Method, device, and storage medium for processing question and answer information

Abstract

The present disclosure provides a method, device and storage medium for processing question and answer information, relating to the technical field of artificial intelligence, in particular the technical field of deep learning, natural language processing and the like. The specific implementation scheme is: in the process of processing a question to be answered, the geographical information corresponding to the question and the location information in the question are obtained, the point of interest information corresponding to the location information is obtained on the administrative division map corresponding to the geographical information, and based on the position information in the point of interest information, the answerer terminal answering the question is obtained, and the answer of the question is determined based on the answer of the answerer terminal. Therefore, through the geographical information and the location information corresponding to the question, the answerer terminal that can accurately answer the question is obtained, and the accuracy of the answer to the question is improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of artificial intelligence, in particular to the technical field of deep learning, natural language processing and the like, and more particularly to a method, device and storage medium for processing question and answer information. BACKGROUND

[0002] With the continuous development of Internet technology and communication technology, the online function has been very common on terminal devices, and people's daily life is increasingly closely related to the Internet. Based on the characteristics of the real-time processing question and answer information device based on the Internet, more and more people tend to get answers to the corresponding questions by asking questions in the question and answer system for various problems encountered in daily life. It is very important to provide accurate answers for the questions asked by the questioners in the question and answer system. If the replies of the answerers may not be targeted, the replies are of low usability for the questioners, and the interaction process of these low usability replies will also occupy bandwidth resources. SUMMARY

[0003] The present disclosure provides a method, device and storage medium for processing question and answer information.

[0004] According to an aspect of the present disclosure, a method for processing question and answer information is provided, which includes: performing regional identification on a question to be answered to obtain regional information corresponding to the question; determining location information in the question; obtaining interest point information corresponding to the location information on a administrative division map corresponding to the regional information, wherein the interest point information includes position information; obtaining an answerer terminal within a preset range from the position information; and obtaining an answer of the answerer terminal to the question.

[0005] According to another aspect of the present disclosure, a device for processing question and answer information is provided, which includes: a regional identification module configured to perform regional identification on a question to be answered to obtain regional information corresponding to the question; a determination module configured to determine location information in the question; a first obtaining module configured to obtain interest point information corresponding to the location information on a administrative division map corresponding to the regional information, wherein the interest point information includes position information; a second obtaining module configured to obtain an answerer terminal within a preset range from the position information; and a third obtaining module configured to obtain an answer of the answerer terminal to the question.

[0006] According to another aspect of the present disclosure, an electronic device is provided, which includes: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method for processing question and answer information of the present disclosure.

[0007] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method for processing question and answer information disclosed by the embodiments of the present disclosure.

[0008] According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method for processing question and answer information of the present disclosure.

[0009] One of the above technical solutions has the following advantages or beneficial effects:

[0010] In the process of processing the question to be answered, the geographical information corresponding to the question and the location information in the question are obtained, and the point of interest information corresponding to the location information is obtained on the administrative division map corresponding to the geographical information, and based on the position information in the point of interest information, the answerer terminal answering the question is obtained, and based on the answer of the answerer terminal, the answer to the question is determined. Therefore, through the geographical information and the location information corresponding to the question, the answerer terminal that can accurately answer the question is obtained, and the accuracy of the answer to the question is improved.

[0011] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0012] The accompanying drawings are used to better understand the present solution and do not limit the present disclosure. Among them:

[0013] Figure 1 is a flowchart of the method for processing question and answer information according to the first embodiment of the present disclosure;

[0014] Figure 2 is a flowchart of the method for processing question and answer information according to the second embodiment of the present disclosure;

[0015] Figure 3 is a flowchart of the method for processing question and answer information according to the third embodiment of the present disclosure;

[0016] Figure 4 is a structural diagram of the device for processing question and answer information according to the fourth embodiment of the present disclosure;

[0017] Figure 5 is a structural diagram of the device for processing question and answer information according to the fifth embodiment of the present disclosure;

[0018] Figure 6This is a block diagram of an electronic device used to implement the method for processing question-and-answer information according to embodiments of the present disclosure. Detailed Implementation

[0019] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0020] The following description, with reference to the accompanying drawings, outlines a method, apparatus, and storage medium for processing question-and-answer information according to embodiments of the present disclosure.

