CN113946652A - Information query method and device, computer readable storage medium and electronic equipment - Google Patents

Abstract

The application provides an information query method, an information query device, a medium and electronic equipment, which relate to the technical field of computers and comprise the following steps: when the user voice is detected, determining the query range of the database according to the user voice; converting the user voice into text information, and identifying entity nouns in the text information; determining a plurality of representation forms corresponding to entity nouns; query results corresponding to entity nouns are queried within a query scope based on a plurality of representations. Therefore, by implementing the method, the problem that the conversion from voice to text is inaccurate due to the fact that the same voice corresponds to multiple vocabularies can be considered, the entity nouns in the converted text information are represented through multiple representation forms, and information query is carried out based on the multiple representation forms, so that the accuracy of the determined query result is improved.

Description

Information query method and device, computer readable storage medium and electronic equipment

Technical Field

The present application relates to the field of computer technologies, and in particular, to an information query method, an information query apparatus, a computer-readable storage medium, and an electronic device.

Background

Generally, the operator provides telephone inquiry services to the user, specifically including telephone charge inquiry, enterprise inquiry, location inquiry and the like. The user can dial the fixed number and speak the query requirement after the call is connected, and the intelligent manual work can convert the received user voice into characters and feed back the content related to the characters as the query result. However, if the characters obtained by conversion in this way are inaccurate, the accuracy of the fed-back query result is affected.

It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present application and therefore may include information that does not constitute prior art known to a person of ordinary skill in the art.

Disclosure of Invention

The present application aims to provide an information query method, an information query device, a computer-readable storage medium, and an electronic device, which can consider the problem that a voice-to-text conversion is inaccurate due to multiple vocabularies corresponding to the same voice, represent entity nouns in text information obtained by conversion through multiple representation forms, and perform information query based on the multiple representation forms, thereby improving the accuracy of a determined query result.

Other features and advantages of the present application will be apparent from the following detailed description, or may be learned by practice of the application.

According to an aspect of the present application, there is provided an information query method, including:

when the user voice is detected, determining the query range of the database according to the user voice;

converting the user voice into text information, and identifying entity nouns in the text information;

determining a plurality of representation forms corresponding to entity nouns;

query results corresponding to entity nouns are queried within a query scope based on a plurality of representations.

In an exemplary embodiment of the present application, determining a query scope of a database according to a user voice includes:

determining an incoming call number corresponding to the voice of the user;

inquiring region information corresponding to the incoming call number; the region information comprises at least one of an area code and a place name;

and determining the query range of the database according to the region information.

In an exemplary embodiment of the present application, the plurality of representations includes: the entity noun corresponds to at least one of full name, short name, full name pinyin, short name pinyin, full name pinyin initial combination and short name pinyin initial combination.

In an exemplary embodiment of the present application, query results corresponding to entity nouns are queried in a query scope based on a plurality of expressions, including:

sorting the plurality of representation forms based on the representation form priorities to obtain a first sorting result;

sequentially inquiring a plurality of representation forms in an inquiry range according to the first ordering result;

and obtaining the description information corresponding to the representation form of the hit database as a query result corresponding to the entity noun.

In an exemplary embodiment of the present application, the method further includes:

if the representation form of the hit real database does not exist in the plurality of representation forms, determining a reference entity corresponding to at least one representation form in the plurality of representation forms; the reference entity comprises at least one of a homophone entity, a polyphonic entity, a fuzzy entity and a near-sound entity;

sorting all the reference entities based on the entity priorities to obtain a second sorting result;

sequentially querying all the reference entities in the query range according to the second sequencing result;

determining reference entities hitting a database, and screening at least one target reference entity with the highest association degree with entity nouns from the reference entities hitting the database;

and acquiring the description information corresponding to at least one target reference entity as a query result corresponding to the noun.

In an exemplary embodiment of the present application, after obtaining the description information corresponding to the representation form of the hit database as the query result corresponding to the entity noun, the method further includes:

if the representation form of the hit database corresponds to a to-be-selected entity, converting the description information of the to-be-selected entity into a voice signal or text information and sending the voice signal or the text information to the user terminal;

if the representation form of the hit database corresponds to multiple entities to be selected, a prompt message for indicating a user to select one entity to be selected from the entities to be selected is output, and when the selection operation is detected, the description information of the entity to be selected corresponding to the selection operation is converted into a voice signal or text information and is sent to the user terminal.

In an exemplary embodiment of the present application, after converting the description information of the to-be-selected entity corresponding to the selection operation into a voice signal or text information and sending the voice signal or text information to the user terminal, the method further includes:

and updating the heat value of the entity to be selected corresponding to the selection operation.

