WO2021051508A1 - Procédé et appareil de génération de dialogue de robot, support de stockage lisible et robot - Google Patents

Procédé et appareil de génération de dialogue de robot, support de stockage lisible et robot Download PDF

Info

Publication number
WO2021051508A1
WO2021051508A1 PCT/CN2019/116630 CN2019116630W WO2021051508A1 WO 2021051508 A1 WO2021051508 A1 WO 2021051508A1 CN 2019116630 W CN2019116630 W CN 2019116630W WO 2021051508 A1 WO2021051508 A1 WO 2021051508A1
Authority
WO
WIPO (PCT)
Prior art keywords
sentence
word
vector
dialogue
cluster
Prior art date
Application number
PCT/CN2019/116630
Other languages
English (en)
Chinese (zh)
Inventor
于凤英
王健宗
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2021051508A1 publication Critical patent/WO2021051508A1/fr

Links

Images

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
    • G06F16/3346—Query execution using probabilistic model
    • 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

Definitions

  • This application belongs to the field of computer technology, and in particular relates to a method and device for generating a robot dialogue, a computer non-volatile readable storage medium, and a robot.
  • clustering the sentences generated in the dialogue process is the basis to ensure that the robot can conduct effective dialogue.
  • the method for clustering sentences is generally based on keyword matching. This method can only take into account the local characteristics of sentences, that is, the characteristics of keywords. The lack of overall consideration of sentences leads to clustering. The accuracy of the class results is low, and the accuracy of the reply sentences generated by the robot based on such clustering results will also be low, which is difficult to meet the needs of actual dialogue scenarios.
  • the embodiments of the present application provide a method and device for generating a robot dialogue, a computer non-volatile readable storage medium, and a robot, so as to solve the problem of low accuracy of response sentences generated by robots in the prior art. problem.
  • the first aspect of the embodiments of the present application provides a method for generating a robot dialogue, which is applied to a preset robot, and the method includes:
  • Obtain a set of sentences to be processed from a preset database the set of sentences includes SN sentences, and SN is an integer greater than 1;
  • the second aspect of the embodiments of the present application provides a device for generating a robot dialogue, which may include modules for implementing the steps of the method for generating a robot dialogue.
  • a third aspect of the embodiments of the present application provides a computer non-volatile readable storage medium, the computer non-volatile readable storage medium stores computer readable instructions, and the computer readable instructions are executed by a processor When realizing the steps of the robot dialog generation method described above.
  • the fourth aspect of the embodiments of the present application provides a robot, including a memory, a processor, and computer-readable instructions stored in the memory and running on the processor, and the processor executes the computer When reading instructions, the steps of the above-mentioned robot dialogue generation method are realized.
  • the embodiment of the application has the beneficial effect that: in the calculation process of the sentence vector, the embodiment of the application fully considers the word vector of each word and the probability of each word, and can represent the sentence as a whole.
  • the embodiment of the application greatly improve the accuracy of the clustering results.
  • the accuracy of the reply sentences generated by the robot based on such clustering results will also be greatly improved.
  • FIG. 1 is a flowchart of an embodiment of a method for generating a robot dialog in an embodiment of the application
  • Figure 2 is a schematic flow chart of clustering each sentence according to the sentence vector
  • FIG. 3 is a structural diagram of an embodiment of an apparatus for generating a robot dialog in an embodiment of the application
  • Fig. 4 is a schematic block diagram of a robot in an embodiment of the application.
  • the method for generating a robot dialogue in the embodiments of the present application can be applied to a preset dialogue robot (Chatterbot), which is a robot used to simulate human dialogue or chat.
  • the dialogue robot can be set in an exhibition hall, a company reception desk, an airport information desk, a hospital information desk, etc., to provide convenient consulting services for passing users.
  • an embodiment of a method for generating a robot dialogue in an embodiment of the present application may include:
  • Step S101 After receiving a preset dialogue instruction, collect the dialogue sentence of the user.
  • the user can issue a dialogue instruction to the dialogue robot in the form of voice.
  • the dialogue robot receives the user’s voice, it can determine whether it includes preset keywords.
  • the keywords include but are not limited to words such as “please ask”, “consult”, “help”, etc. If the user’s voice If the keyword is included, it can be determined that the voice is a dialogue instruction issued by the user.
