CN118277515A - Question answering method, device, equipment, storage medium and vehicle based on interest points - Google Patents

Abstract

The disclosure relates to a question answering method, a question answering device, question answering equipment, a storage medium and a vehicle based on interest points, wherein the question answering method comprises the following steps: acquiring questioning audio data of a user; performing voice recognition processing on the questioning audio data to obtain interest points aimed by the user and questions aimed at the interest points; searching answers to the questions in a preset database; and generating reply information based on the answer of the question and playing the reply information. According to the method and the device, the interest point and the question aimed by the user are identified from the acquired question audio data, answers to the questions are searched in the preset database, and the answer information is generated and played according to the answers to the questions, so that the questions aimed by the user can be automatically answered, a driver does not need to check or analyze the information of the interest point, whether the interest point accords with expectations can be determined, whether the driver needs to drive the vehicle to the interest point is determined, driving safety is improved, and user experience is improved.

Description

Question answering method, device, equipment, storage medium and vehicle based on interest points

Technical Field

The disclosure relates to the field of information technology, and in particular relates to a question answering method, a question answering device, question answering equipment, question answering storage medium and question answering vehicle based on interest points.

Background

In the process of driving the vehicle by the user, the navigation system can acquire information of the interest point (Point Of Interest, POI) and judge whether the type of the interest point is a wanted type, so as to determine whether to drive to the interest point. However, if the driver is traveling alone, viewing or analyzing information of interest points at ease during driving may pose a serious threat to driving safety.

Disclosure of Invention

In order to solve the technical problems, the disclosure provides a question answering method, a question answering device, question answering equipment, a storage medium and a vehicle based on interest points.

A first aspect of an embodiment of the present disclosure provides a question-answering method based on points of interest, the method including:

acquiring questioning audio data of a user;

Performing voice recognition processing on the questioning audio data to obtain interest points aimed by the user and questions aimed at the interest points;

Searching answers to the questions in a preset database;

and generating reply information based on the answer of the question and playing the reply information.

A second aspect of an embodiment of the present disclosure provides a question-answering apparatus based on points of interest, the apparatus including:

The acquisition module is used for acquiring the questioning audio data of the user;

The recognition module is used for carrying out voice recognition processing on the questioning audio data to obtain interest points aimed by the user and questions aimed at the interest points;

The searching module is used for searching answers of the questions in a preset database;

And the playing module is used for generating reply information based on the answer of the question and playing the reply information.

A third aspect of the embodiments of the present disclosure provides a computer device, including a memory and a processor, and a computer program, where the memory stores the computer program, and when the computer program is executed by the processor, implements a question-answering method based on points of interest as in the first aspect.

A fourth aspect of the embodiments of the present disclosure provides a computer-readable storage medium, in which a computer program is stored, which, when executed by a processor, implements a question-answering method based on points of interest as in the first aspect described above.

A fifth aspect of the disclosed embodiments provides a vehicle comprising a memory and a processor, and a computer program, wherein the memory stores the computer program, and when the computer program is executed by the processor, the question-answering method based on the interest points according to the first aspect is implemented.

Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages:

In the question-answering method, the device, the equipment, the storage medium and the vehicle based on the interest points, the question audio data of the user are acquired, the question audio data are subjected to voice recognition processing to obtain the interest points aimed by the user and the questions aimed at the interest points, answers to the questions are searched in the preset database, answer information is generated based on the answers to the questions and is played, the question audio of the user can be automatically answered, a driver does not need to check or analyze the information of the interest points, whether the interest points accord with expectations or not can be determined, whether the driver needs to drive the vehicle to go to the interest points is determined, driving safety is improved, and meanwhile user experience is improved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.

In order to more clearly illustrate the embodiments of the present disclosure or the solutions in the prior art, the drawings that are required for the description of the embodiments or the prior art will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.

FIG. 1 is a flow chart of a question-answering method based on points of interest provided by an embodiment of the present disclosure;

FIG. 2 is a flow chart of a method of identifying questioning audio data provided by an embodiment of the present disclosure;

FIG. 3 is a flow chart of a method of labeling points of interest provided by an embodiment of the present disclosure;

FIG. 4 is a flow chart of a method of searching answers to questions provided by embodiments of the present disclosure;

FIG. 5 is a flow chart of a method of generating and feeding back reply information provided by embodiments of the present disclosure;

FIG. 6 is a flow chart of another method of generating and feeding back reply information provided by embodiments of the present disclosure;

fig. 7 is a schematic structural diagram of a question answering device based on interest points according to an embodiment of the present disclosure;

fig. 8 is a schematic structural diagram of a computer device according to an embodiment of the present disclosure.

