WO2020006835A1 - 智能客服多轮问答方法、设备、存储介质及装置 - Google Patents
智能客服多轮问答方法、设备、存储介质及装置 Download PDFInfo
- Publication number
- WO2020006835A1 WO2020006835A1 PCT/CN2018/102053 CN2018102053W WO2020006835A1 WO 2020006835 A1 WO2020006835 A1 WO 2020006835A1 CN 2018102053 W CN2018102053 W CN 2018102053W WO 2020006835 A1 WO2020006835 A1 WO 2020006835A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- intent
- standard
- target
- signal
- named entity
- 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.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
Definitions
- the present application relates to the technical field of intelligent customer service, and in particular, to a method, device, storage medium and device for multiple rounds of question and answer for intelligent customer service.
- the main purpose of this application is to provide a multi-round question and answer method, device, storage medium and device for intelligent customer service, which aims to solve the technical problem of low accuracy in the multi-round question and answer in the prior art.
- the present application provides a multi-round question answering method for intelligent customer service.
- the multi-round question answering method for intelligent customer service includes the following steps: obtaining a target question of the current round of the user; and searching from the knowledge base for a match with the target question.
- Standard intent and obtain the degree of matching between the standard intent and the target problem; determine whether the degree of matching between the standard intent and the target problem exceeds a preset matching threshold; if it does not exceed, then
- the target problem is identified by a named entity to obtain a recognition result; detecting whether there is a signal inherited in at least one round of user problems before the current round, and obtaining a detection result; according to the recognition result, the detection result, and the target problem And the criteria are intended to determine the target response.
- this application also proposes a multi-round question answering device for intelligent customer service.
- the multi-round question answering device for intelligent customer service includes a memory, a processor, and a processor that is stored on the memory and can run on the processor.
- the intelligent customer service multi-round question and answer readable instruction is configured as the steps of the intelligent customer service multi-round question and answer method described above.
- the present application also proposes a storage medium that stores intelligent customer service multiple rounds of question and answer readable instructions stored on the storage medium.
- the intelligent customer service multiple rounds of question and answer readable instructions are implemented by the processor as described above. The steps of the multi-round question answering method for intelligent customer service.
- this application also proposes a multi-round question answering device for intelligent customer service, including: an acquisition module for acquiring a target question of a user's current round; a search module for searching for the target from a knowledge base A standard intent for question matching, and obtaining a degree of matching between the standard intent and the target problem; a judgment module, configured to determine whether the degree of matching between the standard intent and the target problem exceeds a preset matching threshold; An identification module for identifying a named entity for the target problem to obtain an identification result if it is not exceeded, and a detection module for detecting whether there is a signal inherited from at least one user problem before the current round, Obtaining a detection result; a determination module, configured to determine a target response according to the recognition result, the detection result, the target question, and the standard intent.
- FIG. 1 is a schematic structural diagram of a multi-round question answering device for intelligent customer service in a hardware operating environment according to an embodiment of the present application
- FIG. 2 is a schematic flowchart of a first embodiment of a multi-round question answering method for intelligent customer service in this application;
- FIG. 3 is a schematic flowchart of a second embodiment of a multi-round question answering method for intelligent customer service in this application;
- FIG. 4 is a schematic flowchart of a third embodiment of a multi-round question answering method for intelligent customer service in this application;
- FIG. 5 is a structural block diagram of a first embodiment of a multi-round question answering device for intelligent customer service in this application.
- FIG. 1 is a schematic structural diagram of a multi-round question answering device for intelligent customer service in a hardware operating environment according to an embodiment of the present application.
- the intelligent customer service multi-round question answering device may include a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005.
- the communication bus 1002 is used to implement connection and communication between these components.
- the user interface 1003 may include a display screen.
- the optional user interface 1003 may further include a standard wired interface and a wireless interface.
- the wired interface of the user interface 1003 may be a USB interface in this application.
- the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WIreless-FIdelity (WI-FI) interface).
- WI-FI WIreless-FIdelity
- the memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or may be a stable memory (Non-volatile memory (NVM), such as a disk memory.
- RAM Random Access Memory
- NVM Non-volatile memory
- the memory 1005 may optionally be a storage device independent of the foregoing processor 1001.
- FIG. 1 does not constitute a limitation on the multiple rounds of question answering equipment for intelligent customer service, and may include more or fewer components than shown in the figure, or combine some components, or different components. Layout.
- the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and intelligent customer service multiple rounds of question-and-answer instructions.
- the network interface 1004 is mainly used to connect to a background server and perform data communication with the background server; the user interface 1003 is mainly used to connect to intelligent customer service devices; the intelligent customer service multiple rounds
- the question answering device calls the intelligent customer service multi-round question and answer readable instructions stored in the memory 1005 through the processor 1001, and executes the intelligent customer service multi-round question and answer method provided in the embodiment of the present application.
- FIG. 2 is a schematic flowchart of a first embodiment of a multi-round question and answer method for intelligent customer service in this application.
- the multi-round question and answer method for intelligent customer service includes the following steps:
- Step S10 Obtain the target question of the user's current round.
- the executing subject of this embodiment is an intelligent customer service multi-round question answering device, wherein the intelligent customer service multi-round question answering device may be an electronic device such as a personal computer or a server.
- the intelligent customer service multi-round question answering device may be an electronic device such as a personal computer or a server.
- the user usually asks the target question by voice, then the intelligent customer service multi-round question answering device can perform voice detection, and when the voice information sent by the user is detected, the voice information is obtained as the target question; or through the The display interface of the multi-round question answering device of the intelligent customer service enters the target question, and obtains text information input by the user in the display interface as the target question.
- Step S20 Find a standard intent matching the target problem from the knowledge base, and obtain a degree of matching between the standard intent and the target problem.
- the knowledge base of the intelligent customer service multi-round question answering device includes a variety of standard intents and corresponding standard responses.
- the standard intents in the knowledge base can be compared with the target questions to find and
- the standard intent of the target question is the standard intent that matches the target question.
- the degree of matching between the standard intent and the target question is 100%, that is, a complete match; if it cannot be obtained from the knowledge base,
- the similarity between the target problem and the standard intent in the knowledge base can be calculated, and the standard intent with the highest similarity can be matched with the target problem.
- Standard intent and use the highest similarity as the degree of matching between the standard intent and the target problem.
- Step S30 Determine whether the degree of matching between the standard intent and the target problem exceeds a preset matching threshold.
- the degree of matching between the standard intent and the target question needs to be analyzed. If the degree of matching is low , Indicating that the deviation between the standard intent and the target question is large. At this time, if the response corresponding to the standard intent is used as the answer to the target question, the answer may not be answered. Intent recognition to further determine the intent of the target question, thereby finding a more accurate answer. Therefore, a preset matching threshold is usually set in advance.
- the method further includes: if the degree of matching between the standard intent and the target question exceeds a preset matching threshold, obtaining a standard response corresponding to the standard intent as the target response. After obtaining the standard response corresponding to the standard intent as the target response, the method further includes: displaying the target response.
- the preset matching threshold may be based on historical data to calculate the degree of matching between historical questions with high response accuracy and standard intent, so as to determine a suitable preset matching threshold, for example, the response is accurate
- the degree of matching between the highly historical issues and the standard intent is mostly above 80%, and the preset matching threshold may be set to 80%. If the degree of matching between the standard intent and the target question exceeds 80%, the response corresponding to the standard intent may be displayed as a response to the target question; if the standard intent and the target question are If the degree of matching between them does not exceed 80%, the response corresponding to the standard intent cannot be used as the response to the target question. Intent recognition of the target question is required to further determine the intention of the target question, so as to find more Accurate responses.
- Step S40 if not, perform named entity recognition on the target problem to obtain a recognition result.
- the degree of matching between the standard intent and the target problem does not exceed a preset matching threshold, it means that the standard intent and the target problem have a large deviation, and the target problem may have a missing named entity or a missing manifestation.
- the situation of the words intended by the user causes the intent presented by the target question to be unclear.
- the response corresponding to the standard intent is used as the answer to the target question, the answer will not be asked, and you need to pass
- the target question is intentionally identified, and the intention of the target question is further determined, so as to find a more accurate answer.
- the intent recognition includes naming entity recognition of the target question and detecting whether there is a signal inherited in at least one round of user questions before the current round.
- NER Named Entity Recognition
- LSTM Long-Short Short-Term Memory Network
- CRF Conditional Random Field Algorithm
- Step S50 Detect whether there are signals inherited from at least one round of user questions before the current round, and obtain a detection result.
- the signal refers to the user intention inherited from the questions raised by the user in the previous round or previous rounds, and the signal includes the name inherited from the questions raised by the users in the previous round or previous rounds
- the signal will become weaker as the number of rounds passed increases.
- the user's signal can also be set to specify the number of rounds passed. For example, the signal is set to 2, which means that the current user's intention can only go backwards. Pass two rounds of dialogue. When the third round of dialogue starts, the signal will be invalid. Therefore, the signal has a life cycle. This life cycle can be set by the user. The user can pass the round of signals in the history of multiple rounds of dialogue.
- the number of statistics is used to calculate the number of dialogue rounds with the largest proportion of signal transmission in the history of multiple rounds of dialogue as the life cycle of the signal, and the signal will gradually decay during the transmission. Detect whether there is a signal inherited from at least one round of user issues before the current round, by detecting whether the life cycle of the signal is greater than zero, and if the life cycle of the signal is greater than zero, it can be obtained from the previous round Or the signals inherited from the questions raised by the users in the previous rounds are used as the signals of the target question, and the signals can reflect the user's intention.
- Step S60 Determine a target response according to the recognition result, the detection result, the target question, and the standard intent.
- the signal intent can be determined from the named entity and the signal in the target problem, and the knowledge can be obtained from the knowledge according to the signal intent
- the library searches for a standard intent that matches the signal intent, and uses the response corresponding to the found standard intent as the target response.
- the detection result is the presence of a signal, but the recognition result is the absence of a named entity
- determine whether the signal includes a named entity and if the signal does not include the named entity, issue a named entity inquiry and receive A named entity response made by the user according to the named entity inquiry, a signal intent is determined based on the named entity response and a signal in the target question, and the signal intent can be found in the knowledge base and the signal according to the signal intent
- the response corresponding to the found standard intent is used as the target response.
- the identified result is the existence of a named entity, but the detection result is the absence of a signal
- a preset integrity query is sent, and an integrity reply made by the user according to the preset integrity query is received, according to the The completeness reply and the named entity in the target problem determine the signal intent, and according to the signal intent, a standard intent that matches the signal intent can be found from the knowledge base, and the response corresponding to the found standard intent is taken as The target responds.