According to an aspect of the present application, there is provided an information query apparatus including:

the query range determining unit is used for determining the query range of the database according to the user voice when the user voice is detected;

the voice conversion unit is used for converting the user voice into text information and identifying entity nouns in the text information;

an entity representation form determining unit, which is used for determining a plurality of representation forms corresponding to entity nouns;

and the query unit is used for querying a query result corresponding to the entity noun in the query range based on the plurality of expression forms.

In an exemplary embodiment of the present application, the query range determining unit determines the query range of the database according to the user voice, including:

determining an incoming call number corresponding to the voice of the user;

inquiring region information corresponding to the incoming call number; the region information comprises at least one of an area code and a place name;

and determining the query range of the database according to the region information.

In an exemplary embodiment of the present application, the plurality of representations includes: the entity noun corresponds to at least one of full name, short name, full name pinyin, short name pinyin, full name pinyin initial combination and short name pinyin initial combination.

In an exemplary embodiment of the present application, the query unit queries the query result corresponding to the entity noun in the query range based on a plurality of expressions, including:

sorting the plurality of representation forms based on the representation form priorities to obtain a first sorting result;

sequentially inquiring a plurality of representation forms in an inquiry range according to the first ordering result;

and obtaining the description information corresponding to the representation form of the hit database as a query result corresponding to the entity noun.

In an exemplary embodiment of the present application, the apparatus further includes:

the entity determining unit is used for determining a reference entity corresponding to at least one representation form in the plurality of representation forms when the representation form of the hit real database does not exist in the plurality of representation forms; the reference entity comprises at least one of a homophone entity, a polyphonic entity, a fuzzy entity and a near-sound entity;

the entity sorting unit is used for sorting all the reference entities based on the entity priority to obtain a second sorting result;

the entity query unit is used for sequentially querying all the reference entities in the query range according to the second sequencing result;

the entity screening unit is used for determining reference entities hitting the database and screening at least one target reference entity with the highest association degree with entity nouns from the reference entities hitting the database;

and the information acquisition unit is used for acquiring the description information corresponding to at least one target reference entity as a query result corresponding to the noun.

In an exemplary embodiment of the present application, the apparatus further includes:

the information sending unit is used for converting the description information of the entity to be selected into a voice signal or text information and sending the voice signal or the text information to the user terminal if the representation form of the hit database corresponds to the entity to be selected after the information acquiring unit acquires the description information corresponding to the representation form of the hit database as a query result corresponding to the entity noun; if the representation form of the hit database corresponds to multiple entities to be selected, a prompt message for indicating a user to select one entity to be selected from the entities to be selected is output, and when the selection operation is detected, the description information of the entity to be selected corresponding to the selection operation is converted into a voice signal or text information and is sent to the user terminal.

In an exemplary embodiment of the present application, the apparatus further includes:

and the heat updating unit is used for updating the heat value of the entity to be selected corresponding to the selection operation after the information sending unit converts the description information of the entity to be selected corresponding to the selection operation into a voice signal or text information and sends the voice signal or the text information to the user terminal.

According to an aspect of the present application, there is provided an electronic device including: a processor; and a memory for storing executable instructions for the processor; wherein the processor is configured to perform the method of any of the above via execution of the executable instructions.

According to an aspect of the application, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any one of the above.

According to an aspect of the application, a computer program product or computer program is provided, comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the method provided in the various alternative implementations described above.

The exemplary embodiments of the present application may have some or all of the following advantages:

in the information query method provided by an example embodiment of the present application, when a user voice is detected, a query range of a database may be determined according to the user voice; converting the user voice into text information, and identifying entity nouns in the text information; determining a plurality of representation forms corresponding to entity nouns; query results corresponding to entity nouns are queried within a query scope based on a plurality of representations. According to the technical description, on one hand, the problem that the conversion from voice to text words is inaccurate due to the fact that the same voice corresponds to multiple vocabularies can be considered, the entity nouns in the converted text information are represented through multiple representation forms, information query is conducted based on the multiple representation forms, and therefore the accuracy of the determined query result is improved. On the other hand, the query efficiency can be improved by positioning the query range.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application. It is obvious that the drawings in the following description are only some embodiments of the application, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.

