CN117349417A - Information query method, device, electronic equipment and storage medium - Google Patents

Information query method, device, electronic equipment and storage medium Download PDF

Info

Publication number
CN117349417A
CN117349417A CN202311333579.9A CN202311333579A CN117349417A CN 117349417 A CN117349417 A CN 117349417A CN 202311333579 A CN202311333579 A CN 202311333579A CN 117349417 A CN117349417 A CN 117349417A
Authority
CN
China
Prior art keywords
information
answer
question
target
text
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311333579.9A
Other languages
Chinese (zh)
Inventor
蒲松
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Oppo Mobile Telecommunications Corp Ltd
Original Assignee
Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangdong Oppo Mobile Telecommunications Corp Ltd filed Critical Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority to CN202311333579.9A priority Critical patent/CN117349417A/en
Publication of CN117349417A publication Critical patent/CN117349417A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G06F16/3329—Natural language query formulation or dialogue systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Databases & Information Systems (AREA)
  • Human Computer Interaction (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The application discloses an information query method, an information query device, electronic equipment and a storage medium, and relates to the technical field of data processing. The method comprises the following steps: the electronic equipment receives input target problem information; inquiring target answer information corresponding to target question information from a local knowledge base of the electronic equipment, wherein the local knowledge base comprises a plurality of set question-answer pairs, and each set question-answer pair comprises set question information and set answer information corresponding to the set question information; if the target answer information is queried, outputting the target answer information; if the target answer information is not queried, an answer query request is sent to the server, wherein the answer query request is used for requesting to query the target answer information corresponding to the target question information. Therefore, under the condition that the local knowledge base contains the target answer information corresponding to the target question information, the electronic equipment can quickly inquire and output the target answer information from the local knowledge base, and the feedback efficiency of information inquiry is improved.

Description

Information query method, device, electronic equipment and storage medium
Technical Field
The present disclosure relates to the field of data processing technologies, and in particular, to an information query method, an information query device, an electronic device, and a storage medium.
Background
With the advent of chat generation pre-training converters (Chat Generative Pre-trained Transformer, chatGPT), artificial intelligence (Artificial Intelligence, AI) dialogs, AI queries, and other artificial intelligence tools have received widespread popularity and attention, and various language processing models have evolved. The AI is convenient and efficient, has various functions and wide application, and is beneficial to people in the use process.
In the related art, a user inputs question information to an electronic device, the electronic device transmits the question information to a cloud end through an AI interface, a language processing model of the cloud end generates corresponding answer information, and the cloud end feeds back the generated answer information to the electronic device. However, the answer feedback efficiency in the related art has yet to be improved.
Disclosure of Invention
The application provides an information query method, an information query device, electronic equipment and a storage medium, so as to improve the accuracy of information query.
In a first aspect, an embodiment of the present application provides an information query method, applied to an electronic device, where the method includes: receiving input target problem information; inquiring target answer information corresponding to the target question information from a local knowledge base of the electronic equipment, wherein the local knowledge base comprises a plurality of set question-answer pairs, and each set question-answer pair comprises set question information and set answer information corresponding to the set question information; if the target answer information is queried, outputting the target answer information; and if the target answer information is not queried, sending an answer query request to a server, wherein the answer query request is used for requesting to query the target answer information corresponding to the target question information.
In a second aspect, an embodiment of the present application provides an information query apparatus, where the apparatus includes: the system comprises a problem receiving module, a first query module, an information output module and a second query module. The problem receiving module is used for receiving input target problem information; the first query module is used for querying target answer information corresponding to the target question information from a local knowledge base of the electronic equipment, wherein the local knowledge base comprises a plurality of set question-answer pairs, and each set question-answer pair comprises set question information and set answer information corresponding to the set question information; the information output module is used for outputting the target answer information if the target answer information is inquired; and the second query module is used for sending an answer query request to the server if the target answer information is not queried, wherein the answer query request is used for querying the target answer information corresponding to the target question information.
In a third aspect, an embodiment of the present application provides an electronic device, including: one or more processors; a memory; one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the methods described above.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium having program code stored therein, the program code being callable by a processor to perform the method described above.
In the scheme provided by the application, the electronic equipment receives input target problem information; inquiring target answer information corresponding to target question information from a local knowledge base of the electronic equipment, wherein the local knowledge base comprises a plurality of set question-answer pairs, and each set question-answer pair comprises set question information and set answer information corresponding to the set question information; if the target answer information is queried, outputting the target answer information; if the target answer information is not queried, an answer query request is sent to the server, wherein the answer query request is used for requesting to query the target answer information corresponding to the target question information. Therefore, under the condition that the local knowledge base contains the target answer information corresponding to the target question information, the electronic equipment can quickly inquire and output the target answer information from the local knowledge base, namely the feedback efficiency of information inquiry is improved; and the local knowledge base does not contain target answer information corresponding to the target question information, and then the server is called to further inquire, so that the problems such as information inquiry failure and the like are avoided.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart illustrating an information query method according to an embodiment of the present application.
Fig. 2 shows a schematic device diagram of an electronic device according to an embodiment of the present application.
Fig. 3 is a schematic flow chart of an information query method according to another embodiment of the present application.
Fig. 4 shows a flow diagram of the sub-steps of step S220 in fig. 3 in one embodiment.
Fig. 5 is a flow chart illustrating an information query method according to another embodiment of the present application.
Fig. 6 is a block diagram of an information query apparatus according to an embodiment of the present application.
Fig. 7 is a block diagram of an electronic device for performing an information query method according to an embodiment of the present application.
