Voice question-answering interaction method, device, computer equipment and storage medium

Abstract

The embodiment of the present invention provides a voice question-answering interaction method, device, computer equipment and storage medium. The method is applied to the field of voice interaction, and the method includes obtaining a first voice message input by a user through a client, performing voice recognition on the first voice message to generate a first text message, and performing word segmentation processing on the first text message to obtain a first text keyword. The question message is sent to the client; the second voice message input by the user through the client according to the question message is obtained, and voice recognition is performed on the second voice message to generate a second text message; a question mark is generated according to the second text message and the question message; the answer information corresponding to the second voice message is determined according to the question mark and a preset question-answering database, and the answer information is fed back to the client. The implementation of the embodiment of the present invention can realize the rapid provision of required content to users, simple operation and fast response speed.

Description

Technical Field

[0001] The present invention relates to the field of computer data processing, and in particular to a voice question-answering interaction method, device, computer equipment and computer-readable storage medium. Background Art

[0002] With the continuous development of the Internet, the content of online information is constantly enriched. People can search for various types of information on the Internet, such as weather inquiries, disease consultations, knowledge questions and answers, etc. Although it is convenient for people to obtain information by searching and obtaining the required content through the Internet, people cannot quickly obtain real, effective and reliable information because the information content of the Internet is numerous and messy. At the same time, for some users with low resolution and poor familiarity with Internet search, this content acquisition method is not only cumbersome and inefficient, but also has poor content reliability. Summary of the invention

[0003] The embodiments of the present invention provide a voice question-answering interaction method, apparatus, computer equipment and storage medium, aiming to solve the problems of complicated operation and low efficiency in the process of content acquisition.

[0004] In the first aspect, an embodiment of the present invention provides a voice question-answering interaction method, which includes: obtaining a first voice message input by a user through a client, performing voice recognition on the first voice message to generate a first text message, and performing word segmentation processing on the first text message to obtain a first text keyword. Determine the question information corresponding to the first voice message based on the first text keyword and a preset question-answering database and send the question information to the client; obtain a second voice message input by the user through the client based on the question information and perform voice recognition on the second voice message to generate a second text message; generate a question tag based on the second text message and the question information; determine the answer information corresponding to the second voice message based on the question tag and the preset question-answering database and send the answer information to the client.

[0005] In a second aspect, an embodiment of the present invention provides a voice question-answering interaction device, comprising:

[0006] The first acquisition unit is used to acquire first voice information input by a user through a client, perform voice recognition on the first voice information to generate first text information, and perform word segmentation processing on the first text information to obtain first text keywords.

[0007] A first determining unit, configured to determine question information corresponding to the first voice information according to the first text keyword and a preset question-answer database and send the question information to the client;

[0008] A second acquisition unit, configured to acquire second voice information input by the user through the client according to the question information and perform voice recognition on the second voice information to generate second text information;

[0009] A first generating unit, configured to generate a question mark according to the second text information and the question information;

[0010] The second determining unit is used to determine answer information corresponding to the second voice information according to the question mark and the preset question and answer database and send the answer information to the client.

[0011] In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned voice question-and-answer interaction method when executing the program.

[0012] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the above-mentioned voice question-and-answer interaction method.

[0013] The embodiment of the present invention provides a voice question-and-answer interaction method, device, computer equipment and computer-readable storage medium. The method includes obtaining a first voice message input by a user through a client, performing voice recognition on the first voice message to generate a first text message, and performing word segmentation processing on the first text message to obtain a first text keyword. According to the first text keyword and a preset question-and-answer database, the question information corresponding to the first voice message is determined and the question information is sent to the client; the second voice message input by the user through the client according to the question information is obtained and voice recognition is performed on the second voice message to generate a second text message; a question mark is generated according to the second text message and the question information; the answer information corresponding to the second voice message is determined according to the question mark and the preset question-and-answer database and the answer information is sent to the client. The voice question-and-answer interaction method provided by the embodiment of the present invention is implemented to quickly provide the required content to the user through voice interaction, with simple operation and fast response speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0015] Figure 1 A flowchart of a voice question-answering interactive method provided by one embodiment of the present invention;

