CN118132731A - Dialogue method and device, storage medium, terminal and computer program product - Google Patents
Dialogue method and device, storage medium, terminal and computer program product Download PDFInfo
- Publication number
- CN118132731A CN118132731A CN202410551225.XA CN202410551225A CN118132731A CN 118132731 A CN118132731 A CN 118132731A CN 202410551225 A CN202410551225 A CN 202410551225A CN 118132731 A CN118132731 A CN 118132731A
- Authority
- CN
- China
- Prior art keywords
- text
- knowledge base
- matched
- text block
- input sentence
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000004590 computer program Methods 0.000 title claims abstract description 20
- 238000004364 calculation method Methods 0.000 claims abstract description 41
- 238000012216 screening Methods 0.000 claims description 28
- 238000000605 extraction Methods 0.000 claims description 23
- 238000004458 analytical method Methods 0.000 claims description 15
- 230000009286 beneficial effect Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 230000001360 synchronised effect Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 239000002355 dual-layer Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A dialogue method and device, a storage medium, a terminal, a computer program product, the method comprising: receiving an input sentence of a user; searching a first knowledge base for historical answers matched with the input sentences, wherein the first knowledge base comprises historical answers of a plurality of historical input sentences; if the matched historical answers are not found in the first knowledge base, searching a target text block matched with the input sentence in a second knowledge base, wherein the second knowledge base comprises a plurality of candidate text blocks; if a target text block matched with the input sentence is found in the second knowledge base, generating a final answer of the input sentence according to the target text block. According to the scheme, on the basis of ensuring the accuracy of answers, the operation cost is greatly reduced, and particularly, the dialogue time and the calculation cost can be remarkably saved for a scene of a large number of high-frequency similar input sentences.
Description
Technical Field
The present invention relates to the field of intelligent dialogue technology, and in particular, to a dialogue method and apparatus, a storage medium, a terminal, and a computer program product.
Background
In the technical field of intelligent dialogue, when an intelligent assistant (or a question-answering robot) is actually used on line for a user, after receiving input sentences of the user each time, the actual calculation cost and the time cost are generated when the knowledge base information is searched. On the basis of ensuring the accuracy of the dialogue, the cost is reduced to the greatest extent, and the dialogue efficiency is improved, which is a problem worthy of research in the field.
In the prior art, for each sentence or question input by a user, a knowledge base is generally searched directly, for example, by performing similarity calculation on a text vector of the input sentence and a text vector in the knowledge base, determining a text (i.e., a most similar text) with the highest semantic similarity with the input sentence in the knowledge base, and generating and outputting an answer to the user based on the most similar text. On one hand, because the amount of information contained in the knowledge base to be retrieved is often huge, the method for directly acquiring effective information from huge data needs to consume a lot of resources; on the other hand, when a large number of high-frequency query scenes are faced, particularly, when a large number of similar questions are input, the similar input questions consume a large amount of resources and time repeatedly, so that the cost of intelligent dialogue is greatly increased and the dialogue efficiency is reduced.
Disclosure of Invention
The technical problem solved by the embodiment of the invention is how to efficiently and accurately obtain the answer matched with the sentence input by the user, thereby reducing the operation cost and improving the dialogue efficiency.
In order to solve the above technical problems, an embodiment of the present invention provides a dialogue method, including the following steps: receiving an input sentence of a user; searching a first knowledge base for historical answers matched with the input sentences, wherein the first knowledge base comprises historical answers of a plurality of historical input sentences; if the matched historical answers are not found in the first knowledge base, searching a target text block matched with the input sentence in a second knowledge base, wherein the second knowledge base comprises a plurality of candidate text blocks; if a target text block matched with the input sentence is found in the second knowledge base, generating a final answer of the input sentence according to the target text block.
Optionally, the second knowledge base further includes a text vector of each candidate text block, and each candidate text block in the second knowledge base has a sequence; the generating a final answer to the input sentence according to the target text block includes: for each target text block, performing similarity calculation on the text vector of the target text block and the text vector of one or more candidate text blocks in the sequence in front to determine the above semantic association text block, and/or performing similarity calculation on the text vector of one or more candidate text blocks in the sequence in rear to determine the following semantic association text block; and generating the final answer according to the target text block, the upper Wen Yuyi associated text block and/or the lower semantic associated text block.
Optionally, the calculating the similarity between the text vector of the target text block and the text vector of the one or more candidate text blocks in the preceding order to determine the above semantically associated text block includes: taking the target text block as a text block to be matched, performing similarity calculation on the text vector of the current text block to be matched and the text vector of a candidate text block adjacent to the current text block to be matched, taking the candidate text block adjacent to the current text block to be matched as the current text block to be matched when the calculated similarity is larger than or equal to a first threshold value, and continuously performing similarity calculation on the text vector of the current text block to be matched and the text vector of the candidate text block adjacent to the previous text block until the total calculation times reach the preset times; and taking each candidate text block which is participated in calculation and has the similarity larger than or equal to the first threshold value as the upper Wen Yuyi associated text block.
Optionally, each candidate text block of the second knowledge base has a respective text unit, and each text unit includes a plurality of candidate text blocks; before each candidate text block that has participated in the calculation and has a similarity greater than or equal to the first threshold is taken as the upper Wen Yuyi associated text block, the method further includes: judging whether the number of candidate text blocks which are calculated and have participated in calculation and have the similarity larger than or equal to the first threshold value in the text units to which the text blocks to be matched belong is larger than or equal to the preset number or not when the calculated similarity is smaller than the first threshold value; if the result is yes, continuing to sequentially perform similarity calculation on the text vector of the current text block to be matched and the text vector of the candidate text block in the previous adjacent text unit until the total calculated times reach the preset times or until the similarity calculated at present is smaller than the first threshold value and the number of the text blocks which are participated in calculation and have the similarity larger than or equal to the first threshold value in the text unit to which the current text block to be matched belongs is smaller than the preset number.