Fig. 8 is a storage unit for storing or carrying program code for implementing the information query method according to the embodiment of the present application.
Detailed Description
In order to enable those skilled in the art to better understand the present application, the following description will make clear and complete descriptions of the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present application based on the embodiments herein.
It should be noted that, in some of the processes described in the specification, claims and drawings above, a plurality of operations appearing in a specific order are included, and the operations may be performed out of the order in which they appear herein or in parallel. The sequence numbers of operations such as S110, S120, etc. are merely used to distinguish between the different operations, and the sequence numbers themselves do not represent any execution order. In addition, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. And the terms first, second and the like in the description and in the claims of the present application and in the above-described figures, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or sub-modules is not necessarily limited to those steps or sub-modules that are expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or sub-modules that are not expressly listed.
In the related art, in the process of man-machine question answering, aiming at the question information input by the user, an AI interface is called to inquire the corresponding answer information, which has the following disadvantages: the AI interface is called to charge according to the times, or the number of words of the output answer information is charged, so that the cost is high; the AI interface needs to be used in a network, so that the AI interface is easily influenced by the network; the AI interface is internally provided with a model in a cloud server for carrying out reasoning generation of answer information, and complex problems take longer time.
The inventor provides an information query method, an information query device, electronic equipment and a storage medium. The information query method provided in the embodiment of the present application is described in detail below.
Referring to fig. 1, fig. 1 is a flowchart of an information query method according to an embodiment of the present application, which is applied to an electronic device. The information query method provided in the embodiment of the present application will be described in detail below with reference to fig. 1. The information inquiry method may include the steps of:
step S110: input target problem information is received.
In this embodiment, the electronic device may be a smart phone, a tablet computer, or a desktop computer as shown in fig. 2, and of course, may also be a notebook computer, a smart watch, an electronic book reader, or an MP3 (Moving Picture Experts Group Audio Layer III, dynamic image expert compression standard audio layer 3) player, an MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image expert compression standard audio layer 4) player.
Alternatively, the input mode of the user to input the target problem information to the electronic device may be a text input mode, a voice input mode, or a picture input mode, which is not limited in this embodiment. Based on this, the received target question information may also be information in text form, voice form, or picture form; moreover, the target question information is not only text information in the form of a question as literally described, but may be any sentence, any word, a piece of speech, or a piece of picture.
Step S120: inquiring target answer information corresponding to the target question information from a local knowledge base of the electronic equipment, wherein the local knowledge base comprises a plurality of set question-answer pairs, and each set question-answer pair comprises set question information and set answer information corresponding to the set question information.
In this embodiment, a plurality of question-answer pairs may be stored in advance in a local knowledge base of the electronic device, where each question-answer pair includes question setting information and answer setting information corresponding to the question setting information, and the question setting information and the answer setting information are both text-form information. The local knowledge base can be understood as a part of the storage space of the electronic device, which is divided into a plurality of setting question-answer pairs.
Before inquiring target answer information corresponding to target question information, firstly, unifying file formats of the received target question information, namely, converting the received target question information into target question information in a text form, namely, target question text information. And then, inquiring target answer information corresponding to the target question information in a text form from the local knowledge base. Specifically, whether the set question information matched with the target question text information exists in the local knowledge base or not can be queried, and if so, the set question information corresponding to the set question information matched with the target question text information is obtained and used as the target answer information; if the answer information is not found, determining that the target answer information is not queried.
In some embodiments, whether the local knowledge base has the set problem information matched with the target problem text information or not may be determined by acquiring a similarity between the target problem text information and each set problem information, determining whether the similarity is greater than a first preset threshold, and if the similarity is greater than the first preset threshold, determining that the local knowledge base has the set text information matched with the target problem text information; if the similarity is smaller than or equal to a first preset threshold value, determining that no set problem information matched with the target problem text information exists in the local knowledge base.
In this aspect, if there are a plurality of setting question information having a similarity greater than the first preset threshold, the setting question information having the greatest similarity may be determined as the setting question information matching the target question text information. Therefore, the set question information closest to the target question information can be more accurately matched based on the similarity, and therefore more accurate target answer information is queried.
It can be understood that the electronic device can provide the information query function for the user through the installed information query application, so that the user installs the required information query application in the electronic device, and the information query application is utilized to realize the information query of the application. Alternatively, the information inquiry application may be multiple or one; if the number of the information query applications in the electronic device is multiple, each information query application may correspond to a local knowledge base, and of course, the multiple information query applications may share a local knowledge base, which is not limited in this embodiment.
Step S130: and if the target answer information is queried, outputting the target answer information.
In this embodiment, if the electronic device queries the target answer information from the local knowledge base, the target answer information may be output in a target output manner. The target output mode may be a screen display output mode of the electronic device, a voice output mode, a mail output mode, a short message output mode, or the like, which is not limited in this embodiment.
Alternatively, the default output mode of the electronic device may be used as the target output mode. For example, a screen display output mode of the electronic device.
Alternatively, an output mode set by the user may be used as the target output mode. Such as voice output.
Optionally, the matching output mode can be correspondingly selected according to the information form of the target answer information to serve as the target output mode. For example, the target answer information is in text form, video form or picture form, and the matched output mode can be a screen display output mode of the electronic device. For another example, the target answer information is in a voice form, and the matched output mode may be a voice output mode.
Step S140: and if the target answer information is not queried, sending an answer query request to a server, wherein the answer query request is used for requesting to query the target answer information corresponding to the target question information.