Detailed Description

In order that the above objects, features and advantages of the present disclosure may be more clearly understood, a further description of aspects of the present disclosure will be provided below. It should be noted that, without conflict, the embodiments of the present disclosure and features in the embodiments may be combined with each other.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced otherwise than as described herein; it will be apparent that the embodiments in the specification are only some, but not all, embodiments of the disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

Fig. 1 is a flowchart of a question-answering method based on points of interest, which may be performed by a question-answering apparatus based on points of interest, according to an embodiment of the present disclosure. As shown in fig. 1, the question answering method based on the interest points provided in this embodiment includes the following steps:

s101, acquiring question audio data of a user.

The question audio data in the embodiments of the present disclosure may be understood as audio data including question information collected by an audio collection device, such as a microphone, etc.

In the embodiment of the disclosure, the question answering device based on the interest point may acquire the question audio data of the user acquired by the audio acquisition device, where the audio acquisition device may be a device installed on the question answering device based on the interest point, or may be a device installed at a location other than the question answering device based on the interest point, which is not limited herein.

S102, performing voice recognition processing on the question audio data to obtain the interest point aimed by the user and the problem aimed at the interest point.

Points of interest (Point of Information, POIs) in embodiments of the present disclosure may be understood as points in a map that are significant but not geographically significant, such as shops, bars, gas stations, hospitals, parks, etc., which are defined in terms of geographic coordinates and some additional attributes.

In the embodiment of the disclosure, the question answering device based on the interest point can perform voice recognition processing on the question audio data after obtaining the question audio data of the user, extract the interest point as a question object from the recognition result, and aim at the question of the interest point.

In an exemplary implementation manner of the embodiment of the present disclosure, the question answering device based on the point of interest may obtain, in advance, multiple sentence patterns that may be possessed by the question for the point of interest, determine a sentence pattern type of a speech recognition result of the obtained question audio data of the user, and extract, based on the sentence pattern type, the point of interest targeted by the user and the question for the point of interest from a corresponding position of the recognition result.

S103, searching answers to the questions in a preset database.

The preset database in the embodiment of the present disclosure may be understood as a preset database storing geographic coordinates and various attribute information of interest points, where the preset database may be set in a local storage or a cloud storage, and the preset database may be set based on information included in a navigation system, or may be set through network capturing or manual input by a user, which is not limited herein.

In the embodiment of the disclosure, the question answering device based on the interest points can search the preset database for information related to the interest points after determining the interest points and the questions aiming at the interest points contained in the question audio data of the user, and then determine answers to the questions aiming at the interest points according to the related information.

In an exemplary implementation manner of the embodiment of the present disclosure, the preset database may further include preset questions for various information of the interest point, the question answering device based on the interest point may acquire each preset question of the interest point stored in the preset database after determining the interest point included in the question audio data of the user and the question for the interest point, calculate the similarity between the question of the user and each preset question, thereby obtaining the preset question with the highest similarity, and determine the answer of the question based on the information corresponding to the preset question.

S104, generating reply information based on the answer of the question and playing the reply information.

The reply message in the embodiments of the present disclosure may be understood as information expressing an answer to a question in a natural language that is easily understood by a user.

In the embodiment of the disclosure, after determining the answer of the question posed by the user, the question answering device based on the interest point may express the answer of the question through natural language to obtain the reply information, and play the reply information.

In an exemplary implementation manner of the embodiment of the present disclosure, after determining an answer to a question, the question answering device based on the point of interest may sort information in the answer according to a preset expression order, add some connective words between the information, generate reply information, and play the reply information through a playing device. By way of example, the playback device may be a speaker.

According to the method and the device for processing the question audio data, the question audio data of the user are acquired, voice recognition processing is conducted on the question audio data, the interest point aimed by the user and the question aimed at the interest point are obtained, answers to the questions are searched in the preset database, reply information is generated and played based on the answers to the questions, the question audio data of the user can be automatically answered, a driver does not need to check or analyze the information of the interest point, whether the interest point accords with expectations can be determined, whether the driver is required to drive the vehicle to the interest point is determined, driving safety is improved, and user experience is improved.