[0016] Figure 2 A schematic diagram of an application scenario of a voice question-answering interaction method provided by an embodiment of the present invention;

[0017] Figure 3 A flowchart of a voice question-answering interactive method provided by one embodiment of the present invention;

[0018] Figure 4 A flowchart of a voice question-answering interactive method provided by one embodiment of the present invention;

[0019] Figure 5 A flowchart of a voice question-answering interactive method provided by one embodiment of the present invention;

[0020] Figure 6 A flowchart of a voice question-answering interactive method provided by one embodiment of the present invention;

[0021] Figure 7 A schematic block diagram of a voice question-answering interactive device provided by an embodiment of the present invention;

[0022] Figure 8 Another schematic block diagram of a voice question-answering interactive device provided by an embodiment of the present invention;

[0023] Fig. 9 Another schematic block diagram of a voice question-answering interactive device provided by an embodiment of the present invention;

[0024] Fig.10 Another schematic block diagram of a voice question-answering interactive device provided by an embodiment of the present invention;

[0025] Fig.11 Another schematic block diagram of a voice question-answering interactive device provided by an embodiment of the present invention;

[0026] Fig.12 A schematic block diagram of a computer device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0029] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0030] Please refer to Figure 1 as well as Figure 2 , which is a flow chart and an application scenario chart of a voice question-answering interaction method provided by an embodiment of the present invention. The voice question-answering interaction method is applied to a server 20, which can be an independent server or a server cluster composed of multiple servers. The server 20 can communicate with the client 10 through network communication to achieve data interaction. Among them, the client 10 can be an electronic device with communication function such as a smart phone, a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device.

[0031] The voice question-answering interaction method includes but is not limited to steps S110 - S150 .

[0032] S110, obtaining first voice information input by a user through a client, performing voice recognition on the first voice information to generate first text information, and performing word segmentation processing on the first text information to obtain first text keywords.

[0033] Specifically, the first voice information can be acquired through a voice acquisition device and sent to the server through network communication. The voice acquisition device can be various types of clients with microphones, and the client can send prompt information to the client according to the actual application scenario before acquiring the first voice information, so as to prompt the user to input the corresponding voice information, so as to improve the success rate of voice question and answer interaction. The application scenarios of the voice question and answer include but are not limited to emotional consultation, disease consultation, weather consultation, etc. For example, assuming that the application scenario of the voice question and answer interaction method is intelligent medical consultation, before acquiring the first voice information, the prompt information sent to the client can be "Excuse me, where do you feel uncomfortable?".

[0034] The speech recognition of the first speech information can be realized by calling a speech recognition tool on the server side, and the speech recognition tool includes but is not limited to speech recognition tools based on HMM and N-gram models: CMU Sphinx, Kaldi, HTK, Julius and ISIP.

[0035] The word segmentation processing of the first text information can be implemented by calling tools such as jieba. Assume that the first text information is "My throat is uncomfortable". One or more first text keywords can be obtained by performing word segmentation processing on the first text information. For example, after the word segmentation processing of "My throat is uncomfortable", the first text keywords obtained include "my", "throat", and "uncomfortable".

[0036] S120: Determine question information corresponding to the first voice information according to the first text keyword and a preset question-answer database and send the question information to the client.

[0037] Specifically, in order to improve the accuracy of answer information obtained from voice question and answer interaction, the question information corresponding to the first voice information is determined according to the first text keyword and a preset question and answer database and the question information is sent to the client, and the question information is sent to the client to obtain a second voice information corresponding to the question information.

[0038] The preset question-answer database is used to store various types of question information, answer information, and mapping conditions mapped to the answer information. A question mark can be generated according to the second voice information corresponding to the question information, and then the mapping condition is determined according to the question mark, and then the answer information is determined.

[0039] In some embodiments, Figure 3 As shown, step S120 includes but is not limited to steps S121-S122.

[0040] S121, determining whether the first text keyword matches a preset category keyword.

[0041] Specifically, determining whether the first text keyword matches a preset category keyword includes: determining whether the first text keyword is the same as or similar to a preset type keyword; if the first text keyword is the same as or similar to the preset type keyword, determining that the first text keyword matches the preset category keyword.