It will be appreciated that electronic devices such as smartphones, tablet computers, desktop computers and notebook computers have limited storage space and therefore the number of set question-answer pairs in their local knowledge base is limited. Therefore, the electronic device can send an answer query request to the external server under the condition that the target answer information is not queried in the local knowledge base, wherein the answer query request carries the target question information; correspondingly, the server can respond to the answer inquiry request, inquire target answer information corresponding to the target question information carried by the answer inquiry request, and feed the inquired target answer information back to the electronic equipment. The electronic device can receive and output the target answer information fed back by the server.
Optionally, a plurality of set question-answer pairs different from the plurality of set question-answer pairs in the local knowledge base may be pre-stored in the server, and for convenience of description, the plurality of set question-answer pairs in the local knowledge base are symmetrical to a plurality of first set question-answer pairs, and the plurality of set question-answer pairs in the server are symmetrical to a plurality of second set question-answer pairs. Wherein the number of second set question-answer pairs is much larger than the number of first set question-answer pairs. That is, in order to ensure that the electronic device has enough available storage space, most of set question-answer pairs are stored in the server, so that the problems of operation blocking and the like of the electronic device caused by occupying excessive storage space of the electronic device are avoided; meanwhile, the electronic equipment can query the corresponding target answer information from the server under the condition that the target answer information is not queried from the local knowledge base, so that the smooth progress of information query is ensured.
In other embodiments, in consideration of the fact that the target question information input by the user will be various, it is theoretically impossible to completely count the answers corresponding to all the question information of the user. Based on this, the electronic device may then send an answer query request to the server via the AI interface. At this time, the aforementioned server may be a cloud server of a third party vendor that provides services of AI artificial intelligence, where the services include, but are not limited to, natural language processing, image recognition, voice recognition, machine translation, intelligent recommendation, and the like. As such, the electronic device may invoke these services and functions in the cloud server based on the AI interface.
In this way, the server has a natural language model trained in advance through a large number of training sample sets, the server can generate target answer information corresponding to the target question information by using the natural language model, then the server feeds the generated target answer information back to the electronic equipment, and the electronic equipment can output the target answer information in a target output mode; the target output mode may refer to the foregoing, and will not be described herein.
Obviously, in this way, the AI interface is invoked only when the electronic device cannot query the target answer information in the local knowledge base, and the corresponding target answer information is generated by using the natural language model in the server, instead of invoking the AI interface for each input question information. Therefore, the cost of calling the AI interface is greatly reduced, namely, the information query cost of the electronic equipment is reduced.
The servers may be independent physical servers, server clusters formed by a plurality of physical servers or a distributed system, or cloud servers providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, network acceleration services (Content Delivery Network, CDN), basic cloud computing services such as big data and an artificial intelligence platform, which are not limited in this embodiment.
In this embodiment, in the case that the local knowledge base includes the target answer information corresponding to the target question information, the electronic device may quickly query and output the target answer information from the local knowledge base, so that feedback efficiency of information query is improved; and the local knowledge base does not contain target answer information corresponding to the target question information, and then the natural language model in the server is called through the AI interface to carry out reasoning generation of the answer information, so that the problems such as information query failure are avoided, the problems such as high cost, to-be-verified question response accuracy, long time consumption of complex question response and the like caused by calling the AI interface in each information query process are effectively compensated, and the information query is realized more rapidly and accurately on the premise of lower query cost.
Referring to fig. 3, fig. 3 is a flowchart of an information query method according to another embodiment of the present application, which is applied to an electronic device. The information query method provided in the embodiment of the present application will be described in detail below with reference to fig. 3. The information inquiry method may include the steps of:
step S210: and acquiring the setting text information.
In some embodiments, the setting text information may be generated based on the input target information to be generated as a question-answer pair. The target information may be information in the form of text, picture, video or audio, etc., wherein the text form may include PDF text form and word text form. In the mode, the developer can input target information with high user query probability into the electronic equipment in advance, and the electronic equipment generates a set question-answer pair based on the target information, so that the electronic equipment can quickly query and feed back corresponding answer information in the subsequent user information query process.
In this manner, if the target information is not text-form information, the electronic device can convert the form of the target information into text-form information as the set text information; if the target information is text information, the electronic device may directly use the target information as the setting text information.
In other embodiments, historical question-answer record information may be obtained as the setting text information. It can be understood that, because some answer information in the part of the history question-answering process is fed back by the server, that is, the electronic device does not store the part of question information and the answer information corresponding to the question information, the electronic device can store the history record of each information query, thereby obtaining the history question-answering record information corresponding to each information query, and store the history question-answering record information corresponding to each information query in a text form, so as to obtain the stored history question-answering record information as the setting text information. In this way, the question-answer pairs in the local knowledge base can be further enriched.
In this way, the electronic device may further output first prompt information when each question and answer is finished, that is, when the user closes the information inquiry dialogue window, where the first prompt information is used to prompt the user to score the output historical answer information in the question and answer process; and the electronic equipment stores the history score corresponding to the history scoring corresponding to each history question-answering process. And further acquiring historical question-answering record information corresponding to a historical question-answering process with the historical score larger than a preset score threshold value, and taking the historical question-answering record information as the set text information. Thus, the accuracy of the acquired setting text information is ensured, and the accuracy of the subsequent setting question-answer pairs generated based on the setting text information can be improved.
In this way, the number of texts of the historical question-answer record information may be detected every preset time period, and if the number of texts is greater than the first number threshold, the historical question-answer record information of the part may be obtained as the set text information. In addition, in order to save the storage space of the electronic device, after the set question-answer pair is generated based on the part of the history question-answer record information, the part of the history question-answer record information can be deleted.