In some embodiments of the present disclosure, the question answering device based on the interest point may receive a wake-up instruction, and wake up the terminal in response to the wake-up instruction, so that the terminal obtains question audio data of the user. The wake-up instruction may be understood as an instruction for waking up a terminal device where the question answering device based on the interest point is located to receive the question audio data of the user, and the wake-up instruction may be, for example, a voice instruction including a preset keyword, or may be a touch instruction, an action instruction, or the like, which is not limited herein.

In some embodiments of the present disclosure, when the wake-up instruction is a voice instruction including a preset keyword, the question answering device based on the interest point may collect audio data in real time, and if it is detected that the preset keyword exists in the collected audio, question audio data of the user is obtained from the audio collected in a preset time after the keyword is collected, so that the question answering device based on the interest point can be prevented from constantly analyzing the obtained audio for the interest point and the question, and on the premise that it is ensured that the question audio data of the user can be normally processed, calculation resources are saved.

Fig. 2 is a flowchart of a method for identifying question audio data according to an embodiment of the present disclosure, and as shown in fig. 2, the question audio data may be identified by the following method on the basis of the above-described embodiment.

S201, converting the question audio data into text information based on a pre-trained text conversion model.

The text conversion model in the embodiments of the present disclosure may be understood as a pre-trained model capable of converting audio data into text information.

In the embodiment of the disclosure, the question answering device based on the interest points can process the obtained question audio data of the user through a pre-trained text conversion model, and convert the question audio data into text information.

In an exemplary implementation manner of the disclosed embodiment, the question answering device based on the interest point may preprocess the obtained question audio data of the user through a pre-trained text conversion model, eliminate a mute period included in the question audio data, and then perform framing processing, extract sound features from the obtained audio, and further obtain text information through an acoustic model and a language model, where the language model may be, for example, built based on a recurrent neural network (Recurrent Neural Network, RNN), the acoustic model may be built based on a deep neural network (Deep Neural Networks, DNN), or may be built based on a Long Short Term Memory network (Long Term Memory, LSTM), which is not limited herein.

S202, performing keyword matching processing on the text information based on a preset keyword library related to the interest points to obtain successfully matched target keywords.

Keyword libraries in embodiments of the present disclosure may be understood as databases storing words related to points of interest and questions for the points of interest, such as western style big-city, restaurants, chinese, western style, parking lots, outdoors, indoors, etc.

In the embodiment of the disclosure, the question answering device based on the interest points can respectively match the text information obtained through conversion with the vocabulary contained in the preset keyword library to obtain the target keywords matched with the text information.

In an exemplary implementation manner of the embodiment of the present disclosure, the question-answering device based on the interest point may perform word segmentation processing on the text information, and perform matching processing on the vocabulary included in the text information and the vocabulary included in the preset keyword library, and specifically, may calculate the similarity between the vocabulary included in the text information and the vocabulary included in the preset keyword library, and determine the vocabulary with the highest similarity as the target keyword matched with the text information.

S203, determining interest points contained in the text information and problems aiming at the interest points based on the target keywords.

In the embodiment of the disclosure, the question answering device based on the interest points can analyze and process the target keywords after determining the target keywords matched with the text information, so as to obtain the interest points corresponding to the target keywords and the questions aiming at the interest points.

According to the method and the device for obtaining the information, the question audio data are converted into the text information based on the pre-trained text conversion model, keyword matching processing is conducted on the text information based on the preset keyword library related to the interest points, the successfully matched target keywords are obtained, the interest points contained in the text information and the questions aiming at the interest points are determined based on the target keywords, and the accuracy of obtaining the information can be improved when the information of the interest points and the questions is obtained according to the question audio data, so that more accurate answers are provided later, and user experience is further improved.

Fig. 3 is a flowchart of a method for labeling points of interest according to an embodiment of the present disclosure, as shown in fig. 3, on the basis of the above embodiment, the points of interest may be labeled by the following method.

S301, determining coordinate information corresponding to the interest points based on the corresponding relation between the pre-acquired interest points and the coordinate information.

The coordinate information in the embodiments of the present disclosure may be understood as information capable of representing an accurate geographical location of a point of interest, and in general, the coordinate information may be latitude and longitude information.