[0021] Figure 1 This is a flowchart illustrating a method for processing question-and-answer information according to a first embodiment of the present disclosure.

[0022] like Figure 1 As shown, the method for processing question-and-answer information may include:

[0023] Step 101: Identify the region of the question to be answered in order to obtain the region information corresponding to the question.

[0024] It should be noted that the execution subject of the method for processing question and answer information in this embodiment is a device for processing question and answer information. The device for processing question and answer information can be implemented by software and / or hardware. The device for processing question and answer information can be configured in a question and answer system. The question and answer system can be configured in an electronic device. The electronic device can include, but is not limited to, terminal devices, servers, etc. This embodiment does not specifically limit the electronic device.

[0025] In some exemplary embodiments of this disclosure, the question to be answered may be a question that the question-and-answer system cannot distribute to the responding master terminal based on a general classification. In other exemplary embodiments, the question to be answered may be any question to be processed in the question-and-answer system, and this embodiment does not specifically limit the question to be answered.

[0026] It is understood that the device for processing question-and-answer information in this embodiment can handle various forms of questions, including text-based questions, image-based questions, and voice-based questions.

[0027] In some exemplary embodiments, when the question is in the form of a voice, the device for processing question-and-answer information can perform speech recognition on the voice corresponding to the question to obtain the speech recognition result of the question, and perform regional recognition on the speech recognition result to obtain the regional information of the question.

[0028] In some example embodiments, in the case where the above-mentioned question is in the form of an image, the device for processing question and answer information can perform character recognition on the image corresponding to the question to obtain a character recognition result, and perform geographical recognition on the character recognition result to obtain geographical information of the question.

[0029] Step 102: determining the place information in the question.

[0030] In some embodiments, the above-mentioned determination of the place information in the question can be implemented in different application scenarios in various ways, which are exemplarily explained as follows:

[0031] As an example embodiment, the question can be input into a place extraction model to extract the place information in the question through the place extraction model to obtain the place information in the question.

[0032] As another example embodiment, in order to accurately determine the place information in the question, the question is subjected to place name extraction to obtain a first extraction result, and is subjected to organization name extraction to obtain a second extraction result, and the place information in the question is determined according to the first extraction result and the second extraction result.

[0033] The first extraction result includes at least one place name. The place name can include but is not limited to province, city, curve, road, landmark name, etc.

[0034] The second extraction result can be empty, or can be at least one organization name. The organization name includes but is not limited to government agency, educational institution, recreational entertainment venue, enterprise institution, etc.

[0035] In some embodiments, the above-mentioned possible implementation of determining the place information in the question according to the first extraction result and the second extraction result is as follows: in the case where the second extraction result is empty, it indicates that the question does not contain an organization name, at this time, the multiple place names in the first extraction result can be de-duplicated, and at least one de-duplicated place name can be spliced in the order of the appearance of each place name in the question to obtain a spliced place name, and the spliced place name is taken as the place information in the question.

[0036] In some example embodiments of the present disclosure, in the case where the second extraction result is non-empty, the place information in the question can be obtained by splicing the first extraction result and the second extraction result.

[0037] In some embodiments, the first extraction result and the second extraction result can be spliced in the order of the first extraction result first and the second extraction result second to obtain the place information in the question.

[0038] In step 103, the point of interest information corresponding to the location information on the administrative division map corresponding to the region information is obtained, wherein the point of interest information includes the position information.

[0039] In some embodiments, the point of interest information can further include detailed address information, images, introduction information, etc.

[0040] In step 104, the answerer terminal within a preset range from the position information is obtained.

[0041] The preset range is preset in the device for processing question and answer information, for example, the answerer terminal within a circular range with the position information as the center and a radius of 100 meters can be obtained.

[0042] The answerer terminal refers to the terminal device corresponding to the answerer who can answer the question. The terminal device can include a personal computer, a smart mobile device, etc., which are not limited in this embodiment.

[0043] The answerer terminal can be one or more, which are not limited in this embodiment.

[0044] In step 105, the answer of the answerer terminal to the question is obtained.

[0045] In some embodiments of the present disclosure, in order to further improve the accuracy of the answer, the domain type of the question can be determined, and the target answerer terminal corresponding to the domain type is obtained from the answerer terminal, and the answer of the target answerer terminal to the question is obtained.