[0042] Through character comparison, it can be determined whether the first text keyword is the same as the preset type keyword. Through character comparison and similar keyword combination, it can be determined whether the first text keyword is similar to the preset type keyword. Among them, the keyword combination is used to store similar keywords, for example, a similar keyword combination is such as "head-head-skull". If the first text keyword and the preset type keyword are in the same similar keyword combination, it is determined that the first text keyword is similar to the preset type keyword.

[0043] S122: If the first text keyword matches a preset category keyword, obtain a question type corresponding to the category keyword, and determine question information corresponding to the question type as question information corresponding to the first voice information.

[0044] Specifically, please refer to Table 1, the mapping relationship between the preset category keywords and the question types is one-to-one or many-to-one, that is, one or more keywords can be mapped to the same question type. The mapping relationship between the question type and the question information is one-to-one or one-to-many, that is, the same question type can be mapped to one or more question information, such as the first question information, the second question information, and so on.

[0045]

[0046] Table 1

[0047] For example, the first text keyword is "nose", the category keyword matching the first text keyword is "nose", and the question types corresponding to the category keyword include "cold type" and "face type". Different question types correspond to one or more question information, such as "whether there is a fever", "whether there is a runny nose", etc. The question type corresponding to the category keyword can be obtained through the category keyword, and then the question information corresponding to the question type is determined as the question information corresponding to the first voice information.

[0048] If the first text keyword does not match the preset category keyword, it indicates that the first voice message cannot be recognized, and an error reminder message is sent to the client to remind the customer to re-enter the first voice message.

[0049] In the implementation of the embodiment of the present invention, by determining a category keyword based on the first text keyword corresponding to the first voice, and then determining the question type corresponding to the category keyword based on the category keyword, and determining the question information corresponding to the question type as the question information corresponding to the first voice information, the question information corresponding to the first voice information can be quickly located, the processing speed of voice question answering can be improved, and the processing pressure of question information retrieval can be reduced.

[0050] S130, obtaining second voice information input by the user through the client according to the question information and performing voice recognition on the second voice information to generate second text information.

[0051] Specifically, the question information is sent to the client, and the voice information input by the user is collected, so as to obtain the second voice information corresponding to the question information.

[0052] The speech recognition of the second speech information can be realized by calling a speech recognition tool on the server side, and the speech recognition tool includes but is not limited to speech recognition tools based on HMM and N-gram models: CMU Sphinx, Kaldi, HTK, Julius and ISIP.

[0053] S140: Generate a question mark according to the second text information and the question information.

[0054] In some embodiments, Figure 4 As shown, step S140 includes but is not limited to steps S141-S143.

[0055] S141, performing word segmentation processing on the second text information to obtain second text keywords, and determining whether there are preset forward keywords in the second text keywords and determining whether there are preset reverse keywords in the second text keywords.

[0056] Specifically, the word segmentation processing of the second text information can be implemented by calling tools such as jieba. Specifically, the preset forward keywords can be "yes", "have", etc., and the preset reverse keywords can be "not", "no", etc. Character comparison can be used to determine whether the preset forward keywords exist in the second text keywords and whether the preset reverse keywords exist in the second text keywords.

[0057] S142: If there are preset positive keywords in the second text keywords, generate positive question tags according to the question information.

[0058] S143: If there is a preset reverse keyword in the second text keyword, generate a reverse question mark according to the question information.

[0059] Specifically, a unique question tag can be generated according to each question information and the second text keyword corresponding to the question information, and the question tag includes a positive question tag and a negative question tag. Assuming that the question information is "Is there a cough?", the second text keywords corresponding to the question include "yes", "cough", etc. Through character comparison, it can be determined that the preset positive keyword "yes" exists in the second text keyword, and then a positive question tag is generated according to the question information, and the positive question tag is "there is a cough".

[0060] If the second text keyword does not contain a preset forward keyword and the second text keyword does not contain a preset reverse keyword, it indicates that the second voice information cannot be recognized, and an error reminder message is sent to the client to remind the customer to re-enter the second voice information.

[0061] S150: Determine answer information corresponding to the second voice information according to the question tag and the preset question and answer database, and send the answer information to the client.