- the detection result is that there is no signal, indicating that the target problem has not been inherited from the user's intention from the previous round or previous rounds of user questions, then the user's intention can be directly asked, and the preset integrity reply It can be to inform the user that the target question is incomplete, and ask the user to reply to the complete question, so that according to the complete response made by the user, a clear-cut question can be obtained, so that a clear response can be found from the knowledge base as the target. Answer.
- the user ’s problem is composed of a named entity and an intent.
- the user When the user interacts with the intelligent customer service multi-round question and answer device, the user will omit the named entity or intent that has appeared in the previous round or rounds because of multiple rounds of question and answer , But it is usually not the case that both the named entity and the intent are omitted.
- the target problem of the user's current round is obtained, the standard intent matching the target problem is found from the knowledge base, and the degree of matching between the standard intent and the target problem is obtained, and Whether the degree of matching between the standard intent and the target problem exceeds a preset matching threshold; if not, the target problem is identified by a named entity, a recognition result is obtained, and it is detected whether there is at least one before the current round Signals inherited from a round of user questions to obtain detection results, so as to determine the substantial content of the target problem according to the recognition results and the detection results, and to perform corresponding evaluations based on the determined substantial content and the standard intent. Answer, can intelligently answer questions with users, improve the accuracy of responses in multiple rounds of questions and answers, and improve user experience.
- FIG. 3 is a schematic flowchart of a second embodiment of a multi-round question answering method for intelligent customer service in this application. Based on the first embodiment shown in FIG. 2 above, a second embodiment of a multi-round question answering method for intelligent customer service in this application is proposed.
- the step S60 includes:
- Step S601 If the recognition result is the existence of a named entity and the detection result is the presence of a signal, determine the signal intention according to the named entity and the signal in the target problem.
- the detection result is a presence signal, indicating that the target problem has inherited the user intention from the user problems of the previous round or previous rounds of the current round, and that there is a named entity in the target problem
- the signal intent may be determined according to the named entity in the target question and a signal inherited from a user question from a previous round or previous rounds of the current round.
- Step S602 Calculate a first similarity between the signal intent and the standard intent.
- the standard intent is an intent found from the knowledge base that matches the target problem.
- the standard intent can be corresponding
- the standard response is used as the target response. Whether the standard intent is consistent with the signal intent can be determined by calculating the semantic similarity between the standard intent and the inherited signal intent. If the semantic similarity exceeds a preset similarity threshold, it is considered to be consistent , Otherwise it is considered inconsistent.
- the semantic similarity calculation mainly uses a deep semantic model based on LSTM to obtain the cosine similarity between the standard intent semantic vector and the signal intent semantic vector as a measure of the consistency of the signal intent and the standard intent standard.
- the standard intent and the inherited signal intent are represented as semantic vectors, and then the cosine similarity is calculated for the two semantic vectors.
- the cosine similarity is used to determine whether they are consistent. If the cosine similarity exceeds a preset similarity threshold , The signal intent and the standard intent are considered to be consistent, otherwise the signal intent and the standard intent are considered to be inconsistent.
- the step S602 includes: performing semantic feature extraction of the signal intent and the standard intent through a long-term short-term memory network model, obtaining a signal semantic vector and a standard semantic vector, and calculating the signal semantic vector.
- the cosine similarity with the standard semantic vector, and the cosine similarity is used as the first similarity between the signal intent and the standard intent.
- Step S603 Determine whether the first similarity exceeds a preset similarity threshold.
- the preset similarity threshold may be based on historical data to calculate the degree of matching between the signal intent corresponding to each historical question with a high accuracy of recovery and the standard question, so as to determine an appropriate preset matching threshold. For example, if the degree of matching between the signal intent and the standard intent corresponding to each historical question with high accuracy is more than 90%, the preset similarity threshold may be set to 90%. If the first similarity between the signal intent and the standard intent exceeds 90%, the response corresponding to the standard intent may be displayed as a response to the target question; if the signal intent and the standard intent If the first similarity between the intents does not exceed 90%, the response corresponding to the standard intent cannot be used as the response to the target question.
- Step S604 if it exceeds, determine the target response according to the standard intent.
- the first similarity exceeds the preset similarity threshold, it indicates that the signal intent is consistent with the standard intent, and a response corresponding to the standard intent can be obtained from the knowledge base as The target response, and the target response is displayed, which can be displayed by voice, and can also be displayed through the display interface of the intelligent customer service multi-round question answering device, or by sending the target response to a user device.
- the display may also be performed in other ways, which is not limited in this embodiment.
- the first similarity does not exceed the preset similarity threshold, indicating that the signal intent is inconsistent with the standard intent, it may be directly asked whether the customer's intention is the signal intent.
- the user response determines the user's true intention, and then finds a response corresponding to the user's true intention from the knowledge base as the target response.
- the method before step S602, the method further includes: if the detection result is a signal, but the recognition result is that no named entity exists, determining whether the signal includes a named entity; if the signal If the named entity is not included, a named entity query is issued, and a named entity response made by the user according to the named entity query is received; a signal intent is determined according to the named entity response and a signal in the target question.
- the detection result is a signal indicating that the target problem has inherited the user intention from the user problems of the previous round or previous rounds of the current round, and the signal may be a named entity or other Information, if the signal includes a named entity, the user's signal intention can be determined based on the signal and the target problem.
- a named entity query may be directly issued to determine the named entity of the target question through the user's reply, thereby more accurately identifying the intention of the target question.
- the named entity that the user wants to know can be clearly known, and then the signal in the target problem is combined to determine the complete signal intention.
- the step S40 includes: performing sequence feature extraction of the target problem through the long-term short-term memory network model; performing entity probability calculation of the extracted sequence features through a conditional random field algorithm, and determining the entity Whether the maximum probability exceeds a preset probability threshold; if the maximum probability of the entity exceeds the preset probability threshold, the feature corresponding to the maximum probability of the entity is identified as the named entity of the target problem, and the recognition result is present A named entity; if the maximum value of the entity probability does not exceed the preset probability threshold, a recognition result is obtained that there is no named entity.
- A is the state transition matrix
- represents the probability of transition from the i-th tag to the j-th tag.
- the target problem is input into an LSTM + CRF model, and sequence feature extraction is performed on the target problem through LSTM.
- Each feature in the extracted feature sequence is subjected to entity probability calculation through CRF, and the feature with the highest entity probability is identified as the feature.
- the target problem entity is considered that there is no named entity in the target problem.
- a signal intention is determined by a named entity in the target problem and a signal inherited from a previous round or previous rounds, and if the standard intention is consistent with the signal intention, the The standard response corresponding to the standard intent is used as the target response, which combines the information transmitted in the previous round or previous rounds, thereby improving the accuracy of the responses in multiple rounds of question and answer.
- FIG. 4 is a schematic flowchart of a third embodiment of a multi-round question and answer method for intelligent customer service in this application. Based on the second embodiment shown in FIG. 3 described above, a third embodiment of a multi-round question and answer method for intelligent customer service in this application is proposed.
- the step S20 includes:
- Step S201 Find a candidate intent set matching the target problem from a knowledge base through ES retrieval.
- ES is short for Elaticsearch, which is mainly based on an inverted index to quickly filter the candidate intent set.
- word segmentation system uses the word segmentation system to automatically segment each candidate intent in the knowledge base into word sequences, so that each candidate intent is converted into a data stream composed of word sequences.
- Number, and record which candidate intent in the knowledge base contains this word so as to get the simplest inverted index.
- the knowledge base includes 5 candidate intents.
- the "word ID" column records the word number of each word
- the second column can record the corresponding word
- the third column can record the corresponding inversion of each word. Ranking list.
- the word "activity A” has a word number of 1 and an inverted list of ⁇ 1,2,3,4,5 ⁇ , indicating that each candidate question in the knowledge base contains the word. Then, the target problem can be quickly divided into target word sequences by cutting the target problem into target word sequences, and the inverse index method retrieved by the ES from the knowledge base, the candidate intents and corresponding responses constitute the Candidate intent set.
- Step S202 Calculate a second similarity between the target problem and a candidate intent in the candidate intent set.
- a second similarity between the target problem and the candidate intent in the candidate intent set is generally calculated, Taking the standard intent with the highest similarity as the standard intent that matches the target problem best reflects the true intention of the target problem.
- the step S202 includes: calculating a semantic feature, a text feature, a syntactic feature, and a topic feature between the target question and the candidate intents in the candidate intent set;
- the text features, the syntactic features, and the topic features are aggregated to obtain a second similarity between the target problem and candidate intents in the candidate intent set.
- the semantic features are mainly obtained based on the deep semantic model of LSTM; the text features are mainly based on TF-IDF (TF * IDF, TF word frequency, Term Frequency, IDF reverse file frequency, Inverse Document Frequency) value, editing distance, Features such as the longest common substring and / or shared words; syntactic features based on Harbin Institute of Technology's Language Technology Platform (LTP) model for similarity calculation; topic similarity based on document theme generation (Latent, Dirichlet, Allocation, abbreviated LDA) ) Model.
- LDP Harbin Institute of Technology's Language Technology Platform
- LDA Logistic Regression
- LR Logistic Regression
- Step S203 Use the candidate intent with the second highest similarity as the standard intent matching the target problem, and obtain the highest second similarity as the degree of matching between the standard intent and the target problem.
- the candidate intent with the second highest similarity may be used as the standard intent that matches the target problem and obtained
- the highest second similarity is taken as the degree of matching between the standard intent and the target question, and whether the response corresponding to the candidate intent is taken as the target response is determined by the degree of matching.
- the candidate intent with the highest similarity is closest to the true intent of the target question, thereby improving the accuracy of the responses in multiple rounds of question and answer.
- an embodiment of the present application further provides a storage medium, where the intelligent customer service multi-round question-and-answer readable instructions are stored, and the intelligent customer service multi-round question-and-answer readable instructions are implemented as described above when executed by a processor. Steps of multiple rounds of question and answer methods for smart customer service.
- the storage medium may be a non-volatile readable storage medium.
- an embodiment of the present application also proposes a multi-round question answering device for an intelligent customer service.
- the multi-round question answering device for an intelligent customer service includes: an obtaining module 10 for obtaining a target question of a user's current round; a finding module 20, It is used to find the standard intent that matches the target problem from the knowledge base, and to obtain the degree of matching between the standard intent and the target problem; the determination module 30 is used to determine the standard intent and the target problem Whether the degree of matching between them exceeds a preset matching threshold; an identification module 40 configured to identify a named entity for the target problem to obtain a recognition result if it does not exceed; a detection module 50 configured to detect whether the current round exists Signals inherited from at least one previous round of user questions to obtain detection results; a determination module 60 is configured to determine a target response based on the recognition results, the detection results, the target question, and the standard intent.