Optionally, the first knowledge base further includes one or more keywords in each historical answer, and an attribute of each keyword; the searching the historical answers matched with the input sentences in the first knowledge base comprises the following steps: extracting one or more target keywords from the input sentence, and determining the attribute of each target keyword; matching each target keyword and attribute thereof of the input sentence with each keyword and attribute thereof of each historical answer in the first knowledge base; if the first knowledge base has at least one historical answer keyword and attribute thereof, including all target keywords of the input sentence and attribute thereof, using the at least one historical answer as a preliminary screening historical answer; and determining a historical answer matched with the input sentence from the preliminary screening historical answers.
Optionally, the first knowledge base further includes a text vector for each historical answer; determining from the preliminary screening of historical answers a historical answer that matches the input sentence, comprising: calculating the similarity between the text vector of the input sentence and the text vector of each preliminary screening historical answer; a historical answer matching the input sentence is determined from one or more preliminary screening historical answers with top similarity ranks.
Optionally, extracting one or more target keywords from the input sentence, and determining the attribute of each target keyword includes: performing intent analysis on the input sentence to determine an intent category to which the input sentence belongs, wherein each intent category is provided with a corresponding keyword set to be matched, and the keyword set to be matched comprises at least one candidate keyword and attributes thereof; and carrying out text matching on the input sentence and a keyword set to be matched corresponding to the intention category so as to determine one or more candidate keywords matched with the input sentence and attributes thereof from the keyword set to be matched as the target keywords and the attributes thereof.
Optionally, the second knowledge base further includes one or more keywords extracted from each candidate text block, and an attribute of each keyword; the searching the target text block matched with the input sentence in the second knowledge base comprises the following steps: extracting one or more target keywords from the input sentence, and determining the attribute of each target keyword; matching each target keyword and attribute thereof of the input sentence with each keyword and attribute thereof of each candidate text block in the second knowledge base; if all keywords and attributes of at least one candidate text block exist in the second knowledge base and are completely matched with all target keywords and attributes of the input sentence, the at least one candidate text block is used as a preliminary screening text block; and determining a target text block matched with the input sentence from the preliminary screening text blocks.
Optionally, before searching the second knowledge base for the target text block matched with the input sentence, the method further includes: acquiring a to-be-processed document set, wherein the to-be-processed document set comprises at least one document; identifying the document type of the document set to be processed to determine the document type of each document; for each document, adopting a resource analysis strategy corresponding to the document type to which the document belongs, and carrying out resource type identification on the document to obtain a plurality of resource blocks, wherein each resource block has a resource type to which each resource block belongs; for each resource block, adopting a text extraction strategy corresponding to the resource type of the resource block to extract the text of the resource block; determining a plurality of candidate text blocks based on text extraction results of the resource blocks, and constructing and obtaining the second knowledge base; the document types and the resource analysis strategies have one-to-one correspondence, and the resource types and the text extraction strategies have one-to-one correspondence.
The embodiment of the invention also provides a dialogue device, which comprises: the input sentence receiving module is used for receiving input sentences of a user; the first searching module is used for searching historical answers matched with the input sentences in a first knowledge base, wherein the first knowledge base comprises historical answers of a plurality of historical input sentences; the second searching module is used for searching a target text block matched with the input sentence in a second knowledge base if the matched historical answers are not searched in the first knowledge base, and the second knowledge base comprises a plurality of candidate text blocks; and the answer generation module is used for generating a final answer of the input sentence according to the target text block if the target text block matched with the input sentence is found in the second knowledge base.
The embodiment of the invention also provides a storage medium, on which a computer program is stored, which, when being executed by a processor, performs the steps of the above-mentioned dialog method.
The embodiment of the invention also provides a terminal, which comprises a memory and a processor, wherein the memory stores a computer program capable of running on the processor, and the processor executes the steps of the dialogue method when running the computer program.
The embodiment of the invention also provides a computer program product, comprising a computer program which, when being executed by a processor, performs the steps of the above-mentioned dialog method.
Compared with the prior art, the technical scheme of the embodiment of the invention has the following beneficial effects:
In practical application, since the amount of information contained in the knowledge base to be searched is often very huge, and when a large number of high-frequency query scenes are faced, especially when a large number of similar questions are input, if information similar to the input sentences (i.e. "single knowledge base+single search strategy") is directly searched from the knowledge base with huge data amount, a large amount of resources are required to be consumed, and a large number of similar input questions consume unnecessary resources and time repeatedly, so that the cost of intelligent dialogue is greatly improved and the dialogue efficiency is reduced.
In contrast, in the embodiment of the present invention, a "dual knowledge base+dual search strategy" is adopted, specifically, the historical answers of the historical input sentences are stored in the first knowledge base, for the sentences newly input by the user, whether there are matching answers is searched from the first knowledge base with obviously smaller data size, if no matching answer is found, the process continues to the second knowledge base with more abundant search information. Therefore, on the basis of ensuring the accuracy of answers, the method can greatly reduce operation cost, especially for scenes of a large number of high-frequency similar input sentences, remarkably save conversation time and calculation cost, improve conversation efficiency and optimize user experience.
Further, in practical applications, knowledge blocks or text blocks adjacent to each other in a document (for example, adjacent sentences or paragraphs in a PDF document, or adjacent page contents in a PPT document) generally have a correlation between upper and lower Wen Yuyi, while text blocks constructing the second knowledge base are obtained by splitting original information of the document, and each text block obtained by splitting is often fragmented, so that context semantic association information in an original document is lost. In this case, if the answer is generated based only on the target text blocks that are matched in the second knowledge base, the answer to the user input sentence will not be sufficiently comprehensive and accurate. To solve the foregoing problem, after matching a target text block in the second knowledge base, the embodiment of the present invention further performs vector similarity analysis on a plurality of candidate text blocks before and/or after the target text block, and uses the text blocks semantically related to the target text block and the text blocks semantically related to the context and/or the context to generate a final answer of the input sentence. Therefore, the method and the device are beneficial to improving the completeness and accuracy of the answer and improving the user experience.
Drawings
FIG. 1 is a flow chart of a dialog method in an embodiment of the present invention;
FIG. 2 is a flow chart of one embodiment of step S13 of FIG. 1;
FIG. 3 is a flow chart of one embodiment of step S14 of FIG. 1;
Fig. 4 is a schematic structural diagram of a dialogue device according to an embodiment of the invention.
Detailed Description
In order to make the above objects, features and advantages of the present invention more comprehensible, embodiments accompanied with figures are described in detail below.
Referring to fig. 1, fig. 1 is a flowchart of a dialogue method in an embodiment of the present invention. The method can be applied to a terminal device with a dialogue function (hereinafter referred to as dialogue terminal or dialogue robot), and can be selected from, but not limited to, a computer, a mobile phone, a tablet computer, a smart wearable device (such as a smart watch), a vehicle-mounted terminal device, a question-answering robot and the like.
The method may include the following steps S11 to S14:
step S11: receiving an input sentence of a user;
step S12: searching a first knowledge base for historical answers matched with the input sentences, wherein the first knowledge base comprises historical answers of a plurality of historical input sentences;
step S13: if the matched historical answers are not found in the first knowledge base, searching a target text block matched with the input sentence in a second knowledge base, wherein the second knowledge base comprises a plurality of candidate text blocks;
Step S14: if a target text block matched with the input sentence is found in the second knowledge base, generating a final answer of the input sentence according to the target text block.
In the implementation of step S11, the input sentence may be a sentence in a voice form or a sentence in a text form. The input sentence may be a question sentence, a statement sentence, an anti-question sentence, an exclamation sentence, or the like.
In a specific implementation of step S12, the historical answers in the first knowledge base may be selected from the historical answers generated according to the plurality of historical input sentences and the second knowledge base, that is, after the final answer of the input sentence is generated by performing step S14, the final answer may be taken as a historical answer and stored in the first knowledge base.
Further, if the matched historical answer is found in the first knowledge base, the found historical answer can be directly used as the final answer of the input sentence.
In a specific implementation of step S13, the second knowledge base may be constructed by using a plurality of candidate text blocks obtained by splitting in advance, where the plurality of candidate text blocks may be obtained by splitting knowledge based on one or more documents to be processed. In one embodiment, the second knowledge base may be constructed in the following manner: acquiring a to-be-processed document set, wherein the to-be-processed document set comprises at least one document; identifying the document type of the document set to be processed to determine the document type of each document; for each document, adopting a resource analysis strategy corresponding to the document type to which the document belongs, and carrying out resource type identification on the document to obtain a plurality of resource blocks, wherein each resource block has a resource type to which each resource block belongs; for each resource block, adopting a text extraction strategy corresponding to the resource type of the resource block to extract the text of the resource block; determining a plurality of candidate text blocks based on text extraction results of the resource blocks, and constructing and obtaining the second knowledge base; the document types and the resource analysis strategies have one-to-one correspondence, and the resource types and the text extraction strategies have one-to-one correspondence.
Wherein the document type may be used to indicate different formats of the document, which may also be referred to as document format types. There are often a wide variety of document formats in practical applications, including but not limited to PDF, WORD, EXCEL, PPT, HTML, markdown, plain text, and so on. In addition, even within the same document, different resource types may be included, for example, in the same PDF document, resource types such as, but not limited to, pictures, forms, endorsement text, body text, directories, hyperlinks, etc. may be included.
Wherein determining a plurality of candidate text blocks based on the text extraction results for each resource block may include: and performing operations such as text splitting and merging on text extraction results of each resource block to obtain the plurality of candidate text blocks. For example, text splitting and merging can be performed according to a preset number of characters and/or punctuation marks; as another example, text extraction results of one or more resource blocks belonging to the same page (e.g., the same page of PPT) may be combined into a single candidate text block in units of pages of the original document.
In the prior art, for a to-be-processed document set containing a plurality of documents, manually classifying the formats of the documents in the document set is generally relied on to determine the document type of each document; then, for a document of a certain type, text extraction tools corresponding to the document type are adopted, and text extraction is directly carried out with the whole document as granularity (namely, a strategy of single extraction by adopting the same extraction tool). The method has high labor cost, and the whole document is subjected to one-time text extraction by adopting the same tool, so that specific types of resource information can be omitted, and the text extraction has insufficient integrity and accuracy.
In contrast, in the embodiment of the present invention, a "dual-layer parsing policy" is designed, a one-to-one correspondence is established between a document type and a resource parsing policy, and between a document type and a text extraction policy, and knowledge extraction is performed with different resource information in the document as granularity, specifically: for documents in different formats, adaptively adopting respective corresponding resource analysis strategies to identify resource types so as to obtain a plurality of resource blocks; and for resource blocks belonging to different resource types in the same document, adaptively adopting a corresponding text extraction strategy to extract text contents. Therefore, the user can upload all the documents at one time without separate uploading processing according to types; the coverage degree and accuracy of information extraction can be improved, the problem that valuable information cannot be put into a knowledge base due to improper extraction is avoided, and the accuracy and effectiveness of information recall in the subsequent dialogue application process are improved. Further, the embodiment can flexibly support the lateral expansion of the document type and the resource type.
Referring to fig. 2, fig. 2 is a flowchart of one embodiment of step S13 in fig. 1; in this embodiment, the second knowledge base further includes one or more keywords extracted from each candidate text block, and an attribute of each keyword; in the step S13, searching the second knowledge base for the target text block matched with the input sentence may include the following steps S131 to S134.
In step S131, one or more target keywords are extracted from the input sentence, and an attribute of each target keyword is determined.
Wherein the attribute of the keyword is used to describe the semantics or properties (or meaning) of the keyword in the belonging sentence or text block. Each keyword and its combination of attributes can be analogically a "key value pair", where the attribute of the keyword can be a "key" and the keyword can be a "value".
It will be appreciated that in natural language, the same keyword may have different properties in different input sentences or text blocks, and the expressed semantics will also tend to be different. The attributes of a keyword may be related to the intent expressed by the user's input sentence or text block, in particular, if multiple input sentences or multiple text blocks express different intentions, the semantics or attributes of the keyword in each input sentence will typically be different even if the multiple input sentences contain the same keyword.
As one non-limiting example, some input sentence a that interrogates marketing-related data: "what is the sales sum of the first brand of shoes 9 months of 2023? ", a certain input sentence B asking for personal information: "is the birth date of the young 2023, 9? "both input sentences a and B contain the same target keyword" 2023 year 9 month ", but the keyword has an attribute of" sales month "or" sales time "in the input sentence a, and an attribute of" birth year month "or" birth time "in the input sentence B.
In a specific implementation, extracting one or more target keywords from the input sentence, and determining the attribute of each target keyword includes: performing intent analysis on the input sentence to determine an intent category to which the input sentence belongs, wherein each intent category is provided with a corresponding keyword set to be matched, and the keyword set to be matched comprises at least one candidate keyword and attributes thereof; and carrying out text matching on the input sentence and a keyword set to be matched corresponding to the intention category so as to determine one or more candidate keywords matched with the input sentence and attributes thereof from the keyword set to be matched as the target keywords and the attributes thereof.
Wherein the intent analysis may be implemented by existing intent recognition or intent classification algorithms. As a non-limiting example, common intent categories for the intelligent dialog field may be selected from, but are not limited to: query ticket information, query weather conditions, query news events, query merchandise information, query marketing related data, and the like. The keyword set to be matched corresponding to each intention category can be obtained by extracting and combining keywords of a large number of sample input sentences belonging to the intention category.
In step S132, each target keyword and its attribute of the input sentence are matched with each keyword and its attribute of each candidate text block in the second knowledge base.
In step S133, if the second knowledge base has keywords and attributes of at least one candidate text block, including all target keywords and attributes of the input sentence, the at least one candidate text block is used as a preliminary screening text block.
In step S134, a target text block matching the input sentence is determined from the preliminary screening text blocks.
Further, the step S134 may include: calculating the similarity between the text vector of the input sentence and the text vector of each preliminary screening text block; a target text block that matches the input sentence is determined from one or more top-ranked preliminary text blocks of similarity.
As described above, the same keywords often have different attributes or meanings in sentences or text blocks expressing different intentions, and therefore, in the embodiment of the present invention, the combination of "keywords+attributes" is used to match the input sentences with candidate text blocks in the second knowledge base, and compared with the prior art that text blocks are matched in the knowledge base only by "keywords", the present embodiment is beneficial to improving the matching accuracy, and reduces the number of the preliminary screening text blocks obtained after preliminary screening to a greater extent, thereby improving the efficiency of subsequently screening out target text blocks from the preliminary screening text blocks. Furthermore, on the basis of primary screening of candidate text blocks of the second knowledge base through the combination of the keywords and the attributes, a vector similarity matching method is adopted for the primary screened text blocks with obviously reduced quantity, and compared with a keyword matching or text matching method, the method is beneficial to improving matching to obtain target text blocks with the most similar semantics to input sentences.
With continued reference to fig. 1, in step S14, if a target text block matching the input sentence is found in the second knowledge base, a final answer to the input sentence is generated from the target text block.
In one embodiment, the target text block may be employed directly as the final answer to the input sentence; or after the target text block is subjected to format conversion and other processing, the final answer of the input sentence is obtained.
It is appreciated that knowledge blocks or text blocks that are adjacent in position in a document (e.g., adjacent sentences or paragraphs) typically have a top-bottom Wen Yuyi relevance. For example, a knowledge base is built for documents in PPT format, since each page of content in a PPT generally corresponds to a single topic, each page of content in the PPT (including text, tables, charts, etc. in that page of content) can be treated as a single candidate text block in the knowledge base. However, a PPT is semantically strongly related to its preceding/following page (or pages), such as a background introduction where the preceding page is the current page, a detailed description where the next page is the current page, etc. However, the text blocks for constructing the knowledge base are obtained by splitting the original information of the document, and each text block obtained by splitting is often fragmented, so that context semantic association information in the original document can be lost. In this case, if an answer is generated based on only the information of the current page (corresponding to the matched target text block) and recalled to the user, the information is not comprehensive in solving the query problem of the user.
To avoid the above-mentioned problems, another embodiment may also be used to generate a final answer based on the target text block. For example, after matching to a target text block, vector similarity analysis is also performed on one or more candidate text blocks before and/or after the target text block, and upper and lower Wen Yuyi associated text blocks are determined for use with the target text block in generating a final answer to the input sentence. Therefore, the method and the device are beneficial to improving the completeness and accuracy of the answer and improving the user experience.
The details of the other embodiment are described below with reference to fig. 3.
Referring to fig. 3, fig. 3 is a flowchart of one embodiment of step S14 in fig. 1; in this embodiment, the second knowledge base further includes a text vector of each candidate text block, where each candidate text block in the second knowledge base has a sequence; the step S14 may specifically include steps S141 to S142 described below.
In step S141, for each target text block, a similarity calculation is performed on the text vector of the target text block and the text vector of the one or more candidate text blocks in the preceding order to determine the above semantic-related text block, and/or a similarity calculation is performed on the text vector of the one or more candidate text blocks in the following order to determine the following semantic-related text block.
Further, in a specific embodiment, the method for determining the above semantically related text block in the step S141 may include the following sub-steps (1) to (2):
Substep (1): taking the target text block as a text block to be matched, performing similarity calculation on the text vector of the current text block to be matched and the text vector of a candidate text block adjacent to the current text block to be matched, taking the candidate text block adjacent to the current text block to be matched as the current text block to be matched when the calculated similarity is larger than or equal to a first threshold value, and continuously performing similarity calculation on the text vector of the current text block to be matched and the text vector of the candidate text block adjacent to the previous text block until the total calculation times reach the preset times;
Substep (2): and taking each candidate text block which is participated in calculation and has the similarity larger than or equal to the first threshold value as the upper Wen Yuyi associated text block.