[0062] In some embodiments, Figure 5 As shown, step S150 includes but is not limited to steps S151-S152.

[0063] S151, obtaining a mapping condition matching the question tag in a preset question and answer database.

[0064] Specifically, assuming that the text keyword is "nose", the category keyword matching the text keyword is "nose", and the question types corresponding to the category keyword include "cold type" and "face type". The question information in "cold type" and "face type" is sent to the client to obtain the second voice information. The questions generated according to the second voice information and the question information are marked as "sneezing", "no nasal congestion", and "no fever".

[0065] If the question mark is the same as or similar to the mapping condition, it is determined that the question mark matches the mapping condition. The mapping condition matching the three question marks can be obtained by performing character comparison in the preset question database.

[0066] S152: Determine answer information corresponding to the second voice information according to the mapping condition and a preset answer mapping relationship.

[0067] Specifically, the preset question-answer database is used to store various types of question information, answer information, and mapping conditions mapped to the answer information. A question tag can be generated according to the second text keyword corresponding to the question information, and then the mapping condition is determined according to the question tag to determine the answer information, and then the answer information is determined.

[0068] Please refer to Table 2, the preset answer mapping relationship is used to store the mapping relationship between the mapping conditions and the answer information. The mapping relationship between the mapping conditions and the answer information can be a one-to-one or many-to-one mapping relationship. Different answer mappings correspond to different mapping conditions, and the number of mapping conditions corresponding to the answer information can be one or more. As shown in Table 2, the answer information corresponding to the three mapping conditions "sneezing", "no nasal congestion", and "no fever" is "rhinitis". If the question is marked as "sneezing", "no nasal congestion", and "no fever", the answer information corresponding to the mapping condition obtained according to the question mark is "rhinitis". After determining the answer information, the answer information is sent to the client.

[0069] First mapping condition Second mapping condition The third mapping condition Answer information There is sneezing No nasal congestion No fever rhinitis

[0070] Table 2

[0071] In some embodiments, Figure 6 As shown, step S150 may further include steps S160-S180.

[0072] S160, obtaining the current location information of the client, and determining the hospital information closest to the current location information according to the current location information.

[0073] Specifically, the hospital information can be preset to limit the level or type of the hospital. For example, the hospital information can be preset to be a tertiary hospital or a public hospital, etc.

[0074] S170: Determine department information matching the disease information according to the disease information and a preset department mapping relationship.

[0075] Specifically, the preset department mapping relationship is used to store the mapping relationship between disease information and department information. If the disease information is a determined value, the department information matching the disease information can be determined through the determined disease information and the preset department mapping relationship. For example, the preset department mapping relationship includes: rhinitis is mapped to the ENT department. If the disease information is rhinitis, the department information can be determined to be the ENT department through the preset department mapping relationship.

[0076] S180, sending the hospital information and the department information to the client.

[0077] Among them, sending the hospital information and the department information to the client can be achieved through text messages, emails, WeChat messages, etc.

[0078] By implementing the embodiments of the present invention, it is possible to determine the nearest hospital information and the department information matching the disease information based on the disease information. By sending the hospital information and the department information to the client, it is helpful to reduce the number of operations required by the user to obtain information, thereby realizing intelligent voice interaction.

[0079] Figure 7 is a schematic block diagram of a voice question-answering interactive device 100 provided in an embodiment of the present invention. Figure 7 As shown, corresponding to the above voice question and answer interaction method, the present invention also provides a voice question and answer interaction device 100. The voice question and answer interaction device 100 includes a unit for executing the above voice question and answer interaction method, and the device can be configured in a server side, which can be an independent server or a server cluster composed of multiple servers.

[0080] Specifically, see Figure 7 The voice question and answer interaction device 100 includes a first acquisition unit 110, a first determination unit 120, a second acquisition unit 130, a first generation unit 140 and a second determination unit 150.

[0081] The first acquisition unit 110 is used to acquire first voice information input by a user through a client, perform voice recognition on the first voice information to generate first text information, and perform word segmentation processing on the first text information to obtain first text keywords.

[0082] The first determining unit 120 is used to determine the question information corresponding to the first voice information according to the first text keyword and a preset question and answer database and send the question information to the client.