[0046] The method for processing question and answer information in the embodiment of the present disclosure, in the process of processing the question to be answered, obtains the region information corresponding to the question and the location information in the question, obtains the point of interest information corresponding to the location information on the administrative division map corresponding to the region information, and obtains the answerer terminal answering the question based on the position information in the point of interest information, and determines the answer to the question based on the answer of the answerer terminal. Therefore, by the region information and the location information corresponding to the question, the answerer terminal accurately answering the question is obtained, and the accuracy of the answer to the question is improved.

[0047] Figure 2 is a flowchart of the method for processing question and answer information according to the second embodiment of the present disclosure.

[0048] It should be noted that the present embodiment is a further refinement of the above-mentioned embodiments.

[0049] As shown in Figure 2 The method for processing question and answer information can include:

[0050] In step 201, the question to be answered is input into the region identification model to obtain the region information corresponding to the question through the region identification model.

[0051] In some embodiments, the region identification model can perform hierarchical region matching on the question to obtain the region information in the question.

[0052] In some embodiments, when matching the hierarchical region, a strategy of sub-region priority matching and parent region auxiliary correction can be adopted.

[0053] In step 202, a plurality of entity words in the question and an entity type corresponding to each entity word are determined.

[0054] In some embodiments, the plurality of entity words in the question and the entity type corresponding to each entity word can be determined in various ways, which are exemplarily described as follows.

[0055] As an example, the question can be segmented to obtain a segmentation result of the question. For each word in the segmentation result, the word can be queried based on the word in an entity word library. If the word is queried in the entity word library, the word is determined as an entity word, and the entity type corresponding to the word is determined according to the entity type corresponding to the entity word matching the word in the entity word library.

[0056] As another example, in order to accurately and quickly determine the entity words in the question and the corresponding entity types, the question can be input into a named entity recognition model to obtain the plurality of entity words in the question and the entity type corresponding to each entity word.

[0057] The entity type can include, but is not limited to, a person, a place, a time, and the like.

[0058] In some embodiments, the named entity recognition model can be a model trained on a traditional machine learning model and capable of recognizing named entities. The traditional machine learning model can include a conditional random field (CRF) model and the like.

[0059] In some other embodiments, the named entity recognition model can be a model trained on a deep learning model and capable of recognizing named entities. The deep learning model can include, but is not limited to, a model based on the fusion of a long-short term memory (LSTM) network and CRF, a model based on the fusion of a semantic representation model and CRF.

[0060] In step 203, a target entity word with a place category as the entity type is obtained from the plurality of entity words, and the target entity word is taken as a first extraction result of the question.

[0061] Step 204, input the question into the organization name extraction model to extract the organization name in the question by the organization name extraction model to obtain a second extraction result.

[0062] In this embodiment, the organization name in the question is accurately extracted by the organization name extraction model, so that the organization name information in the question can be accurately determined.

[0063] Step 205, determine the location information in the question according to the first extraction result and the second extraction result.

[0064] Step 206, obtain the point of interest information corresponding to the location information on the administrative division map corresponding to the regional information, wherein the point of interest information includes the position information.

[0065] Step 207, obtain the answerer terminal within a preset range from the position information.

[0066] Step 208, obtain the answer of the answerer terminal to the question.

[0067] It should be noted that the specific description of steps 205 to 208 can be referred to the related description of the above embodiments, which will not be repeated here.

[0068] In this embodiment, in the process of processing the question to be answered, the regional information of the question is extracted based on the regional recognition model to obtain the regional information corresponding to the question, and each entity word in the question and the corresponding entity type are determined, and the target entity word with the entity type of the location category is taken as the first extraction result of the question. The question is input into the organization name extraction model to extract the organization name in the question by the organization name extraction model to obtain a second extraction result. The regional information and the location information corresponding to the question are accurately determined by combining the first extraction result and the second extraction result, so that the accuracy of obtaining the answerer terminal of the question can be improved.

[0069] Figure 3 is a flowchart of a method for processing question and answer information according to the third embodiment of the present disclosure.

[0070] As shown in Figure 3 , the method can include:

[0071] Step 301, obtaining a question to be answered.

[0072] Step 302, input the question into the regional recognition model to obtain the regional recognition result of the question.

[0073] Step 303, determine whether the regional identification result exists regional information, if not, execute step 304, if yes, execute step 305.