- the technical solution of the present application is essentially in the form of a software product that contributes to the existing technology.
- the computer software product is stored in a storage medium (such as a read-only memory image (Read Only Memory image, ROM)). / Random Access Memory (Random Access Memory, RAM), magnetic disks, compact discs, including a number of instructions to enable a terminal device (can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute this application
- a terminal device can be a mobile phone, computer, server, air conditioner, or network device, etc.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
一种智能客服多轮问答方法、设备、存储介质及装置,该方法包括:获取用户当前轮次的目标问题(S10);从知识库中查找与目标问题匹配的标准意图,获取标准意图与目标问题之间的匹配程度(S20);判断标准意图与目标问题之间的匹配程度是否超过预设匹配阈值(S30);未超过,对目标问题进行命名实体识别,获得识别结果(S40);检测是否存在当前轮次之前的至少一轮用户问题中继承的信号,获得检测结果(S50);根据识别结果、检测结果、目标问题和标准意图确定目标应答(S60)。
Description
本申请要求于2018年07月03日提交中国专利局、申请号为201810722735.3、发明名称为“智能客服多轮问答方法、设备、存储介质及装置”的中国专利申请的优先权,其全部内容通过引用结合在申请中。
本申请涉及智能客服技术领域,尤其涉及一种智能客服多轮问答方法、设备、存储介质及装置。
随着科技的发展,智能客服系统越来越得到重视,用户与智能客服出现多轮问答时,后面的几个问题可能会省略掉命名实体或信号,所述信号为从用户前几轮问题中继承到的用户意图,导致问题因缺失命名实体或信号而出现问题内容不明确的情况,导致智能客服系统在和用户进行多轮问答时,易出现无法判断问题的实质内容,无法进行相应的应答,导致用户体验差。因此,如何识别出多轮问答中用户问题的实质内容,以提高多轮问答中回复的准确度是亟待解决的技术问题。
发明内容
本申请的主要目的在于提供一种智能客服多轮问答方法、设备、存储介质及装置,旨在解决现有技术中多轮问答中回复的准确度低的技术问题。
为实现上述目的,本申请提供一种智能客服多轮问答方法,所述智能客服多轮问答方法包括以下步骤:获取用户当前轮次的目标问题;从知识库中查找与所述目标问题匹配的标准意图,并获取所述标准意图与所述目标问题之间的匹配程度;判断所述标准意图与所述目标问题之间的匹配程度是否超过预设匹配阈值;若未超过,则对所述 目标问题进行命名实体识别,获得识别结果;检测是否存在所述当前轮次之前的至少一轮用户问题中继承的信号,获得检测结果;根据所述识别结果、所述检测结果、所述目标问题和所述标准意图确定目标应答。
此外,为实现上述目的,本申请还提出一种智能客服多轮问答设备,所述智能客服多轮问答设备包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的智能客服多轮问答可读指令,所述智能客服多轮问答可读指令配置为实现如上文所述的智能客服多轮问答方法的步骤。
此外,为实现上述目的,本申请还提出一种存储介质,所述存储介质上存储有智能客服多轮问答可读指令,所述智能客服多轮问答可读指令被处理器执行时实现如上文所述的智能客服多轮问答方法的步骤。
此外,为实现上述目的,本申请还提出一种智能客服多轮问答装置,包括:获取模块,用于获取用户当前轮次的目标问题;查找模块,用于从知识库中查找与所述目标问题匹配的标准意图,并获取所述标准意图与所述目标问题之间的匹配程度;判断模块,用于判断所述标准意图与所述目标问题之间的匹配程度是否超过预设匹配阈值;识别模块,用于若未超过,则对所述目标问题进行命名实体识别,获得识别结果;述检测模块,用于检测是否存在所述当前轮次之前的至少一轮用户问题中继承的信号,获得检测结果;确定模块,用于根据所述识别结果、所述检测结果、所述目标问题和所述标准意图确定目标应答。
图1是本申请实施例方案涉及的硬件运行环境的智能客服多轮问答设备结构示意图;
图2为本申请智能客服多轮问答方法第一实施例的流程示意图;
图3为本申请智能客服多轮问答方法第二实施例的流程示意图;
图4为本申请智能客服多轮问答方法第三实施例的流程示意图;
图5为本申请智能客服多轮问答装置第一实施例的结构框图。
此处所描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。
参照图1,图1为本申请实施例方案涉及的硬件运行环境的智能客服多轮问答设备结构示意图。
如图1所示,该智能客服多轮问答设备可以包括:处理器1001,例如中央处理器(Central Processing Unit,CPU),通信总线1002、用户接口1003,网络接口1004,存储器1005。其中,通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏(Display),可选用户接口1003还可以包括标准的有线接口、无线接口,对于用户接口1003的有线接口在本申请中可为USB接口。网络接口1004可选的可以包括标准的有线接口、无线接口(如无线保真(WIreless-FIdelity,WI-FI)接口)。存储器1005可以是高速的随机存取存储器(Random Access Memory,RAM)存储器,也可以是稳定的存储器(Non-volatile Memory,NVM),例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
本领域技术人员可以理解,图1中示出的结构并不构成对智能客服多轮问答设备的限定,可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置。
如图1所示,作为一种计算机存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及智能客服多轮问答可读指令。
在图1所示的智能客服多轮问答设备中,网络接口1004主要用于连接后台服务器,与所述后台服务器进行数据通信;用户接口1003主要用于连接智能客服设备;所述智能客服多轮问答设备通过处理器1001调用存储器1005中存储的智能客服多轮问答可读指令,并执行本申请实施例提供的智能客服多轮问答方法。
基于上述硬件结构,提出本申请智能客服多轮问答方法的实施例。
参照图2,图2为本申请智能客服多轮问答方法第一实施例的流程示意图,第一实施例中,所述智能客服多轮问答方法包括以下步骤:
步骤S10:获取用户当前轮次的目标问题。
应理解的是,本实施例的执行主体是智能客服多轮问答设备,其中,所述智能客服多轮问答设备可为个人电脑、服务器等电子设备。用户通常通过语音方式提出所述目标问题,则所述智能客服多轮问答设备可进行语音检测,当检测到用户发出的语音信息时,获取所述语音信息作为所述目标问题;或者通过所述智能客服多轮问答设备的显示界面输入所述目标问题,获取显示界面中用户输入的文本信息作为所述目标问题。
步骤S20:从知识库中查找与所述目标问题匹配的标准意图,并获取所述标准意图与所述目标问题之间的匹配程度。
在具体实现中,所述智能客服多轮问答设备的知识库中包括多种标准意图和对应的标准答复,可通过将所述知识库中的标准意图与所述目标问题进行比对,查找与所述目标问题一致的标准意图,作为与所述目标问题匹配的标准意图,所述标准意图与所述目标问题之间的匹配程度为100%,即完全匹配;若不能从所述知识库中查找到与所述目标问题一致的标准意图,可通过计算所述目标问题与所述知识库中的标准意图之间的相似度,将所述相似度最高的标准意图作为与所述目标问题匹配的标准意图,并将所述最高相似度作为述标准意图与所述目标问题之间的匹配程度。
步骤S30:判断所述标准意图与所述目标问题之间的匹配程度是否超过预设匹配阈值。
需要说明的是,为了提高所述智能客服多轮问答设备回复所述目标问题的准确度,需对所述标准意图与所述目标问题之间的匹配程度进行分析,若所述匹配程度较低,说明所述标准意图与所述目标问题的偏差较大,此时若将所述标准意图对应的答复作为所述目标问题的答复,会出现答非所问的情况,则需要通过对所述目标问题进行意图 识别,进一步确定所述目标问题的意图,从而找到更加准确的答复。因此,通常预先设置预设匹配阈值,若所述标准意图与所述目标问题之间的匹配程度未超过所述预设匹配阈值,则说明所述标准意图不能体现所述目标问题的意图;若所述标准意图与所述目标问题之间的匹配程度超过所述预设匹配阈值,则说明所述标准意图能体现所述目标问题的意图,将所述标准意图对应的答复作为所述目标问题的答复,就能准确的回复用户的所述目标问题。本实施例中,所述步骤S30之后,还包括:若所述标准意图与所述目标问题之间的匹配程度超过预设匹配阈值,则获取所述标准意图对应的标准答复作为目标应答。所述获取所述标准意图对应的标准答复作为目标应答之后,还包括:将所述目标应答进行展示。
应理解的是,所述预设匹配阈值可根据历史数据,将回复准确度高的各历史问题与标准意图之间的匹配程度进行统计,从而确定出合适的预设匹配阈值,比如,回复准确度高的各历史问题与标准意图之间的匹配程度大多数都在80%以上,则可将所述预设匹配阈值设置为80%。若所述标准意图与所述目标问题之间的匹配程度超过80%,则可将所述标准意图对应的回复作为所述目标问题的回复进行展示;若所述标准意图与所述目标问题之间的匹配程度未超过80%,则不能将所述标准意图对应的回复作为所述目标问题的回复,还需对所述目标问题进行意图识别,进一步确定所述目标问题的意图,从而找到更加准确的答复。
步骤S40:若未超过,则对所述目标问题进行命名实体识别,获得识别结果。
若所述标准意图与所述目标问题之间的匹配程度未超过预设匹配阈值,说明所述标准意图与所述目标问题的偏差较大,所述目标问题可能存在缺失命名实体或缺失能体现用户意图的词句的情况,导致所述目标问题所呈现的意图不明确,此时若将所述标准意图对应的答复作为所述目标问题的答复,会出现答非所问的情况,则需要通过对所述目标问题进行意图识别,进一步确定所述目标问题的意图,从而找到更加准确的答复。所述意图识别包括对所述目标问题进行命名实 体识别和检测是否存在所述当前轮次之前的至少一轮用户问题中继承的信号。所述命名实体识别(Named Entity Recognition,简称NER),又称作“专名识别”,是指识别文本中具有特定意义的实体,主要包括人名、地名、机构名、专有名词等。对所述目标问题进行命名实体识别,可通过长期短期记忆网络(Long-Short Term Memory,简称LSTM)+条件随机场算法(conditional random field algorithm,简称CRF)模型实现。
步骤S50:检测是否存在所述当前轮次之前的至少一轮用户问题中继承的信号,获得检测结果。
需要说明的是,所述信号是指从上一轮或上几轮用户提出的问题中继承下来的用户意图,所述信号包括从上一轮或上几轮用户提出的问题中继承下来的命名实体或其他信息,随着传递轮数的增加,信号将越来越弱,当然用户的信号也可以通过设置,指定传递的轮数,比如信号设置为2,表示当前用户的意图只能往后传递两轮对话,第三轮对话开始时,该信号将会失效,因此,信号是有生命周期的,此生命周期可以由用户来设定,用户可对历史多轮对话中中的信号传递轮数进行统计,将历史多轮对话中信号传递占比最大的对话轮数作为所述信号的生命周期,而且所述信号在传递的过程中是会逐渐衰减的。检测是否存在所述当前轮次之前的至少一轮用户问题中继承的信号,可通过检测所述信号的生命周期是否大于零,若所述信号的生命周期大于零,则可获取从上一轮或上几轮用户提出的问题中继承下来的信号作为所述目标问题的信号,所述信号能体现出用户的意图。
步骤S60:根据所述识别结果、所述检测结果、所述目标问题和所述标准意图确定目标应答。
可理解的是,若所述识别结果为存在命名实体,并且所述检测结果为存在信号,则可所述目标问题中的命名实体和信号确定信号意图,根据所述信号意图可从所述知识库中查找与所述信号意图匹配的标准意图,将查找到的标准意图对应的答复作为所述目标应答。若所述检测结果为存在信号,但所述识别结果为不存在命名实体,则判断所述信号是否包括命名实体,若所述信号不包括所述命名实体,则发 出命名实体问询,并接收用户根据所述命名实体问询做出的命名实体回复,根据所述命名实体回复和所述目标问题中的信号确定信号意图,根据所述信号意图可从所述知识库中查找与所述信号意图匹配的标准意图,将查找到的标准意图对应的答复作为所述目标应答。
若所述识别结果为存在命名实体,但所述检测结果为不存在信号,则发出预设完整性问询,接收用户根据所述预设完整性问询所做出的完整性回复,根据所述完整性回复和所述目标问题中的命名实体确定信号意图,根据所述信号意图可从所述知识库中查找与所述信号意图匹配的标准意图,将查找到的标准意图对应的答复作为所述目标应答。所述检测结果为不存在信号,说明所述目标问题未从上一轮或上几轮的用户问题中继承到用户意图,则可直接问询用户的意图是什么,所述预设完整性回复,可以是告知用户所述目标问题不完整,请用户回复完整的问题,从而根据用户所做出的完整性回复,获得意图明确的问题,从而能从知识库中找到明确的回复作为所述目标应答。通常用户的问题是有命名实体和意图组成,用户在与所述智能客服多轮问答设备进行交互时,会因进行了多轮问答而省略掉前面一轮或几轮出现过的命名实体或意图,但通常不会出现将所述命名实体和意图同时省略的情况。
在第一实施例中,获取用户当前轮次的目标问题,从知识库中查找与所述目标问题匹配的标准意图,并获取所述标准意图与所述目标问题之间的匹配程度,判断所述标准意图与所述目标问题之间的匹配程度是否超过预设匹配阈值,若未超过,则对所述目标问题进行命名实体识别,获得识别结果,检测是否存在所述当前轮次之前的至少一轮用户问题中继承的信号,获得检测结果,从而根据所述识别结果和所述检测结果确定出所述目标问题的实质性内容,根据确定出的实质性内容和所述标准意图进行相应的应答,能够与用户之间进行智能问答,提高多轮问答中回复的准确度,提升用户体验。
参照图3,图3为本申请智能客服多轮问答方法第二实施例的流程示意图,基于上述图2所示的第一实施例,提出本申请智能客服多 轮问答方法的第二实施例。
在第二实施例中,所述步骤S60,包括:
步骤S601:若所述识别结果为存在命名实体,并且所述检测结果为存在信号,则根据所述目标问题中的命名实体和信号确定信号意图。
可理解的是,所述检测结果为存在信号,说明所述目标问题从所述当前轮次的前一轮或前几轮的用户问题中继承了用户意图,并且所述目标问题中存在命名实体,则可根据所述目标问题中的命名实体和从从所述当前轮次的前一轮或前几轮的用户问题中继承的信号确定信号意图。例如:多轮问答场景一,问题1:活动什么时间开始?应答1:请问您询问哪个活动?问题2:活动A。应答2:活动A的开始时间为:2018年5月4日。
在上述多轮问答场景一中,所述问题2存在命名实体,所述命名实体为活动A,也存在信号,所述信号为从问题1中继承的信号:什么时间开始,则根据所述命名实体和所述信号确定的信号意图为:活动A什么时间开始?
步骤S602:计算所述信号意图和所述标准意图之间的第一相似度。
需要说明的是,所述标准意图为从知识库中查找到的与所述目标问题匹配的意图,为了进一步确定所述标准意图是否与所述信号意图一致,从而能将所述标准意图对应的标准答复作为所述目标应答。所述标准意图是否与所述信号意图是否一致,可通过计算所述标准意图和继承下来的信号意图的语义相似度来判断,若所述语义相似度超过预设相似度阈值,认为是一致的,否则认为是不一致的。
应理解的是,语义相似度计算,主要采用基于LSTM的深度语义模型,获得标准意图语义向量和信号意图语义向量之间的余弦相似性,作为所述信号意图和所述标准意图一致性的衡量标准。经由LSTM网络,将标准意图和继承的信号意图表示为语义向量的形式,然后对两个语义向量计算余弦相似度,通过余弦相似度来确定是否为一致,若余弦相似度超过预设相似度阈值,认为所述信号意图和所述 标准意图是一致的,否则认为所述信号意图和所述标准意图是不一致的。因此,本实施例中,所述步骤S602,包括:将所述信号意图和所述标准意图通过长期短期记忆网络模型进行语义特征提取,获得信号语义向量和标准语义向量,计算所述信号语义向量和标准语义向量之间的余弦相似度,并将所述余弦相似度作为所述信号意图和所述标准意图之间的第一相似度。
步骤S603:判断所述第一相似度是否超过预设相似度阈值。
在具体实现中,所述预设相似度阈值可根据历史数据,将回复准确度高的各历史问题对应的信号意图与标准问题之间的匹配程度进行统计,从而确定出合适的预设匹配阈值,比如,回复准确度高的各历史问题对应的信号意图与标准意图之间的匹配程度大多数都在90%以上,则可将所述预设相似度阈值设置为90%。若所述信号意图与所述标准意图之间的第一相似度超过90%,则可将所述标准意图对应的回复作为所述目标问题的回复进行展示;若所述信号意图与所述标准意图之间的第一相似度未超过90%,则不能将所述标准意图对应的回复作为所述目标问题的回复。
步骤S604:若超过,则根据所述标准意图确定目标应答。
可理解的是,若所述第一相似度超过所述预设相似度阈值,说明所述信号意图与所述标准意图一致,可通过从所述知识库中获取所述标准意图对应的答复作为所述目标应答,并将所述目标应答进行展示,可通过语音形式进行展示,还可通过所述智能客服多轮问答设备的显示界面进行展示,还可通过将所述目标应答发送至用户设备进行展示,还可通过其他方式进行展示,本实施例对此不加以限制。
需要说明的是,若所述第一相似度不超过所述预设相似度阈值,说明所述信号意图与所述标准意图不一致,则可直接问询客户的意图是否为所述信号意图,根据用户回复确定用户的真实意图,进而从知识库中查找到与用户回复的真实意图对应的答复作为所述目标应答。
在第二实施例中,所述步骤S602之前,还包括:若所述检测结果为存在信号,但所述识别结果为不存在命名实体,则判断所述信号是否包括命名实体;若所述信号不包括所述命名实体,则发出命名实 体问询,并接收用户根据所述命名实体问询做出的命名实体回复;根据所述命名实体回复和所述目标问题中的信号确定信号意图。
应理解的是,所述检测结果为存在信号,说明所述目标问题从所述当前轮次的前一轮或前几轮的用户问题中继承了用户意图,所述信号可以是命名实体或其他信息,若所述信号包括命名实体,则可根据所述信号和所述目标问题就可确定出用户的信号意图。例如:多轮问答场景二,问题3:活动A什么时间开始?应答3:活动A的开始时间为:2018年4月5日。问题4:什么时间结束?应答4:活动A的结束时间为:2018年4月8日。
在上述多轮问答场景二中,所述问题4不存在命名实体,但存在从上一轮问题3中继承的信号为命名实体:活动A,则根据所述信号和所述问题4可确定出用户的信号意图为:活动A什么时间结束?
需要说明的是,若所述信号不包括所述命名实体,说明所述目标问题中不存在所述命名实体,从所述信号中也无法获知所述命名实体,则所述目标问题缺失命名实体,则可直接发出命名实体问询,以通过用户的回复确定所述目标问题的命名实体,从而更准确的识别出所述目标问题的意图。
在具体实现中,根据所述命名实体回复可明确知晓用户想了解的命名实体,再结合所述目标问题中的信号从而确定出完整的信号意图。
在第二实施例中,所述步骤S40包括:将所述目标问题通过所述长期短期记忆网络模型进行序列特征提取;将提取出的序列特征通过条件随机场算法进行实体概率计算,并判断实体概率最大值是否超过预设概率阈值;若所述实体概率最大值超过所述预设概率阈值,则认定所述实体概率最大值对应的特征为所述目标问题的命名实体,获得识别结果为存在命名实体;若所述实体概率最大值未超过所述预设概率阈值,则获得识别结果为不存在命名实体。
应理解的是,通过LSTM+CRF模型实现命名实体识别,通过LSTM网络的处理,相当于得到了一个比较好的对输入的所述目标问题的表示方法,LSTM单元最终输出的向量即可以看成是输入的所述 目标问题的一种表示形式,最终在打标签阶段,通过LSTM与CRF结合,使用LSTM解决提取序列特征的问题,使用CRF有效利用了句子级别的标记信息。
在LSTM+CRF模型下,输出的将不再是相互独立的标签,而是最佳的标签序列。对于输入:|X=(x1,x2,...,xn)|,我们可以定义LSTM的输出概率矩阵|Pn*k|其中k是输出标签的个数。|Pi,j|是指第i个字被标记为第j个标签的概率。对于待预测的标签序列:|y=(y1,y2,...,yn)|,我们可以有如下定义:
其中A是状态转移矩阵,|Ai,j|代表从第i个标签(tag)转移到第j个标签的概率。通过求得最大的|s(X,y)|,即可得到最佳的输出标签序列。这里引入的CRF,其实只是对输出标签二元组进行了建模,然后使用动态规划进行计算即可,最终根据得到的最优路径进行标注。
将所述目标问题输入LSTM+CRF模型,通过LSTM对所述目标问题进行序列特征提取,通过CRF对提取出的特征序列中的各特征进行实体概率计算,将实体概率最大的特征认定为所述目标问题的实体。但是,当输出的实体识别结果表示不存在命名实体,或者命名实体概率太小,认为所述目标问题不存在命名实体。
在第二实施例中,通过所述目标问题中的命名实体和从上一轮或上几轮中继承的信号确定出信号意图,若所述标准意图与所述信号意图一致,则将所述标准意图对应的标准答复作为所述目标应答,结合了上一轮或上几轮中传递的信息,从而提高多轮问答中回复的准确度。
参照图4,图4为本申请智能客服多轮问答方法第三实施例的流程示意图,基于上述图3所示的第二实施例,提出本申请智能客服多轮问答方法的第三实施例。
在第三实施例中,所述步骤S20包括:
步骤S201:通过ES检索从知识库中查找与所述目标问题匹配的候选意图集合。
可理解的是,ES为Elaticsearch简写,主要基于倒排索引的方式快速筛选候选意图集合。首先要用分词系统将知识库中各候选意图自动切分成单词序列,这样每个候选意图就转换为由单词序列构成的数据流,为了后续处理方便,需要对每个不同的单词赋予唯一的单词编号,同时记录下所述知识库中哪些候选意图包含这个单词,从而得到最简单的倒排索引。比如,知识库中包括5个候选意图,倒排索引中,“单词ID”一栏记录每个单词的单词编号,第二栏可记录对应的单词,第三栏可记录每个单词对应的倒排列表。比如单词“活动A”,其单词编号为1,倒排列表为{1,2,3,4,5},说明所述知识库中每个候选问题都包含了这个单词。则可通过将所述目标问题切分成目标单词序列,从所述知识库中通过ES检索的倒排索引方式快速筛选出包含目标单词序列的候选意图,所述候选意图和对应的应答构成所述候选意图集合。
步骤S202:计算所述目标问题与所述候选意图集合中的候选意图之间的第二相似度。
应理解的是,为了从所述候选意图集合中确定出与所述目标问题匹配的标准意图,通常需计算所述目标问题与所述候选意图集合中的候选意图之间的第二相似度,将相似度最高的标准意图作为与所述目标问题匹配的标准意图,最能体现所述目标问题的真实意图。
进一步地,所述步骤S202,包括:计算所述目标问题与所述候选意图集合中的候选意图之间的语义特征、文本特征、句法特征和主题特征;通过逻辑回归将所述语义特征、所述文本特征、所述句法特征和所述主题特征进行聚合,获得所述目标问题与所述候选意图集合中的候选意图之间的第二相似度。
需要说明的是,语义特征主要是基于LSTM的深度语义模型获得;文本特征主要是基于TF-IDF(TF*IDF,TF词频,Term Frequency,IDF逆向文件频率,Inverse Document Frequency)值、编辑距离、最长公共子串和/或共有词占比等特征;句法特征基于哈工大的语言技术平台(Language Technology Platform,LTP)模型进行相似度计算;主题相似度基于文档主题生成(Latent Dirichlet Allocation,简写LDA) 模型。最后训练一个逻辑回归(Logistic Regression,LR)模型,将以上特征结合在一起,进行聚合,获得所述目标问题与各候选意图之间的第二相似度。
步骤S203:将所述第二相似度最高的候选意图作为与所述目标问题匹配的标准意图,并获取最高的第二相似度作为所述标准意图与所述目标问题之间的匹配程度。
需要说明的是,所述相似度最高的候选意图与所述目标问题的真实意图最接近,则可将所述第二相似度最高的候选意图作为与所述目标问题匹配的标准意图,并获取最高的第二相似度作为所述标准意图与所述目标问题之间的匹配程度,通过所述匹配程度判断是否将所述候选意图对应的答复作为所述目标应答。相似度最高的候选意图与所述目标问题的真实意图最接近,从而提高多轮问答中回复的准确度。
此外,本申请实施例还提出一种存储介质,所述存储介质上存储有智能客服多轮问答可读指令,所述智能客服多轮问答可读指令被处理器执行时实现如上文所述的智能客服多轮问答方法的步骤。所述存储介质可以为非易失性可读存储介质。
此外,参照图5,本申请实施例还提出一种智能客服多轮问答装置,所述智能客服多轮问答装置包括:获取模块10,用于获取用户当前轮次的目标问题;查找模块20,用于从知识库中查找与所述目标问题匹配的标准意图,并获取所述标准意图与所述目标问题之间的匹配程度;判断模块30,用于判断所述标准意图与所述目标问题之间的匹配程度是否超过预设匹配阈值;识别模块40,用于若未超过,则对所述目标问题进行命名实体识别,获得识别结果;检测模块50,用于检测是否存在所述当前轮次之前的至少一轮用户问题中继承的信号,获得检测结果;确定模块60,用于根据所述识别结果、所述检测结果、所述目标问题和所述标准意图确定目标应答。
本申请所述智能客服多轮问答装置的其他实施例或具体实现方式可参照上述各方法实施例,此处不再赘述。
本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质(如只读存储器镜像(Read Only Memory image,ROM)/随机存取存储器(Random Access Memory,RAM)、磁碟、光盘)中,包括若干指令用以使得一台终端设备(可以是手机,计算机,服务器,空调器,或者网络设备等)执行本申请各个实施例所述的方法。凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本申请的专利保护范围内。
Claims (20)
- 一种智能客服多轮问答方法,其特征在于,所述智能客服多轮问答方法包括以下步骤:获取用户当前轮次的目标问题;从知识库中查找与所述目标问题匹配的标准意图,并获取所述标准意图与所述目标问题之间的匹配程度;判断所述标准意图与所述目标问题之间的匹配程度是否超过预设匹配阈值;若未超过,则对所述目标问题进行命名实体识别,获得识别结果;检测是否存在所述当前轮次之前的至少一轮用户问题中继承的信号,获得检测结果;根据所述识别结果、所述检测结果、所述目标问题和所述标准意图确定目标应答。
- 如权利要求1所述的智能客服多轮问答方法,其特征在于,所述根据所述识别结果、所述检测结果、所述目标问题和所述标准意图确定目标应答,包括:若所述识别结果为存在命名实体,并且所述检测结果为存在信号,则根据所述目标问题中的命名实体和信号确定信号意图;计算所述信号意图和所述标准意图之间的第一相似度;判断所述第一相似度是否超过预设相似度阈值;若超过,则根据所述标准意图确定目标应答。
- 如权利要求2所述的智能客服多轮问答方法,其特征在于,所述计算所述信号意图和所述标准意图之间的第一相似度之前,所述智能客服多轮问答方法还包括:若所述检测结果为存在信号,但所述识别结果为不存在命名实体,则判断所述信号是否包括命名实体;若所述信号不包括所述命名实体,则发出命名实体问询,并接收用户根 据所述命名实体问询做出的命名实体回复;根据所述命名实体回复和所述目标问题中的信号确定信号意图。
- 如权利要求2所述的智能客服多轮问答方法,其特征在于,所述计算所述信号意图和所述标准意图之间的第一相似度,包括:将所述信号意图和所述标准意图通过长期短期记忆网络模型进行语义特征提取,获得信号语义向量和标准语义向量;计算所述信号语义向量和标准语义向量之间的余弦相似度,并将所述余弦相似度作为所述信号意图和所述标准意图之间的第一相似度。
- 如权利要求4所述的智能客服多轮问答方法,其特征在于,所述对所述目标问题进行命名实体识别,获得识别结果,包括:将所述目标问题通过所述长期短期记忆网络模型进行序列特征提取;将提取出的序列特征通过条件随机场算法进行实体概率计算,并判断实体概率最大值是否超过预设概率阈值;若所述实体概率最大值超过所述预设概率阈值,则认定所述实体概率最大值对应的特征为所述目标问题的命名实体,获得识别结果为存在命名实体;若所述实体概率最大值未超过所述预设概率阈值,则获得识别结果为不存在命名实体。
- 如权利要求1所述的智能客服多轮问答方法,其特征在于,所述从知识库中查找与所述目标问题匹配的标准意图,并获取所述标准意图与所述目标问题之间的匹配程度,包括:通过ES检索从知识库中查找与所述目标问题匹配的候选意图集合;计算所述目标问题与所述候选意图集合中的候选意图之间的第二相似度;将所述第二相似度最高的候选意图作为与所述目标问题匹配的标准意图,并获取最高的第二相似度作为所述标准意图与所述目标问题之间的匹配程度。
- 如权利要求6所述的智能客服多轮问答方法,其特征在于,所述计算所述目标问题与所述候选意图集合中的候选意图之间的第二相似度,包括:计算所述目标问题与所述候选意图集合中的候选意图之间的语义特征、文本特征、句法特征和主题特征;通过逻辑回归将所述语义特征、所述文本特征、所述句法特征和所述主题特征进行聚合,获得所述目标问题与所述候选意图集合中的候选意图之间的第二相似度。
- 一种智能客服多轮问答设备,其特征在于,所述智能客服多轮问答设备包括:存储器、处理器及存储在所述存储器上并可在所述处理器上运行的智能客服多轮问答可读指令,所述智能客服多轮问答可读指令被所述处理器执行,以实现以下步骤:获取用户当前轮次的目标问题;从知识库中查找与所述目标问题匹配的标准意图,并获取所述标准意图与所述目标问题之间的匹配程度;判断所述标准意图与所述目标问题之间的匹配程度是否超过预设匹配阈值;若未超过,则对所述目标问题进行命名实体识别,获得识别结果;检测是否存在所述当前轮次之前的至少一轮用户问题中继承的信号,获得检测结果;根据所述识别结果、所述检测结果、所述目标问题和所述标准意图确定目标应答。
- 如权利要求8所述的智能客服多轮问答设备,其特征在于,所述根据所述识别结果、所述检测结果、所述目标问题和所述标准意图确定目标应答的步骤包括:若所述识别结果为存在命名实体,并且所述检测结果为存在信号,则根据所述目标问题中的命名实体和信号确定信号意图;计算所述信号意图和所述标准意图之间的第一相似度;判断所述第一相似度是否超过预设相似度阈值;若超过,则根据所述标准意图确定目标应答。
- 如权利要求9所述的智能客服多轮问答设备,其特征在于,所述计算所述信号意图和所述标准意图之间的第一相似度的步骤之前包括:若所述检测结果为存在信号,但所述识别结果为不存在命名实体,则判断所述信号是否包括命名实体;若所述信号不包括所述命名实体,则发出命名实体问询,并接收用户根据所述命名实体问询做出的命名实体回复;根据所述命名实体回复和所述目标问题中的信号确定信号意图。
- 如权利要求9所述的智能客服多轮问答设备,其特征在于,所述计算所述信号意图和所述标准意图之间的第一相似度的步骤包括:将所述信号意图和所述标准意图通过长期短期记忆网络模型进行语义特征提取,获得信号语义向量和标准语义向量;计算所述信号语义向量和标准语义向量之间的余弦相似度,并将所述余弦相似度作为所述信号意图和所述标准意图之间的第一相似度。
- 如权利要求11所述的智能客服多轮问答设备,其特征在于,所述对所述目标问题进行命名实体识别,获得识别结果的步骤包括:将所述目标问题通过所述长期短期记忆网络模型进行序列特征提取;将提取出的序列特征通过条件随机场算法进行实体概率计算,并判断实体概率最大值是否超过预设概率阈值;若所述实体概率最大值超过所述预设概率阈值,则认定所述实体概率最大值对应的特征为所述目标问题的命名实体,获得识别结果为存在命名实体;若所述实体概率最大值未超过所述预设概率阈值,则获得识别结果为不存在命名实体。
- 如权利要求8所述的智能客服多轮问答设备,其特征在于,所述从知识库中查找与所述目标问题匹配的标准意图,并获取所述标准意图与所述目标问题之间的匹配程度的步骤包括:通过ES检索从知识库中查找与所述目标问题匹配的候选意图集合;计算所述目标问题与所述候选意图集合中的候选意图之间的第二相似度;将所述第二相似度最高的候选意图作为与所述目标问题匹配的标准意图,并获取最高的第二相似度作为所述标准意图与所述目标问题之间的匹配程度。
- 一种存储介质,其特征在于,所述存储介质上存储有智能客服多轮问答可读指令,所述智能客服多轮问答可读指令被处理器执行,以实现以下步骤:获取用户当前轮次的目标问题;从知识库中查找与所述目标问题匹配的标准意图,并获取所述标准意图与所述目标问题之间的匹配程度;判断所述标准意图与所述目标问题之间的匹配程度是否超过预设匹配阈值;若未超过,则对所述目标问题进行命名实体识别,获得识别结果;检测是否存在所述当前轮次之前的至少一轮用户问题中继承的信号,获得检测结果;根据所述识别结果、所述检测结果、所述目标问题和所述标准意图确定目标应答。
- 如权利要求14所述的存储介质,其特征在于,所述根据所述识别结果、所述检测结果、所述目标问题和所述标准意图确定目标应答的步骤包括:若所述识别结果为存在命名实体,并且所述检测结果为存在信号,则根据所述目标问题中的命名实体和信号确定信号意图;计算所述信号意图和所述标准意图之间的第一相似度;判断所述第一相似度是否超过预设相似度阈值;若超过,则根据所述标准意图确定目标应答。
- 如权利要求15所述的存储介质,其特征在于,所述计算所述信号意 图和所述标准意图之间的第一相似度的步骤之前包括:若所述检测结果为存在信号,但所述识别结果为不存在命名实体,则判断所述信号是否包括命名实体;若所述信号不包括所述命名实体,则发出命名实体问询,并接收用户根据所述命名实体问询做出的命名实体回复;根据所述命名实体回复和所述目标问题中的信号确定信号意图。
- 如权利要求15所述的存储介质,其特征在于,所述计算所述信号意图和所述标准意图之间的第一相似度的步骤包括:将所述信号意图和所述标准意图通过长期短期记忆网络模型进行语义特征提取,获得信号语义向量和标准语义向量;计算所述信号语义向量和标准语义向量之间的余弦相似度,并将所述余弦相似度作为所述信号意图和所述标准意图之间的第一相似度。
- 如权利要求17所述的存储介质,其特征在于,所述对所述目标问题进行命名实体识别,获得识别结果的步骤包括:将所述目标问题通过所述长期短期记忆网络模型进行序列特征提取;将提取出的序列特征通过条件随机场算法进行实体概率计算,并判断实体概率最大值是否超过预设概率阈值;若所述实体概率最大值超过所述预设概率阈值,则认定所述实体概率最大值对应的特征为所述目标问题的命名实体,获得识别结果为存在命名实体;若所述实体概率最大值未超过所述预设概率阈值,则获得识别结果为不存在命名实体。
- 如权利要求14所述的存储介质,其特征在于,所述从知识库中查找与所述目标问题匹配的标准意图,并获取所述标准意图与所述目标问题之间的匹配程度的步骤包括:通过ES检索从知识库中查找与所述目标问题匹配的候选意图集合;计算所述目标问题与所述候选意图集合中的候选意图之间的第二相似度;将所述第二相似度最高的候选意图作为与所述目标问题匹配的标准意图,并获取最高的第二相似度作为所述标准意图与所述目标问题之间的匹配程度。
- 一种智能客服多轮问答装置,其特征在于,所述智能客服多轮问答装置包括:获取模块,用于获取用户当前轮次的目标问题;查找模块,用于从知识库中查找与所述目标问题匹配的标准意图,并获取所述标准意图与所述目标问题之间的匹配程度;判断模块,用于判断所述标准意图与所述目标问题之间的匹配程度是否超过预设匹配阈值;识别模块,用于若未超过,则对所述目标问题进行命名实体识别,获得识别结果;检测模块,用于检测是否存在所述当前轮次之前的至少一轮用户问题中继承的信号,获得检测结果;确定模块,用于根据所述识别结果、所述检测结果、所述目标问题和所述标准意图确定目标应答。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810722735.3 | 2018-07-03 | ||
| CN201810722735.3A CN109727041B (zh) | 2018-07-03 | 2018-07-03 | 智能客服多轮问答方法、设备、存储介质及装置 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020006835A1 true WO2020006835A1 (zh) | 2020-01-09 |
Family
ID=66294539
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2018/102053 Ceased WO2020006835A1 (zh) | 2018-07-03 | 2018-08-24 | 智能客服多轮问答方法、设备、存储介质及装置 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109727041B (zh) |
| WO (1) | WO2020006835A1 (zh) |
Cited By (38)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111427996A (zh) * | 2020-03-02 | 2020-07-17 | 云知声智能科技股份有限公司 | 一种人机交互文本中抽取日期时间的方法和装置 |
| CN111444341A (zh) * | 2020-03-16 | 2020-07-24 | 中国平安人寿保险股份有限公司 | 用户画像构建方法、装置、设备及可读存储介质 |
| CN111552880A (zh) * | 2020-04-30 | 2020-08-18 | 杭州网易再顾科技有限公司 | 基于知识图谱的数据处理方法、装置、介质及电子设备 |
| CN111563150A (zh) * | 2020-04-30 | 2020-08-21 | 广东美的制冷设备有限公司 | 空调器知识库更新方法、空调器、服务器及系统 |
| CN111694937A (zh) * | 2020-04-26 | 2020-09-22 | 平安科技(深圳)有限公司 | 基于人工智能的面试方法、装置、计算机设备及存储介质 |
| CN111723559A (zh) * | 2020-06-19 | 2020-09-29 | 苏州思必驰信息科技有限公司 | 一种实时信息抽取方法及装置 |
| CN111857668A (zh) * | 2020-07-24 | 2020-10-30 | 高浩然 | 效果广告机制的智能网页客服系统 |
| CN112035613A (zh) * | 2020-08-28 | 2020-12-04 | 光大科技有限公司 | 基于多轮对话的信息推送方法及装置、存储介质、电子装置 |
| CN112256824A (zh) * | 2020-09-17 | 2021-01-22 | 国网安徽省电力有限公司 | 一种用于机器人服务的业务引导方法、系统和存储单元 |
| CN112307187A (zh) * | 2020-12-08 | 2021-02-02 | 浙江百应科技有限公司 | 一种基于智能客服辅助交互的方法 |
| CN112417114A (zh) * | 2020-11-11 | 2021-02-26 | 北京沃东天骏信息技术有限公司 | 一种应答方法、装置、设备及计算机可读存储介质 |
| CN112948555A (zh) * | 2021-03-03 | 2021-06-11 | 北京奇艺世纪科技有限公司 | 人机交互方法、装置、电子设备及存储介质 |
| CN113033664A (zh) * | 2021-03-26 | 2021-06-25 | 网易(杭州)网络有限公司 | 问答模型训练方法、问答方法、装置、设备及存储介质 |
| CN113157890A (zh) * | 2021-04-25 | 2021-07-23 | 深圳壹账通智能科技有限公司 | 智能问答方法、装置、电子设备及可读存储介质 |
| CN113344125A (zh) * | 2021-06-29 | 2021-09-03 | 中国平安人寿保险股份有限公司 | 长文本匹配识别方法、装置、电子设备及存储介质 |
| CN113379229A (zh) * | 2021-06-08 | 2021-09-10 | 北京沃东天骏信息技术有限公司 | 一种资源调度方法和装置 |
| CN113468306A (zh) * | 2021-06-30 | 2021-10-01 | 西安乾阳电子科技有限公司 | 语音对话方法、装置、电子设备及存储介质 |
| CN113516515A (zh) * | 2021-07-21 | 2021-10-19 | 深圳追一科技有限公司 | 信息推送方法、装置、系统、电子设备及存储介质 |
| CN113761144A (zh) * | 2020-11-16 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | 应答信息确定方法和装置 |
| CN113781061A (zh) * | 2020-06-17 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | 一种信息推送管理方法和装置 |
| CN113961591A (zh) * | 2021-09-15 | 2022-01-21 | 北京三快在线科技有限公司 | 信息处理方法、装置、电子设备及存储介质 |
| CN113961667A (zh) * | 2021-09-23 | 2022-01-21 | 哈尔滨工业大学(深圳) | 一种基于Bert的动态阈值调整的智能问答系统 |
| CN114168723A (zh) * | 2021-11-29 | 2022-03-11 | 神思电子技术股份有限公司 | 一种用于解决多轮对话中虚槽值的方法、设备及介质 |
| CN114187903A (zh) * | 2021-11-12 | 2022-03-15 | 北京百度网讯科技有限公司 | 语音交互的方法、装置、系统、电子设备及存储介质 |
| CN114490972A (zh) * | 2021-12-30 | 2022-05-13 | 北京五八信息技术有限公司 | 一种消息处理方法、装置、电子设备和存储介质 |
| CN114596854A (zh) * | 2022-02-22 | 2022-06-07 | 平安科技(深圳)有限公司 | 基于全双工通信协议的语音处理方法及系统、计算机设备 |
| CN115344671A (zh) * | 2022-08-22 | 2022-11-15 | 平安科技(深圳)有限公司 | 智能问答方法、装置、计算机设备及存储介质 |
| CN115641875A (zh) * | 2022-10-17 | 2023-01-24 | 北京百度网讯科技有限公司 | 语音信息处理方法、装置、设备、存储介质以及程序产品 |
| CN115881099A (zh) * | 2021-09-29 | 2023-03-31 | 中国移动通信有限公司研究院 | 一种语音应答方法、装置、电子设备及可读存储介质 |
| CN116313162A (zh) * | 2023-05-12 | 2023-06-23 | 北京梆梆安全科技有限公司 | 一种基于ai模型的医疗问诊系统 |
| CN116860952A (zh) * | 2023-09-04 | 2023-10-10 | 富璟科技(深圳)有限公司 | 基于人工智能的rpa智能应答处理方法及系统 |
| CN118427333A (zh) * | 2024-07-04 | 2024-08-02 | 国网湖北省电力有限公司信息通信公司 | 一种智能语音客服实现方法和装置 |
| CN118485447A (zh) * | 2024-05-30 | 2024-08-13 | 浙江英集动力科技有限公司 | 一种供热数字人以及基于供热数字人的客服处理方法 |
| CN118760759A (zh) * | 2024-09-06 | 2024-10-11 | 阿里云飞天(杭州)云计算技术有限公司 | 面向文档的问答方法、装置、电子设备、存储介质及产品 |
| CN119441464A (zh) * | 2025-01-09 | 2025-02-14 | 浙江孚临科技有限公司 | 一种在问答中多轮对话的意图识别方法 |
| WO2025123631A1 (zh) * | 2023-12-13 | 2025-06-19 | 百度智能云(成都)科技有限公司 | 基于llm的意图识别方法、装置、设备和存储介质 |
| CN120911609A (zh) * | 2025-07-29 | 2025-11-07 | 广州未来一手网络科技有限公司 | 基于难度学习的智能客服引导方法、系统、设备及介质 |
| CN121146095A (zh) * | 2025-11-18 | 2025-12-16 | 船舶信息研究中心(中国船舶集团有限公司第七一四研究所) | 多轮问答下的大模型多路检索问答参数与数据源调优方法 |
Families Citing this family (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245216A (zh) * | 2019-06-13 | 2019-09-17 | 出门问问信息科技有限公司 | 用于问答系统的语义匹配方法、装置、设备及存储介质 |
| CN110503143B (zh) * | 2019-08-14 | 2024-03-19 | 平安科技(深圳)有限公司 | 基于意图识别的阈值选取方法、设备、存储介质及装置 |
| CN110489538B (zh) * | 2019-08-27 | 2020-12-25 | 腾讯科技(深圳)有限公司 | 基于人工智能的语句应答方法、装置及电子设备 |
| CN110704588B (zh) * | 2019-09-04 | 2023-05-30 | 平安科技(深圳)有限公司 | 基于长短期记忆网络的多轮对话语义分析方法和系统 |
| CN110619041A (zh) * | 2019-09-16 | 2019-12-27 | 出门问问信息科技有限公司 | 一种智能对话方法、装置以及计算机可读存储介质 |
| CN111143524A (zh) * | 2019-12-06 | 2020-05-12 | 联想(北京)有限公司 | 一种用户意图确定方法及电子设备 |
| CN110765343A (zh) * | 2019-12-10 | 2020-02-07 | 北京中电普华信息技术有限公司 | 一种语义检索方法及装置 |
| CN111191016B (zh) * | 2019-12-27 | 2023-06-02 | 车智互联(北京)科技有限公司 | 一种多轮对话处理方法、装置及计算设备 |
| CN111324693A (zh) * | 2020-01-21 | 2020-06-23 | 招商银行股份有限公司 | 智能应答方法、装置及计算机可读存储介质 |
| CN111353017A (zh) * | 2020-02-20 | 2020-06-30 | 上海智臻智能网络科技股份有限公司 | 智能交互方法和装置 |
| CN111429157A (zh) * | 2020-03-27 | 2020-07-17 | 上海东普信息科技有限公司 | 投诉工单的评价处理方法、装置、设备及存储介质 |
| CN111695354B (zh) * | 2020-05-20 | 2026-04-21 | 平安科技(深圳)有限公司 | 基于命名实体的文本问答方法、装置及可读存储介质 |
| CN111708870A (zh) * | 2020-05-27 | 2020-09-25 | 盛视科技股份有限公司 | 基于深度神经网络的问答方法、装置及存储介质 |
| CN111897930A (zh) * | 2020-06-13 | 2020-11-06 | 南京奥拓电子科技有限公司 | 一种自动问答方法与系统、智能设备及存储介质 |
| CN111723190A (zh) * | 2020-06-29 | 2020-09-29 | 深圳壹账通智能科技有限公司 | 信息交互方法、电子设备及存储介质 |
| CN112148848B (zh) * | 2020-08-28 | 2024-12-10 | 出门问问创新科技有限公司 | 一种问答处理方法及装置 |
| CN112183075B (zh) * | 2020-10-10 | 2023-06-30 | 网易(杭州)网络有限公司 | 一种对话中的槽提取方法、装置、电子设备及存储介质 |
| CN112256825B (zh) * | 2020-10-19 | 2023-06-16 | 平安科技(深圳)有限公司 | 医疗领域多轮对话智能问答方法、装置和计算机设备 |
| CN112685546B (zh) * | 2020-12-29 | 2023-10-31 | 王福山 | 人机多轮对话方法、装置及计算机可读存储介质 |
| CN113360620A (zh) * | 2021-06-17 | 2021-09-07 | 北京一维大成科技有限公司 | 一种智能客服方法、装置以及设备 |
| CN113360590B (zh) * | 2021-06-22 | 2024-03-12 | 北京百度网讯科技有限公司 | 兴趣点信息的更新方法、装置、电子设备及存储介质 |
| CN113420136A (zh) * | 2021-06-22 | 2021-09-21 | 中国工商银行股份有限公司 | 一种对话方法、系统、电子设备、存储介质和程序产品 |
| CN113806508A (zh) * | 2021-09-17 | 2021-12-17 | 平安普惠企业管理有限公司 | 基于人工智能的多轮对话方法、装置及存储介质 |
| CN114678014A (zh) * | 2022-03-23 | 2022-06-28 | 平安普惠企业管理有限公司 | 意图识别方法、装置、计算机设备及计算机可读存储介质 |
| CN115174748A (zh) * | 2022-06-27 | 2022-10-11 | 深圳市北科瑞声科技股份有限公司 | 基于语义识别的语音外呼方法、装置、设备及介质 |
| CN115240676B (zh) * | 2022-08-02 | 2026-01-02 | 中国平安人寿保险股份有限公司 | 智能外呼方法、装置、计算机设备及存储介质 |
| CN117235218A (zh) * | 2023-09-14 | 2023-12-15 | 杭州网易再顾科技有限公司 | 问答方法、介质、装置和计算设备 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102624675A (zh) * | 2011-01-27 | 2012-08-01 | 腾讯科技(深圳)有限公司 | 自助式客服系统、方法 |
| CN107908803A (zh) * | 2017-12-26 | 2018-04-13 | 上海智臻智能网络科技股份有限公司 | 问答交互的响应方法及装置、存储介质、终端 |
| US20180143968A1 (en) * | 2016-11-24 | 2018-05-24 | Institute For Information Industry | System, method and non-transitory computer readable storage medium for conversation analysis |
| CN108073600A (zh) * | 2016-11-11 | 2018-05-25 | 阿里巴巴集团控股有限公司 | 一种智能问答交互方法、装置以及电子设备 |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10127274B2 (en) * | 2016-02-08 | 2018-11-13 | Taiger Spain Sl | System and method for querying questions and answers |
| CN106649739B (zh) * | 2016-12-23 | 2020-09-11 | 广东惠禾科技发展有限公司 | 多轮交互信息继承识别方法、装置以及交互系统 |
| CN107193978A (zh) * | 2017-05-26 | 2017-09-22 | 武汉泰迪智慧科技有限公司 | 一种基于深度学习的多轮自动聊天对话方法及系统 |
| CN108090177B (zh) * | 2017-12-15 | 2020-05-05 | 上海智臻智能网络科技股份有限公司 | 多轮问答系统的生成方法、设备、介质及多轮问答系统 |
-
2018
- 2018-07-03 CN CN201810722735.3A patent/CN109727041B/zh active Active
- 2018-08-24 WO PCT/CN2018/102053 patent/WO2020006835A1/zh not_active Ceased
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102624675A (zh) * | 2011-01-27 | 2012-08-01 | 腾讯科技(深圳)有限公司 | 自助式客服系统、方法 |
| CN108073600A (zh) * | 2016-11-11 | 2018-05-25 | 阿里巴巴集团控股有限公司 | 一种智能问答交互方法、装置以及电子设备 |
| US20180143968A1 (en) * | 2016-11-24 | 2018-05-24 | Institute For Information Industry | System, method and non-transitory computer readable storage medium for conversation analysis |
| CN107908803A (zh) * | 2017-12-26 | 2018-04-13 | 上海智臻智能网络科技股份有限公司 | 问答交互的响应方法及装置、存储介质、终端 |
Cited By (52)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111427996B (zh) * | 2020-03-02 | 2023-10-20 | 云知声智能科技股份有限公司 | 一种人机交互文本中抽取日期时间的方法和装置 |
| CN111427996A (zh) * | 2020-03-02 | 2020-07-17 | 云知声智能科技股份有限公司 | 一种人机交互文本中抽取日期时间的方法和装置 |
| CN111444341A (zh) * | 2020-03-16 | 2020-07-24 | 中国平安人寿保险股份有限公司 | 用户画像构建方法、装置、设备及可读存储介质 |
| CN111444341B (zh) * | 2020-03-16 | 2024-04-12 | 中国平安人寿保险股份有限公司 | 用户画像构建方法、装置、设备及可读存储介质 |
| CN111694937A (zh) * | 2020-04-26 | 2020-09-22 | 平安科技(深圳)有限公司 | 基于人工智能的面试方法、装置、计算机设备及存储介质 |
| CN111563150A (zh) * | 2020-04-30 | 2020-08-21 | 广东美的制冷设备有限公司 | 空调器知识库更新方法、空调器、服务器及系统 |
| CN111552880B (zh) * | 2020-04-30 | 2023-06-30 | 杭州网易再顾科技有限公司 | 基于知识图谱的数据处理方法、装置、介质及电子设备 |
| CN111552880A (zh) * | 2020-04-30 | 2020-08-18 | 杭州网易再顾科技有限公司 | 基于知识图谱的数据处理方法、装置、介质及电子设备 |
| CN111563150B (zh) * | 2020-04-30 | 2024-04-16 | 广东美的制冷设备有限公司 | 空调器知识库更新方法、空调器、服务器及系统 |
| CN113781061B (zh) * | 2020-06-17 | 2024-07-19 | 北京沃东天骏信息技术有限公司 | 一种信息推送管理方法和装置 |
| CN113781061A (zh) * | 2020-06-17 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | 一种信息推送管理方法和装置 |
| CN111723559B (zh) * | 2020-06-19 | 2023-06-23 | 思必驰科技股份有限公司 | 一种实时信息抽取方法及装置 |
| CN111723559A (zh) * | 2020-06-19 | 2020-09-29 | 苏州思必驰信息科技有限公司 | 一种实时信息抽取方法及装置 |
| CN111857668A (zh) * | 2020-07-24 | 2020-10-30 | 高浩然 | 效果广告机制的智能网页客服系统 |
| CN112035613A (zh) * | 2020-08-28 | 2020-12-04 | 光大科技有限公司 | 基于多轮对话的信息推送方法及装置、存储介质、电子装置 |
| CN112035613B (zh) * | 2020-08-28 | 2023-09-12 | 光大科技有限公司 | 基于多轮对话的信息推送方法及装置、存储介质、电子装置 |
| CN112256824A (zh) * | 2020-09-17 | 2021-01-22 | 国网安徽省电力有限公司 | 一种用于机器人服务的业务引导方法、系统和存储单元 |
| CN112256824B (zh) * | 2020-09-17 | 2023-10-20 | 国网安徽省电力有限公司 | 一种用于机器人服务的业务引导方法、系统和存储介质 |
| CN112417114A (zh) * | 2020-11-11 | 2021-02-26 | 北京沃东天骏信息技术有限公司 | 一种应答方法、装置、设备及计算机可读存储介质 |
| CN113761144A (zh) * | 2020-11-16 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | 应答信息确定方法和装置 |
| CN112307187A (zh) * | 2020-12-08 | 2021-02-02 | 浙江百应科技有限公司 | 一种基于智能客服辅助交互的方法 |
| CN112948555A (zh) * | 2021-03-03 | 2021-06-11 | 北京奇艺世纪科技有限公司 | 人机交互方法、装置、电子设备及存储介质 |
| CN112948555B (zh) * | 2021-03-03 | 2023-09-01 | 北京奇艺世纪科技有限公司 | 人机交互方法、装置、电子设备及存储介质 |
| CN113033664A (zh) * | 2021-03-26 | 2021-06-25 | 网易(杭州)网络有限公司 | 问答模型训练方法、问答方法、装置、设备及存储介质 |
| CN113157890B (zh) * | 2021-04-25 | 2024-06-11 | 深圳壹账通智能科技有限公司 | 智能问答方法、装置、电子设备及可读存储介质 |
| CN113157890A (zh) * | 2021-04-25 | 2021-07-23 | 深圳壹账通智能科技有限公司 | 智能问答方法、装置、电子设备及可读存储介质 |
| CN113379229A (zh) * | 2021-06-08 | 2021-09-10 | 北京沃东天骏信息技术有限公司 | 一种资源调度方法和装置 |
| CN113344125B (zh) * | 2021-06-29 | 2024-04-05 | 中国平安人寿保险股份有限公司 | 长文本匹配识别方法、装置、电子设备及存储介质 |
| CN113344125A (zh) * | 2021-06-29 | 2021-09-03 | 中国平安人寿保险股份有限公司 | 长文本匹配识别方法、装置、电子设备及存储介质 |
| CN113468306A (zh) * | 2021-06-30 | 2021-10-01 | 西安乾阳电子科技有限公司 | 语音对话方法、装置、电子设备及存储介质 |
| CN113516515B (zh) * | 2021-07-21 | 2024-02-27 | 深圳追一科技有限公司 | 信息推送方法、装置、系统、电子设备及存储介质 |
| CN113516515A (zh) * | 2021-07-21 | 2021-10-19 | 深圳追一科技有限公司 | 信息推送方法、装置、系统、电子设备及存储介质 |
| CN113961591A (zh) * | 2021-09-15 | 2022-01-21 | 北京三快在线科技有限公司 | 信息处理方法、装置、电子设备及存储介质 |
| CN113961667A (zh) * | 2021-09-23 | 2022-01-21 | 哈尔滨工业大学(深圳) | 一种基于Bert的动态阈值调整的智能问答系统 |
| CN115881099A (zh) * | 2021-09-29 | 2023-03-31 | 中国移动通信有限公司研究院 | 一种语音应答方法、装置、电子设备及可读存储介质 |
| CN114187903A (zh) * | 2021-11-12 | 2022-03-15 | 北京百度网讯科技有限公司 | 语音交互的方法、装置、系统、电子设备及存储介质 |
| CN114168723A (zh) * | 2021-11-29 | 2022-03-11 | 神思电子技术股份有限公司 | 一种用于解决多轮对话中虚槽值的方法、设备及介质 |
| CN114490972A (zh) * | 2021-12-30 | 2022-05-13 | 北京五八信息技术有限公司 | 一种消息处理方法、装置、电子设备和存储介质 |
| CN114596854A (zh) * | 2022-02-22 | 2022-06-07 | 平安科技(深圳)有限公司 | 基于全双工通信协议的语音处理方法及系统、计算机设备 |
| CN115344671A (zh) * | 2022-08-22 | 2022-11-15 | 平安科技(深圳)有限公司 | 智能问答方法、装置、计算机设备及存储介质 |
| CN115641875A (zh) * | 2022-10-17 | 2023-01-24 | 北京百度网讯科技有限公司 | 语音信息处理方法、装置、设备、存储介质以及程序产品 |
| CN116313162A (zh) * | 2023-05-12 | 2023-06-23 | 北京梆梆安全科技有限公司 | 一种基于ai模型的医疗问诊系统 |
| CN116313162B (zh) * | 2023-05-12 | 2023-08-18 | 北京梆梆安全科技有限公司 | 一种基于ai模型的医疗问诊系统 |
| CN116860952B (zh) * | 2023-09-04 | 2023-11-03 | 富璟科技(深圳)有限公司 | 基于人工智能的rpa智能应答处理方法及系统 |
| CN116860952A (zh) * | 2023-09-04 | 2023-10-10 | 富璟科技(深圳)有限公司 | 基于人工智能的rpa智能应答处理方法及系统 |
| WO2025123631A1 (zh) * | 2023-12-13 | 2025-06-19 | 百度智能云(成都)科技有限公司 | 基于llm的意图识别方法、装置、设备和存储介质 |
| CN118485447A (zh) * | 2024-05-30 | 2024-08-13 | 浙江英集动力科技有限公司 | 一种供热数字人以及基于供热数字人的客服处理方法 |
| CN118427333A (zh) * | 2024-07-04 | 2024-08-02 | 国网湖北省电力有限公司信息通信公司 | 一种智能语音客服实现方法和装置 |
| CN118760759A (zh) * | 2024-09-06 | 2024-10-11 | 阿里云飞天(杭州)云计算技术有限公司 | 面向文档的问答方法、装置、电子设备、存储介质及产品 |
| CN119441464A (zh) * | 2025-01-09 | 2025-02-14 | 浙江孚临科技有限公司 | 一种在问答中多轮对话的意图识别方法 |
| CN120911609A (zh) * | 2025-07-29 | 2025-11-07 | 广州未来一手网络科技有限公司 | 基于难度学习的智能客服引导方法、系统、设备及介质 |
| CN121146095A (zh) * | 2025-11-18 | 2025-12-16 | 船舶信息研究中心(中国船舶集团有限公司第七一四研究所) | 多轮问答下的大模型多路检索问答参数与数据源调优方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109727041A (zh) | 2019-05-07 |
| CN109727041B (zh) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020006835A1 (zh) | 智能客服多轮问答方法、设备、存储介质及装置 | |
| CN110334241B (zh) | 客服录音的质检方法、装置、设备及计算机可读存储介质 | |
| US12026194B1 (en) | Query modification based on non-textual resource context | |
| US11436489B2 (en) | Combining statistical methods with a knowledge graph | |
| US9911082B2 (en) | Question classification and feature mapping in a deep question answering system | |
| US9141662B2 (en) | Intelligent evidence classification and notification in a deep question answering system | |
| JP6759844B2 (ja) | 画像を施設に対して関連付けるシステム、方法、プログラム及び装置 | |
| US20250094460A1 (en) | Query answering method based on large model, electronic device, storage medium, and intelligent agent | |
| US8606780B2 (en) | Image re-rank based on image annotations | |
| CN111522915A (zh) | 中文事件的抽取方法、装置、设备及存储介质 | |
| CN111708942B (zh) | 多媒体资源推送方法、装置、服务器及存储介质 | |
| CN111737443B (zh) | 答案文本的处理方法和装置、关键文本的确定方法 | |
| CN120706544A (zh) | 智能文档问答方法、装置、设备及存储介质 | |
| CN113065025A (zh) | 视频查重方法、装置、设备及存储介质 | |
| CN117373698A (zh) | 基于会话交互的导医信息获取方法、装置和设备 | |
| CN117216256A (zh) | 意图识别方法、装置、设备及计算机存储介质 | |
| CN117743505A (zh) | 查询词改写模型的训练方法、查询方法及相关产品 | |
| CN112541091A (zh) | 图像搜索方法、装置、服务器和存储介质 | |
| CN115186075A (zh) | 一种保险知识库建立及问题查询方法、设备及存储介质 | |
| JP2020016960A (ja) | 推定装置、推定方法及び推定プログラム | |
| CN107908724B (zh) | 一种数据模型匹配方法、装置、设备及存储介质 | |
| CN117076602A (zh) | 基于多媒体内容的内容生成方法、装置、设备和介质 | |
| CN116975405A (zh) | 搜索词处理方法、装置、设备、存储介质和程序产品 | |
| US20260057025A1 (en) | Content query | |
| CN120561220A (zh) | 一种基于关键字匹配的问答结果检索方法、装置及设备 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18925335 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 18925335 Country of ref document: EP Kind code of ref document: A1 |