[0083] In some embodiments, Figure 8 As shown, the first determining unit 120 includes a first judging unit 121 and a third determining unit 122 .

[0084] The first determination unit 121 is configured to determine whether the first text keyword matches a preset category keyword.

[0085] The third determining unit 122 is configured to obtain a question type corresponding to the category keyword if the first text keyword matches a preset category keyword, and determine the question information corresponding to the question type as the question information corresponding to the first voice information.

[0086] The second acquisition unit 130 is configured to acquire second voice information input by the user through the client according to the question information and perform voice recognition on the second voice information to generate second text information.

[0087] The first generating unit 140 is configured to generate a question mark according to the second text information and the question information.

[0088] In some embodiments, Fig. 9 As shown, the first generating unit 140 includes a second judging unit 141 , a second generating unit 142 and a third generating unit 143 .

[0089] The second judgment unit 141 is used to perform word segmentation processing on the second text information to obtain second text keywords, and to judge whether there are preset forward keywords in the second text keywords and whether there are preset reverse keywords in the second text keywords.

[0090] The second generating unit 142 is configured to generate a positive question tag according to the question information if there is a preset positive keyword in the second text keyword.

[0091] The third generating unit 143 is configured to generate a reverse question tag according to the question information if there is a preset reverse keyword in the second text keyword.

[0092] The second determining unit 150 is used to determine answer information corresponding to the second voice information according to the question tag and the preset question and answer database and send the answer information to the client.

[0093] In some embodiments, Fig.10 As shown, the second determining unit 150 includes a third acquiring unit 151 and a fourth determining unit 152 .

[0094] The third acquisition unit 151 is used to acquire a mapping condition matching the question tag in a preset question and answer database.

[0095] The fourth determining unit 152 is used to determine the answer information corresponding to the second voice information according to the mapping condition and a preset answer mapping relationship.

[0096] In some embodiments, Fig.11 As shown, the device further includes a fourth acquiring unit 160 , a fifth determining unit 170 and a sending unit 180 .

[0097] The fourth acquisition unit 160 is used to acquire the current location information of the client, and determine the hospital information closest to the current location information according to the current location information.

[0098] The fifth determining unit 170 is used to determine the department information matching the disease information according to the disease information and a preset department mapping relationship.

[0099] The sending unit 180 is used to send the hospital information and the department information to the client.

[0100] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned voice question and answer interaction device 100 and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and brevity of description, it will not be repeated here.

[0101] The above-mentioned device 100 can be implemented in the form of a computer program. The computer program can be implemented in Fig.12 Runs on the computer device shown.

[0102] See also Fig.12 , Fig.12 5 is a schematic block diagram of a computer device provided in an embodiment of the present invention. The computer device 500 may be a client. The client may be an electronic device with communication function such as a smart phone, a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device.

[0103] The computer device 500 includes a processor 520 , a memory, and a network interface 550 connected via a system bus 510 , wherein the memory may include a non-volatile storage medium 530 and an internal memory 540 .

[0104] The non-volatile storage medium 530 may store an operating system 531 and a computer program 532. When the computer program 532 is executed, the processor 520 may execute a voice question-answering interaction method.

[0105] The processor 520 is used to provide computing and control capabilities and support the operation of the entire computer device 500.

[0106] The internal memory 540 provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor 520, the processor 520 can execute a voice question-answering interaction method.

[0107] The network interface 550 is used to communicate with other devices over a network. Those skilled in the art will appreciate that the schematic block diagram of the computer device is only a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device 500 to which the solution of the present invention is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0108] The processor 520 is used to run the program code stored in the memory to implement the following functions: obtaining the first voice information input by the user through the client and performing voice recognition on the first voice information to generate the first text information, and performing word segmentation processing on the first text information to obtain the first text keyword. Determine the question information corresponding to the first voice information according to the first text keyword and the preset question and answer database and send the question information to the client; obtain the second voice information input by the user through the client according to the question information and perform voice recognition on the second voice information to generate the second text information; generate a question tag according to the second text information and the question information; determine the answer information corresponding to the second voice information according to the question tag and the preset question and answer database and send the answer information to the client.