[0074] Step 304, determine that there is no regional information in the question.

[0075] Step 305, input the question into the named entity recognition model to obtain a plurality of entity words in the question and an entity type corresponding to each entity word.

[0076] Step 306, from the plurality of entity words, obtain a target entity word of which the entity type is a place category.

[0077] Step 307, input the question into the organization name extraction model to extract the organization name by the organization name extraction model to obtain the organization name extraction result of the question.

[0078] Step 308, splice the target entity word and the organization name extraction result to obtain the place information in the question.

[0079] In some embodiments, the target entity word can be de-duplicated, and the target entity word and the organization name can be sorted according to the order of appearance of the de-duplicated target entity word and the organization name in the question to obtain a sorting result, and the candidate entity word in the sorting result can be spliced to obtain the place information in the question. Wherein, the candidate entity word includes the target entity word and the organization name.

[0080] When splicing the candidate entity word in the sorting result, for any two adjacent candidate entity words, if the start position of the latter candidate entity word in the question is the end position of the former candidate entity word in the question, the two candidate entity words are directly spliced.

[0081] For example, the question is "A province B city some some Jiang shipyard nearby store room what price", if the question is extracted for the place and the organization name, and the extracted results are sorted according to the order of appearance of each extracted result in the question to obtain a sorting result, wherein the sorting result is: A province B city, some some Jiang shipyard. At this time, it can be determined that the start position of the latter candidate entity word "some some Jiang shipyard" in the question is the end position of the former candidate entity word "A province B city", at this time, the two candidate entity words can be spliced, and the splicing result is: A province B city some some Jiang shipyard, at this time, the splicing result can be used as the place information of the question.

[0082] In some embodiments, if the start position of the latter candidate entity word in the question is not the end position of the former candidate entity word in the question, and is not the middle position of the former candidate entity word in the question, the two candidate entity words are not concatenated.

[0083] In some other embodiments, if the start position of the latter candidate entity word in the question is not the end position of the former candidate entity word in the question, and is not the middle position of the former candidate entity word in the question, the two candidate entity words are not concatenated.

[0084] For example, the question is "A province B can now come to C city?", and it is assumed that the candidate entity words of the place category corresponding to the question are: A province B, C city. For the start position of the latter candidate entity word "C city" in the question, it is not the end position of the former candidate entity word "A province B", nor is it the middle position of the former candidate entity word "A province B" in the question. Therefore, the two candidate entity words are not concatenated, and "A province B, C city" is directly taken as the place information of the question.

[0085] After the concatenation is completed, in the case where there are multiple place information, the place information can be sorted according to the length of the place information, and it is judged in a loop whether the place information with a short length is a substring of the place information with a long length. If so, the place information with the short length is deleted.

[0086] For example, the question is "A province B city C economic development zone D town E village 2021 year team secretary name is? E village secretary name", and it is assumed that the place information obtained by concatenating the entity words of the place category includes place information a: A province B city C economic development zone D town E village, and place information b: Taoyuan village. It can be determined by comparison that the place information b is a substring of the place information a, that is, the place information b is contained in the place information a. At this time, the place information b can be deleted, and for the question, the final obtained place information is the place information a.

[0087] In some other embodiments, if the start position of the latter candidate entity word in the question is not the end position of the former candidate entity word in the question, and is not the middle position of the former candidate entity word in the question, the two candidate entity words are not concatenated.

[0088] In step 309, the point of interest information corresponding to the place information on the administrative zoning map corresponding to the region information is obtained, wherein the point of interest information includes position information.

[0089] In some embodiments, location information and regional information can be sent to the map interface. Correspondingly, the location information returned by the map interface is the point of interest information on the administrative division map corresponding to the regional information, wherein the point of interest information includes location information.

[0090] Step 310: Obtain the answerer terminal whose location information is within the preset range.

[0091] In other words, when matching the answerer's terminal, you can select answerer information around the location information and send the question to the terminal device corresponding to that answerer information.

[0092] Step 311: Obtain the answer from the respondent's terminal regarding the question.

[0093] In some embodiments, the answer returned by the respondent terminal may be received and used as the answer to the question.

[0094] In this embodiment, the question is analyzed to obtain its geographic and location information. Based on this information, a matching answerer terminal is quickly and accurately identified. The answer to the question is then determined based on the response provided by that answerer terminal. This achieves an accurate answer to the question.

[0095] To implement the above embodiments, this disclosure also provides an apparatus for processing question-and-answer information.

[0096] Figure 4 This is a schematic diagram of the structure of a device for processing question and answer information according to the fourth embodiment of this disclosure.

[0097] like Figure 4 As shown, the device 400 for processing question-and-answer information may include a region identification module 401, a determination module 402, a first acquisition module 403, a second acquisition module 404, and a third acquisition module 405, wherein:

[0098] The region identification module 401 is used to identify the region of the question to be answered in order to obtain the region information corresponding to the question.

[0099] Module 402 is used to determine the location information in the problem.

[0100] The first acquisition module 403 is used to acquire the point of interest information corresponding to the location information on the administrative division map corresponding to the geographical information, wherein the point of interest information includes location information.

[0101] The second acquisition module 404 is used to acquire the answerer terminal whose distance from the location information is within a preset range.

[0102] The third obtaining module 405 is configured to obtain an answer of a question by the answerer terminal.

[0103] It should be noted that the above description of the method for processing question and answer information is also applicable to this embodiment, and thus will not be described herein.

[0104] The device for processing question and answer information provided in the embodiments of the present disclosure obtains the regional information corresponding to the question and the location information in the question in the process of processing the question to be answered, obtains the point of interest information corresponding to the location information on the administrative division map corresponding to the regional information, and obtains the answerer terminal answering the question based on the location information in the point of interest information, and determines the answer to the question based on the answer of the answerer terminal. Thus, the answerer terminal that can accurately answer the question is obtained based on the regional information and the location information corresponding to the question, and the accuracy of the answer to the question is improved.

[0105] In one embodiment of the present disclosure, as shown in Figure 5 The device 500 for processing question and answer information can include a regional identification module 501, a determination module 502, a first obtaining module 503, a second obtaining module 504, and a third obtaining module 505. The determination module 502 can include a first extraction sub-module 5021, a second extraction sub-module 5022, and a determination sub-module 5023. The first extraction sub-module 5021 can include a determination unit 50211 and an obtaining unit 50212.

[0106] It should be noted that the detailed description of the first obtaining module 503, the second obtaining module 504, and the third obtaining module 505 can refer to the description of the first obtaining module 403, the second obtaining module 404, and the third obtaining module 405 in the embodiment shown in Figure 4

[0107] In one embodiment of the present disclosure, the regional identification module 501 is specifically configured to input the question into a regional identification model to obtain the regional information corresponding to the question through the regional identification model.

[0108] In one embodiment of the present disclosure, the determination module 502 can include:

[0109] The first extraction sub-module 5021 is configured to perform place name extraction on the question to obtain a place name extraction result.

[0110] The second extraction sub-module 5022 is configured to perform organization name extraction on the question to obtain an organization name extraction result.

[0111] The determination sub-module 5023 is configured to determine the location information in the question according to the first extraction result and the second extraction result​

[0112] In an embodiment of the present disclosure, the first extraction submodule 5021 described above includes:

[0113] The determination unit 50211 is configured to determine a plurality of entity words in the question and an entity type corresponding to each entity word.

[0114] The acquisition unit 50212 is configured to acquire a target entity word with an entity type of a place category from the plurality of entity words, and take the target entity word as a first extraction result of the question.

[0115] In an embodiment of the present disclosure, the determination unit 50211 is specifically configured to input the question into a named entity recognition model to obtain the plurality of entity words in the question and the entity type corresponding to each entity word.

[0116] In an embodiment of the present disclosure, the extraction submodule 5022 is specifically configured to input the question into an organization name extraction model to perform organization name extraction through the organization name extraction model to obtain the second extraction result.

[0117] It should be noted that the above-mentioned method for processing question and answer information is also applicable to the device for processing question and answer information in this embodiment, and will not be described here.

[0118] According to embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0119] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present disclosure described and / or claimed in this document.

[0120] As Figure 6As shown, the electronic device 600 can include a computing unit 601 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the device 600 can also be stored in the RAM 603. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0121] A plurality of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, and the like; an output unit 607, such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, an optical disk, and the like; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0122] The computing unit 601 can be various general and / or special-purpose processing components having processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, and the like. The computing unit 601 performs various methods and processes described above, such as the method of processing question and answer information. For example, in some embodiments, the method of processing question and answer information can be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the method of processing question and answer information described above can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the method of processing question and answer information by any other appropriate means, such as by means of firmware.