Compared with the method that the preset matching quantity is set, semantic similarity analysis is conducted on the target text block and the previous and/or subsequent candidate text blocks to determine the text blocks related to the upper and lower Wen Yuyi, the method of calculating the semantic similarity sequentially one by one is adopted in the embodiment, when the calculated similarity is greater than or equal to a first threshold value, the similar text blocks are used as new text blocks to be matched, and semantic similarity calculation is conducted on the new text blocks to be matched and the previous adjacent candidate text blocks. Therefore, the method is beneficial to reducing the total times of invalid computation and the operation cost; and the semantic similarity calculation is carried out sequentially forward, so that the semantic continuity (or continuity) rule of the context is more accordant, and the accuracy of the obtained text blocks related to the context Wen Yuyi can be improved.
Further, each candidate text block of the second knowledge base has a respective associated text unit, each text unit comprising a plurality of candidate text blocks; before performing the above sub-step (2), the method further comprises: judging whether the number of candidate text blocks which are calculated and have participated in calculation and have the similarity larger than or equal to the first threshold value in the text units to which the text blocks to be matched belong is larger than or equal to the preset number or not when the calculated similarity is smaller than the first threshold value; if the judgment result is yes, continuing to sequentially calculate the similarity between the text vector of the current text block to be matched and the text vector of the candidate text block in the previous adjacent text unit until the condition one is satisfied: calculating the total times to reach the preset times or meeting the second condition: the similarity calculated at present is smaller than the first threshold value, and the number of text blocks which are participating in calculation and have the similarity larger than or equal to the first threshold value in the text units to which the text blocks to be matched at present belong is smaller than the preset number.
It should be noted that, the above condition two is for whether to continue to enter the previous adjacent text unit for similarity calculation, specifically, when the condition two is satisfied, the text vector of the current text block to be matched is not further for similarity calculation with the candidate text block in the previous adjacent text unit (i.e., the previous adjacent text unit of the text unit to which the current text block to be matched belongs), but the above substep (2) is directly performed to determine the above semantic association text block of the target text block.
The step of sequentially performing similarity calculation on the current text block to be matched and the candidate text block in the previous adjacent text unit may specifically include: and performing similarity calculation on the text vector of the current text block to be matched and the text vector of the candidate text block which is sequentially last in the previous adjacent text unit, taking the candidate text block as the current text block to be matched if the calculated similarity is greater than or equal to the first threshold value, and continuously performing similarity calculation on the text vector of the candidate text block to be matched and the text vector of the previous adjacent candidate text block. The foregoing sequential similarity calculation method may be performed with reference to the content of the foregoing sub-step (1).
It can be understood that, for a text unit containing multiple text blocks, if the semantics of multiple continuous candidate text blocks in the text unit are similar, then there is a greater probability that there is a context content related to the semantics in text units adjacent to the text unit, so when a situation that the semantic similarity between a certain text block T and a previous adjacent text block is not high is encountered, it is further determined whether the text unit T to which the text block T belongs has multiple continuous related text blocks, and if so, the text unit F adjacent to the text unit T is continuously searched for text blocks with similar semantics. Thus, the integrity and accuracy of text block recalls can be further improved.
The method of how to determine the text blocks of the target text block that are semantically associated with the text blocks of the context is performed with reference to the specific method of determining the text blocks of the context described above, and will not be described in detail herein.
In step S142, the final answer is generated based on the target text block, the upper Wen Yuyi associated text block, and/or the lower semantic associated text block.
In specific implementation, the target text block, the upper Wen Yuyi associated text block and/or the lower semantic associated text block can be spliced according to the original sequence in the respective knowledge base, and the splicing result is used as a final answer; or the target text block, the upper Wen Yuyi associated text block and/or the lower semantic associated text block may be subjected to operations such as deduplication, format conversion, templating (e.g., templating using a prompt template (template) tool), and the like, to generate a final answer.
Further, in the step S12, the first knowledge base may further include one or more keywords in each of the historical answers, and an attribute of each keyword; the step S12 may specifically include: extracting one or more target keywords from the input sentence, and determining the attribute of each target keyword; matching each target keyword and attribute thereof of the input sentence with each keyword and attribute thereof of each historical answer in the first knowledge base; if the first knowledge base has at least one historical answer keyword and attribute thereof, including all target keywords of the input sentence and attribute thereof, using the at least one historical answer as a preliminary screening historical answer; and determining a historical answer matched with the input sentence from the preliminary screening historical answers.
The keywords and the attributes of each historical answer in the first knowledge base can be the keywords and the attributes of each candidate text block used for generating the historical answer in the second knowledge base.
Still further, the first knowledge base further includes a text vector for each historical answer; determining from the preliminary screening of historical answers a historical answer that matches the input sentence, comprising: calculating the similarity between the text vector of the input sentence and the text vector of each preliminary screening historical answer; a historical answer matching the input sentence is determined from one or more preliminary screening historical answers with top similarity ranks.
In a specific implementation, extracting one or more target keywords from the input sentence, and determining the attribute of each target keyword includes: performing intent analysis on the input sentence to determine an intent category to which the input sentence belongs, wherein each intent category is provided with a corresponding keyword set to be matched, and the keyword set to be matched comprises at least one candidate keyword and attributes thereof; and carrying out text matching on the input sentence and a keyword set to be matched corresponding to the intention category so as to determine one or more candidate keywords matched with the input sentence and attributes thereof from the keyword set to be matched as the target keywords and the attributes thereof.
The above method for performing preliminary screening on the first knowledge base by adopting the combination of the keywords and the attributes, the method for performing vector similarity calculation based on the preliminary screened historical answers to determine the historical answers matched with the input sentence, and related principles and technical effects can refer to the related descriptions of the foregoing steps and the steps shown in fig. 2, and are not repeated herein.