In still other embodiments, the setting text information is generated based on the input target information to be generated as the question-answer pair, and at the same time, the history question-answer record information is also acquired as the setting text information. That is, the electronic device may obtain the setting text information according to the target information and the history question-answer record information input by the user at the same time, so as to enrich the number of the setting question-answer pairs in the local knowledge base based on more setting text information.
Step S220: and generating a set question-answer pair corresponding to the set text information based on the text content in the set text information.
In some embodiments, considering that in practical applications, the text lengths of the set text information are inconsistent, and the text lengths of part of the set text information are longer, if a set question-answer pair is generated directly based on all text contents in the set text information, the content in the set question-answer pair will be too much, which is unfavorable for information retrieval. Therefore, referring to fig. 4, step S220 may specifically include the following steps S221 to S224:
Step S221: and acquiring the text length of the set text information.
The text length may be represented by the number of characters, for example, the set text information includes 500 characters (for example, text, english letters, and punctuation marks), and the text length of the set text information is 500.
Step S222: if the text length is greater than a first length threshold, dividing the set text information according to a target division rule to obtain a plurality of sub-text information, wherein the text length of each sub-text information is smaller than or equal to the first length threshold.
The first length threshold may be a value that is empirically preset, such as 500 or 300. If the text length of the set text information is greater than the first length threshold, the set text information may be divided into a plurality of sub-text information according to the target division rule, and the text length of each sub-text information is less than or equal to the first length threshold. The target dividing rule may be to divide the set text information once every first length threshold, and if the dividing position is not at the end of a sentence but in the middle of a sentence, the dividing may be performed at the end of the previous sentence at the current dividing position. Therefore, the method can avoid dividing a sentence into two parts, which results in the fact that the important content of the sentence cannot be accurately extracted later.
Step S223: and generating a set question-answer pair corresponding to each piece of sub-text information according to the text content in each piece of sub-text information.
Further, after obtaining the plurality of sub-text information, a set question-answer pair corresponding to each sub-text information can be generated according to the text content in each sub-text information.
In some embodiments, the Fasttext classification tool may be used to classify the subject of each sub-text message to obtain a subject class corresponding to each sub-text message; and then, carrying out content abstract on each piece of sub-text information by using a TextRank algorithm to obtain content abstract information of each piece of sub-text information, generating corresponding question information based on the content abstract information, further, taking the generated question information as set question information in a set question-answer pair corresponding to each piece of sub-text information, and taking the extracted content abstract information as set answer information in the set question-answer pair corresponding to each piece of sub-text information, thereby obtaining the set question-answer pair corresponding to each piece of sub-text information. Wherein the content summary information can be understood as a shorter text information summarizing important information content in the sub-text information.
Step S224: and if the text length of the set text information is smaller than or equal to the first length threshold value, generating a set question-answer pair corresponding to the set text information according to the text content in the set text information.
Similarly, performing theme classification on the set text information by using a Fasttext classification tool to obtain theme categories corresponding to the set text information; and then, carrying out content summarization on the set text information by using a TextRank algorithm to obtain content summarization information of the set text information, generating corresponding question information based on the set text information, further, taking the generated question information as set question information in a set question-answer pair corresponding to the set text information, and taking the extracted content summarization information as set answer information in the set question-answer pair corresponding to the set text information, thereby obtaining the set question-answer pair corresponding to the set text information.
In other embodiments, before step S221, it may further be detected whether the set text information includes a plurality of paragraph identifiers, so as to determine whether the set text information includes a plurality of paragraphs; if only one paragraph identifier is included, the contents of step S221 to step S224 are executed; if a plurality of paragraph identifiers are included, the content in steps S221 to S224 may be executed for each text paragraph corresponding to the paragraph identifier. That is, in this manner, the division of the sub-text information can be made more rapid in combination with the paragraph identifications and the text lengths of the text paragraphs to which each paragraph identification corresponds.
Step S230: and adding the set question-answer pairs to the local knowledge base.
In this embodiment, the local knowledge base may include a plurality of set topic categories and a plurality of set question-answer pairs under each set topic category. Based on this, before adding the generated set question-answer pair to the local knowledge base, it may be first determined whether the same set topic category as the topic category of the generated set question-answer pair exists in the local knowledge base, and if not, the topic category of the generated set question-answer pair is newly added to the local knowledge base, and the generated set question-answer pair is added to the newly added topic category for storage.
Optionally, if so, it may be further determined whether a first set of question-answer pairs identical to the generated question information of the set of question-answer pairs exist in the same set of question-answer categories as the generated set of question-answer pairs, where the first set of question-answer pairs is any one of the set of question-answer pairs in the same set of question-answer categories; if the first set question-answer pair which is the same as the generated set question-answer pair exists, further judging that the answer information in the generated set question-answer pair is matched with the set answer information in the first set question-answer pair, and if the answer information in the generated set question-answer pair is matched with the set answer information in the first set question-answer pair, adding the generated set question-answer pair into a local knowledge base is not needed. If the answer information in the first set question-answer pair is not matched with the answer information in the first set question-answer pair, the answer information in the first set question-answer pair can be modified into the answer information in the generated set question-answer pair; if the answer information in the generated set question-answer pair is not matched with the answer information in the first set question-answer pair, the answer information in the generated set question-answer pair can be added to the answer information in the first set question-answer pair. The answer information being matched may be understood that the content similarity between the two answer information is greater than a preset similarity threshold.
In some embodiments, if the answer information in the generated set question-answer pair matches the answer information in the first set question-answer pair, the repetition frequency value corresponding to the first set question-answer pair may be increased by a preset value, for example, the repetition frequency value corresponding to the first set question-answer pair may be increased by 1, in addition to the generated set question-answer pair being unnecessary to be added to the local knowledge base.