[0109] In one embodiment, when the processor 520 executes the step of determining the question information corresponding to the first voice information based on the first text keyword and the preset question and answer database and sending the question information to the client, it specifically performs the following steps: determining whether the first text keyword matches the preset category keyword; if the first text keyword matches the preset category keyword, obtaining the question type corresponding to the category keyword, and determining the question information corresponding to the question type as the question information corresponding to the first voice information.

[0110] In one embodiment, when the processor 520 executes the step of generating a question tag based on the second text information and the question information, it specifically performs the following steps: performing word segmentation processing on the second text information to obtain second text keywords, and determining whether there are preset forward keywords in the second text keywords and determining whether there are preset reverse keywords in the second text keywords; if there are preset forward keywords in the second text keywords, generating a forward question tag based on the question information; if there are preset reverse keywords in the second text keywords, generating a reverse question tag based on the question information.

[0111] In one embodiment, when the processor 520 executes the step of determining the answer information corresponding to the second voice information based on the question tag and the preset question and answer database and sending the answer information to the client, it specifically performs the following steps: obtaining a mapping condition that matches the question tag in the preset question and answer database; determining the answer information corresponding to the second voice information based on the mapping condition and the preset answer mapping relationship.

[0112] In one embodiment, after executing the step of determining the answer information corresponding to the second voice information according to the question mark and the preset question and answer database and sending the answer information to the client, the processor 520 specifically performs the following steps: obtaining the current location information of the client, and determining the hospital information closest to the current location information according to the current location information; determining the department information matching the disease information according to the disease information and the preset department mapping relationship; and sending the hospital information and the department information to the client.

[0113] It should be understood that in the embodiment of the present invention, the processor 520 may be a central processing unit (CPU), and the processor 520 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0114] Those skilled in the art will appreciate that the schematic block diagram of the computer device 500 does not limit the computer device 500 , and the computer device 500 may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0115] In another embodiment of the present invention, a computer-readable storage medium is provided, which stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by the processor, the following steps are implemented: obtaining a first voice message input by a user through a client and performing voice recognition on the first voice message to generate a first text message, and performing word segmentation processing on the first text message to obtain a first text keyword. Determine the question information corresponding to the first voice message based on the first text keyword and a preset question-and-answer database and send the question information to the client; obtain a second voice message input by a user through the client based on the question information and perform voice recognition on the second voice message to generate a second text message; generate a question tag based on the second text message and the question information; determine the answer information corresponding to the second voice message based on the question tag and the preset question-and-answer database and send the answer information to the client.

[0116] In one embodiment, when the program instructions are executed by the processor to implement the step of determining the question information corresponding to the first voice information based on the first text keyword and a preset question and answer database and sending the question information to the client, the following steps are specifically implemented: determining whether the first text keyword matches the preset category keyword; if the first text keyword matches the preset category keyword, obtaining the question type corresponding to the category keyword, and determining the question information corresponding to the question type as the question information corresponding to the first voice information.

[0117] In one embodiment, when the program instructions are executed by the processor to implement the step of generating a question tag based on the second text information and the question information, the following steps are specifically implemented: performing word segmentation processing on the second text information to obtain second text keywords, and determining whether there are preset forward keywords in the second text keywords and determining whether there are preset reverse keywords in the second text keywords; if there are preset forward keywords in the second text keywords, generating a forward question tag based on the question information; if there are preset reverse keywords in the second text keywords, generating a reverse question tag based on the question information.

[0118] In one embodiment, when the program instructions are executed by the processor to implement the step of determining the answer information corresponding to the second voice information based on the question tag and the preset question and answer database and sending the answer information to the client, the following steps are specifically implemented: obtaining a mapping condition that matches the question tag in the preset question and answer database; determining the answer information corresponding to the second voice information based on the mapping condition and the preset answer mapping relationship.

[0119] In one embodiment, after the program instructions are executed by the processor to implement the step of determining the answer information corresponding to the second voice information based on the question tag and the preset question and answer database and sending the answer information to the client, the following steps are specifically implemented: obtaining the current location information of the client, and determining the hospital information closest to the current location information based on the current location information; determining the department information matching the disease information based on the disease information and the preset department mapping relationship; and sending the hospital information and the department information to the client.