  • the user can also issue a dialogue instruction to the dialogue robot through the physical buttons or virtual buttons in the designated human-computer interaction interface.
  • the dialogue robot may include a touch screen for interacting with the user. To issue a dialogue instruction to the dialogue robot, a specific button displayed therein can be clicked.
  • the dialogue robot receives the dialogue instruction issued by the user, it can collect the dialogue sentence of the user through its own microphone, microphone and other voice collection devices.
  • Step S102 Obtain a set of sentences to be processed from a preset database.
  • the sentence set includes SN sentences, and SN is an integer greater than 1.
  • a database including massive instant messaging (IM) data can be established in advance, and the database contains as many instant messaging data generated during a certain statistical time period as possible.
  • IM massive instant messaging
  • the statistical time period can be set according to the actual situation, for example, it can be set to a time period within a week, a month, a quarter, or a year from the current moment.
  • Step S103 Perform word segmentation processing on each sentence in the sentence set to obtain each word set corresponding to each sentence.
  • Word segmentation processing refers to segmenting a sentence into individual words.
  • the sentence can be segmented according to a general dictionary to ensure that the separated words are all normal vocabulary. If the word is not in the dictionary, single words are separated .
  • both the forward and backward directions can be formed into words, such as "request for god”, it will be divided according to the statistical word frequency. If the word frequency of "requirement” is high, the word “requirement/shen” is divided, and if the word frequency of "quest for god" is high, it is divided into “must” /Pray for God".
  • the segmented words can be formed into a word set corresponding to the sentence.
  • Step S104 query the word vector of each word in each word set in the preset word vector database.
  • the word vector database is a database that records the correspondence between words and word vectors.
  • the word vector may be a corresponding word vector obtained by training the word according to the word2vec model. That is, the probability of occurrence of the word is expressed according to the context information of the word.
  • the training of word vectors is still based on the idea of word2vec. First, each word is represented as a 0-1 vector (one-hot) form, and then the word2vec model is trained with the word vector, and n-1 words are used to predict the nth word , The intermediate process obtained after the neural network model prediction is used as the word vector.
  • the one-hot vector of "celebration” is assumed to be [1,0,0,0,...,0] and the one-hot vector of "meeting” is [0,1,0,0,... ...,0], the one-hot vector for "smooth” is [0,0,1,0, whil,0], the vector for predicting "closing” [0,0,0,1,>,0],
  • the model is trained to generate the coefficient matrix W of the hidden layer.
  • the product of the one-hot vector of each word and the coefficient matrix is the word vector of the word.
  • the final form will be similar to "Celebrate [-0.28,0.34,-0.02, ......,0.92]" such a multi-dimensional vector.
  • Step S105 Count the probability of each word in each word set appearing in the sentence set.
  • Step S106 Calculate the sentence vector of each sentence according to the word vector of each word and the probability of each word appearing in the sentence set.
  • the maximum likelihood method can be used to estimate the sentence vector.
  • all word vectors are roughly uniformly distributed in the entire vector space, and the likelihood function of each sentence is constructed as shown below:
  • s is the sequence number of each sentence in the sentence set
  • 1 ⁇ s ⁇ SN, 1 ⁇ w ⁇ WN s , WN s is the number of words in the sth sentence
  • ⁇ is a preset constant
  • p( w) is the probability that the wth word in the sth sentence appears in the sentence set
  • v w is the word vector of the wth word in the sth sentence
  • v s is the sentence vector of the sth sentence
  • ⁇ v s ,v w > is the angle between the two vectors v s and v w
  • Z is the preset constant
  • Sentense s is the sth sentence
  • v s ) is the sth sentence
  • the likelihood function is the probability that the wth word in the sth sentence appears in the sentence set
  • v w is the word vector of the wth word in the sth sentence
  • v s is the sentence vector of the
  • ln is the natural logarithm function
  • word w is the wth word in the sth sentence
  • v s ) is the likelihood function of the wth word in the sth sentence.
  • the sentence vector of each sentence can be expressed as a weighted average of the word vectors of the words contained, namely:
  • the sentence vector obtained by the above method is its maximum likelihood estimate, or from the Bayesian point of view, the maximum posterior probability. Compared with the traditional simple average, this method takes into account the semantic level information, and the clustering effect is better; compared with the deep learning system, this method is more efficient and effective, and more importantly, it does not need to be labeled. Training data, sentence vectorization makes sentences can be calculated and clustered.
