further includes:
searching whether composite voice data matched with the current voice data exists in a composite voice library;
if yes, obtaining a composite menu list corresponding to composite voice data matched with the current voice data, and outputting a display page corresponding to a basic menu item in the composite menu list according to the sequence of the basic menu items in the composite menu list;
if not, executing the following steps: and splitting the current voice data to obtain a plurality of basic voice data.
Preferably, after the comparing the basic keyword with the keyword list corresponding to each menu item to obtain the target menu item matched with the basic keyword, the method further includes:
splicing the target menu items to obtain a composite menu list;
and adding the current voice data into a composite voice library, wherein the current voice data and the composite menu list have a corresponding relation.
In the method, preferably, the menu item corresponds to a standard keyword list and a fuzzy keyword list;
the comparing the basic keyword with the keyword list corresponding to each menu item to obtain the target menu item matched with the basic keyword comprises:
comparing the basic keyword with the standard keywords in the standard keyword list corresponding to the menu item to obtain a first comparison result;
under the condition that the standard keywords in the standard keyword list corresponding to the menu item are represented by the first comparison result and matched with the basic keywords, determining the menu item corresponding to the first comparison result as a target menu item;
under the condition that the first comparison result represents that the standard keywords in the standard keyword list corresponding to the menu item are not matched with the basic keywords, comparing the basic keywords with the fuzzy keywords in the fuzzy keyword list corresponding to the menu item to obtain a second comparison result;
and under the condition that the fuzzy keywords in the fuzzy keyword list corresponding to the menu item represented by the second comparison result are matched with the basic keywords, determining the menu item corresponding to the second comparison result as a target menu item.
In the above method, preferably, the standard keyword list of the menu item is obtained by:
obtaining a business function form corresponding to the menu item;
extracting form keywords in the business function form;
and adding the keywords of which the repetition times meet the first screening condition in the form keywords into a standard keyword list.
Preferably, in the above method, the fuzzy keyword list of the menu item is obtained by:
obtaining historical voice data matched with the standard keyword list of the menu items;
extracting fuzzy keywords which are not in the standard keyword list from all keywords in the historical voice data;
and adding the keywords of which the repetition times meet a second screening condition in the fuzzy keywords into a fuzzy keyword list.
The above method, preferably, further comprises:
under the condition that the standard keywords in the standard keyword list corresponding to the menu item are matched with the basic keywords represented by the first comparison result, adding 1 to the number of hits of the standard keywords matched with the basic keywords;
and adding 1 to the hit times of the fuzzy keywords matched with the basic keywords under the condition that the fuzzy keywords in the fuzzy keyword list corresponding to the menu item represented by the second comparison result are matched with the basic keywords.
The above method, preferably, further comprises:
obtaining the hit times of the standard keywords matched with the basic keywords in the standard keyword list;
acquiring the hit times of the fuzzy keywords matched with the basic keywords in the fuzzy keyword list;
exchanging a first keyword in the standard keyword list with a second keyword list in the fuzzy keyword list, wherein the hit frequency of the first keyword is less than the hit frequency of the second keyword.
A control device, the device comprising:
a voice obtaining unit for obtaining current voice data;
the voice splitting unit is used for splitting the current voice data to obtain a plurality of basic voice data;
a keyword obtaining unit, configured to obtain a basic keyword in each basic voice data;
the keyword comparison unit is used for comparing the basic keywords with the keyword list corresponding to each menu item to obtain target menu items matched with the basic keywords;
and the page output unit is used for outputting the display page corresponding to the corresponding target menu item according to the voice sequence among the basic keywords.
An electronic device, comprising:
a memory for storing a computer program and data generated by the operation of the computer program;
a processor for executing the computer program to implement: obtaining current voice data; splitting the current voice data to obtain a plurality of basic voice data; obtaining basic keywords in each basic voice data; comparing the basic keywords with the keyword list corresponding to each menu item to obtain target menu items matched with the basic keywords; and outputting a display page corresponding to the corresponding target menu item according to the voice sequence among the basic keywords.
According to the technical scheme, the control method, the control device and the electronic equipment can receive a composite voice containing a plurality of basic voice data, namely a short voice, namely a long voice, so that the long voice input by a user is split, the obtained short voice keywords are matched with the keyword list of each menu item, and the display page of the matched menu item is output according to the sequence of the short voice in the long voice. Therefore, the method and the device support the user to input the long voice so as to output the corresponding display page for the user conveniently, do not need the user to perform voice input for many times or menu item selection operation for many times, and further reduce the complexity of user operation.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart of a control method according to an embodiment of the present application;
fig. 2 is another flowchart of a control method according to an embodiment of the present application;
fig. 3 is another flowchart of a control method according to an embodiment of the present disclosure;
fig. 4 is a partial flowchart of a control method according to an embodiment of the present application;
fig. 5-fig. 8 are respectively another partial flow charts of a control method according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of a control device according to a second embodiment of the present application;
fig. 10 is a schematic structural diagram of an electronic device according to a third embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, a flowchart for implementing a control method provided in an embodiment of the present invention is shown, where the method may be applied to an electronic device capable of performing voice processing and menu control, such as an intelligent counter. The technical scheme in the embodiment is mainly used for reducing the complexity of menu page operation of a user.
Specifically, the present embodiment may include the following steps:
step 101: current speech data is obtained.
Specifically, in this embodiment, the current voice data of the user may be collected by an audio collection device, such as a microphone. The current voice data here may be a long voice, that is, voice data containing a plurality of short voices. For example, the current voice data is "i want to handle a service first, then B service, and then C service".
Step 102: and splitting the current voice data to obtain a plurality of basic voice data.
Here, the basic voice data may be short voice.
Specifically, in this embodiment, the current voice data may be split by a voice processing algorithm through recognizing a voice pause (a time interval between pronunciations is greater than or equal to an interval threshold) in the current voice data, so as to obtain a plurality of basic voice data constituting the current voice data. For example, the split basic voice data includes: "I want to transact A business first", "transact B business again" and "do C processing again".
Step 103: and obtaining basic keywords in each basic voice data.
In this embodiment, the basic speech data may be first recognized by using a speech recognition algorithm to recognize the basic text data corresponding to each basic speech data, and then the keywords in each basic text data are extracted to obtain the basic keywords in each basic speech data.
For example, a basic keyword in the speech basic data "i want to handle a service first" has "a service", a basic keyword in the speech basic data "handle B service second" has "B service", and a basic keyword in the speech basic data "do C processing next" has "C processing".
Step 104: and comparing the basic keywords with the keyword list corresponding to each menu item to obtain the target menu items matched with the basic keywords.
Based on this, in the embodiment, for each piece of basic voice data, the basic keyword of the piece of basic voice data is respectively compared with the keywords in the keyword list corresponding to each menu item, so as to obtain the comparison result of each piece of basic voice data with respect to the keywords of each menu item, and then, based on these comparison results, the target menu item on which each piece of basic voice data is matched with the basic keyword is obtained.
For example, the basic keyword "a service" is compared with the keywords in the keyword list of each menu item, respectively, to obtain a comparison result corresponding to the "a service" on each menu item, and based on the comparison result, the target menu item matched with the "a service" is obtained; respectively comparing the basic keyword 'B service' with keywords in a keyword list of each menu item to obtain a comparison result of the 'B service' corresponding to each menu item, and obtaining a target menu item matched with the 'B service' based on the comparison result; and respectively comparing the basic keyword 'C processing' with the keywords in the keyword list of each menu item to obtain a comparison result corresponding to the 'C processing' on each menu item, and obtaining a target menu item matched with the 'C processing' based on the comparison result.
Step 105: and outputting the display page corresponding to the corresponding target menu item according to the target sequence among the basic keywords.
The target sequence among the basic keywords refers to a logical sequence among the basic voice data in the current voice data. Specifically, the target sequence between the basic keywords can be obtained by analyzing the voice sequence between the basic voice data in the current voice data and the semantic sequence between the basic voice data.
Specifically, in this embodiment, connection words between basic voice data in the current voice data, such as "first", "second", and "last" connection words, may be recognized first, and based on these connection words, a target sequence between the basic voice data, that is, a target sequence between the basic keywords, is obtained.
It should be noted that, in the case that there is no connection word between the basic voice data in the current voice data, the target sequence between the basic voice data may be determined according to the voice sequence between the basic voice data. For example, the target sequence between "a service", "B service", and "C process" is a semantic sequence (consistent with the voice sequence) between "i want to process a service first", "process B service", and "then process C" of the voice basic data, based on which, according to the respective target menu items of "a service", "B service", and "C process", the display page corresponding to the corresponding target menu item is output, such as outputting the a service processing page first, after the service processing corresponding to the a service processing page is completed, outputting the B service processing page, and after the service processing corresponding to the B service processing page is completed, outputting the C service processing page until the C service processing is completed.
It can be seen from the foregoing technical solutions that, in a control method provided in this embodiment of the present application, a composite voice, that is, a long voice, including a plurality of basic voice data, that is, a short voice, can be received, and then the long voice input by a user is split, and then an obtained keyword of a phrase voice is matched with a keyword list of each menu item, so that a display page of the matched menu item is output according to an order of the short voice in the long voice. Therefore, the user is supported to input long voice in the embodiment, so that a corresponding display page is output for the user, the user does not need to perform voice input or menu item selection operation for multiple times, and the complexity of user operation is further reduced.
Based on the above implementation, in an implementation manner, before step 102, the method in this embodiment may further include the following steps, as shown in fig. 2:
step 106: and searching whether composite voice data matched with the current voice data exists in the composite voice library, if so, executing step 107, and if not, executing step 102.
Step 107: acquiring a composite menu list corresponding to composite voice data matched with the current voice data;
step 108: and outputting a display page corresponding to the basic menu items in the composite menu list according to the sequence of the basic menu items in the composite menu list.
The composite voice database comprises at least one piece of composite voice data, the composite voice data is voice data comprising a plurality of basic voice data, each basic voice data in the composite voice data respectively corresponds to a matched menu item, and the menu items form a composite menu list corresponding to the composite voice data. That is, each piece of compound speech data in the compound speech library respectively corresponds to a compound menu list, and the compound menu list includes at least one basic menu item.
It should be noted that the synthesized voice data in the synthesized voice library can be obtained based on the historical voice data. Specifically, in this embodiment, history voice data, which is subjected to menu item matching and includes that each piece of basic voice data is matched to a corresponding menu item, may be stored as composite voice data in a composite voice library, and a menu item, which is matched to each piece of basic voice data in the history voice data, may be added as a basic menu item to a composite menu list corresponding to the history voice data.
Based on this, in this embodiment, before splitting the current voice data, it may be first found whether the composite voice database already has composite voice data matched with the current voice data, and if the composite voice database already has composite voice data matched with the current voice data, then it is not necessary to split the current voice data, and the display pages corresponding to the basic menu items may be output directly according to the sequence between the basic menu items in the composite menu list corresponding to the matched composite voice data.
For example, if composite voice data ' a service is finished, a service bar is finished, and a service C is watched, exists in a composite voice library, the composite voice data is matched with current voice data ' i want to firstly handle the service a, then handle the service B, and then do C processing ', at this time, the matched composite voice data ' a service is finished, a service bar is finished, and a composite menu list corresponding to the service C ' is watched without executing the processes of splitting, obtaining basic keywords, comparing and the like on the current voice data, the matched composite voice data can be directly obtained, the three basic menu items are included in the composite menu list, namely, the service menu item a, the service menu item B and the service menu item C, and then the display pages corresponding to the menu items are output according to the sequence of the menu items in the composite menu list. For example, the service processing page a is output first, the service processing page B is output after the service processing corresponding to the service processing page a is completed, and the service processing page C is output after the service processing corresponding to the service processing page B is completed until the service processing C is completed.
Based on the above implementation, the following steps may also be included in this embodiment after step 104, as shown in fig. 3:
step 109: and splicing the target menu items to obtain a composite menu list.
And the composite menu list spliced by the target menu items corresponds to the current voice data. For example, the respective corresponding target menu items of "a service", "B service", and "C process" are spliced according to the target sequence among the basic keywords to form a composite menu list corresponding to the current voice data "i want to handle a service first, then handle B service, and then do C process".
Step 110: and adding the current voice data into the composite voice library, wherein the current voice data and the composite menu list have a corresponding relation.
That is to say, in this embodiment, after the matching of the current voice data is completed, the composite voice data in the composite voice library is updated, the current voice data is added to the composite voice library as the composite voice data, and accordingly, the target menu item matched by the current voice data forms the corresponding composite menu list.
In one implementation, each menu item corresponds to two keyword lists, namely: a list of standard keywords and a list of fuzzy keywords. The standard keyword list comprises at least one standard keyword, and the fuzzy keyword list also comprises at least one fuzzy keyword.
Based on this, step 104 may be implemented by, as shown in fig. 4:
step 401: comparing the basic keywords with the standard keywords in the standard keyword list corresponding to the menu item to obtain a first comparison result;
step 402: judging whether the first comparison result represents that the standard keywords in the standard keyword list corresponding to the menu item are matched with the basic keywords, and executing the step 403 under the condition that the standard keywords in the standard keyword list corresponding to the first comparison result representation menu item are matched with the basic keywords; executing step 404 if the standard keywords in the standard keyword list corresponding to the first comparison result representation menu item are not matched with the basic keywords;
step 403: determining the menu item corresponding to the first comparison result as a target menu item;
step 404: and comparing the basic keywords with the fuzzy keywords in the fuzzy keyword list corresponding to the menu item to obtain a second comparison result.
Step 405: judging whether the second comparison result represents that the fuzzy keywords in the fuzzy keyword list corresponding to the menu item are matched with the basic keywords, executing a step 406 under the condition that the fuzzy keywords in the fuzzy keyword list corresponding to the second comparison result represents that the fuzzy keywords in the menu item are matched with the basic keywords, and indicating that the basic keywords are not matched with the menu item and the menu item cannot be used as the target menu item under the condition that the fuzzy keywords in the fuzzy keyword list corresponding to the second comparison result represents that the fuzzy keywords in the menu item are not matched with the basic keywords.