Fig. 1 is a schematic diagram illustrating an exemplary system architecture to which an information query method and an information query apparatus according to an embodiment of the present application may be applied;

FIG. 2 illustrates a schematic structural diagram of a computer system suitable for use in implementing an electronic device of an embodiment of the present application;

FIG. 3 schematically shows a flow diagram of an information query method according to an embodiment of the present application;

FIG. 4 schematically illustrates a block diagram of an information query system according to one embodiment of the present application;

FIG. 5 schematically illustrates a block diagram of an information query system according to another embodiment of the present application;

FIG. 6 schematically shows a flow diagram of an information query method according to an embodiment of the present application;

fig. 7 schematically shows a block diagram of an information inquiry apparatus in an embodiment according to the present application.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the subject matter of the present application can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present application.

Furthermore, the drawings are merely schematic illustrations of the present application and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

Fig. 1 is a schematic diagram illustrating a system architecture of an exemplary application environment to which an information query method and an information query apparatus according to an embodiment of the present application may be applied.

As shown in fig. 1, the system architecture 100 may include one or more of terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few. The terminal devices 101, 102, 103 may be various electronic devices having a display screen, including but not limited to desktop computers, portable computers, smart phones, tablet computers, and the like. It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. For example, server 105 may be a server cluster comprised of multiple servers, or the like.

The information query method provided by the embodiment of the present application is generally executed by the server 105, and accordingly, the information query apparatus is generally disposed in the server 105. However, it is easily understood by those skilled in the art that the information query method provided in the embodiment of the present application may also be executed by the terminal device 101, 102, or 103, and accordingly, the information query apparatus may also be disposed in the terminal device 101, 102, or 103, which is not particularly limited in this exemplary embodiment. For example, in one exemplary embodiment, server 105, upon detecting a user voice, determines a query range of the database based on the user voice; converting the user voice into text information, and identifying entity nouns in the text information; determining a plurality of representation forms corresponding to entity nouns; query results corresponding to entity nouns are queried within a query scope based on a plurality of representations.

FIG. 2 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.

It should be noted that the computer system 200 of the electronic device shown in fig. 2 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in fig. 2, the computer system 200 includes a Central Processing Unit (CPU)201 that can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)202 or a program loaded from a storage section 208 into a Random Access Memory (RAM) 203. In the RAM 203, various programs and data necessary for system operation are also stored. The CPU 201, ROM 202, and RAM 203 are connected to each other via a bus 204. An input/output (I/O) interface 205 is also connected to bus 204.

The following components are connected to the I/O interface 205: an input portion 206 including a keyboard, a mouse, and the like; an output section 207 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 208 including a hard disk and the like; and a communication section 209 including a network interface card such as a LAN card, a modem, or the like. The communication section 209 performs communication processing via a network such as the internet. A drive 210 is also connected to the I/O interface 205 as needed. A removable medium 211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like, is mounted on the drive 210 as necessary, so that a computer program read out therefrom is installed into the storage section 208 as necessary.

In particular, according to embodiments of the present application, the processes described below with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 209 and/or installed from the removable medium 211. The computer program, when executed by a Central Processing Unit (CPU)201, performs various functions defined in the methods and apparatus of the present application.

The example embodiment provides an information query method. The information query method may be applied to the server 105, and may also be applied to one or more of the terminal devices 101, 102, and 103, which is not particularly limited in this exemplary embodiment. As shown in fig. 3, the information query method may include the following steps S310 to S340.

Step S310: and when the user voice is detected, determining the query range of the database according to the user voice.

Step S320: the user speech is converted into text information, and entity nouns in the text information are identified.

Step S330: a plurality of representations corresponding to the entity nouns are determined.

Step S340: query results corresponding to entity nouns are queried within a query scope based on a plurality of representations.

Therefore, by implementing the method shown in fig. 3, the problem that the conversion from speech to text is inaccurate due to the fact that the same speech corresponds to multiple vocabularies can be considered, the entity nouns in the converted text information are represented in multiple representation forms, and information query is performed based on the multiple representation forms, so that the accuracy of the determined query result is improved. In addition, the query efficiency can be improved by positioning the query range.

The above steps of the present exemplary embodiment will be described in more detail below.

In step S310, when the user voice is detected, a query range of the database is determined according to the user voice.

The user voice may be an audio obtained in the call process, and before step S310, the method may further include: and automatically answering the incoming call of the user and continuously acquiring the voice of the user. Furthermore, determining the query range of the database according to the voice of the user comprises the following steps: extracting key words (such as Beijing) in the voice of the user, and determining the query range of the database according to the key words.