In the embodiment of the disclosure, after determining the interest point aimed by the user, the question answering device based on the interest point can search and determine the coordinate information of the interest point aimed by the user from the corresponding relation between the pre-acquired interest point and the coordinate information.

S302, marking the interest points on a map acquired in advance based on the coordinate information.

In the embodiment of the disclosure, after the coordinate information of the interest point is determined, the question answering device based on the interest point can determine the position of the coordinate information on the map acquired in advance, and mark the interest point at the corresponding position.

In an exemplary implementation manner of the embodiment of the present disclosure, after determining coordinate information of an interest point, the question answering device based on the interest point may determine a position of the coordinate information on a map obtained in advance, and add a preset icon to a corresponding position, so as to implement labeling of the interest point.

According to the embodiment of the disclosure, the corresponding coordinate information of the interest point is determined based on the corresponding relation between the pre-acquired interest point and the coordinate information, the interest point is marked on the pre-acquired map based on the coordinate information, the position information of the interest point can be intuitively displayed on the map, the user can conveniently check, and the user experience is further improved.

Fig. 4 is a flowchart of a method for searching answers to questions provided in an embodiment of the present disclosure, and as shown in fig. 4, answers to questions may be searched by the following method on the basis of the above-described embodiment.

S401, searching first information of the interest points in the preset database, wherein the first information comprises name information, position information and category information.

The first information in the embodiment of the present disclosure may be understood as information related to the point of interest, such as name information, location information, category information of the point of interest, where the location information may include latitude and longitude information, may also include block and house number information, may also include other information for indicating the location of the point of interest, such as a certain mall three-layer, a certain square western side, etc., and the category information may include category information of different levels, such as a parking lot, an open parking lot, etc., which is not limited herein.

In the embodiment of the disclosure, after the point of interest is determined, the question answering device based on the point of interest may search the preset database for the first information related to the point of interest, and specifically, may search the name information, the location information and the category information of the point of interest.

In an exemplary implementation manner of the embodiment of the present disclosure, the question answering device based on the interest point may determine, from a preset database storing correspondence between the interest point and first information, the first information corresponding to the interest point for which the user is aimed, where the first information includes name information, location information, and category information.

In another exemplary implementation manner of the embodiment of the present disclosure, the question answering device based on the interest points may acquire information related to the interest points targeted by the user from a preset database storing information related to each interest point, and classify the acquired information to obtain first information of the interest points including name information, location information, and category information.

S402, converting the first information into second information based on a pre-trained structural conversion model, wherein the second information is information with a hierarchical structure.

The structured transformation model in the embodiments of the present disclosure may be understood as a model that is pre-trained and capable of transforming information into structured information.

The second information in the embodiments of the present disclosure may be understood as data information related to points of interest having a hierarchical structure, and when the first information of the parking lot includes an underground two-layer, the second information may include a parking lot, an indoor parking lot, an underground parking lot, and an underground two-layer parking lot, for example.

In the embodiment of the disclosure, the question answering device based on the interest points can input the obtained first information of the interest points into the pre-trained structural conversion model to obtain the output second information with the hierarchical structure.

S403, extracting the requirement type of the user from the problem aiming at the interest point.

The requirement type in the embodiment of the present disclosure may be understood as the type of information that the user wants to determine in the question about the point of interest, for example, when the question about parking lot a is "parking lot a is open air" and "parking lot a is outdoor", the requirement type of the user is open air parking lot.

In the embodiment of the disclosure, the question answering device based on the interest points can extract information which the user wants to determine from the questions aiming at the interest points, and determine the type of the information as the type of the user's requirement, and the extraction method includes but is not limited to the following steps:

In an exemplary implementation manner of the embodiment of the present disclosure, the question-answering device based on the interest point may perform matching processing on the question of the interest point and the preset keyword related to the requirement type, so as to obtain the requirement type of the user.

In another exemplary implementation manner of the embodiment of the present disclosure, the question answering device based on the interest point may abstract the question aimed at the interest point, then match the abstract question with a preset question template, and determine, according to the matching result, a requirement type corresponding to the question template that is successfully matched as a requirement type of the user.

S404, judging whether the interest points meet the requirement type or not based on the second information.

In the embodiment of the disclosure, after the request type of the user is extracted, the question answering device based on the interest point can search whether the information meeting the request type exists in the second information, so as to judge whether the interest point meets the request type.