Step S240: input target problem information is received.
Step S250: inquiring target answer information corresponding to the target question information from a local knowledge base of the electronic equipment, wherein the local knowledge base comprises a plurality of set question-answer pairs, and each set question-answer pair comprises set question information and set answer information corresponding to the set question information.
Because the local knowledge base in the embodiment contains a plurality of set topic categories, when inquiring the target answer information corresponding to the target question information, the Fasttext classification tool can also be used for classifying the topic of the target question information to obtain the target topic category corresponding to the target question information; further, the set topic category identical to the target topic category is determined from the set topic categories, and then target answer information corresponding to the target question information is queried from the set question-answer pairs under the target topic category in the local knowledge base.
Step S260: and if the target answer information is queried, outputting the target answer information.
Step S270: and if the target answer information is not queried, sending an answer query request to a server, wherein the answer query request is used for requesting to query the target answer information corresponding to the target question information.
In this embodiment, the specific implementation of step S240 to step S270 may refer to the content in the foregoing embodiment, and will not be described herein.
In this embodiment, the electronic device may construct and enrich the set question-answer pairs in the local knowledge base according to the multivariate information, that is, not only may generate the set question-answer pairs according to the historical question-answer record information, but also may generate the set question-answer pairs after unifying the formats of the target information input by the user; thus, the set question and answer pairs in the local knowledge base are richer and more comprehensive. And the set text information is subjected to text length blocking, topic classification and abstract extraction to generate set question-answer pairs, so that the information query efficiency can be improved more effectively, namely, the electronic equipment can timely feed back target answer information corresponding to target question information to the user, and further, the information query experience of the user is improved. Furthermore, the present embodiment can also achieve the effects of the foregoing embodiments, that is, achieve faster and more accurate information query on the premise of lower query cost.
Referring to fig. 5, fig. 5 is a flowchart of an information query method according to another embodiment of the present application, which is applied to an electronic device. The information query method provided in the embodiment of the present application will be described in detail below with reference to fig. 5. The information inquiry method may include the steps of:
step S310: and acquiring the setting text information.
Step S320: and generating a set question-answer pair corresponding to the set text information based on the text content in the set text information.
Step S330: and adding the set question-answer pairs to the local knowledge base.
Step S340: input target problem information is received.
Step S350: and obtaining a target theme category corresponding to the target problem information.
In this embodiment, the specific implementation of step S310 to step S350 may refer to the content in the foregoing embodiment, and will not be described herein.
Step S360: if the set topic category matched with the target topic category corresponding to the target question information does not exist, determining that the target answer information is not queried, and sending an answer query request to a server.
In this embodiment, the local knowledge base includes a plurality of set topic categories and a plurality of set question-answer pairs under each set topic category. Based on this, after the target topic category corresponding to the input target question information is acquired, it may be further determined whether there is a set topic category matching the target topic category among the plurality of set topic categories.
Optionally, if the set topic category matched with the target topic category corresponding to the target question information does not exist, determining that the target answer information is not queried, and sending an answer query request to the server. The specific implementation manner of sending the answer query request to the server may refer to the content in the foregoing embodiment, which is not described herein again.
Step S370: and if a first topic category matched with the target topic category corresponding to the target problem information exists, acquiring a plurality of set question-answer pairs under the first topic category as a plurality of first question-answer pairs, wherein the first topic category is any one of the set topic categories.
Step S380: and if the set question information in the second question-answer pair is matched with the target question information, acquiring the set answer information in the second question-answer pair as target answer information corresponding to the target question information, wherein the second question-answer pair is any one of the first question-answer pairs.
Optionally, if there is a first topic category matching the target topic, further acquiring a plurality of set question-answer pairs under the first topic category as a plurality of first question-answer pairs, where the first topic category is any one of the plurality of set topic categories. Further, judging whether set question information in a plurality of first question-answer pairs is matched with target question information or not, wherein the second question-answer pair is any one of the plurality of first question-answer pairs; the matching between the problem information may be understood as that the similarity threshold between the problem contents between the problem information is greater than the first similarity threshold, that is, the similarity between the two problem information is higher.
Based on the above, if the set question information in the second question-answer pair is matched with the target question information, the set answer information in the second question-answer pair is acquired and used as the target answer information corresponding to the target question information. Therefore, the topic categories are roughly screened, and then the second question-answer pair matched with the target question information is further screened according to the similarity between the question information, and the set answer information in the second question-answer pair is used as the target answer information, so that the answer query speed is greatly improved.
In some embodiments, if the number of the second question-answer pairs is 1, the set answer information in the second question-answer pair may be directly obtained as the target answer information.
In other embodiments, the number of second question-answer pairs is a plurality, and each of the second question-answer pairs carries a corresponding historical query frequency value. Based on the set answer information in the third question-answer pair, which is the second question-answer pair with the largest historical query frequency value carried in the second question-answer pairs, can be obtained and used as the target answer information corresponding to the target question information. In other words, the larger the historical query frequency value of the question-answer pair is, the higher the historical frequency value representing the set answer information in the question-answer pair is output, i.e. the more accurate the set answer information is represented. Therefore, in the case that a plurality of second question-answer pairs exist, more accurate set answer information can be screened out as target answer information according to the historical query frequency value.
In this way, after the set answer information in the third question-answer pair is obtained and is used as the target answer information corresponding to the target question information, the historical query frequency value carried by the third question-answer pair is increased; wherein, can be. The historical query frequency value may also be regarded as the repetition frequency value mentioned in the foregoing embodiment, that is, each set answer pair may be increased by a preset value, for example, by 1, if it is queried once.