As an alternative embodiment of step S310, determining the query range of the database according to the user voice includes: determining an incoming call number corresponding to the voice of the user; inquiring region information corresponding to the incoming call number; the region information comprises at least one of an area code and a place name; and determining the query range of the database according to the region information. Therefore, the query range can be reduced, the query of the whole database is avoided, the query quantity can be reduced, and the query efficiency is improved. For example, if the region information corresponding to the incoming call number indicates that the incoming call number is registered in south chang or dialed from south chang, and the user voice includes "find house administration", the find house administration in south chang city is determined. And if the region information corresponding to the incoming call number indicates that the incoming call number is dialed from the administrative district of the Nanchang red valley beach, and the voice of the user contains 'house checking management bureau', the house management bureau of the administrative district of the Nanchang red valley beach is inquired by default.

The incoming call number may be a real telephone number or a virtual telephone number, and may be represented as a combination of multiple digits, for example, 18612345678. In addition, the region information is used to represent a region where the incoming call user is located, the region may take province, city, district, county, town or village as a minimum unit, the region information may be represented as text, character string, numerical value, and the like, the embodiment of the present application is not limited, and the region information may include at least one of province, city, district, county, town and village. For example, the region information may be: the Haitai district of Beijing. In addition, the area code (e.g., 12345) and the place name (e.g., Tong county) may both be representative of the area where the user is located.

Optionally, after determining the incoming call number corresponding to the user voice, the method further includes: determining whether the incoming call number is a real number or a virtual number; if the number is a virtual number, outputting a voice prompt for prompting the user to provide a real position, continuously detecting the voice of the user, and determining region information according to the position of the user after detecting that the voice of the user contains the position of the user; and if the number is the real number, inquiring the attribution corresponding to the real number, and determining the region information according to the attribution.

Further, optionally, determining the query range of the database according to the region information includes: and inquiring a field corresponding to the region information in the database, and determining all values corresponding to the field as an inquiry range. Where a database may be used to store a region field (e.g., Tong county) and a corresponding value (e.g., Tong county police), which may be understood as an entity vocabulary.

Optionally, after querying the region information corresponding to the incoming call number, the method may further include: and inquiring the current location corresponding to the incoming call number. Based on this, the query range of the database is determined according to the region information, and the query range comprises the following steps: and determining the query range of the database according to the current positioning and the region information. Based on this, further, a specific implementation of determining the query range of the database according to the current location and the regional information may be: determining the query range of a database (such as Beijing) according to the regional information, and determining the region (such as Hai lake region) of the user according to the current positioning; if the area belongs to the area limited by the area information, the query range is narrowed according to the area; if the area does not belong to the area defined by the area information, outputting a prompt voice for inquiring the area range which needs to be inquired by the user, receiving the feedback operation of the user (such as the selection operation of the area or the area information), and correcting the inquiry range according to the real area corresponding to the feedback operation.

In step S320, the user speech is converted into text information, and a noun in the text information is identified.

As an alternative embodiment of step S320, converting the user speech into text information includes: user Speech is converted into text information based on Speech recognition technology (ASR). The method specifically comprises the following steps: processing user voice into digital signals based on ASR, splitting the digital signals according to millisecond-level frames, and representing the split digital signals into multidimensional vectors; and performing state recognition on the split digital signals, recognizing the digital signals into phonemes according to the state recognition result, and determining text information according to each phoneme. Based on this, identifying entity nouns in text information includes: and performing word segmentation processing on the text information, and performing named entity recognition on the word segmentation processing result based on a user-defined rule, a word set or a recognition model. The number of entity nouns in the text message may be one or more, and the entity nouns may be composed of one or more words. For example, the entity noun may be a merchant name, landmark, secondary name, etc.

In addition, optionally, after the entity nouns in the text message are identified, the method may further include: the identified entity nouns are structurally represented (e.g., node tree), and the structural representation result may include a hierarchical relationship between entity nouns, for example, a primary entity noun may be beijing, a secondary entity noun may be hai lake, and a secondary entity noun is subordinate to the primary entity noun. Based on the above, query results corresponding to entity nouns are queried in a query range based on a plurality of expressions, including: query results corresponding to entity nouns are queried in a query range based on multiple representation forms in the structured representation results, and therefore query efficiency can be improved.

In step S330, a plurality of expressions corresponding to the entity nouns are determined. Wherein the plurality of representations includes: the entity noun corresponds to at least one of full name, short name, full name pinyin, short name pinyin, full name pinyin initial combination and short name pinyin initial combination. For example, the various representations may be expressed as { 'full name': 'judicial bureau', 'full-name pinyin': 'si fa ju', 'full pinyin initial combination': 'SFJ' }, { 'abbreviation': 'judicial place', 'Pinyin for short': 'si fa suo', 'pinyin initial combination for short': 'SFS' }.

In step S340, query results corresponding to the entity nouns are queried in the query scope based on the plurality of representations.

As an alternative embodiment of step S340, query the query result corresponding to the entity noun in the query scope based on multiple expressions, including: sorting the plurality of representation forms based on the representation form priorities to obtain a first sorting result; sequentially inquiring a plurality of representation forms in an inquiry range according to the first ordering result; and obtaining the description information corresponding to the representation form of the hit database as a query result corresponding to the entity noun. Therefore, the query efficiency can be improved, the accuracy of the query result is improved, and the labor cost is reduced.

The representation form priority may be used to characterize query priority among various representation forms, where the first ranking result and the second ranking result are different ranking results respectively, and corresponding ranking objects are different. In addition, the description information includes detailed information (e.g., is a special army of the international security association dedicated to handling various singular events) for a named entity (e.g., the miracle) in a representation (e.g., the shannon). In addition, the query result may include at least one of text, picture, video, audio, and the like, and the embodiment of the present application is not limited. The query result is a comprehensive presentation of the description information, and the presentation mode of the query result includes but is not limited to: voice reply and message reply.

In addition, a plurality of expressions are sequentially queried in a query range according to the first sequencing result, including: the plurality of representations are sequentially queried by the search engine within a query scope based on the first ranked result. The search engine may be a full text search Engine (ES), or may be another search engine, which is not limited in the embodiment of the present application.

Further, the method further comprises: if the representation form of the hit real database does not exist in the plurality of representation forms, determining a reference entity corresponding to at least one representation form in the plurality of representation forms; the reference entity comprises at least one of a homophone entity, a polyphonic entity, a fuzzy entity and a near-sound entity; sorting all the reference entities based on the entity priorities to obtain a second sorting result; sequentially querying all the reference entities in the query range according to the second sequencing result; determining reference entities hitting a database, and screening at least one target reference entity with the highest association degree with entity nouns from the reference entities hitting the database; and acquiring the description information corresponding to at least one target reference entity as a query result corresponding to the noun. This can improve the query accuracy.

The number of the reference entities corresponding to at least one of the multiple representations may be one or more, the reference entities may be a vocabulary formed by one or more words, and the entity priority may be used to characterize the query priority among the various reference entities. The at least one target reference entity with the highest degree of association with the entity noun may be N entities with the smallest cosine/euclidean distance to the entity noun, where N is a positive integer.

It should be noted that the homophonic entities are entity words which are identical in spelling but different in pronunciation or in terms of characters, the polyphonic entities are entity words which are identical in terms of characters but corresponding to other pronunciations, the fuzzy entities are high-frequency error-prone entity words which are mainly common near-sound words in the mainstream input method, and the near-sound entities are entity words with similar pronunciation.

Furthermore, after obtaining the description information corresponding to the representation form of the hit database as the query result corresponding to the entity noun, the method further includes: if the representation form of the hit database corresponds to a to-be-selected entity, converting the description information of the to-be-selected entity into a voice signal or text information and sending the voice signal or the text information to the user terminal; if the representation form of the hit database corresponds to multiple entities to be selected, a prompt message for indicating a user to select one entity to be selected from the entities to be selected is output, and when the selection operation is detected, the description information of the entity to be selected corresponding to the selection operation is converted into a voice signal or text information and is sent to the user terminal. Therefore, richer interactive experience can be promoted, and self-service query experience is improved.

Optionally, outputting a prompt message for instructing a user to select one entity to be selected from the entities to be selected, where the prompt message includes: broadcasting entities to be selected corresponding to the various kinds of description information and the numbers corresponding to the entities to be selected by voice; detecting a number selected/input by a user, the number corresponding to an entity to be selected, and judging that the selection operation is detected. For example, when the entities to be selected corresponding to the queried description information are "business bureau" and "human society bureau", respectively, the query result including the business bureau and the human society bureau, the business bureau 1 and the human society bureau 2 may be selected and broadcast in a call with the user, the user may press 1 or 2 through a numeric keypad in a call interface, or call a virtual keypad to input 1 or 2, and further, it may be determined that the selection operation is detected.

Furthermore, after converting the description information of the entity to be selected corresponding to the selection operation into a voice signal or text information and sending the voice signal or text information to the user terminal, the method further comprises the following steps: and updating the heat value of the entity to be selected corresponding to the selection operation. Therefore, the feedback of the recommendation sequencing can be realized, and the query precision of the query service is improved.

The selection operation may be a click operation, a touch screen operation, a voice input operation, and the like, and the embodiment of the present application is not limited. In addition, the heat value of a noun is used to characterize the frequency with which the noun is queried, and the higher the heat value is, the more times the noun is queried is indicated. After the description information of the entity to be selected corresponding to the selection operation is converted into a voice signal or text information and sent to the user terminal, the heat value of the entity noun may be +1, or the entity to be selected that is not selected by the user may be selected. Based on this, the above method may further include: and optimizing the search engine according to the updated heat value of the entity nouns.