And S405, generating an answer to the question based on the judging result, wherein the answer to the question is used for informing the user whether the interest point meets the requirement type.

In the embodiment of the disclosure, the question answering device based on the interest point may generate an answer for informing the user whether the interest point satisfies the requirement type question after obtaining the determination result of whether the interest point satisfies the requirement type.

According to the method and the device for searching the interest points, the first information of the interest points is searched in the preset database, the first information comprises name information, position information and category information, the first information is converted into the second information based on the pre-trained structural conversion model, the second information is information with a hierarchical structure, the requirement type of a user is extracted from the questions aiming at the interest points, whether the interest points meet the requirement type is judged based on the second information, answers of the questions are generated based on judgment results, whether the interest points of the user meet the requirement type is informed to the user, and the answers of the questions can be searched in a targeted mode according to the second information with the hierarchical structure related to the interest points and the requirement type of the user, so that the accuracy of the answers is improved, and the experience of the user is further improved.

Fig. 5 is a flowchart of a method for generating and feeding back reply information according to an embodiment of the disclosure, and as shown in fig. 5, on the basis of the above embodiment, reply information may be generated and fed back by the following method.

S501, generating the reply information based on the answers of the questions and a preset reply template.

In the embodiment of the disclosure, the question answering device based on the interest points may generate the answer information corresponding to the answer of the question according to the preset answer template after determining the interest points and the answer of the question aimed by the user.

In an exemplary implementation manner of the embodiment of the present disclosure, the question answering device based on the interest point may determine whether the problem of the user belongs to a closed type problem or an open type problem, and select a corresponding template from preset templates according to the determination result, for example, when the problem of the user is "the parking lot a is open air," the preset template may be the template "XX" corresponding to the closed type problem and "XX is not XX".

S502, playing the reply information.

In the embodiment of the disclosure, after the reply information is generated, the question answering device based on the interest point may convert the reply information into an audio file, and play the audio file corresponding to the reply information through a playing device, such as a sound device, where the sound device may be a device installed on the question answering device based on the interest point, or may be a device installed at a location other than the question answering device based on the interest point, which is not limited herein.

According to the method and the device for playing the answer information, the answer information is generated based on the answer of the question and the preset answer template, the answer information is played, a user does not need to check the answer of the question, and the played answer information can be directly heard, so that the possibility of distraction of the user in the driving process is further reduced, the driving safety is improved, and the user experience is improved.

Fig. 6 is a flowchart of another method for generating and feeding back reply information according to an embodiment of the disclosure, and as shown in fig. 6, on the basis of the above embodiment, reply information may be generated and fed back by the following method.

S601, inputting answers to the questions into a pre-trained natural language generation model, and generating the reply information.

The natural language generation model in the embodiments of the present disclosure may be understood as a model capable of generating an easy-to-understand natural language from the obtained information.

In the embodiment of the disclosure, the question answering device based on the interest points can input answers of questions into a natural language generation model which is trained in advance, and reply information is generated through the steps of content determination, text structure determination, sentence aggregation, grammar, reference expression generation, language implementation and the like.

S602, playing the reply information.

In the embodiment of the disclosure, after the reply information is generated, the question answering device based on the interest point can convert the reply information into the audio file, and play the audio file corresponding to the reply information through a playing device such as a sound.

According to the method and the device for playing the answer of the questions, the answer of the questions is input into the pre-trained natural language generation model, the answer information is generated, the answer information is played, the answer information which is easier to be understood by people can be obtained, the user experience is further improved, the user does not need to check the answer of the questions, and the played answer information can be directly heard, so that the possibility of distraction of the user in the driving process is reduced, and the driving safety is improved.

Fig. 7 is a schematic structural diagram of a question-answering device based on interest points according to an embodiment of the present disclosure, and as shown in fig. 7, the question-answering device 700 based on interest points includes: the device comprises a first acquisition module 710, an identification module 720, a search module 730 and a play module 740, wherein the first acquisition module 710 is used for acquiring the questioning audio data of a user; the recognition module 720 is configured to perform a voice recognition process on the question audio data to obtain an interest point targeted by the user and a question targeted to the interest point; a searching module 730, configured to search a preset database for an answer to the question; and the playing module 740 is used for generating reply information based on the answer of the question and playing the reply information.

Optionally, the question answering apparatus 700 based on the interest point further includes: the wake-up module is specifically configured to: receiving a wake-up instruction; the first obtaining module 710 is specifically configured to: and waking up the terminal in response to the wake-up instruction so that the terminal obtains the questioning audio data of the user.

Optionally, the identifying module 720 includes: the first conversion unit is used for converting the questioning audio data into text information based on a pre-trained text conversion model; the matching unit is used for carrying out keyword matching processing on the text information based on a preset keyword library related to the interest points to obtain successfully matched target keywords; and the determining unit is used for determining the interest points contained in the text information and the problems aiming at the interest points based on the target keywords.

Optionally, the question answering apparatus 700 based on the interest point further includes: the second acquisition module is used for determining coordinate information corresponding to the interest points based on the corresponding relation between the pre-acquired interest points and the coordinate information; and the labeling module is used for labeling the interest points on a map acquired in advance based on the coordinate information.

Optionally, the search module 730 includes: the searching unit is used for searching first information of the interest points in the preset database, wherein the first information comprises name information, position information and category information; the second conversion unit is used for converting the first information into second information based on a pre-trained structural conversion model, wherein the second information is information with a hierarchical structure; an extracting unit, configured to extract a requirement type of the user from the question for the point of interest; the judging unit is used for judging whether the interest point meets the requirement type or not based on the second information; and the generating unit is used for generating an answer to the question based on the judging result, wherein the answer to the question is used for informing the user whether the interest point meets the requirement type.

Optionally, the playing module 740 includes: the first generation unit is used for generating the reply information based on the answers of the questions and a preset reply template; and the first playing unit is used for playing the reply information.

Optionally, the playing module 740 includes: the second generating unit is used for inputting answers to the questions into a pre-trained natural language generating model to generate the reply information; and the second playing unit is used for playing the reply information.

The question answering device based on the interest point provided in this embodiment can execute the method described in any one of the above embodiments, and the execution mode and the beneficial effects thereof are similar, and are not repeated here.

Fig. 8 is a schematic structural diagram of a computer device according to an embodiment of the present disclosure.

As shown in fig. 8, the computer device may include a processor 810 and a memory 820 storing computer program instructions.

In particular, the processor 810 may include a Central Processing Unit (CPU), or an Application SPECIFIC INTEGRATED Circuit (ASIC), or may be configured as one or more integrated circuits that implement embodiments of the present application.

Memory 820 may include mass storage for information or instructions. By way of example, and not limitation, memory 820 may comprise a hard disk drive (HARD DISK DRIVE, HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or universal serial bus (Universal Serial Bus, USB) drive, or a combination of two or more of these. Memory 820 may include removable or non-removable (or fixed) media, where appropriate. The memory 820 may be internal or external to the integrated gateway device, where appropriate. In a particular embodiment, the memory 820 is a non-volatile solid state memory. In a particular embodiment, the Memory 820 includes Read-Only Memory (ROM). The ROM may be mask programmed ROM, programmable ROM (PROM), erasable PROM (ELECTRICAL PROGRAMMABLE ROM, EPROM), electrically erasable PROM (ELECTRICALLY ERASABLE PROGRAMMABLE ROM, EEPROM), electrically rewritable ROM (ELECTRICALLY ALTERABLE ROM, EAROM), or flash memory, or a combination of two or more of these, where appropriate.

Processor 810, by reading and executing computer program instructions stored in memory 820, performs the steps of the point-of-interest based question-answering method provided by embodiments of the present disclosure.

In one example, the computer device may also include a transceiver 830 and a bus 840. In which, as shown in fig. 8, the processor 810, the memory 820 and the transceiver 830 are connected and communicate with each other through a bus 840.

Bus 840 includes hardware, software, or both. By way of example, and not limitation, the buses may include an accelerated graphics Port (ACCELERATED GRAPHICS Port, AGP) or other graphics BUS, an enhanced industry Standard architecture (Extended Industry Standard Architecture, EISA) BUS, a Front Side BUS (FSB), a HyperTransport (HT) interconnect, an industry Standard architecture (Industrial Standard Architecture, ISA) BUS, an Infiniband interconnect, a Low Pin Count (LPC) BUS, a memory BUS, a micro channel architecture (Micro Channel Architecture, MCA) BUS, a peripheral control interconnect (PERIPHERAL COMPONENT INTERCONNECT, PCI) BUS, a PCI-Express (PCI-X) BUS, a serial advanced technology attachment (SERIAL ADVANCED Technology Attachment, SATA) BUS, a video electronics standards Association local (Video Electronics Standards Association Local Bus, VLB) BUS, or other suitable BUS, or a combination of two or more of these. Bus 840 may include one or more buses, where appropriate. Although embodiments of the application have been described and illustrated with respect to a particular bus, the application contemplates any suitable bus or interconnect.

The embodiments of the present disclosure also provide a computer-readable storage medium, which may store a computer program that, when executed by a processor, causes the processor to implement the question-answering method based on points of interest provided by the embodiments of the present disclosure.

The storage medium described above may, for example, include a memory 820 of computer program instructions executable by the processor 810 of the point of interest based question and answer device to perform the point of interest based question and answer method provided by embodiments of the present disclosure. Alternatively, the storage medium may be a non-transitory computer readable storage medium, for example, a ROM, a random access memory (Random Access Memory, RAM), a Compact Disc ROM (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like. The computer programs described above may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.

The embodiment of the disclosure further provides a vehicle, which includes a memory, a processor, and a computer program, where the memory stores the computer program, and when the computer program is executed by the processor, the processes and effects in the foregoing embodiments of the disclosure may be implemented, which is not described herein.

The foregoing is merely a specific embodiment of the disclosure to enable one skilled in the art to understand or practice the disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown and described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (11)

1. A question-answering method based on points of interest, comprising:

acquiring questioning audio data of a user;

Performing voice recognition processing on the questioning audio data to obtain interest points aimed by the user and questions aimed at the interest points;

Searching answers to the questions in a preset database;

and generating reply information based on the answer of the question and playing the reply information.

2. The method of claim 1, wherein prior to the obtaining the questioning audio data of the user, the method further comprises:

receiving a wake-up instruction;

the acquiring the question audio data of the user comprises the following steps:

And waking up the terminal in response to the wake-up instruction so that the terminal obtains the questioning audio data of the user.

3. The method of claim 1, wherein the performing speech recognition processing on the question audio data to obtain the point of interest targeted by the user and the question targeted to the point of interest comprises:

converting the question audio data into text information based on a pre-trained text conversion model;

performing keyword matching processing on the text information based on a preset keyword library related to the interest points to obtain successfully matched target keywords;

And determining the interest points contained in the text information and the problems aiming at the interest points based on the target keywords.

4. The method of claim 1, wherein after performing the voice recognition processing on the question audio data to obtain the point of interest targeted by the user and the question targeted to the point of interest, the method further comprises:

determining coordinate information corresponding to the interest points based on a corresponding relation between the pre-acquired interest points and the coordinate information;

And marking the interest points on a map acquired in advance based on the coordinate information.

5. The method of claim 1, wherein searching a preset database for an answer to the question comprises:

Searching first information of the interest points in the preset database, wherein the first information comprises name information, position information and category information;

converting the first information into second information based on a pre-trained structured conversion model, wherein the second information is information with a hierarchical structure;

extracting the requirement type of the user from the problem aiming at the interest points;

judging whether the interest point meets the requirement type or not based on the second information;

and generating an answer to the question based on the judging result, wherein the answer to the question is used for informing the user whether the interest point meets the requirement type.

6. The method of claim 1, wherein generating and playing back a reply message based on an answer to the question comprises:

generating the reply information based on the answer of the question and a preset reply template;

and playing the reply information.

7. The method of claim 1, wherein generating and playing back a reply message based on an answer to the question comprises:

inputting answers to the questions into a pre-trained natural language generation model to generate the reply information;

and playing the reply information.

8. A question-answering apparatus based on points of interest, comprising:

The first acquisition module is used for acquiring the questioning audio data of the user;

The recognition module is used for carrying out voice recognition processing on the questioning audio data to obtain interest points aimed by the user and questions aimed at the interest points;

The searching module is used for searching answers of the questions in a preset database;

And the playing module is used for generating reply information based on the answer of the question and playing the reply information.

9. An electronic device, comprising:

A processor;

A memory for storing executable instructions;

wherein the processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the method of any of the preceding claims 1-7.

10. A computer readable storage medium, characterized in that the storage medium stores a computer program, which when executed by a processor causes the processor to implement the question-answering method based on points of interest according to any one of the preceding claims 1-7.

11. A vehicle, characterized by comprising: a memory; a processor; a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any of claims 1-7.