It can be understood that, because the amount of information contained in the second knowledge base is usually quite large, if the second knowledge base is directly searched, the problem of larger computing resources and time overhead may be faced, and in the intersecting manner, in the embodiment of the present invention, the historical answers of the historical input sentences are stored in the first knowledge base, and subsequently, for the sentences newly input by the user, whether the matched answers exist or not can be directly searched from the first knowledge base with obviously smaller data amount, and if yes, the matching answers are directly returned to the user; if not, continuing to search a second knowledge base with more abundant information. Therefore, on the basis of ensuring the accuracy of the answer, the operation cost can be reduced as much as possible, and the conversation efficiency can be improved.
Further, if it is confirmed that the matching target text block is not found yet in the second knowledge base, the process may be shifted to manual processing, or an answer template corresponding to the type of intention to which the input sentence belongs may be adopted as a final answer.
Further, the historical answers in the first knowledge base are selected from the historical answers generated from the plurality of historical input sentences and the second knowledge base; the dialogue method further comprises the following steps: receiving an information updating instruction, wherein the information updating instruction is used for indicating candidate text blocks in the second knowledge base to be updated; and taking the historical answers generated by the corresponding generation of the updated candidate text blocks as failure historical answers, and deleting the failure historical answers in the first knowledge base. Therefore, the corresponding answers in the first knowledge base can be adaptively updated according to the update of the second knowledge base, and timeliness of information of the two knowledge bases to be searched is guaranteed.
Further, the method further comprises: judging whether each history answer in the first knowledge base is out of date according to the preset effective duration, and deleting the out-of-date history answer.
Further, before step S13 is performed (i.e., before the target text block matching the input sentence is searched in the second knowledge base), risk verification may also be performed on the input sentence of the user (especially for a conversation robot set in a public place), for example, whether the input sentence contains a sensitive word in a preset sensitive word set may be judged, if the input sentence contains a sensitive word, a question-answer procedure may be ended, or a preset template answer may be output to the user. In this way, the security of the intelligent conversation may be improved.
Fig. 4 is a schematic structural diagram of a dialogue device according to an embodiment of the present invention, where the dialogue device may include the following modules:
An input sentence receiving module 41 for receiving an input sentence of a user;
A first searching module 42, configured to search a first knowledge base for historical answers matched with the input sentence, where the first knowledge base includes historical answers of a plurality of historical input sentences;
a second searching module 43, configured to search a second knowledge base for a target text block matched with the input sentence if the matched historical answer is not found in the first knowledge base, where the second knowledge base includes a plurality of candidate text blocks;
an answer generation module 44, configured to generate a final answer of the input sentence according to the target text block if the target text block matching the input sentence is found in the second knowledge base.
Regarding the principle, implementation and advantageous effects of the dialogue device, please refer to the related description of the dialogue method shown in the foregoing and any embodiment of fig. 1 to 3, which is not repeated herein.
The embodiments of the present invention also provide a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, performs the steps of the dialog method shown in any of the above-described embodiments of fig. 1 to 3. The computer readable storage medium may include non-volatile memory (non-volatile) or non-transitory memory, and may also include optical disks, mechanical hard disks, solid state disks, and the like.
Specifically, in the embodiment of the present invention, the processor may be a central processing unit (central processing unit, abbreviated as CPU), which may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL processors, abbreviated as DSP), application Specific Integrated Circuits (ASIC), off-the-shelf programmable gate arrays (field programmable GATE ARRAY, abbreviated as FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It should also be appreciated that the memory in embodiments of the present application may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an erasable programmable ROM (erasable PROM EPROM), an electrically erasable programmable ROM (ELECTRICALLY EPROM, EEPROM), or a flash memory. The volatile memory may be a random access memory (random access memory, RAM for short) which acts as an external cache. By way of example, and not limitation, many forms of random access memory (random access memory, RAM) are available, such as static random access memory (STATIC RAM, SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (double DATA RATE SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (ENHANCED SDRAM, ESDRAM), synchronous link dynamic random access memory (SYNCHLINK DRAM, SLDRAM), and direct memory bus random access memory (direct rambus RAM, DR RAM).
The embodiment of the invention also provides a terminal, which comprises a memory and a processor, wherein the memory stores a computer program capable of running on the processor, and the processor executes the steps of the dialogue method shown in any embodiment of the figures 1 to 3 when running the computer program.
The embodiments of the present invention also provide a computer program product comprising a computer program which, when run by a processor, performs the steps of the method of dialog shown in any of the embodiments of figures 1 to 3 described above.
It should be understood that the term "and/or" is merely an association relationship describing the associated object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In this context, the character "/" indicates that the front and rear associated objects are an "or" relationship.
The term "plurality" as used in the embodiments of the present application means two or more.
The first, second, etc. descriptions in the embodiments of the present application are only used for illustrating and distinguishing the description objects, and no order is used, nor is the number of the devices in the embodiments of the present application limited, and no limitation on the embodiments of the present application should be construed.
It should be noted that the serial numbers of the steps in the present embodiment do not represent a limitation on the execution sequence of the steps.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be made by one skilled in the art without departing from the spirit and scope of the invention, and the scope of the invention should be assessed accordingly to that of the appended claims.
Claims (13)
1. A method of dialog, the method comprising:
Receiving an input sentence of a user;
Searching a first knowledge base for historical answers matched with the input sentences, wherein the first knowledge base comprises historical answers of a plurality of historical input sentences;
If the matched historical answers are not found in the first knowledge base, searching a target text block matched with the input sentence in a second knowledge base, wherein the second knowledge base comprises a plurality of candidate text blocks;
If a target text block matched with the input sentence is found in the second knowledge base, generating a final answer of the input sentence according to the target text block;
Wherein the historical answers in the first knowledge base are selected from the historical answers generated from the plurality of historical input sentences and the second knowledge base.
2. The method of claim 1, wherein the second knowledge base further comprises a text vector for each candidate text block, the candidate text blocks in the second knowledge base having a precedence order;
the generating a final answer to the input sentence according to the target text block includes:
For each target text block, performing similarity calculation on the text vector of the target text block and the text vector of one or more candidate text blocks in the sequence in front to determine the above semantic association text block, and/or performing similarity calculation on the text vector of one or more candidate text blocks in the sequence in rear to determine the following semantic association text block;
And generating the final answer according to the target text block, the upper Wen Yuyi associated text block and/or the lower semantic associated text block.
3. The method of claim 2, wherein said similarity calculating the text vector of the target text block with the text vector of the one or more candidate text blocks in the preceding order to determine the above semantically-related text block comprises:
Taking the target text block as a text block to be matched, performing similarity calculation on the text vector of the current text block to be matched and the text vector of a candidate text block adjacent to the current text block to be matched, taking the candidate text block adjacent to the current text block to be matched as the current text block to be matched when the calculated similarity is larger than or equal to a first threshold value, and continuously performing similarity calculation on the text vector of the current text block to be matched and the text vector of the candidate text block adjacent to the previous text block until the total calculation times reach the preset times;
And taking each candidate text block which is participated in calculation and has the similarity larger than or equal to the first threshold value as the upper Wen Yuyi associated text block.
4. A method according to claim 3, wherein each candidate text block of the second knowledge base has a respective associated text unit, each text unit comprising a plurality of candidate text blocks;
before each candidate text block that has participated in the calculation and has a similarity greater than or equal to the first threshold is taken as the upper Wen Yuyi associated text block, the method further includes:
Judging whether the number of candidate text blocks which are calculated and have participated in calculation and have the similarity larger than or equal to the first threshold value in the text units to which the text blocks to be matched belong is larger than or equal to the preset number or not when the calculated similarity is smaller than the first threshold value;
If the result is yes, continuing to sequentially perform similarity calculation on the text vector of the current text block to be matched and the text vector of the candidate text block in the previous adjacent text unit until the total calculated times reach the preset times or until the similarity calculated at present is smaller than the first threshold value and the number of the text blocks which are participated in calculation and have the similarity larger than or equal to the first threshold value in the text unit to which the current text block to be matched belongs is smaller than the preset number.
5. The method of claim 1, wherein the first knowledge base further comprises one or more keywords in each historical answer, and attributes of each keyword;
the searching the historical answers matched with the input sentences in the first knowledge base comprises the following steps:
Extracting one or more target keywords from the input sentence, and determining the attribute of each target keyword;
matching each target keyword and attribute thereof of the input sentence with each keyword and attribute thereof of each historical answer in the first knowledge base;
if the first knowledge base has at least one historical answer keyword and attribute thereof, including all target keywords of the input sentence and attribute thereof, using the at least one historical answer as a preliminary screening historical answer;
And determining a historical answer matched with the input sentence from the preliminary screening historical answers.
6. The method of claim 5, wherein the first knowledge base further comprises a text vector for each historical answer;
Determining from the preliminary screening of historical answers a historical answer that matches the input sentence, comprising:
Calculating the similarity between the text vector of the input sentence and the text vector of each preliminary screening historical answer;
A historical answer matching the input sentence is determined from one or more preliminary screening historical answers with top similarity ranks.
7. The method of claim 5 or 6, wherein extracting one or more target keywords from the input sentence and determining the attribute of each target keyword comprises:
Performing intent analysis on the input sentence to determine an intent category to which the input sentence belongs, wherein each intent category is provided with a corresponding keyword set to be matched, and the keyword set to be matched comprises at least one candidate keyword and attributes thereof;
And carrying out text matching on the input sentence and a keyword set to be matched corresponding to the intention category so as to determine one or more candidate keywords matched with the input sentence and attributes thereof from the keyword set to be matched as the target keywords and the attributes thereof.
8. The method of claim 1, wherein the second knowledge base further comprises one or more keywords extracted from each candidate text block, and attributes of each keyword;
The searching the target text block matched with the input sentence in the second knowledge base comprises the following steps:
Extracting one or more target keywords from the input sentence, and determining the attribute of each target keyword;
Matching each target keyword and attribute thereof of the input sentence with each keyword and attribute thereof of each candidate text block in the second knowledge base;
If all keywords and attributes of at least one candidate text block exist in the second knowledge base and are completely matched with all target keywords and attributes of the input sentence, the at least one candidate text block is used as a preliminary screening text block;
and determining a target text block matched with the input sentence from the preliminary screening text blocks.
9. The method of claim 1, wherein prior to looking up the target text block in the second knowledge base that matches the input sentence, the method further comprises:
acquiring a to-be-processed document set, wherein the to-be-processed document set comprises at least one document;
identifying the document type of the document set to be processed to determine the document type of each document;
for each document, adopting a resource analysis strategy corresponding to the document type to which the document belongs, and carrying out resource type identification on the document to obtain a plurality of resource blocks, wherein each resource block has a resource type to which each resource block belongs;
For each resource block, adopting a text extraction strategy corresponding to the resource type of the resource block to extract the text of the resource block;
Determining a plurality of candidate text blocks based on text extraction results of the resource blocks, and constructing and obtaining the second knowledge base;
the document types and the resource analysis strategies have one-to-one correspondence, and the resource types and the text extraction strategies have one-to-one correspondence.
10. A dialog device, comprising:
the input sentence receiving module is used for receiving input sentences of a user;
The first searching module is used for searching historical answers matched with the input sentences in a first knowledge base, wherein the first knowledge base comprises historical answers of a plurality of historical input sentences;
the second searching module is used for searching a target text block matched with the input sentence in a second knowledge base if the matched historical answers are not searched in the first knowledge base, and the second knowledge base comprises a plurality of candidate text blocks;
The answer generation module is used for generating a final answer of the input sentence according to the target text block if the target text block matched with the input sentence is found in the second knowledge base;
Wherein the historical answers in the first knowledge base are selected from the historical answers generated from the plurality of historical input sentences and the second knowledge base.
11. A storage medium having stored thereon a computer program, which, when executed by a processor, performs the steps of the dialog method of any of claims 1 to 9.
12. A terminal comprising a memory and a processor, the memory having stored thereon a computer program executable on the processor, characterized in that the processor executes the steps of the dialog method of any of claims 1 to 9 when the computer program is executed.
13. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, performs the steps of the dialog method as claimed in any of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410551225.XA CN118132731B (en) | 2024-05-06 | 2024-05-06 | Dialogue method and device, storage medium, terminal and computer program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410551225.XA CN118132731B (en) | 2024-05-06 | 2024-05-06 | Dialogue method and device, storage medium, terminal and computer program product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118132731A true CN118132731A (en) | 2024-06-04 |
| CN118132731B CN118132731B (en) | 2024-08-06 |
Family
ID=91232992
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410551225.XA Active CN118132731B (en) | 2024-05-06 | 2024-05-06 | Dialogue method and device, storage medium, terminal and computer program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118132731B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543020A (en) * | 2018-11-27 | 2019-03-29 | 科大讯飞股份有限公司 | Inquiry handles method and system |
| WO2021051521A1 (en) * | 2019-09-18 | 2021-03-25 | 平安科技（深圳）有限公司 | Response information obtaining method and apparatus, computer device, and storage medium |
| WO2021114682A1 (en) * | 2019-12-10 | 2021-06-17 | 平安国际智慧城市科技股份有限公司 | Session task generation method and apparatus, computer device, and storage medium |
| CN114064859A (en) * | 2021-11-29 | 2022-02-18 | 工银科技有限公司 | Knowledge extraction method, apparatus, device, medium, and program product |
| WO2022257578A1 (en) * | 2021-06-07 | 2022-12-15 | 京东科技信息技术有限公司 | Method for recognizing text, and apparatus |
| CN117149967A (en) * | 2023-08-18 | 2023-12-01 | 中国电信股份有限公司技术创新中心 | Response generation method, device, server and computer readable storage medium |
| CN117609476A (en) * | 2024-01-19 | 2024-02-27 | 北京十环信息有限公司 | Public service data analysis system based on artificial intelligence |
| CN117786086A (en) * | 2024-01-08 | 2024-03-29 | 腾讯科技（深圳）有限公司 | Reply text generation method, reply text generation device, computer equipment and readable storage medium |
-
2024
- 2024-05-06 CN CN202410551225.XA patent/CN118132731B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543020A (en) * | 2018-11-27 | 2019-03-29 | 科大讯飞股份有限公司 | Inquiry handles method and system |
| WO2021051521A1 (en) * | 2019-09-18 | 2021-03-25 | 平安科技（深圳）有限公司 | Response information obtaining method and apparatus, computer device, and storage medium |
| WO2021114682A1 (en) * | 2019-12-10 | 2021-06-17 | 平安国际智慧城市科技股份有限公司 | Session task generation method and apparatus, computer device, and storage medium |
| WO2022257578A1 (en) * | 2021-06-07 | 2022-12-15 | 京东科技信息技术有限公司 | Method for recognizing text, and apparatus |
| CN114064859A (en) * | 2021-11-29 | 2022-02-18 | 工银科技有限公司 | Knowledge extraction method, apparatus, device, medium, and program product |
| CN117149967A (en) * | 2023-08-18 | 2023-12-01 | 中国电信股份有限公司技术创新中心 | Response generation method, device, server and computer readable storage medium |
| CN117786086A (en) * | 2024-01-08 | 2024-03-29 | 腾讯科技（深圳）有限公司 | Reply text generation method, reply text generation device, computer equipment and readable storage medium |
| CN117609476A (en) * | 2024-01-19 | 2024-02-27 | 北京十环信息有限公司 | Public service data analysis system based on artificial intelligence |
Non-Patent Citations (2)
| Title |
|---|
| SHERVIN MINAEE: "Automatic Question-Answering Using A Deep Similarity Neural Network", 《IEEE》, 5 August 2017 (2017-08-05) * |
| 何天文;王红;刘海燕;: "基于词语相关性的对话系统话题分割", 计算机应用研究, no. 04, 9 February 2018 (2018-02-09) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118132731B (en) | 2024-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111881307B (en) | Presentation generation method and device, computer equipment and storage medium | |
| CN111859960B (en) | Semantic matching method, device, computer equipment and medium based on knowledge distillation | |
| US11392775B2 (en) | Semantic recognition method, electronic device, and computer-readable storage medium | |
| WO2020077896A1 (en) | Method and apparatus for generating question data, computer device, and storage medium | |
| CN109858010B (en) | Method and device for recognizing new words in field, computer equipment and storage medium | |
| CA3174601C (en) | Text intent identifying method, device, computer equipment and storage medium | |
| CN112215008B (en) | Entity identification method, device, computer equipment and medium based on semantic understanding | |
| WO2018126325A1 (en) | Learning document embeddings with convolutional neural network architectures | |
| WO2020114100A1 (en) | Information processing method and apparatus, and computer storage medium | |
| CN106649612B (en) | Method and device for automatically matching question and answer templates | |
| CN117688163A (en) | Online intelligent question-answering method and device based on instruction fine tuning and retrieval enhancement generation | |
| CN114610845B (en) | Intelligent question-answering method, device and equipment based on multiple systems | |
| CN110851576A (en) | Question and answer processing method, device, equipment and readable medium | |
| CN112632258A (en) | Text data processing method and device, computer equipment and storage medium | |
| CN117453851A (en) | Text index enhanced question-answering method and system based on knowledge graph | |
| US11379527B2 (en) | Sibling search queries | |
| CN114238715A (en) | Question-answering system based on social aid, construction method, computer equipment and medium | |
| CN118132731B (en) | Dialogue method and device, storage medium, terminal and computer program product | |
| CN117076946A (en) | Short text similarity determination method, device and terminal | |
| CN109918661B (en) | Synonym acquisition method and device | |
| CN118093849B (en) | Dialogue method and device, storage medium, terminal and computer program product | |
| CN110851709A (en) | Information pushing method and device, computer equipment and storage medium | |
| CN115081457A (en) | Information processing method and system based on artificial intelligence technology | |
| CN114580398A (en) | Text information extraction model generation method, text information extraction method and device | |
| CN113297353B (en) | Text matching method, device, equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |