CN112328738A

CN112328738A - Voice retrieval method, terminal device and readable storage medium

Info

Publication number: CN112328738A
Application number: CN202011073697.7A
Authority: CN
Inventors: 金益帆; 张磊
Original assignee: Agricultural Bank of China Hebei Branch
Current assignee: Agricultural Bank of China Hebei Branch
Priority date: 2020-10-10
Filing date: 2020-10-10
Publication date: 2021-02-05

Abstract

The present application belongs to the field of communications technologies, and in particular, to a voice retrieval method, a terminal device, and a readable storage medium. Wherein, the method comprises the following steps: acquiring voice retrieval contents and converting the voice retrieval contents into corresponding text retrieval contents; when the character retrieval content needs to be corrected, acquiring the corrected character retrieval content; inquiring a target document in a plurality of preset operation procedure documents according to the corrected text retrieval content; and outputting the target document. The voice retrieval method, the terminal device and the readable storage medium provided by the embodiment of the application can realize the convenience of supporting the counter service, namely realize voice query, and support the correction of the content of voice identification, can flexibly adapt to users with different accents and noisy working environments, and solve the problem of long time consumption in the prior art of manually browsing and querying the supporting content of the service.

Description

Voice retrieval method, terminal device and readable storage medium

Technical Field

The present application belongs to the field of communications technologies, and in particular, to a voice retrieval method, a terminal device, and a readable storage medium.

Background

With the development of standardized finance, the business operation process is unified and standardized, the counter operation standardization is realized, the service experience of customers is improved, and a large number of operation regulation documents are compiled to serve as the standard of basic business operation. However, in the actual operation process of the basic level, because the operation procedure document covers all counter services, the size is large, for basic level staff unfamiliar with the structure and content of operation procedure chapters, if the mode of searching according to chapters is complicated, the target content cannot be quickly and accurately positioned, the average time for searching the service support content in the service handling process is about 10-20 minutes, a large amount of time cost is increased, and the service experience and satisfaction of customers are influenced.

Disclosure of Invention

In view of this, embodiments of the present application provide a voice retrieval method, a terminal device, and a readable storage medium, so as to solve the problem that the time consumption is too long when the query service support content is manually turned over at present.

According to a first aspect, an embodiment of the present application provides a speech retrieval method, including: acquiring voice retrieval contents and converting the voice retrieval contents into corresponding text retrieval contents; when the character retrieval content needs to be corrected, acquiring the corrected character retrieval content; inquiring a target document in a plurality of preset operation procedure documents according to the corrected text retrieval content; and outputting the target document.

With reference to the first aspect, in some embodiments of the present application, before the step of querying a target document from a plurality of preset operation procedure documents according to the corrected text retrieval content, the voice retrieval method further includes: and setting corresponding keywords for the operation procedure documents respectively.

With reference to the first aspect, in some embodiments of the application, the step of querying a target document among a plurality of preset operation procedure documents according to the corrected text retrieval content includes: and when any operation procedure document comprises the keywords which are the same as the corrected character retrieval content, determining that the operation procedure document is the target document.

With reference to the first aspect, in some embodiments of the application, the step of querying a target document from a plurality of preset operation procedure documents according to the corrected text retrieval content further includes: and when the key words of any operation procedure document are synonyms or synonyms of the corrected character retrieval content, determining that the operation procedure document is the target document.

With reference to the first aspect, in some embodiments of the present application, when the target document includes a plurality of files, a secondary query request is obtained, and the target document is ranked according to the secondary query request.

With reference to the first aspect, in some embodiments of the present application, the step of outputting the target document includes: and adopting a special display mode different from other characters for the keywords in the target document, which are the same as the corrected character retrieval content, and the synonyms or synonyms of the corrected character retrieval content contained in the target document.

With reference to the first aspect, in some embodiments of the present application, before the step of converting the voice search content into corresponding text search content, the voice search method further includes: training a preset machine learning model according to the voice retrieval content and the corrected character retrieval content; the machine learning model is used for converting the voice retrieval contents into corresponding character retrieval contents.

According to a second aspect, an embodiment of the present application provides a terminal device, including: the input unit is used for acquiring voice retrieval contents and converting the voice retrieval contents into corresponding character retrieval contents; the correction unit is used for acquiring corrected character retrieval contents when the character retrieval contents need to be corrected; the query unit is used for querying a target document in a plurality of preset operation procedure documents according to the corrected text retrieval content; an output unit for outputting the target document.

According to a third aspect, an embodiment of the present application provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method according to the first aspect or any embodiment of the first aspect when executing the computer program.

According to a fourth aspect, embodiments of the present application provide a computer-readable storage medium, which stores a computer program, and the computer program, when executed by a processor, implements the steps of the method according to the first aspect or any embodiment of the first aspect.

The voice retrieval method, the terminal device and the readable storage medium provided by the embodiment of the application can realize the convenience of supporting the counter service, namely realize voice query, and support the correction of the content of voice identification, can flexibly adapt to users with different accents and noisy working environments, and solve the problem of long time consumption in the prior art of manually browsing and querying the supporting content of the service. According to the voice retrieval method, the terminal device and the readable storage medium, the relevant operation procedure documents are retrieved by extracting the keywords, the plurality of keywords can be displayed according to the weight and the relevance in a sequencing mode, secondary query, chapter screening, field sequence display according to the updating date, the click rate and the like can be achieved on the basis of the original query result.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described 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 based on these drawings without inventive exercise.

Fig. 1 is a flowchart of a specific example of a speech retrieval method provided in an embodiment of the present application;

FIG. 2 is a flow chart of another specific example of a speech retrieval method provided by an embodiment of the present application;

fig. 3 is a schematic structural diagram of a specific example of a terminal device provided in an embodiment of the present application;

fig. 4 is a schematic structural diagram of another specific example of the terminal device provided in the embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, 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.

In order to explain the technical solution described in the present application, the following description will be given by way of specific examples.

The embodiment of the application provides a voice retrieval method, which can be applied to various system platforms, and the execution subject of the method can be any system related to article retrieval. As shown in fig. 1, the method may include the steps of:

step S101: and acquiring voice retrieval contents, and converting the voice retrieval contents into corresponding character retrieval contents.

The user can input the query conditions through voice and characters. After the user inputs the voice retrieval content, the system can convert the voice retrieval content into corresponding character retrieval content through a preset machine learning model so as to continue character retrieval in the subsequent steps.

Step S102: and when the character retrieval content needs to be corrected, acquiring the corrected character retrieval content.

The user inputs voice into the system through the microphone, and the system can automatically recognize the voice and convert the voice into characters to be written into a search box as search condition query. When a user finds that the text retrieval content obtained by the system through the machine learning model conversion has deviation with the voice retrieval content input by the microphone, the user can modify the query condition through manually inputting the text and can select whether to import the text into the template library or not, so that the accuracy of voice recognition is improved.

When the system obtains the character retrieval content through the machine learning model conversion and the voice retrieval content input by the user through the microphone is consistent, the user can input 'query' through voice or manually click a query button, and all documents containing the keyword or related to the keyword in the knowledge base can be retrieved.

Step S103: and inquiring a target document in a plurality of preset operation procedure documents according to the corrected text retrieval content.

Before step S103, the system administrator may set corresponding keywords for the plurality of operation procedure documents in advance, respectively. The system management personnel upload maintenance operation procedure documents and query keywords to the system in advance for the user to search and query. The system administrator uploads the documents and the keywords to the knowledge base, can add, delete and modify the documents and the keywords in the knowledge base, and can set the weight of the keywords. When the document is uploaded, files in txt, wps, et, dps, doc, docx, xls, xlsxx, ppt, html, xml, pdf and the like formats are supported. The system can automatically record all operations of the administrator on the documents and the keywords in the knowledge base, and can also cancel improper operations.

Under the condition that a plurality of keywords exist in the text retrieval content at the same time, the input retrieval condition can be preprocessed, namely word segmentation processing is carried out, the extracted keywords are compared with a keyword library, and the weight of the keywords in the knowledge library document is calculated. For the case of multiple keywords, relevance ranking is required according to the weight of the keywords, and documents containing keywords with larger weights are ranked in front.

Specifically, when any operation procedure document includes a keyword that is the same as the corrected character retrieval content, the operation procedure document is determined to be a target document.

The system supports query expansion and fuzzy query, improves recall ratio, and enables retrieval conditions and query results to be closer to natural language. In order to improve the query efficiency and enable the query result to be more accurate, on the construction of a database, the database comprises a homophone dictionary, a synonym dictionary, a related dictionary and the like, the automatic classification of operation procedure files in a transmission library can be realized, an index library can be automatically established for keywords, query high-frequency words and the like, and the efficiency of retrieving query files is improved from a bottom structure. In addition, the database can automatically build and mark searched contents, and after each retrieval is completed, the system can automatically add the contents such as the searched keywords, file titles and the like into the related index database for storage.

Specifically, when the keyword of any operation procedure document is a synonym or a synonym of the corrected text search content, it may be determined that the operation procedure document is the target document.

Step S104: and outputting the target document.

And adopting a special display mode different from other characters for the keywords in the target document, which are the same as the corrected character retrieval content, and the synonyms or synonyms of the corrected character retrieval content contained in the target document. By way of example, the retrieved documents highlight keywords and support the user in making secondary queries, such as by chapter filtering, or by field sorting, such as by date of update, click through, etc.

In a specific embodiment, after the user inputs an original query request, the idea of query expansion is to combine the search preprocessing and the search post-processing technologies, and introduce system feedback to make the closed-loop system converge and stable. By means of query expansion, new query sentences can be automatically added according to the semantics of users, and the query expansion can solve part of the problem of multiple synonyms or synonyms. In some cases, because the expression of the user is not reasonable or the semantic expansion degree is large, the retrieval result is different from the expectation, and an interactive and self-learning mode is needed. After the user inputs the retrieval request, the user waits for the initial query result and then feeds back the adjustment opinion of the user, so that the system automatically adjusts the algorithm of semantic expansion and the expansion depth. Through a large amount of queries, after a plurality of times of learning and self-adaptation, the system can realize faster retrieval and show relatively better retrieval results.

The speaking modes of each user are different, and the user can train a machine learning model suitable for individuals according to the use data of the user, so that the accuracy of the system in the aspect of speech recognition is improved, and the use is convenient.

Specifically, as shown in fig. 2, the following steps may be added before step S101:

step S101': and training a preset machine learning model according to the voice retrieval content and the corrected character retrieval content.

The voice retrieval method provided by the embodiment of the application can realize the convenience of supporting the counter service, namely, the voice query is realized, the content of the voice identification is supported to be corrected, the method can flexibly adapt to users with different accents and noisy working environments, and the problem that the time consumption is too long when the content is supported by manually browsing the query service at present is solved. According to the voice retrieval method, the terminal device and the readable storage medium, the relevant operation procedure documents are retrieved by extracting the keywords, the plurality of keywords can be displayed according to the weight and the relevance in a sequencing mode, secondary query, chapter screening, field sequence display according to the updating date, the click rate and the like can be achieved on the basis of the original query result.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

An embodiment of the present application further provides a terminal device, as shown in fig. 3, where the terminal device may include: input section 301, correction section 302, search section 303, and output section 304.

Specifically, the input unit 301 is configured to obtain a voice search content, and convert the voice search content into a corresponding text search content; the corresponding implementation process can be referred to the record of step S101 in the above method embodiment.

When the text retrieval content needs to be modified, the modifying unit 302 is configured to obtain the modified text retrieval content; the corresponding implementation process can be referred to the description of step S102 in the above method embodiment.

The query unit 303 is configured to query a target document among a plurality of preset operation procedure documents according to the corrected text retrieval content; the corresponding implementation process can be referred to the description of step S103 in the above method embodiment.

An output unit 304 for outputting a target document; the corresponding implementation process can be referred to the record of step S104 in the above method embodiment.

In practical application, the input unit 301 is further configured to train a preset machine learning model according to the voice search content and the corrected text search content; the machine learning model is used for converting the voice retrieval content into corresponding text retrieval content. This function of the input unit 301 can be realized by referring to the description of step S101' in the above method embodiment.

Fig. 4 is a schematic diagram of another terminal device provided in an embodiment of the present application. As shown in fig. 4, the terminal device 400 of this embodiment includes: a processor 401, a memory 402 and a computer program 403, such as a voice retrieval program, stored in the memory 402 and executable on the processor 401. The processor 401, when executing the computer program 403, implements the steps in the above-described embodiments of the speech retrieval method, such as the steps S101 to S104 shown in fig. 1. Alternatively, the processor 401, when executing the computer program 403, implements the functions of the modules/units in the device embodiments, such as the functions of the input unit 301, the correction unit 302, the query unit 303, and the output unit 304 in fig. 3.

The computer program 403 may be partitioned into one or more modules/units that are stored in the memory 402 and executed by the processor 401 to accomplish the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used for describing the execution process of the computer program 403 in the terminal device 400. For example, the computer program 403 may be partitioned into a synchronization module, a summarization module, an acquisition module, a return module (a module in a virtual device).

The terminal device 400 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal device may include, but is not limited to, a processor 401, a memory 402. Those skilled in the art will appreciate that fig. 4 is merely an example of a terminal device 400 and does not constitute a limitation of terminal device 400 and may include more or fewer components than shown, or some components may be combined, or different components, e.g., the terminal device may also include input-output devices, network access devices, buses, etc.

The Processor 401 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The storage 402 may be an internal storage unit of the terminal device 400, such as a hard disk or a memory of the terminal device 400. The memory 402 may also be an external storage device of the terminal device 400, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (D) Card, a Flash memory Card (Flash Card), and the like, which are provided on the terminal device 400. Further, the memory 402 may also include both an internal storage unit and an external storage device of the terminal device 400. The memory 402 is used for storing the computer programs and other programs and data required by the terminal device. The memory 402 may also be used to temporarily store data that has been output or is to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

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 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.

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 ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed 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 can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method of the embodiments described above can be realized by a computer program, which can be stored in a computer-readable storage medium and can realize the steps of the embodiments of the methods described above when the computer program is executed by a processor. . Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.

Claims

1. A method for voice retrieval, comprising:

acquiring voice retrieval contents and converting the voice retrieval contents into corresponding text retrieval contents;

when the character retrieval content needs to be corrected, acquiring the corrected character retrieval content;

inquiring a target document in a plurality of preset operation procedure documents according to the corrected text retrieval content;

and outputting the target document.

2. The voice retrieval method according to claim 1, wherein before the step of searching for a target document among a plurality of preset operation procedure documents based on the corrected text retrieval contents, the voice retrieval method further comprises:

and setting corresponding keywords for the operation procedure documents respectively.

3. The speech retrieval method of claim 2, wherein the step of searching for a target document among a plurality of preset operation procedure documents according to the corrected text retrieval contents comprises:

and when any operation procedure document comprises the keywords which are the same as the corrected character retrieval content, determining that the operation procedure document is the target document.

4. The speech retrieval method of claim 3, wherein the step of searching for a target document among a plurality of preset operation procedure documents according to the corrected text retrieval contents further comprises:

and when the key words of any operation procedure document are synonyms or synonyms of the corrected character retrieval content, determining that the operation procedure document is the target document.

5. The speech retrieval method according to claim 3 or 4, wherein when the target document includes a plurality of files, a secondary query request is obtained, and the target document is ranked according to the secondary query request.

6. The voice retrieval method of claim 5, wherein the step of outputting the target document comprises:

and adopting a special display mode different from other characters for the keywords in the target document, which are the same as the corrected character retrieval content, and the synonyms or synonyms of the corrected character retrieval content contained in the target document.

7. The voice retrieval method of claim 1, wherein, prior to the step of converting the voice retrieval content into corresponding text retrieval content, the voice retrieval method further comprises:

training a preset machine learning model according to the voice retrieval content and the corrected character retrieval content; the machine learning model is used for converting the voice retrieval contents into corresponding character retrieval contents.

8. A terminal device, comprising:

the input unit is used for acquiring voice retrieval contents and converting the voice retrieval contents into corresponding character retrieval contents;

the correction unit is used for acquiring corrected character retrieval contents when the character retrieval contents need to be corrected;

the query unit is used for querying a target document in a plurality of preset operation procedure documents according to the corrected text retrieval content;

an output unit for outputting the target document.

9. 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 method according to any of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.