In one possible implementation manner, if the number of the third question-answer pairs is 1, the set answer information in the third question-answer pair may be directly obtained as the target answer information.
In another possible implementation manner, if the number of third question-answer pairs is multiple, a history time of last output of answer information set in each third question-answer pair is obtained; obtaining a third question-answer pair with the latest output history time closest to the current time from a plurality of third question-answer pairs, and taking the third question-answer pair as a fourth question-answer pair; and acquiring set answer information in the fourth question-answer pair as target answer information corresponding to the target question information. Obviously, the set answer information that is output most recently is often the latest answer information, and therefore, in the case where a plurality of third question-answer pairs are found, the set answer information in the fourth question-answer pair whose history time that is output most recently is closest to the current time can be obtained as the target answer information. Thus, it can be ensured that the latest answer information is fed back every time aiming at the input target question information.
In this way, the plurality of set question-answer pairs under the same set subject category in the local knowledge base may be sorted and stored according to the history query frequency from large to small, and the plurality of set question-answer pairs aiming at the same history query frequency may be further sorted according to the order from near to far of the last output history time. Thus, in the information query process, the corresponding target answer information can be queried more quickly.
Step S390: if the set question information in the second question-answer pair is not matched with the target question information, determining that the target answer information is not queried, and sending an answer query request to a server.
In this embodiment, in the case that it is determined that the target answer information is not queried in step S390, the specific implementation manner of sending the answer query request to the server may refer to the content in the foregoing embodiment, which is not described herein again.
In this embodiment, the set topic category identical to the target topic category is determined from the multiple set topic categories, and then the target answer information corresponding to the target question information is queried from the multiple set question-answer pairs under the target topic category in the local knowledge base, so that the information query efficiency can be improved. In addition, under the condition that a plurality of possible answer information exists in the query, the historical query frequency value and the last output historical time of the answer information are combined, so that more accurate query of the target answer information is realized, the accuracy of the target answer fed back to the user is ensured, and the user experience of the user for information query is further improved.
Referring to fig. 6, a block diagram of an information query apparatus 400 according to an embodiment of the present application is shown and applied to an electronic device. The apparatus 400 may include: a question receiving module 410, a first query module 420, an information outputting module 430, and a second query module 440.
The question receiving module 410 is configured to receive input target question information.
The first query module 420 is configured to query, from a local knowledge base of the electronic device, target answer information corresponding to the target question information, where the local knowledge base includes a plurality of set question-answer pairs, and each set question-answer pair includes set question information and set answer information corresponding to the set question information.
The information output module 430 is configured to output the target answer information if the target answer information is queried.
The second query module 440 is configured to send an answer query request to a server if the target answer information is not queried, where the answer query request is used to query the target answer information corresponding to the target question information.
In some embodiments, the information query apparatus 400 may further include: setting a text acquisition module, a question-answer pair generation module and an addition module. The setting text obtaining module may be specifically configured to obtain setting text information before querying, from the local knowledge base of the electronic device, target answer information corresponding to the target question information. The question-answer pair generation module can be used for generating a set question-answer pair corresponding to the set text information based on the text content in the set text information. An adding module may be used to add the set question-answer pair to the local knowledge base.
In this manner, the question-answer pair generating module may be specifically configured to obtain a text length of the set text information; dividing the set text information according to a target division rule to obtain a plurality of sub-text information if the text length is greater than a first length threshold, wherein the text length of each sub-text information is smaller than or equal to the first length threshold; generating a set question-answer pair corresponding to each piece of sub-text information according to the text content in each piece of sub-text information; and if the text length of the set text information is smaller than or equal to the first length threshold value, generating a set question-answer pair corresponding to the set text information according to the text content in the set text information.
In this manner, the setting text obtaining module may be configured to generate the setting text information based on the input target information to be generated as the question-answer pair; and/or acquiring historical question-answer record information as the setting text information.
In some embodiments, the local knowledge base includes a plurality of set topic categories and a plurality of set question-answer pairs under each of the set topic categories, and the first query module may include: the system comprises a theme acquisition unit and a first query unit. The topic obtaining unit may be configured to obtain a target topic category corresponding to the target question information. The first querying element may be specifically configured to: if the set topic category matched with the target topic category corresponding to the target question information does not exist, determining that the target answer information is not queried; if a first topic category matched with a target topic category corresponding to the target problem information exists, acquiring a plurality of set question-answer pairs under the first topic category as a plurality of first question-answer pairs, wherein the first topic category is any one of the set topic categories; if the set question information in the second question-answer pair is matched with the target question information, acquiring the set answer information in the second question-answer pair as target answer information corresponding to the target question information, wherein the second question-answer pair is any one of the first question-answer pairs; and if the set question information in the second question-answer pair does not exist and is matched with the target question information, determining that the target answer information is not queried.
In this manner, the number of the second question-answer pairs is plural, and each of the second question-answer pairs carries a corresponding historical query frequency value. The first query unit may be specifically configured to obtain set answer information in a third question-answer pair, where the third question-answer pair is a second question-answer pair with a largest historical query frequency value carried in the plurality of second question-answer pairs, as target answer information corresponding to the target question information.
In this manner, the information inquiry apparatus 400 may further include: and a frequency increment module. The frequency adjustment module may be configured to increase a historical query frequency value carried by the third question-answer pair after the set answer information in the third question-answer pair is obtained and used as the target answer information corresponding to the target question information.