Step 406: and determining the menu item corresponding to the second comparison result as a target menu item.
That is, in this embodiment, the standard keywords corresponding to each menu item are preferentially compared with the basic keywords, only when the standard keywords corresponding to the menu item are all unmatched with the basic keywords, the fuzzy keywords corresponding to the menu item are compared with the basic keywords, if the fuzzy keywords corresponding to the menu item are also all unmatched with the basic keywords, it is indicated that the basic keywords are unmatched with the menu item, and if the standard keywords exist in the standard keyword list corresponding to the menu item and are matched with the basic keywords, it is indicated that the menu item is matched with the basic keywords, at this time, the menu item is determined as the target menu item, if the standard keywords do not exist in the standard keyword list corresponding to the menu item and are matched with the basic keywords but the fuzzy keywords exist in the fuzzy keyword list corresponding to the menu item and are matched with the basic keywords, at this time, the menu item is determined as the target menu item.
Based on the above implementation, the standard keyword list for each menu item can be obtained as shown in fig. 5:
step 501: and obtaining a business function form corresponding to the menu item.
The business function form represents a display page corresponding to the menu item to provide various business services for the user, such as A1 function of the a business, A2 function of the a business, A3 function of the a business and the like.
Step 502: and extracting form keywords in the business function form.
Specifically, in this embodiment, a text in the service function form may be identified, and then form keywords may be extracted. For example, "A1" in the A1 function of the a service is extracted as a form keyword, "A2" in the A2 function of the a service is extracted as a form keyword, and "A3" in the A3 function of the a service is extracted as a form keyword.
Step 503: and adding the keywords of which the repetition times meet the first screening condition in the form keywords into a standard keyword list.
The first screening condition here may be: the number of repetitions is greater than or equal to a first number threshold; alternatively, the first screening condition may be: the repetition times are sequenced from large to small in the top M, and M is a positive integer greater than or equal to 1.
Therefore, in the embodiment, one or more keywords with higher repetition times are selected from the form keywords extracted from the service function form of the menu item as standard keywords, and the standard keywords are added to the standard keyword list corresponding to the menu item.
In one implementation, the fuzzy keyword list for each menu item may be obtained by:
step 601: historical speech data is obtained that matches the list of standard keywords for the menu item.
Wherein, the historical voice data refers to the voice data of historical input, the basic key words of which can be matched with the standard key words of the menu items. Specifically, in this embodiment, the hit historical speech data may be first screened out from the historical speech data, and then the historical speech data of the standard keyword list matching the menu item may be screened out from the historical speech data, that is, the historical speech data may be divided into different groups according to different matched menu items, and the different groups correspond to each menu item respectively.
Step 602: among all keywords in the historical voice data, fuzzy keywords that are not in the standard keyword list are extracted.
Specifically, in this embodiment, relevant keywords may be recognized in the historical speech data first, then, keywords that match with the standard keywords in the standard keyword list are removed from the keywords, only the keywords that do not match with the standard keywords are reserved, and the reserved keywords are marked as fuzzy keywords.
Step 603: and adding the keywords of which the repetition times meet the second screening condition in the fuzzy keywords into a fuzzy keyword list.
Here, the second screening condition may be: the number of repetitions is greater than or equal to a second number threshold; alternatively, the second screening condition may be: the repetition times are sequenced from large to small in the first N, and N is a positive integer greater than or equal to 1.
Based on this, in this embodiment, after the corresponding standard keyword list is generated for each menu item, the corresponding fuzzy keyword list is generated for each menu item through the historical voice data, and the fuzzy keywords in the fuzzy keyword list are different from the standard keywords in the standard keyword list.
In an implementation manner, in the case that it is determined in step 402 that the standard keyword in the standard keyword list corresponding to the first comparison result representation menu item matches the basic keyword, the method in this embodiment may further include the following steps, as shown in fig. 7:
step 407: the number of hits for the standard keyword that matches the base keyword is increased by 1.
In step 405, when it is determined that the fuzzy keyword in the fuzzy keyword list corresponding to the second comparison result representation menu item matches the basic keyword, the method in this embodiment may further include the following steps, as shown in fig. 7:
step 408: the number of hits for the fuzzy keyword that matches the base keyword is increased by 1.
Therefore, in this embodiment, the hit times of each standard keyword and each fuzzy keyword corresponding to each menu item can be counted.
Based on this, after step 407 and step 408, the method in this embodiment may further include the following steps, as shown in fig. 8:
step 801: and obtaining the hit times of the standard keywords matched with the basic keywords in the standard keyword list.
Step 802: and obtaining the hit times of the fuzzy keywords matched with the basic keywords in the fuzzy keyword list.
Step 803: and exchanging a first keyword in the standard keyword list with a second keyword in the fuzzy keyword list, wherein the hit frequency of the first keyword is less than that of the second keyword.
That is, in this embodiment, after the number of hits of the standard keyword or the number of hits of the fuzzy keyword is updated each time, the size of the number of hits of each standard keyword and each fuzzy keyword is determined, so as to determine that the standard keyword whose number of hits in the standard keyword list is smaller than the number of hits of the fuzzy keyword in the fuzzy keyword list is denoted as a first keyword, and the fuzzy keyword whose number of hits in the fuzzy keyword list is greater than the number of hits of the standard keyword in the standard keyword list is denoted as a second keyword, that is, the number of hits of the standard keyword in the standard keyword list is lower, and the number of hits of the fuzzy keyword list in the fuzzy keyword list is higher and exceeds the number of hits of one or more standard keywords, at this time, these keywords are replaced, that is: the first keyword is added to the fuzzy keyword list and the first keyword in the standard keyword list is deleted, and the second keyword is added to the standard keyword list and the second keyword in the fuzzy keyword list is deleted.
Referring to fig. 9, a schematic structural diagram of a control device provided in the second embodiment of the present application is shown, where the control device may be configured in an electronic device capable of performing voice processing and menu control, such as an intelligent counter. The technical scheme in the embodiment is mainly used for reducing the complexity of menu page operation of a user.
Specifically, the apparatus in this embodiment may include the following units:
a voice obtaining unit 901 configured to obtain current voice data;
a voice splitting unit 902, configured to split the current voice data to obtain multiple pieces of basic voice data;
a keyword obtaining unit 903, configured to obtain a basic keyword in each basic voice data;
a keyword comparison unit 904, configured to compare the basic keyword with a keyword list corresponding to each menu item to obtain a target menu item matched with the basic keyword;
and a page output unit 905, configured to output a display page corresponding to the corresponding target menu item according to the target sequence among the basic keywords.
It can be seen from the foregoing technical solutions that, in a control device provided in the second embodiment of the present application, a composite voice, that is, a long voice, including multiple pieces of basic voice data, that is, a short voice, can be received, and then the long voice input by a user is split, and then an obtained keyword of a short voice is matched with a keyword list of each menu item, so that a display page of the matched menu item is output according to an order of the short voice in the long voice. Therefore, in the embodiment, the user is supported to input the long voice, so that the corresponding display page is conveniently output for the user, the user does not need to perform voice input for many times or menu item selection operations for many times, and the complexity of user operation is further reduced.
In one implementation, before splitting the current voice data to obtain a plurality of base voice data, the voice splitting unit 902 is further configured to: searching whether composite voice data matched with the current voice data exists in a composite voice library; if yes, obtaining a composite menu list corresponding to composite voice data matched with the current voice data, and outputting a display page corresponding to a basic menu item in the composite menu list according to the sequence of the basic menu items in the composite menu list; if not, executing the following steps: and splitting the current voice data to obtain a plurality of basic voice data.
In one implementation, after the comparing the basic keyword with the keyword list corresponding to each menu item to obtain the target menu item matching the basic keyword, the keyword comparison unit 904 is further configured to: splicing the target menu items to obtain a composite menu list; and adding the current voice data into a composite voice library, wherein the current voice data and the composite menu list have a corresponding relation.
In one implementation, the menu items correspond to a standard keyword list and a fuzzy keyword list; the keyword comparison unit 904 is specifically configured to: comparing the basic keyword with the standard keywords in the standard keyword list corresponding to the menu item to obtain a first comparison result; under the condition that the standard keywords in the standard keyword list corresponding to the menu item are represented by the first comparison result and matched with the basic keywords, determining the menu item corresponding to the first comparison result as a target menu item; under the condition that the first comparison result represents that the standard keywords in the standard keyword list corresponding to the menu item are not matched with the basic keywords, comparing the basic keywords with the fuzzy keywords in the fuzzy keyword list corresponding to the menu item to obtain a second comparison result; and under the condition that the fuzzy keywords in the fuzzy keyword list corresponding to the menu item represented by the second comparison result are matched with the basic keywords, determining the menu item corresponding to the second comparison result as a target menu item.
In one implementation, the list of standard keywords for the menu item is obtained by: obtaining a business function form corresponding to the menu item; extracting form keywords in the business function form; and adding the keywords of which the repetition times meet the first screening condition in the form keywords into a standard keyword list.
In one implementation, the fuzzy keyword list of menu items is obtained by: obtaining historical voice data matched with the standard keyword list of the menu item; extracting fuzzy keywords which are not in the standard keyword list from all keywords in the historical voice data; and adding keywords of which the repetition times meet second screening conditions in the fuzzy keywords into a fuzzy keyword list.
In one implementation, the keyword comparison unit 904 is further configured to: under the condition that the standard keywords in the standard keyword list corresponding to the menu item are matched with the basic keywords represented by the first comparison result, adding 1 to the number of hits of the standard keywords matched with the basic keywords; and adding 1 to the hit times of the fuzzy keywords matched with the basic keywords under the condition that the fuzzy keywords in the fuzzy keyword list corresponding to the menu item represented by the second comparison result are matched with the basic keywords.
In one implementation, the keyword comparison unit 904 is further configured to: obtaining the hit times of the standard keywords matched with the basic keywords in the standard keyword list; acquiring the hit times of the fuzzy keywords matched with the basic keywords in the fuzzy keyword list; exchanging a first keyword in the standard keyword list with a second keyword list in the fuzzy keyword list, wherein the hit frequency of the first keyword is less than the hit frequency of the second keyword.
It should be noted that, for the specific implementation of each unit in the present embodiment, reference may be made to the corresponding content in the foregoing, and details are not described here.
Referring to fig. 10, a schematic structural diagram of an electronic device according to a third embodiment of the present application is shown, where the electronic device may include the following structure:
a memory 1001 for storing a computer program and data generated by the computer program;
a processor 1002 for executing the computer program to implement: obtaining current voice data; splitting the current voice data to obtain a plurality of basic voice data; obtaining basic keywords in each basic voice data; comparing the basic keywords with the keyword list corresponding to each menu item to obtain target menu items matched with the basic keywords; and outputting a display page corresponding to the corresponding target menu item according to the target sequence among the basic keywords.
It can be seen from the foregoing technical solutions that, in the electronic device provided in the third embodiment of the present application, a composite voice, that is, a long voice, including multiple pieces of basic voice data, that is, a short voice, can be received, and then the long voice input by the user is split, and then the obtained keywords of the phrase voice are matched with the keyword list of each menu item, so that the display page of the matched menu item is output according to the order of the short voice in the long voice. Therefore, in the embodiment, the user is supported to input the long voice, so that the corresponding display page is conveniently output for the user, the user does not need to perform voice input for many times or menu item selection operations for many times, and the complexity of user operation is further reduced.
Taking a scene of handling business at an intelligent counter of a bank as an example, part of work menus are hidden at a deeper level, and meanwhile, text short links and passwords are not convenient to refer in the intelligent counter, so that a short link mode related to voice is necessary to be introduced, huge operation convenience is brought to a client, the business handling time of the client can be reduced, and the handling efficiency of a bank lobby is improved.
In view of this, a working scheme of voice short link connection on an intelligent counter is established in the application, the scheme traverses a current service menu at the intelligent counter, establishes a basic short link library (basic voice data) based on the frequency of keywords (keywords) of the menu, expands the basic short link library according to a semantic lexical library in a system to generate a composite short link library (composite voice library), improves the operation convenience of a client to a greater extent, and finally continuously updates and iterates the basic short link library and the composite short link library in the using process of the system to improve the accuracy of the voice short link connection.
The technical scheme in the application is mainly divided into the following three parts:
1. and (3) generating a voice short link template: and calculating the keyword frequency of each function page based on the bottom menu items of the system to obtain a basic short link library.
2. Voice short link processing: and dynamically combining the basic short-link library based on the semantic lexical library to generate a composite short-link library.
3. And (3) menu item matching optimization: matching and short link library storage optimization are carried out on the function menu items when the customer voice short link is input.
The specific scheme is as follows:
firstly, a voice short-link library template, namely a basic voice short-link library, is established. A template unit is arranged in the intelligent counter, the menu items and functions of the intelligent counter are traversed, and a unique function path and a path password key value pair, namely the menu items and a keyword list thereof, are generated for each bottom menu item. The path password generation method comprises the following steps: and extracting a keyword list from the current path service function form, carrying out frequent item statistics on the element items in the keyword list one by one, and selecting the keyword with the highest occurrence frequency as a standard keyword. And recording the voice hit vocabulary of the current menu in the use process of the voice password, and adding the accumulated keywords which exceed a certain number of times into the fuzzy keyword list.
Then, a certain proportion of cutting operation is performed on the key value pair information generated by all the function menu items, for example: the keywords with more use times in a certain time are kept unchanged; adding the rest part of the keyword password information into a pruning list, counting the keywords in the pruning list in the password using process of the client, replacing the password (keyword) with the times that the fuzzy keyword list is larger than the standard keyword aiming at the keyword list of the key value pair in the password information in the pruning list, and adding the path and the instruction corresponding to the standard keyword and the fuzzy keyword into a basic password library (the keyword list corresponding to the menu item).