[0120] The computer-readable storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which may store program codes.

[0121] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described device and unit can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0122] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, more than one unit or component can be combined or integrated into another system, or some features can be ignored or not executed.

[0123] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs.

[0124] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0125] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a client, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0126] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A voice question-answering interactive method, characterized in that: The method comprises: Acquire first voice information input by a user through a client, perform voice recognition on the first voice information to generate first text information, and perform word segmentation processing on the first text information to obtain first text keywords; Determine question information corresponding to the first voice information according to the first text keyword and a preset question-answer database and send the question information to the client; Acquiring second voice information input by the user through the client according to the question information and performing voice recognition on the second voice information to generate second text information; generating a question mark according to the second text information and the question information; Determining answer information corresponding to the second voice information according to the question tag and the preset question-answer database and sending the answer information to the client; The determining, according to the first text keyword and a preset question-answer database, question information corresponding to the first voice information and sending the question information to the client includes: Determining whether the first text keyword matches a preset category keyword; If the first text keyword matches a preset category keyword, obtaining a question type corresponding to the category keyword, and determining question information corresponding to the question type as question information corresponding to the first voice information; The answer information is disease information. After determining the answer information corresponding to the second voice information according to the question tag and the preset question-answer database and sending the answer information to the client, the method further includes: Acquire the current location information of the client, and determine the hospital information closest to the current location information according to the current location information; Determining department information matching the disease information according to the disease information and a preset department mapping relationship; Sending the hospital information and the department information to the client; The generating a question mark according to the second text information and the question information includes: Performing word segmentation processing on the second text information to obtain second text keywords, and determining whether there are preset forward keywords in the second text keywords and determining whether there are preset reverse keywords in the second text keywords; If there is a preset positive keyword in the second text keyword, generate a positive question mark according to the question information; If there is a preset reverse keyword in the second text keyword, a reverse question mark is generated according to the question information.

2. The method according to claim 1, characterized in that The determining answer information corresponding to the second voice information according to the question mark and the preset question-answer database and sending the answer information to the client includes: Acquire a mapping condition matching the question tag in a preset question-answer database; The answer information corresponding to the second voice information is determined according to the mapping condition and a preset answer mapping relationship.

3. A voice question-answering interactive device, characterized in that: The device comprises: A first acquisition unit, configured to acquire first voice information input by a user through a client, perform voice recognition on the first voice information to generate first text information, and perform word segmentation processing on the first text information to obtain first text keywords; A first determining unit, configured to determine question information corresponding to the first voice information according to the first text keyword and a preset question-answer database and send the question information to the client; A second acquisition unit, configured to acquire second voice information input by the user through the client according to the question information and perform voice recognition on the second voice information to generate second text information; A first generating unit, configured to generate a question mark according to the second text information and the question information; A second determining unit, configured to determine answer information corresponding to the second voice information according to the question tag and the preset question-answer database and send the answer information to the client, wherein the answer information is disease information; The first determining unit includes a first judging unit and a third determining unit: The first determination unit is used to determine whether the first text keyword matches a preset category keyword; The third determining unit is configured to obtain a question type corresponding to the category keyword if the first text keyword matches a preset category keyword, and determine the question information corresponding to the question type as the question information corresponding to the first voice information; A fourth acquisition unit, configured to acquire the current location information of the client, and determine the hospital information closest to the current location information according to the current location information; a fifth determining unit, configured to determine department information matching the disease information according to the disease information and a preset department mapping relationship; A sending unit, used for sending the hospital information and the department information to the client; The first generating unit comprises: A second judgment unit is used to perform word segmentation processing on the second text information to obtain second text keywords, and to judge whether there are preset forward keywords in the second text keywords and whether there are preset reverse keywords in the second text keywords; A second generating unit, configured to generate a positive question mark according to the question information if there is a preset positive keyword in the second text keyword; The third generating unit is configured to generate a reverse question tag according to the question information if there is a preset reverse keyword in the second text keyword.

4. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the voice question and answer interaction method according to any one of claims 1 to 2 is implemented.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, enables the processor to perform the voice question-and-answer interaction method as described in any one of claims 1-2.

Images