In this manner, the number of the third question-answer pairs is plural, and the first query unit may specifically be configured to: acquiring the last outputted historical time of answer information set in each third question-answer pair; obtaining a third question-answer pair with the latest output history time closest to the current time from a plurality of third question-answer pairs, and taking the third question-answer pair as a fourth question-answer pair; and acquiring set answer information in the fourth question-answer pair as target answer information corresponding to the target question information.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus and modules described above may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.
In several embodiments provided herein, the coupling of the modules to each other may be electrical, mechanical, or other.
In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module. The integrated modules may be implemented in hardware or in software functional modules.
In summary, the electronic device receives input target problem information; inquiring target answer information corresponding to target question information from a local knowledge base of the electronic equipment, wherein the local knowledge base comprises a plurality of set question-answer pairs, and each set question-answer pair comprises set question information and set answer information corresponding to the set question information; if the target answer information is queried, outputting the target answer information; if the target answer information is not queried, an answer query request is sent to the server, wherein the answer query request is used for requesting to query the target answer information corresponding to the target question information. Therefore, under the condition that the local knowledge base contains the target answer information corresponding to the target question information, the electronic equipment can quickly inquire and output the target answer information from the local knowledge base, namely the feedback efficiency of information inquiry is improved; and the local knowledge base does not contain target answer information corresponding to the target question information, and then the server is called to further inquire, so that the problems such as information inquiry failure and the like are avoided.
An electronic device provided in the present application will be described with reference to fig. 7.
Referring to fig. 7, fig. 7 shows a block diagram of an electronic device 500 according to an embodiment of the present application, where the method according to the embodiment of the present application may be performed by the electronic device 500. The electronic device may be an electronic terminal with data processing function, including but not limited to a smart phone, tablet computer, notebook computer, desktop computer, smart watch, electronic book reader, MP3 (Moving Picture Experts Group Audio Layer III, dynamic image expert compression standard audio layer 3) player, MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image expert compression standard audio layer 4) player, smart home device, etc.
The electronic device 500 in embodiments of the present application may include one or more of the following components: a processor 501, a memory 502, and one or more application programs, wherein the one or more application programs may be stored in the memory 502 and configured to be executed by the one or more processors 501, the one or more program(s) configured to perform the method as described in the foregoing method embodiments.
The processor 501 may include one or more processing cores. The processor 501 utilizes various interfaces and lines to connect various portions of the overall electronic device 500, perform various functions of the electronic device 500, and process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 502, and invoking data stored in the memory 502. Alternatively, the processor 501 may be implemented in hardware in at least one of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 501 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for being responsible for rendering and drawing of display content; the modem is used to handle wireless communications. It will be appreciated that the modem may also be integrated into the processor 501 and implemented solely by a communication chip.
The Memory 502 may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (Read-Only Memory). Memory 502 may be used to store instructions, programs, code sets, or instruction sets. The memory 502 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (e.g., a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described below, etc. The storage data area may also store data created by the electronic device 500 in use (such as the various correspondences described above), and so forth.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus and modules described above may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.
In the several embodiments provided herein, the illustrated or discussed coupling or direct coupling or communication connection of the modules to each other may be through some interfaces, indirect coupling or communication connection of devices or modules, electrical, mechanical, or other forms.
In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module. The integrated modules may be implemented in hardware or in software functional modules.
Referring to fig. 8, a block diagram of a computer readable storage medium according to an embodiment of the present application is shown. The computer readable medium 600 has stored therein program code which can be invoked by a processor to perform the methods described in the method embodiments described above.
The computer readable storage medium 600 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer readable storage medium 600 comprises a non-transitory computer readable medium (non-transitory computer-readable storage medium). The computer readable storage medium 600 has storage space for program code 610 that performs any of the method steps described above. The program code can be read from or written to one or more computer program products. Program code 610 may be compressed, for example, in a suitable form.
In some embodiments, a computer program product or computer program is provided that includes computer instructions stored in a computer readable storage medium. The processor of the electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions to cause the electronic device to perform the steps of the method embodiments described above.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the foregoing embodiments, one of ordinary skill in the art will appreciate that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not drive the essence of the corresponding technical solutions to depart from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims (10)

1. An information query method, applied to an electronic device, comprising:
receiving input target problem information;
inquiring target answer information corresponding to the target question information from a local knowledge base of the electronic equipment, wherein the local knowledge base comprises a plurality of set question-answer pairs, and each set question-answer pair comprises set question information and set answer information corresponding to the set question information;
If the target answer information is queried, outputting the target answer information;
and if the target answer information is not queried, sending an answer query request to a server, wherein the answer query request is used for requesting to query the target answer information corresponding to the target question information.
2. The method of claim 1, wherein prior to querying the target answer information corresponding to the target question information from the local knowledge base of the electronic device, the method further comprises:
acquiring setting text information;
generating a set question-answer pair corresponding to the set text information based on the text content in the set text information;
and adding the set question-answer pairs to the local knowledge base.
3. The method of claim 2, wherein generating the set question-answer pair corresponding to the set text information based on the text content in the set text information, comprises:
acquiring the text length of the set text information;
dividing the set text information according to a target division rule to obtain a plurality of sub-text information if the text length is greater than a first length threshold, wherein the text length of each sub-text information is smaller than or equal to the first length threshold;
Generating a set question-answer pair corresponding to each piece of sub-text information according to the text content in each piece of sub-text information;
and if the text length of the set text information is smaller than or equal to the first length threshold value, generating a set question-answer pair corresponding to the set text information according to the text content in the set text information.