Further, a splicing combination method is adopted for the obtained basic short link library to generate a composite voice password (namely composite voice data), namely, for a built-in semantic lexical library in the intelligent counter, for example, "XXX service is transacted firstly, the number of my transfer phone is 10010, then, my business is wanted to transact YY. And meanwhile, when a plurality of basic voices are spliced in the semantic lexical library, a transfer area is set, filling information of the handling service item is input, when a client handles the next service, firstly, the client filling item in the transfer area is matched, and secondly, the input of the column item of the client is monitored, so that seamless butt joint and information utilization during handling of a plurality of services are realized.
Based on the method, when a customer uses the intelligent counter to handle business, the customer does not need to click menu items step by step to jump to a business handling page, the customer only needs to face the voice short link input responding to the intelligent counter, after the system receives the request of the customer, the voice short link input of the customer is matched with the composite voice library, and if the composite voice data is matched, the system navigates to the page corresponding to each menu in the composite menu list corresponding to the composite voice data; if the matched basic short-link library is not matched with the target voice, splitting a plurality of voices in the voice of the user, matching a plurality of basic voices obtained through splitting with the standard keywords of the basic short-link library, continuously matching the missed instructions with the fuzzy keywords, carrying out corresponding page navigation on the successfully matched basic voices, and carrying out addition on the hit navigation path passwords, namely counting the hit times. And for the basic voice with unsuccessful hit, matching the input of the client with a fuzzy keyword password library, counting the hit times of the hit fuzzy keyword password, replacing the fuzzy keyword password library and the fuzzy keyword password library when the accumulated hit times in the fuzzy library is greater than that in the standard keyword password library, and reordering the data of the fuzzy library according to the hit times.
Therefore, the working scheme of the intelligent counter with the voice short link is established, the scheme conducts path traversal on complete menu items of the intelligent counter and generates short link basic passwords of all function menus, meanwhile basic passwords can be combined to expand parameter input and command combination of clients, finally different requirements of voice short link input are met, and different use scenes of the intelligent counter of a large number of clients are met.
The control method, the control device and the electronic equipment provided by the invention can be used in the financial field or other fields, for example, can be used in a self-service business handling scene of a financial business intelligent counter in the financial field. Other fields are any fields other than the financial field, for example, the field of artificial intelligence. The above description is only an example and does not limit the application field of the invention name provided by the present invention.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed in the embodiment corresponds to the method disclosed in the embodiment, so that the description is simple, and the relevant points can be referred to the description of the method part.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the components and steps of the various examples have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. 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.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. A control method, characterized in that the method comprises:
obtaining current voice data;
splitting the current voice data to obtain a plurality of basic voice data;
obtaining basic keywords in each basic voice data;
comparing the basic keywords with a keyword list corresponding to each menu item to obtain target menu items matched with the basic keywords;
and outputting a display page corresponding to the corresponding target menu item according to the target sequence among the basic keywords.
2. The method of claim 1, wherein prior to splitting the current speech data to obtain a plurality of base speech data, the method further comprises:
searching whether composite voice data matched with the current voice data exists in a composite voice library;
if yes, obtaining a composite menu list corresponding to composite voice data matched with the current voice data, and outputting a display page corresponding to a basic menu item in the composite menu list according to the sequence of the basic menu items in the composite menu list;
if not, performing the following: and splitting the current voice data to obtain a plurality of basic voice data.
3. The method of claim 2, wherein after comparing the basic keyword with the keyword list corresponding to each menu item to obtain the target menu item matching the basic keyword, the method further comprises:
splicing the target menu items to obtain a composite menu list;
and adding the current voice data into a composite voice library, wherein the current voice data and the composite menu list have a corresponding relation.
4. The method according to claim 1 or 2, wherein the menu items correspond to a standard keyword list and a fuzzy keyword list;
wherein, the comparing the basic keyword with the keyword list corresponding to each menu item to obtain the target menu item matched with the basic keyword comprises:
comparing the basic keyword with the standard keywords in the standard keyword list corresponding to the menu item to obtain a first comparison result;
under the condition that the standard keywords in the standard keyword list corresponding to the menu item represented by the first comparison result are matched with the basic keywords, determining the menu item corresponding to the first comparison result as a target menu item;
under the condition that the first comparison result represents that the standard keywords in the standard keyword list corresponding to the menu item are not matched with the basic keywords, comparing the basic keywords with the fuzzy keywords in the fuzzy keyword list corresponding to the menu item to obtain a second comparison result;
and under the condition that the second comparison result represents that fuzzy keywords in the fuzzy keyword list corresponding to the menu item are matched with the basic keywords, determining the menu item corresponding to the second comparison result as a target menu item.
5. The method of claim 4, wherein the list of standard keywords of menu items is obtained by:
obtaining a business function form corresponding to the menu item;
extracting form keywords in the business function form;
and adding the keywords of which the repetition times meet the first screening condition in the form keywords into a standard keyword list.
6. The method of claim 4, wherein the fuzzy keyword list of menu items is obtained by:
obtaining historical voice data matched with the standard keyword list of the menu item;
extracting fuzzy keywords which are not in the standard keyword list from all keywords in the historical voice data;
and adding the keywords of which the repetition times meet a second screening condition in the fuzzy keywords into a fuzzy keyword list.
7. The method of claim 4, further comprising:
under the condition that the standard keywords in the standard keyword list corresponding to the menu item are matched with the basic keywords represented by the first comparison result, adding 1 to the number of hits of the standard keywords matched with the basic keywords;
and under the condition that the second comparison result represents that the fuzzy keywords in the fuzzy keyword list corresponding to the menu item are matched with the basic keywords, adding 1 to the hit times of the fuzzy keywords matched with the basic keywords.
8. The method of claim 7, further comprising:
obtaining the hit times of the standard keywords matched with the basic keywords in the standard keyword list;
acquiring the hit times of the fuzzy keywords matched with the basic keywords in the fuzzy keyword list;
and exchanging a first keyword in the standard keyword list and a second keyword list in the fuzzy keyword list, wherein the hit frequency of the first keyword is less than that of the second keyword.
9. A control device, characterized in that the device comprises:
a voice obtaining unit for obtaining current voice data;
the voice splitting unit is used for splitting the current voice data to obtain a plurality of basic voice data;
a keyword obtaining unit, configured to obtain a basic keyword in each of the basic voice data;
the keyword comparison unit is used for comparing the basic keywords with the keyword list corresponding to each menu item to obtain target menu items matched with the basic keywords;
and the page output unit is used for outputting the display page corresponding to the corresponding target menu item according to the target sequence among the basic keywords.
10. An electronic device, comprising:
a memory for storing a computer program and data generated by the operation of the computer program;
a processor for executing the computer program to implement: obtaining current voice data; splitting the current voice data to obtain a plurality of basic voice data; obtaining basic keywords in each basic voice data; comparing the basic keywords with the keyword list corresponding to each menu item to obtain target menu items matched with the basic keywords; and outputting a display page corresponding to the corresponding target menu item according to the target sequence among the basic keywords.
CN202211020026.3A 2022-08-24 2022-08-24 Control method and device and electronic equipment Pending CN115392253A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211020026.3A CN115392253A (en) 2022-08-24 2022-08-24 Control method and device and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211020026.3A CN115392253A (en) 2022-08-24 2022-08-24 Control method and device and electronic equipment

Publications (1)

Publication Number Publication Date
CN115392253A true CN115392253A (en) 2022-11-25

Family

ID=84122797

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211020026.3A Pending CN115392253A (en) 2022-08-24 2022-08-24 Control method and device and electronic equipment

Country Status (1)

Country Link
CN (1) CN115392253A (en)

Similar Documents

Publication Publication Date Title
CN108255934B (en) Voice control method and device
KR100446627B1 (en) Apparatus for providing information using voice dialogue interface and method thereof
WO2021017612A1 (en) Question and answer method and apparatus based on speech analysis, device and storage medium
US11762848B2 (en) Combining parameters of multiple search queries that share a line of inquiry
CN107229627B (en) Text processing method and device and computing equipment
CN109344240B (en) Data processing method, server and electronic equipment
US8135579B2 (en) Method of analyzing conversational transcripts
US11347947B2 (en) Encoder with double decoder machine learning models
JP3204154B2 (en) Time series data analyzer
CN111767393A (en) Text core content extraction method and device
US20180096680A1 (en) Apparatus and Method for Analyzing Utterance Meaning
CN112000776A (en) Topic matching method, device and equipment based on voice semantics and storage medium
KR20060070605A (en) Using domain dialogue model and language model in intelligent robot speech recognition service device and method
CN111159334A (en) Method and system for house source follow-up information processing
EP4187463A1 (en) An artificial intelligence powered digital meeting assistant
WO2024045475A1 (en) Speech recognition method and apparatus, and device and medium
CN113064980A (en) Intelligent question and answer method and device, computer equipment and storage medium
KR20060100646A (en) Method and system for searching the position of an image thing
JP5050993B2 (en) Information retrieval apparatus and program
CN113343692A (en) Search intention recognition method, model training method, device, medium and equipment
CN115392253A (en) Control method and device and electronic equipment
CN113868508B (en) Writing material query method and device, electronic equipment and storage medium
CN115174285A (en) Conference record generation method and device and electronic equipment
CN113948069A (en) Equipment operation method and system based on voice
JP7216627B2 (en) INPUT SUPPORT METHOD, INPUT SUPPORT SYSTEM, AND PROGRAM

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