[0123] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0124] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0125] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0126] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0127] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0128] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, which solves the defects of large management difficulty and weak business scalability in traditional physical host and VPS (Virtual Private Server, or VPS for short) services. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0129] It should be noted that artificial intelligence is a discipline that studies enabling computers to simulate some thinking processes and intelligent behaviors of human beings (such as learning, reasoning, thinking, planning, etc.), and has both hardware-level technology and software-level technology. Artificial intelligence hardware technology generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing, etc.; artificial intelligence software technology mainly includes computer vision technology, speech recognition technology, natural language processing technology, and machine learning / deep learning, big data processing technology, knowledge graph technology, etc.

[0130] It should be understood that the various forms of flow shown above can be used to reorder, add or delete steps. For example, each step described in the present disclosure can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions of the present disclosure can be achieved, which is not limited herein.

[0131] The above specific embodiments do not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for processing question-and-answer information, comprising: The question to be answered is geographically identified to obtain the geographic information corresponding to the question; Determine the location information in the problem; Obtain the point of interest information corresponding to the location information on the administrative division map corresponding to the geographical information, wherein the point of interest information includes location information; Acquire the respondent terminal within a preset range from the location information; Obtain the answer from the respondent's terminal regarding the question; Determining the location information in the problem includes: Place name extraction is performed on the problem to obtain the first extraction result; The organization name is extracted from the problem to obtain a second extraction result; The location information in the problem is determined by splicing the first extraction result and the second extraction result together.

2. The method according to claim 1, wherein, The process of identifying the geographic location of the question to be answered, in order to obtain the geographic information corresponding to the question, includes: The question is input into the region identification model to obtain the region information corresponding to the question through the region identification model.

3. The method according to claim 2, wherein, The step of extracting place names from the problem to obtain a first extraction result includes: Determine the multiple entity words in the problem and the entity type corresponding to each entity word; From multiple entity words, target entity words of the location category are obtained, and these target entity words are used as the first extraction result for the problem.

4. The method according to claim 3, wherein, Determining the multiple entity words in the problem and the entity type corresponding to each entity word includes: The question is input into a named entity recognition model to obtain multiple entity words in the question and the entity type corresponding to each entity word.

5. The method according to claim 3, wherein, The step of extracting organization names from the problem to obtain a second extraction result includes: The problem is input into the organization name extraction model to extract the organization name through the organization name extraction model, so as to obtain the second extraction result.

6. An apparatus for processing question-and-answer information, comprising: The region identification module is used to identify the region of the question to be answered in order to obtain the region information corresponding to the question; The determination module is used to determine the location information in the problem; The first acquisition module is used to acquire the point of interest information corresponding to the location information on the administrative division map corresponding to the geographical information, wherein the point of interest information includes location information; The second acquisition module is used to acquire answerer terminals that are within a preset range from the location information; The third acquisition module is used to acquire the answer from the respondent's terminal to the question; The determining module includes: The first extraction submodule is used to extract place names from the problem to obtain a first extraction result; The second extraction submodule is used to extract the organization name from the problem to obtain the second extraction result; The determination submodule is used to concatenate the first extraction result and the second extraction result to determine the location information in the problem.

7. The apparatus according to claim 6, wherein, The region identification module is specifically used for: The question is input into the region identification model to obtain the region information corresponding to the question through the region identification model.

8. The apparatus according to claim 6, wherein, The first extraction submodule includes: A determining unit is used to determine multiple entity words in the problem and the entity type corresponding to each entity word; The acquisition unit is used to acquire target entity words of the location category from multiple entity words, and to use the target entity words as the first extraction result of the question.

9. The apparatus according to claim 8, wherein, The determining unit is specifically used for: The question is input into a named entity recognition model to obtain multiple entity words in the question and the entity type corresponding to each entity word.

10. The apparatus according to claim 8, wherein, The extraction submodule is specifically used for: The problem is input into the organization name extraction model to extract the organization name through the organization name extraction model, so as to obtain the second extraction result.

11. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.

12. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-5.

13. A computer program product comprising a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-5.

Images