Optionally, as a system for implementing the steps shown in fig. 3, referring to fig. 4, the information query system 400 specifically includes: the system comprises a sound receiving module 401, a merchant labeling module 402, a semantic understanding module 403, a search engine module 404 and a merchant popularity module 405.

And the radio receiving module 401 is used for acquiring the voice of the user.

And the labeling module 402 is configured to label entity nouns and store the labeled entity nouns in a structured database.

A semantic understanding module 403, configured to convert the user speech into text information, and identify entity nouns in the text information; a plurality of representations corresponding to the entity nouns are determined.

A search engine module 404, configured to determine a query range of the database according to the user voice; query results corresponding to entity nouns are queried within a query scope based on a plurality of representations.

And a heat update module 405, configured to convert the description information of the entity to be selected corresponding to the selection operation into a voice signal or text information, and send the voice signal or text information to the user terminal, and then update the heat value of the entity to be selected corresponding to the selection operation.

Further, please refer to fig. 5. As shown in fig. 5, another information query system is provided, which may specifically include: call center 510, speech recognition module 520, hub control module 530, semantic understanding module 540, interaction engine 550, flow engine 560, task scheduling engine 570, database 580, business system 590. Among them, the interaction engine 550 may include: context management module 5501, user query module 5502. The flow engine 560 may include: a slot missing processing module 5601, a flow scheduling module 5602, and an exception handling module 5603. The task scheduling engine 570 may include: an interface scheduling module 5701 and an extended scheduling module 5702.

The call center 510 is used for automatically receiving the incoming call of the user.

The speech recognition module 520 is configured to obtain a user speech, convert the user speech into text information, and recognize a noun in the text information.

And the central control module 530 is configured to schedule the to-be-processed tasks corresponding to the interaction engine 550, the flow engine 560 and the task scheduling engine 570, respectively.

The semantic understanding module 540 is used for converting the user voice into text information and identifying entity nouns in the text information; a plurality of representations corresponding to the entity nouns are determined.

The interaction engine 550 is used for determining entity nouns more conforming to the real meaning of the user through the context management module 5501, and determining the query range of the database according to the user voice through the user query module 5502.

The process engine 560 serves as a bottom support platform, and the correctness of the process engine can be verified through upper-layer application. The process engine kernel mainly includes process loading, process execution and data synchronization, and can be implemented by controlling the slot missing processing module 5601, the process scheduling module 5602 and the exception handling module 5603.

And the task scheduling engine 570 is used for calling each interface through the interface scheduling module 5701 and scheduling other required contents through the extended scheduling module 5702.

A database 580 for providing data query services.

And the business system 590 is used for providing business information query service and information calling service.

Therefore, with the system shown in fig. 4/5, it is possible to consider the problem that the conversion of speech into text words is inaccurate due to the fact that the same speech corresponds to multiple vocabularies, express the entity nouns in the converted text information in multiple expression forms, and perform information query based on the multiple expression forms, thereby improving the accuracy of the determined query result. In addition, the query efficiency can be improved by positioning the query range.

In addition, as an optional embodiment, the steps shown in fig. 3 and the embodiment thereof are integrated to show the information query method shown in fig. 6, which specifically includes: step S600 to step S680.

Step S600: and when the voice of the user is detected, determining the incoming call number corresponding to the voice of the user.

Step S610: inquiring region information corresponding to the incoming call number; the region information comprises at least one of an area code and a place name; and determining the query range of the database according to the region information.

Step S620: the user speech is converted into text information, and entity nouns in the text information are identified.

Step S630: a plurality of representations corresponding to the entity nouns are determined.

Step S640: and sequencing the plurality of expression forms based on the expression form priorities to obtain a first sequencing result, sequentially querying the plurality of expression forms in a query range according to the first sequencing result until the database is hit, and acquiring the description information corresponding to the expression forms of the hit database as the query result corresponding to the entity nouns.

Step S650: if the representation form of the hit real database does not exist in the plurality of representation forms, determining a reference entity corresponding to at least one representation form in the plurality of representation forms; the reference entity comprises at least one of a homophone entity, a polyphonic entity, a fuzzy entity and a near-sound entity.

Step S660: and sequencing all the reference entities based on the entity priorities to obtain a second sequencing result, sequentially querying all the reference entities in the query range according to the second sequencing result, determining the reference entities hitting the database, screening at least one target reference entity with the highest association degree with the entity nouns from the reference entities of the database hitting, and obtaining the description information corresponding to the at least one target reference entity as the query result corresponding to the nouns. If the representation of the hit database corresponds to a candidate entity, step S670 is performed. If the representation form of the hit database corresponds to the plurality of entities to be selected, step S680 is performed.

Step S670: and converting the description information of the entity to be selected into a voice signal or text information and sending the voice signal or text information to the user terminal.

Step S680: and outputting a prompt message for indicating a user to select one entity to be selected from the entities to be selected, converting the description information of the entity to be selected corresponding to the selection operation into a voice signal or text information and sending the voice signal or the text information to the user terminal when the selection operation is detected, and updating the heat value of the entity to be selected corresponding to the selection operation.

It should be noted that steps S600 to S680 correspond to the steps and embodiments shown in fig. 3, and for the specific implementation of steps S600 to S680, please refer to the steps and embodiments shown in fig. 3, which are not described herein again.

Therefore, by implementing the method shown in fig. 6, the problem that the conversion from speech to text is inaccurate due to the fact that the same speech corresponds to multiple vocabularies can be considered, the entity nouns in the converted text information are represented in multiple representation forms, and information query is performed based on the multiple representation forms, so that the accuracy of the determined query result is improved. In addition, the query efficiency can be improved by positioning the query range.

Further, in the present exemplary embodiment, an information query apparatus is also provided. Referring to the information query apparatus 700 shown in fig. 7, the information query apparatus 700 corresponds to the steps shown in fig. 3, and the information query apparatus 700 may include:

a query range determining unit 701, configured to determine a query range of the database according to the user voice when the user voice is detected;

a voice conversion unit 702, configured to convert the user voice into text information, and identify a noun in the text information;

an entity representation form determining unit 703, configured to determine multiple representation forms corresponding to entity nouns;

a query unit 704, configured to query the query range for query results corresponding to the entity nouns based on multiple representations.

Wherein the plurality of representations includes: the entity noun corresponds to at least one of full name, short name, full name pinyin, short name pinyin, full name pinyin initial combination and short name pinyin initial combination.

Therefore, by implementing the apparatus shown in fig. 7, the problem that the conversion of speech into text words is inaccurate due to the fact that the same speech corresponds to multiple vocabularies can be considered, the entity nouns in the converted text information are represented in multiple representation forms, and information query is performed based on the multiple representation forms, so that the accuracy of the determined query result is improved. In addition, the query efficiency can be improved by positioning the query range.

In an exemplary embodiment of the present application, the query range determining unit 701 determines the query range of the database according to the user voice, including:

determining an incoming call number corresponding to the voice of the user;

inquiring region information corresponding to the incoming call number; the region information comprises at least one of an area code and a place name;

and determining the query range of the database according to the region information.

Therefore, by implementing the optional embodiment, the query range can be reduced, the query of the whole database is avoided, the query quantity can be reduced, and the query efficiency is improved.

In an exemplary embodiment of the present application, the query unit 704 queries the query result corresponding to the entity noun in the query range based on a plurality of expressions, including:

sorting the plurality of representation forms based on the representation form priorities to obtain a first sorting result;

sequentially inquiring a plurality of representation forms in an inquiry range according to the first ordering result;

and obtaining the description information corresponding to the representation form of the hit database as a query result corresponding to the entity noun.

Therefore, by implementing the optional embodiment, the query efficiency can be improved, the accuracy of the query result can be improved, and the labor cost can be reduced.

In an exemplary embodiment of the present application, the apparatus further includes:

an entity determining unit (not shown) configured to determine a reference entity corresponding to at least one of the plurality of representations when there is no representation hit in the real database among the plurality of representations; the reference entity comprises at least one of a homophone entity, a polyphonic entity, a fuzzy entity and a near-sound entity;

an entity sorting unit (not shown) configured to sort all reference entities based on entity priorities to obtain a second sorting result;

the entity query unit 704 is further configured to sequentially query all the reference entities within the query range according to the second sorting result;

an entity screening unit (not shown) for determining reference entities hitting the database and screening at least one target reference entity having the highest association degree with the entity nouns from the reference entities hitting the database;

and the information acquisition unit is used for acquiring the description information corresponding to at least one target reference entity as a query result corresponding to the noun.

Therefore, the query precision can be improved by implementing the alternative embodiment.

In an exemplary embodiment of the present application, the apparatus further includes:

an information sending unit (not shown) for converting the description information of the entity to be selected into a voice signal or text information and sending the voice signal or text information to the user terminal if the representation form of the hit database corresponds to the entity to be selected after the information obtaining unit obtains the description information corresponding to the representation form of the hit database as a query result corresponding to the entity noun; if the representation form of the hit database corresponds to multiple entities to be selected, a prompt message for indicating a user to select one entity to be selected from the entities to be selected is output, and when the selection operation is detected, the description information of the entity to be selected corresponding to the selection operation is converted into a voice signal or text information and is sent to the user terminal.

Therefore, by implementing the optional embodiment, richer interactive experience can be promoted, and self-service query experience can be improved.

In an exemplary embodiment of the present application, the apparatus further includes:

and a heat updating unit (not shown) for updating the heat value of the entity to be selected corresponding to the selection operation after the information sending unit converts the description information of the entity to be selected corresponding to the selection operation into a voice signal or text information and sends the voice signal or text information to the user terminal.

Therefore, the implementation of the optional embodiment can realize the feedback of the recommendation ranking, and is beneficial to improving the query precision of the query service.

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the application. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

For details that are not disclosed in the embodiments of the apparatus of the present application, please refer to the embodiments of the information query method described above for the details that are not disclosed in the embodiments of the apparatus of the present application.

As another aspect, the present application also provides a computer-readable medium, which may be contained in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by an electronic device, cause the electronic device to implement the method described in the above embodiments.

It should be noted that the computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software, or may be implemented by hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims (10)

1. An information query method, comprising:

when user voice is detected, determining a query range of a database according to the user voice;

converting the user voice into text information, and identifying entity nouns in the text information;

determining a plurality of representation forms corresponding to the entity nouns;

querying a query result corresponding to the entity noun in the query range based on the plurality of representations.

2. The method of claim 1, wherein determining a query scope of a database based on the user speech comprises:

determining an incoming call number corresponding to the user voice;

inquiring the region information corresponding to the incoming call number; the region information comprises at least one of an area code and a place name;

and determining the query range of the database according to the region information.

3. The method of claim 1, wherein the plurality of representations comprises: the entity noun corresponds to at least one of full name, short name, full name pinyin, short name pinyin, full name pinyin initial combination and short name pinyin initial combination.

4. The method of claim 1, wherein querying the query range for query results corresponding to the noun based on the plurality of representations comprises:

sorting the plurality of representation forms based on the representation form priority to obtain a first sorting result;

sequentially inquiring the plurality of representation forms in the inquiry range according to the first ordering result;

and obtaining the description information corresponding to the representation form hitting the database as a query result corresponding to the entity noun.

5. The method of claim 4, further comprising:

if the representation form which hits the real database does not exist in the plurality of representation forms, determining a reference entity corresponding to at least one representation form in the plurality of representation forms; wherein the reference entity comprises at least one of a homophonic entity, a polyphonic entity, a fuzzy entity and a nearsighted entity;

sorting all the reference entities based on the entity priorities to obtain a second sorting result;

sequentially querying all the reference entities in the query range according to the second sequencing result;

determining reference entities hitting the database, and screening at least one target reference entity with the highest association degree of the entity nouns from the reference entities hitting the database;

and acquiring the description information corresponding to the at least one target reference entity as a query result corresponding to the noun.

6. The method of claim 4, wherein after obtaining the description information corresponding to the representation that hits the database as a result of the query corresponding to the entity noun, the method further comprises:

if the representation form of hitting the database corresponds to a to-be-selected entity, converting the description information of the to-be-selected entity into a voice signal or text information and sending the voice signal or the text information to a user terminal;

if the representation form of the hit database corresponds to multiple entities to be selected, outputting a prompt message for indicating a user to select one entity to be selected from the entities to be selected, and converting the description information of the entity to be selected corresponding to the selection operation into a voice signal or text information to be sent to the user terminal when the selection operation is detected.

7. The method according to claim 6, wherein after converting the query result of the entity noun corresponding to the selection operation into a voice signal or a text message and sending the voice signal or the text message to the user terminal, the method further comprises:

and updating the heat value of the entity to be selected corresponding to the selection operation.

8. An information inquiry apparatus, comprising:

the query range determining unit is used for determining the query range of the database according to the user voice when the user voice is detected;

the voice conversion unit is used for converting the user voice into text information and identifying entity nouns in the text information;

an entity representation form determining unit, configured to determine a plurality of representation forms corresponding to the entity noun;

and the query unit is used for querying a query result corresponding to the entity noun in the query range based on the plurality of expression forms.

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

10. An electronic device, comprising:

a processor; and

a memory for storing executable instructions of the processor;

wherein the processor is configured to perform the method of any of claims 1-7 via execution of the executable instructions.

Images