  • the sentence vector of each sentence can also be constructed as a sentence matrix of the sentence set, wherein the sentence vector of each sentence is used as a row of the sentence matrix, so The number of rows of the sentence matrix is consistent with the number of sentences included in the sentence set.
  • PCA Principal Component Analysis
  • u is the principal component in the sentence matrix
  • the updated sentence vector is obtained, that is, the sentence vector from which the principal component interference is removed. It should be noted that the sentence vector used in the subsequent steps refers to the updated sentence vector.
  • sentence vector of each sentence can also be normalized according to the following formula:
  • mean is the averaging function
  • var is the variance function
  • ⁇ norm is the preset constant
  • normalized sentence vector is obtained. It should be noted that the sentence vectors used in the subsequent steps all refer to the normalized sentence vectors.
  • sentence vector of each sentence can also be whitened according to the following formula:
  • VDV T cov(Matrix)
  • Matrix is the sentence matrix constructed from the sentence vectors of each sentence
  • cov is the function for finding the covariance matrix
  • ⁇ zca is the preset constant
  • I is the whitened sentence vector of the identity matrix. It should be noted that the sentence vectors used in the subsequent steps all refer to the whitened sentence vectors.
  • Step S107 Perform clustering processing on each sentence according to the sentence vector to obtain each cluster group.
  • step S107 may specifically include the following steps:
  • Step S1071 initialize the cluster center set.
  • cluster center set as shown below can be initialized:
  • k is the serial number of each cluster center, 1 ⁇ k ⁇ KN
  • KN is the preset number of cluster centers, 1 ⁇ KN ⁇ SN
  • the specific value can be set according to the actual situation, for example, it can be set Is 5, 10, 15, 20 or other values
  • c k (0) is the initialization vector of the k-th cluster center
  • T is the transposed symbol
  • Centre(0) is the initialized cluster center set.
  • Step S1072 update the cluster center set for the g th time.
  • the g-th update of the cluster center set can be performed according to the following formula:
  • Step S1073 Determine whether the set of cluster centers meets a preset convergence condition.
  • UpGdDis k,g VecDis(c k (g),c k (g-1))
  • VecDis is a function for finding the distance between two vectors
  • UpGdDis k,g is the g-th update distance of the k-th cluster center.
  • MaxDis g Max(UpGdDis 0,g ,UpGdDis 1,g ,...,UpGdDis k,g ,...,UpGdDis KN,g )
  • Max is a maximum value function
  • MaxDis g is the maximum update distance of the g-th cluster center set.
  • Thresh is a preset distance threshold, and its specific value can be set according to actual conditions. For example, it can be set to 0.1, 0.01, 0.001 or other values.
  • step S1074 and subsequent steps are performed, and if the set of cluster centers meets the convergence condition, step S1075 is performed.
  • Step S1074 Increase g by one counting unit.
  • Step S1075 Perform clustering processing on each sentence according to the cluster center set after the gth update to obtain each cluster group.
  • the distance between its sentence vector and the vector of each cluster center in the cluster center set can be calculated separately, and clustered to the cluster center with the smallest distance therefrom.
  • each sentence clustered to the same cluster center forms a clustering group, and the final clustering result can be obtained.
  • Step S108 Calculate the similarity between the dialogue sentence of the user and each cluster group respectively.
  • the sentence vector of the dialogue sentence of the user can be calculated, which is denoted as SenVec here.
  • the specific calculation process is similar to the process in step S103 to step S106, and you can refer to the foregoing content, which will not be repeated here.
  • Recip is a function for calculating the reciprocal
  • SimDeg k is the similarity between the dialogue sentence of the user and the k-th cluster group.
  • Step S109 Select a preferred group from each cluster group.
  • the preferred group is the cluster group with the greatest similarity to the dialogue sentences of the user, namely:
  • argmin is the smallest independent variable function
  • SelGroup is the serial number of the preferred group.
  • Step S110 Query the reply sentence corresponding to the dialogue sentence of the user in the preset preferred reply sentence set, and use the reply sentence to respond to the dialogue sentence of the user.
  • the set of preferred reply sentences is a set of reply sentences corresponding to the preferred group.
  • a set of reply sentences corresponding to each cluster group can be separately set in advance.
  • Each set of reply sentences includes a predetermined number of reply sentences, and each reply sentence is used to perform a certain preset specified sentence. answer.
  • the dialogue robot needs to respond to the user's dialogue sentence, it can calculate the distance between the sentence vector of the user's dialogue sentence and the sentence vector of each specified sentence, and determine the corresponding distance when the minimum value is obtained. Then, query the reply sentence corresponding to the specified sentence in the preferred reply sentence set, and use this reply sentence to respond to the dialog sentence of the user.
  • the word vector of each word and the probability of each word appearing are fully considered, which can characterize the characteristics of the sentence as a whole, and greatly improve the accuracy of the clustering result.
  • the accuracy of the reply sentences generated by the robot based on such clustering results will also be greatly improved.
  • FIG. 3 shows a structural diagram of an embodiment of a device for generating a robot dialog provided by an embodiment of the present application.
  • an apparatus for generating a robot dialog may include:
  • the dialogue sentence collection module 301 is used to collect the user's dialogue sentence after receiving a preset dialogue instruction
  • the sentence set obtaining module 302 is configured to obtain a sentence set to be processed from a preset database, the sentence set includes SN sentences, and SN is an integer greater than 1;
  • the word segmentation processing module 303 is configured to perform word segmentation processing on each sentence in the sentence set to obtain each word set corresponding to each sentence respectively;
  • the word vector query module 304 is used to query the word vector of each word in each word set in a preset word vector database
  • the probability statistics module 305 is used to separately count the probability of each word in each word set appearing in the sentence set;
  • the sentence vector calculation module 306 is configured to calculate the sentence vector of each sentence according to the word vector of each word and the probability of each word appearing in the sentence set;
  • the clustering processing module 307 is configured to perform clustering processing on each sentence according to the sentence vector to obtain each clustering group;
  • the similarity calculation module 308 is configured to calculate the similarity between the dialogue sentence of the user and each cluster group respectively;
  • the preferred group selection module 309 is configured to select a preferred group from each cluster group, and the preferred group is the cluster group with the greatest similarity to the dialog sentence of the user;
  • the dialogue response module 310 is used to query the reply sentence corresponding to the dialogue sentence of the user in the preset preferred reply sentence set, and use the reply sentence to respond to the dialogue sentence of the user, the preferred reply sentence
  • the set is a set of reply sentences corresponding to the preferred group.
  • the clustering processing module may include:
  • the initialization unit is used to initialize the cluster center set
  • An update unit configured to update the cluster center set for the g th time
  • a convergence judging unit configured to judge whether the set of cluster centers meets a preset convergence condition
  • a counting unit configured to increase g by one counting unit if the set of cluster centers does not meet the convergence condition
  • the clustering processing unit is configured to, if the cluster center set meets the convergence condition, perform clustering processing on each sentence according to the cluster center set after the gth update to obtain each cluster group.
  • the convergence judgment unit may include:
  • the first calculation subunit is used to calculate the g-th update distance of each cluster center
  • the second calculation subunit is used to calculate the g-th maximum update distance of the cluster center set
  • the convergence judgment subunit is used to judge whether the set of cluster centers meets the convergence condition.
  • the device for generating a robot dialogue may further include:
  • the matrix construction module is used to construct the sentence vector of each sentence into the sentence matrix of the sentence set;
  • the principal component calculation module is used to calculate the principal components in the sentence matrix
  • the vector update module is used to update the statement vector of each statement.
  • Fig. 4 shows a schematic block diagram of a robot provided by an embodiment of the present application. For ease of description, only parts related to the embodiment of the present application are shown.
  • the robot 4 may include: a processor 40, a memory 41, and computer-readable instructions 42 stored in the memory 41 and executable on the processor 40, such as executing the aforementioned robot dialogue. Generate computer-readable instructions for the method.
  • the processor 40 executes the computer-readable instructions 42, the steps in the above embodiments of the robot dialog generation method are implemented.
  • the computer-readable instructions 42 may be divided into one or more modules/units, and the one or more modules/units are stored in the memory 41 and executed by the processor 40, To complete this application.
  • the one or more modules/units may be a series of computer-readable instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer-readable instructions 42 in the robot 4.
  • Non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory may include random access memory (RAM) or external cache memory.
  • RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

Landscapes

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

Abstract

La présente invention concerne un procédé et un appareil de génération de dialogue de robot, un support de stockage non volatile lisible par ordinateur et un robot, qui se rapportent au domaine technique des ordinateurs. Après réception d'une instruction de dialogue prédéfinie, une formulation de dialogue d'un utilisateur est acquise ; un ensemble de formulations à traiter est obtenu ; un traitement de segmentation de mots est effectué respectivement sur chaque formulation dans l'ensemble de formulations pour obtenir chaque ensemble de mots correspondant à chaque formulation ; un vecteur de mot de chaque mot dans chaque ensemble de mots est interrogé respectivement ; la probabilité d'occurrence de chaque mot dans chaque ensemble de mots dans l'ensemble de formulations est comptée respectivement ; un vecteur de formulation de chaque formulation est calculé respectivement ; un traitement de groupement est effectué sur chaque formulation en fonction du vecteur de formulation pour obtenir chaque groupe de groupement ; la similarité entre la formulation de dialogue de l'utilisateur et chaque groupe de groupement est calculée respectivement ; et une formulation de réponse correspondant à la formulation de dialogue de l'utilisateur est interrogée, et il est répondu à la formulation de dialogue de l'utilisateur à l'aide de la formulation de réponse, de telle sorte que la précision d'une formulation de réponse générée par un robot en fonction d'un résultat de groupement est améliorée.
PCT/CN2019/116630 2019-09-18 2019-11-08 Procédé et appareil de génération de dialogue de robot, support de stockage lisible et robot WO2021051508A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910880859.9A CN110750629A (zh) 2019-09-18 2019-09-18 机器人对话生成方法、装置、可读存储介质及机器人
CN201910880859.9 2019-09-18

Publications (1)

Publication Number Publication Date
WO2021051508A1 true WO2021051508A1 (fr) 2021-03-25

Family

ID=69276649

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/116630 WO2021051508A1 (fr) 2019-09-18 2019-11-08 Procédé et appareil de génération de dialogue de robot, support de stockage lisible et robot

Country Status (2)

Country Link
CN (1) CN110750629A (fr)
WO (1) WO2021051508A1 (fr)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111694941B (zh) * 2020-05-22 2024-01-05 腾讯科技（深圳）有限公司 一种回复信息确定方法、装置、存储介质及电子设备
CN111858891A (zh) * 2020-07-23 2020-10-30 平安科技（深圳）有限公司 问答库构建方法、装置、电子设备及存储介质
CN112100677B (zh) * 2020-11-13 2021-02-05 支付宝(杭州)信息技术有限公司 隐私数据的保护方法、装置及电子设备
CN112328776A (zh) * 2021-01-04 2021-02-05 北京百度网讯科技有限公司 对话生成方法、装置、电子设备和存储介质
CN113239668B (zh) * 2021-05-31 2023-06-23 平安科技（深圳）有限公司 关键词智能提取方法、装置、计算机设备及存储介质
CN113723115B (zh) * 2021-09-30 2024-02-09 平安科技（深圳）有限公司 基于预训练模型的开放域问答预测方法及相关设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2017037602A (ja) * 2015-08-14 2017-02-16 Ｐｓソリューションズ株式会社 対話インターフェース
CN106844587A (zh) * 2017-01-11 2017-06-13 北京光年无限科技有限公司 一种用于对话交互系统的数据处理方法及装置
CN108345672A (zh) * 2018-02-09 2018-07-31 平安科技（深圳）有限公司 智能应答方法、电子装置及存储介质
CN109102809A (zh) * 2018-06-22 2018-12-28 北京光年无限科技有限公司 一种用于智能机器人的对话方法及系统
CN109766437A (zh) * 2018-12-07 2019-05-17 中科恒运股份有限公司 一种文本聚类方法、文本聚类装置及终端设备
CN109885664A (zh) * 2019-01-08 2019-06-14 厦门快商通信息咨询有限公司 一种智能对话方法、机器人对话系统、服务器及存储介质
CN109977207A (zh) * 2019-03-21 2019-07-05 网易（杭州）网络有限公司 对话生成方法、对话生成装置、电子设备及存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103810218B (zh) * 2012-11-14 2018-06-08 北京百度网讯科技有限公司 一种基于问题簇的自动问答方法和装置
CN105955965A (zh) * 2016-06-21 2016-09-21 上海智臻智能网络科技股份有限公司 问句信息处理方法及装置
JP6709748B2 (ja) * 2017-04-13 2020-06-17 日本電信電話株式会社 クラスタリング装置、回答候補生成装置、方法、及びプログラム
CN110008465B (zh) * 2019-01-25 2023-05-12 网经科技（苏州）有限公司 句子语义距离的度量方法
CN110096580B (zh) * 2019-04-24 2022-05-24 北京百度网讯科技有限公司 一种faq对话方法、装置及电子设备

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2017037602A (ja) * 2015-08-14 2017-02-16 Ｐｓソリューションズ株式会社 対話インターフェース
CN106844587A (zh) * 2017-01-11 2017-06-13 北京光年无限科技有限公司 一种用于对话交互系统的数据处理方法及装置
CN108345672A (zh) * 2018-02-09 2018-07-31 平安科技（深圳）有限公司 智能应答方法、电子装置及存储介质
CN109102809A (zh) * 2018-06-22 2018-12-28 北京光年无限科技有限公司 一种用于智能机器人的对话方法及系统
CN109766437A (zh) * 2018-12-07 2019-05-17 中科恒运股份有限公司 一种文本聚类方法、文本聚类装置及终端设备
CN109885664A (zh) * 2019-01-08 2019-06-14 厦门快商通信息咨询有限公司 一种智能对话方法、机器人对话系统、服务器及存储介质
CN109977207A (zh) * 2019-03-21 2019-07-05 网易（杭州）网络有限公司 对话生成方法、对话生成装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN110750629A (zh) 2020-02-04

Similar Documents

Publication Publication Date Title
WO2021051508A1 (fr) Procédé et appareil de génération de dialogue de robot, support de stockage lisible et robot
WO2020143844A1 (fr) Procédé et appareil d'analyse d'intention, terminal d'affichage et support de stockage lisible par ordinateur
US20240202446A1 (en) Method for training keyword extraction model, keyword extraction method, and computer device
US11093854B2 (en) Emoji recommendation method and device thereof
WO2020042925A1 (fr) Procédé et appareil de conversation entre humain et machine, dispositif électronique et support lisible par ordinateur
US11295090B2 (en) Multi-scale model for semantic matching
Geng et al. Facial age estimation by learning from label distributions
WO2020232877A1 (fr) Procédé et appareil de sélection d'une réponse à une question, dispositif informatique et support de stockage
CN105183833B (zh) 一种基于用户模型的微博文本推荐方法及其推荐装置
WO2020082560A1 (fr) Procédé, appareil et dispositif d'extraction de mot-clé de texte, ainsi que support de stockage lisible par ordinateur
JP2021532499A (ja) 機械学習に基づく医療データ分類方法、装置、コンピュータデバイス及び記憶媒体
US20170150235A1 (en) Jointly Modeling Embedding and Translation to Bridge Video and Language
US20020194158A1 (en) System and method for context-dependent probabilistic modeling of words and documents
CN110222560B (zh) 一种嵌入相似性损失函数的文本人员搜索方法
CN107832326B (zh) 一种基于深层卷积神经网络的自然语言问答方法
US11461613B2 (en) Method and apparatus for multi-document question answering
Li et al. A general framework for association analysis of heterogeneous data
CN107992477A (zh) 文本主题确定方法、装置及电子设备
JP2022063250A (ja) ＳｕｐｅｒＬｏｓｓ：堅牢なカリキュラム学習のための一般的な損失
US20170193197A1 (en) System and method for automatic unstructured data analysis from medical records
CN110795542A (zh) 对话方法及相关装置、设备
CN110705247A (zh) 基于χ2-C的文本相似度计算方法
Peng et al. Learning on probabilistic labels
Han et al. Conditional word embedding and hypothesis testing via bayes-by-backprop
WO2021253938A1 (fr) Procédé et appareil d'apprentissage de réseau neuronal, et procédé et appareil de reconnaissance vidéo

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: 19945647

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: 19945647

Country of ref document: EP

Kind code of ref document: A1