4. The method of claim 2, wherein the obtaining the set text information comprises at least one of the following ways of obtaining:
generating the setting text information based on the input target information of the question-answer pair to be generated;
and acquiring historical question-answer record information as the setting text information.
5. The method according to any one of claims 1-4, wherein the local knowledge base includes a plurality of set topic categories and a plurality of set question-answer pairs under each set topic category, and the querying, from the local knowledge base of the electronic device, target answer information corresponding to the target question information includes:
acquiring a target theme class corresponding to the target problem information;
if the set topic category matched with the target topic category corresponding to the target question information does not exist, determining that the target answer information is not queried;
If a first topic category matched with a target topic category corresponding to the target problem information exists, acquiring a plurality of set question-answer pairs under the first topic category as a plurality of first question-answer pairs, wherein the first topic category is any one of the set topic categories;
if the set question information in the second question-answer pair is matched with the target question information, acquiring the set answer information in the second question-answer pair as target answer information corresponding to the target question information, wherein the second question-answer pair is any one of the first question-answer pairs;
and if the set question information in the second question-answer pair does not exist and is matched with the target question information, determining that the target answer information is not queried.
6. The method of claim 5, wherein the number of second question-answer pairs is a plurality, each of the second question-answer pairs carrying a corresponding historical query frequency value;
the obtaining the set answer information in the second question-answer pair as the target answer information corresponding to the target question information includes:
acquiring set answer information in a third question-answer pair, wherein the third question-answer pair is a plurality of second question-answer pairs with the largest historical query frequency values carried in the second question-answer pair, and the set answer information is used as target answer information corresponding to the target question information;
After the set answer information in the third question-answer pair is obtained and is used as the target answer information corresponding to the target question information, the method comprises the following steps:
and increasing the historical query frequency value carried by the third question-answer pair.
7. The method of claim 6, wherein the number of the third question-answer pairs is plural, and the obtaining the set answer information in the third question-answer pair as the target answer information corresponding to the target question information includes:
acquiring the last outputted historical time of answer information set in each third question-answer pair;
obtaining a third question-answer pair with the latest output history time closest to the current time from a plurality of third question-answer pairs, and taking the third question-answer pair as a fourth question-answer pair;
and acquiring set answer information in the fourth question-answer pair as target answer information corresponding to the target question information.
8. An information query apparatus, applied to an electronic device, comprising:
the problem receiving module is used for receiving input target problem information;
the first query module is used for querying target answer information corresponding to the target question information from a local knowledge base of the electronic equipment, wherein the local knowledge base comprises a plurality of set question-answer pairs, and each set question-answer pair comprises set question information and set answer information corresponding to the set question information;
The information output module is used for outputting the target answer information if the target answer information is inquired;
and the second query module is used for sending an answer query request to the server if the target answer information is not queried, wherein the answer query request is used for querying the target answer information corresponding to the target question information.
9. An electronic device, comprising:
one or more processors;
a memory;
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the method of any of claims 1-7.
10. A computer readable storage medium having stored therein program code which is callable by a processor to perform the method according to any one of claims 1 to 7.
CN202311333579.9A 2023-10-13 2023-10-13 Information query method, device, electronic equipment and storage medium Pending CN117349417A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311333579.9A CN117349417A (en) 2023-10-13 2023-10-13 Information query method, device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311333579.9A CN117349417A (en) 2023-10-13 2023-10-13 Information query method, device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN117349417A true CN117349417A (en) 2024-01-05

Family

ID=89355384

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311333579.9A Pending CN117349417A (en) 2023-10-13 2023-10-13 Information query method, device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117349417A (en)

Similar Documents

Publication Publication Date Title
US11386271B2 (en) Mathematical processing method, apparatus and device for text problem, and storage medium
CN111930940B (en) Text emotion classification method and device, electronic equipment and storage medium
WO2018157703A1 (en) Natural language semantic extraction method and device, and computer storage medium
CN111367490B (en) Voice playing method and device and electronic equipment
CN111046133A (en) Question-answering method, question-answering equipment, storage medium and device based on atlas knowledge base
US10803850B2 (en) Voice generation with predetermined emotion type
CN109461437B (en) Verification content generation method and related device for lip language identification
CN111737414B (en) Song recommendation method and device, server and storage medium
CN110795913A (en) Text encoding method and device, storage medium and terminal
CN111930792A (en) Data resource labeling method and device, storage medium and electronic equipment
CN114757176A (en) Method for obtaining target intention recognition model and intention recognition method
CN112307166B (en) Intelligent question-answering method and device, storage medium and computer equipment
CN112632244A (en) Man-machine conversation optimization method and device, computer equipment and storage medium
CN111639162A (en) Information interaction method and device, electronic equipment and storage medium
CN112686051A (en) Semantic recognition model training method, recognition method, electronic device, and storage medium
CN111625636B (en) Method, device, equipment and medium for rejecting man-machine conversation
CN113704623A (en) Data recommendation method, device, equipment and storage medium
CN115640398A (en) Comment generation model training method, comment generation device and storage medium
CN115186080A (en) Intelligent question-answering data processing method, system, computer equipment and medium
CN117610539A (en) Intention execution method, device, electronic equipment and storage medium
CN117556099A (en) File question and answer method and device and electronic equipment
US20230308731A1 (en) Method for providing service of producing multimedia conversion content by using image resource matching, and apparatus thereof
CN110781327B (en) Image searching method and device, terminal equipment and storage medium
CN116701636A (en) Data classification method, device, equipment and storage medium
CN112328871B (en) Reply generation method, device, equipment and storage medium based on RPA module

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination