CN116049372A - Man-machine conversation method and device and electronic equipment - Google Patents
Man-machine conversation method and device and electronic equipment Download PDFInfo
- Publication number
- CN116049372A CN116049372A CN202310124978.8A CN202310124978A CN116049372A CN 116049372 A CN116049372 A CN 116049372A CN 202310124978 A CN202310124978 A CN 202310124978A CN 116049372 A CN116049372 A CN 116049372A
- Authority
- CN
- China
- Prior art keywords
- text
- user
- information
- source
- source identifier
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 107
- 230000008569 process Effects 0.000 claims abstract description 62
- 230000006399 behavior Effects 0.000 claims description 41
- 230000003993 interaction Effects 0.000 claims description 33
- 238000012545 processing Methods 0.000 claims description 21
- 230000004044 response Effects 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 12
- 239000004973 liquid crystal related substance Substances 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 abstract description 2
- 238000003058 natural language processing Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 11
- 238000000605 extraction Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G06F16/3343—Query execution using phonetics
-
- 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
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure provides a man-machine conversation method, a man-machine conversation device and electronic equipment, relates to the technical field of artificial intelligence, and particularly relates to the technical field of deep learning, natural language processing and intelligent searching. The specific implementation scheme is as follows: acquiring a user identifier, a current problem text and a context text of a user in a dialogue process; based on the identification, preference information and/or state information of a user aiming at least one product source identification are obtained; selecting a target source identifier from at least one product source identifier according to the current question text and the context text; and determining a reply text corresponding to the current problem text according to preference information and/or state information of the user aiming at the target source identifier, so that the requirement of the user aiming at the product source identifier can be determined by combining the preference information and/or state information of the user aiming at least one product source identifier in the man-machine conversation process, conversation turns are reduced, and conversation efficiency of the man-machine conversation system is improved.
Description
Technical Field
The disclosure relates to the technical field of artificial intelligence, in particular to the technical fields of deep learning, natural language processing and intelligent searching, and particularly relates to a man-machine conversation method, a man-machine conversation device and electronic equipment.
Background
The current man-machine dialogue system acquires the current problem text and the context text of the user in the dialogue process; and determining a reply text corresponding to the current question text according to the current question text and the dialogue context. When the man-machine dialogue system generates a reply text, the requirements of the user are mined by combining the dialogue context, and the reply text is generated according to the requirements of the user.
When the system is applied to scenes such as brand marketing, the man-machine dialogue system can acquire requirements of users for brands through multiple rounds of dialogue, the number of rounds of dialogue is too large, the acquired requirements are not accurate enough, and the dialogue efficiency is poor.
Disclosure of Invention
The disclosure provides a man-machine conversation method, a man-machine conversation device and electronic equipment.
According to an aspect of the present disclosure, there is provided a human-machine conversation method applied to a human-machine conversation system, the method including: acquiring an identification of a user, a current problem text of the user and a context text in a dialogue process; based on the identification, preference information and/or state information of the user for at least one product source identification are obtained; selecting a target source identifier from at least one of the product source identifiers according to the current question text and the context text; and determining a reply text corresponding to the current question text according to preference information and/or state information of the user aiming at the target source identification, the current question text and the context text.
According to another aspect of the present disclosure, there is provided a human-machine conversation device applied to a human-machine conversation system, the device comprising: the first acquisition module is used for acquiring the identification of the user, the current problem text of the user and the context text in the dialogue process; the second acquisition module is used for acquiring preference information and/or state information of the user aiming at least one product source identifier based on the identifier; a selection module, configured to select a target source identifier from at least one of the product source identifiers according to the current question text and the context text; and the first determining module is used for determining a reply text corresponding to the current question text according to preference information and/or state information of the user aiming at the target source identification, the current question text and the context text.
According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the human-machine interaction method set forth above in the present disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the man-machine conversation method proposed above in the present disclosure.
According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the steps of the human-machine interaction method set forth above in the present disclosure.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic diagram according to a first embodiment of the present disclosure;
FIG. 2 is a schematic diagram according to a second embodiment of the present disclosure;
FIG. 3 is a schematic diagram according to a third embodiment of the present disclosure;
FIG. 4 is a schematic diagram according to a fourth embodiment of the present disclosure;
fig. 5 is a block diagram of an electronic device for implementing a human-machine conversation method of an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The current man-machine dialogue system acquires the current problem text and the context text of the user in the dialogue process; and determining a reply text corresponding to the current question text according to the current question text and the dialogue context. When the man-machine dialogue system generates a reply text, the requirements of the user are mined by combining the dialogue context, and the reply text is generated according to the requirements of the user.
When the system is applied to scenes such as brand marketing, the man-machine dialogue system can acquire requirements of users for brands through multiple rounds of dialogue, the number of rounds of dialogue is too large, the acquired requirements are not accurate enough, and the dialogue efficiency is poor.
Aiming at the problems, the disclosure provides a man-machine conversation method, a man-machine conversation device and electronic equipment.
Fig. 1 is a schematic diagram of a first embodiment of the disclosure, and it should be noted that the man-machine conversation method of the embodiments of the disclosure may be applied to a man-machine conversation device, where the device may be configured in a man-machine conversation system, or in an electronic device provided with a man-machine conversation system, so that the electronic device may perform man-machine conversation functions. In the following embodiments, a human-machine conversation system will be described as an example of an execution subject.
The electronic device may be any device with computing capability and man-machine interaction function, for example, may be a personal computer (Personal Computer, abbreviated as PC), a mobile terminal, a server, etc., and the mobile terminal may be, for example, a vehicle-mounted device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, a smart speaker, etc., and has various hardware devices including an operating system, a touch screen, and/or a display screen.
As shown in fig. 1, the man-machine interaction method may include the steps of:
step 101, obtaining the user identification, the current question text and the context text of the user in the dialogue process.
In the embodiment of the disclosure, the user identification, such as a mobile phone number, a mailbox address, a mall account number, a website account number, and the like. If the number of the identifiers of the single user is multiple, an association relationship between the identifiers, for example, an association relationship between the mobile phone number of the user and the mailbox address of the user, may be established. The mall account is an account registered by a user in at least one mall software.
The current question text of the user is currently input by the user in the dialogue process, and the replied question text is not acquired. The context text is a question text input by a user in a history manner and a history reply text of the man-machine conversation system in the conversation process of the man-machine conversation system and the user.
It should be noted that, in the case that the man-machine dialogue system performs a text dialogue with the user, the man-machine dialogue system may directly obtain the current question text input by the user and obtain the context text. Under the condition that the man-machine dialogue system carries out voice dialogue with a user or voice dialogue and text dialogue, the man-machine dialogue system can carry out text recognition processing on voice in the dialogue process, and then the current problem text and the context text of the user are respectively obtained according to recognition processing results.
In the embodiment of the present disclosure, the process of executing step 101 by the human-machine interaction system may be, for example, obtaining a registered user identifier on the human-machine interaction system; in the case that the number of registered user identifications is single, the registered user identifications are used as the identifications of the users in the conversation process; under the condition that the number of registered user identifiers is a plurality of, acquiring registered voiceprint information corresponding to the registered user identifiers and current voiceprint information of the user in the conversation process; determining first registered voiceprint information matched with current voiceprint information according to registered voiceprint information corresponding to a plurality of registered user identifiers and the current voiceprint information of a user in a conversation process; the registered user identification corresponding to the first registered voiceprint information is used as the identification of the user in the conversation process; and acquiring the current question text and the context text of the user.
The process of acquiring the current voiceprint information of the user in the dialogue process may be, for example, acquiring the voice input by the user in the dialogue process, or prompting the user to input a reference voice and performing voice acquisition to obtain the voice of the user; and carrying out voiceprint extraction processing on the voice of the user to obtain the current voiceprint information of the user. The reference voice may be any voice input by the user, or a voice after the user reads the reference text provided by the man-machine conversation system.
In the case that the number of registered user identifiers is multiple, for example, the man-machine interaction system is arranged in an intelligent sound box in a household, the number of the household is multiple, each user in the household registers the user identifier in the intelligent sound box, but preference information and/or state information of different users are different, requirements are different, and specific users are required to be distinguished according to current voiceprint information of the users. The man-machine conversation system is arranged in hardware equipment accompanied with a user, such as an intelligent sound box and a mobile phone, so that the user can conveniently perform conversation processing with the man-machine conversation system in real time according to the needs, and the conversation efficiency is further improved.
The process of determining the first registered voiceprint information matched with the current voiceprint information by the man-machine interaction system may be, for example, that the man-machine interaction system determines a similarity between each registered voiceprint information and the current voiceprint information; performing descending order sorting treatment on each registered voiceprint information according to the similarity to obtain a sorting result; and the registered voiceprint information which is ranked at the forefront in the ranking result is used as first registered voiceprint information.
The man-machine conversation system can accurately determine the user identification in the conversation process according to the registered voiceprint information corresponding to the registered user identification and the current voiceprint information of the user in the conversation process, and further can accurately determine a reply text suitable for the current problem text by combining preference information and/or state information of the user for at least one product source identification, so that the conversation efficiency of the man-machine conversation system is improved.
Step 102, based on the identification, preference information and/or status information of the user for at least one product source identification is obtained.
In the embodiment of the disclosure, the number of the identifiers of the users may be multiple, and an association relationship may be established between the multiple identifiers of the users. The man-machine interaction system may be provided with a preference database comprising a correspondence between an identification and preference data, one identification being any of the following: cell phone number, mailbox address, mall account number, website account number, etc. In particular, the preference data may be preference information and/or status information identified by the user for at least one product source.
Under the condition that the user identification is multiple, the man-machine interaction system can directly inquire the man-machine interaction system according to the user identification, or inquire the man-machine interaction system according to the identification associated with the identification, and acquire preference information and/or state information of the user aiming at least one product source identification.
In the disclosed embodiment, prior to step 102, in one example, a human-machine dialog system may obtain preference information and/or status information for at least one product source identification for a plurality of users by interacting with a plurality of hit databases. In another example, the human-machine interaction system may communicate with a background server through which preference information and/or status information for at least one product source identification by a plurality of users is obtained.
In the embodiment of the present disclosure, before step 102, the process of the ergonomic dialogue system obtaining preference information and/or status information of a plurality of users for at least one product source identifier may be, for example, obtaining hit behavior data of the plurality of users, where the hit behavior data includes hit behavior records of the users for the plurality of product source identifiers; for each user, preference information and/or status information for the user for at least one product source identifier is determined from hit behavior records for the user for a plurality of product source identifiers. In addition, the man-machine dialogue system can also extract preference information of the user according to the current problem text and the context text of the user; and updating the preference information of the user aiming at the at least one product source identifier according to the preference information, so that the accuracy of the preference information of the user aiming at the at least one product source identifier is improved.
The process of the man-machine interaction system obtaining hit behavior data of a plurality of users may be, for example, determining an identifier of at least one hit database; aiming at each hit database, acquiring sub-hit behavior data of a plurality of users in the hit database based on the identification of the hit database; and determining hit behavior data of the plurality of users according to the sub-hit behavior data of the plurality of users in the at least one hit database.
The product source identifier may be, for example, a brand, a field, etc. Taking a product source identifier as a brand as an example, status information of a user for the brand may be used to indicate whether the user has consumption behavior for a product under the brand. That is, when the state information is in a miss state, the state information indicates that the user does not have consumption behavior on the product under the brand within a certain period of time; and when the state information is hit state, the state information indicates that the user has consumption behavior on the product under the brand within a certain period of time. Correspondingly, the hit database may be specifically a consumption database, for example, a database of each merchant on each mall software, etc.
The process of determining the preference information of the user for at least one brand by the human-computer interaction system under the condition that the product source is identified as the brand may be, for example, determining, for each brand, according to a consumption behavior record of the user for the brand, a consumption frequency, a consumption time period, and the like of the commodity of the brand by the user, and if the consumption frequency is greater than a first preset frequency threshold value, or the consumption frequency in a certain period is greater than a first consumption frequency threshold value, determining that the preference information of the user for the brand is forward preference information; if the consumption frequency is smaller than a second preset frequency threshold value or the consumption frequency in a certain period of time is smaller than a second consumption frequency threshold value, and the like, determining that the preference information of the user for the brand is negative preference information.
Taking the product source identifier as an example of the domain, the state information of the user aiming at the domain can be used for indicating whether the user has browsing behaviors on the web pages in the domain. That is, when the state information is in a miss state, the state information indicates that the user does not have browsing behaviors on the web page in the field within a certain period of time; and when the state information is in a hit state, the state information indicates that the user has browsing behaviors on the web page in the field within a certain period of time. The hit database may be a browsing database, for example, a browsing database on each website.
In the case that the product source identifier is a domain, the process of determining the preference information of the user for at least one domain by the man-machine interaction system may be, for example, determining, for each domain, according to a browsing behavior record of the user for the domain, a browsing frequency, a browsing time period, and the like of a web page of the user for the domain, and if the browsing frequency is greater than a third preset frequency threshold, or the browsing frequency in a certain time period is greater than a third browsing frequency threshold, determining that the preference information of the user for the domain is forward preference information; if the browsing frequency is smaller than a fourth preset frequency threshold value or the browsing frequency in a certain time period is smaller than a fourth browsing frequency threshold value, and the like, determining that the preference information of the user for the field is negative preference information.
The man-machine conversation system interacts with at least one hit database, hit behavior data of a plurality of users are determined according to sub-hit behavior data of the plurality of users in the at least one hit database, preference information and/or state information of the plurality of users aiming at least one product source identifier are further determined, the preference information and/or state information of the users aiming at one product source identifier can be prevented from being acquired through multiple conversations in the man-machine conversation process, conversation rounds in the man-machine conversation process are reduced, reply texts suitable for current problem texts are accurately determined, and conversation efficiency of the man-machine conversation system is improved.
Step 103, selecting a target source identifier from at least one product source identifier according to the current question text and the context text.
In an embodiment of the disclosure, the human-machine interaction system may determine a relevance of the current question text and the context text to the at least one product source identifier; and selecting a target source identifier from at least one product source identifier according to the correlation degree. For example, for each product source identifier, the human-machine interaction system may input the current question text, the context text, and the product source identifier into a relevance model, and obtain a relevance of the output of the relevance model.
Step 104, determining a reply text corresponding to the current question text according to preference information and/or state information of the user aiming at the target source identification, the current question text and the context text.
According to the man-machine conversation method, the identification of the user, the current problem text of the user and the context text in the conversation process are obtained; based on the identification, preference information and/or state information of a user aiming at least one product source identification are obtained; selecting a target source identifier from at least one product source identifier according to the current question text and the context text; according to preference information and/or state information of a user aiming at a target source identifier, a current question text and a context text, a reply text corresponding to the current question text is determined, so that the requirement of the user aiming at the product source identifier can be determined by combining the preference information and/or state information of the user aiming at least one product source identifier in the man-machine conversation process, the requirement of the user aiming at the product source identifier is avoided being acquired through multiple times, conversation times are reduced, accurate requirements can be acquired, and conversation efficiency of a man-machine conversation system is improved.
Wherein, in order to accurately select the target source identifier, the source characteristics of at least one product source identifier can be combined with the text source characteristics determined according to the current question text and the context text, and the target source identifier can be selected from the at least one product source identifier. As shown in fig. 2, fig. 2 is a schematic diagram of a second embodiment according to the present disclosure, and the embodiment shown in fig. 2 may include the following steps:
step 201, obtaining the user identification, the current question text and the context text of the user in the dialogue process.
Step 202, based on the identification, obtaining preference information and/or status information of the user for at least one product source identification.
In step 203, text source characteristics are determined according to the current question text and the context text.
In the embodiment of the disclosure, the process of determining the text source feature by the man-machine interaction system may be, for example, inputting the current question text and the context text into the source feature extraction model, and obtaining the text source feature output by the source feature extraction model.
Step 204, obtaining source characteristics of at least one product source identifier.
In the embodiment of the disclosure, the process of determining the source characteristic of at least one product source identifier by the man-machine interaction system may, for example, be that, for each product source identifier, a description text of the product source identifier is obtained; the text is input into the source feature extraction model to obtain the source features output by the source feature extraction model. The training process of the source feature extraction model may be, for example, inputting two groups of descriptive texts into the source feature extraction model to obtain two output source features; determining a predicted similarity between the two source features of the output; and constructing a loss function according to the predicted similarity and the reference similarity marked between the two groups of description texts, and performing parameter adjustment on the source feature extraction model to obtain a trained source feature extraction model.
Step 205, selecting a target source identifier from the at least one product source identifier based on the text source characteristics and the source characteristics of the at least one product source identifier.
In the embodiment of the present disclosure, the man-machine interaction system performs the process of step 205, for example, may be to determine a similarity between the text source feature and the at least one source feature according to the text source feature and the source feature of the at least one product source identifier; acquiring a first source feature with the corresponding similarity larger than a preset similarity threshold value in at least one source feature; and determining the product source identifier corresponding to the first source characteristic as a target source identifier.
The target source identifier is selected according to the similarity between the text source feature and at least one source feature, and the product source identifier related to the current demand of the user can be selected from at least one product source identifier, so that the matching degree between the reply text determined and obtained based on the target source identifier and the demand of the user can be improved.
If the similarity corresponding to at least one source feature is less than or equal to the preset similarity threshold, the man-machine interaction system may determine that the target source identifier is not selected. If the target source identifier is not selected, the man-machine interaction system can combine the current question text and the context text to generate a reply text corresponding to the current question text, and then jump to step 201 to execute the steps 201 and later again.
Step 206, determining a reply text corresponding to the current question text according to the preference information and/or the status information of the user aiming at the target source identification, the current question text and the context text.
It should be noted that, for details of step 201, step 202 and step 206, reference may be made to step 101, step 102 and step 104 in the embodiment shown in fig. 1, and detailed description thereof will not be given here.
According to the man-machine conversation method, the identification of the user, the current problem text of the user and the context text in the conversation process are obtained; based on the identification, preference information and/or state information of a user aiming at least one product source identification are obtained; determining text source characteristics according to the current question text and the context text; acquiring source characteristics of at least one product source identifier; selecting a target source identifier from the at least one product source identifier according to the text source characteristics and the source characteristics of the at least one product source identifier; according to preference information and/or state information of a user aiming at a target source identifier, a current question text and a context text, a reply text corresponding to the current question text is determined, so that the requirement of the user aiming at the product source identifier can be determined by combining the preference information and/or state information of the user aiming at least one product source identifier in the man-machine conversation process, the requirement of the user aiming at the product source identifier is avoided being acquired through multiple times, conversation times are reduced, accurate requirements can be acquired, and conversation efficiency of a man-machine conversation system is improved.
After determining the target source identifier, determining information to be pushed or service information of the target source identifier for generating a reply text according to preference information and/or state information of a user aiming at the target source identifier; and then, generating a reply text by combining the information to be pushed or the service information, and improving the generating accuracy of the reply text. As shown in fig. 3, fig. 3 is a schematic diagram of a third embodiment according to the present disclosure, and the embodiment shown in fig. 3 may include the following steps:
step 301, obtaining the user identification, the current question text and the context text of the user in the dialogue process.
Step 302, based on the identification, obtaining preference information and/or status information of the user for at least one product source identification.
In the embodiment of the present disclosure, taking the product source identifier as an example of a brand, the status information indicates whether the consumer behavior exists for the product under the brand, and taking the user C as an example, preference information and/or status information of the user C for at least one brand may be shown in table 1 below, for example.
TABLE 1 preference information and/or status information for user C for at least one brand
Step 303, selecting a target source identifier from at least one product source identifier according to the current question text and the context text.
Step 304, in the case that the preference information of the user for the target source identifier is forward preference information and the status information of the user for the target source identifier is a miss status, obtaining the information to be pushed of the target source identifier.
In the embodiment of the present disclosure, the information to be pushed and/or the service information of the product source identifier a and the product source identifier B in table 1 may be, for example, as shown in table 2 below.
TABLE 2 information to be pushed and/or service information for product Source identification
| Product source identification | Information to be pushed | Service information |
| A | Without any means for | Automobile maintenance information |
| B | Promotion information of certain down jacket |
The product source identifier is taken as an example, and the information to be pushed can be pre-sale marketing information. The service information may be after-sales service marketing information. Taking the product source identifier as an example of the field, the information to be pushed can be a page relevant to the field, and the like. The service information may be a page of a sub-field under the field, etc.
Step 305, determining a reply text corresponding to the current question text according to the information to be pushed, the current question text and the context text.
In the embodiment of the present disclosure, the process of executing step 305 by the man-machine conversation system may be, for example, inputting the information to be pushed, the current problem text and the context text into the conversation model, and obtaining the reply text output by the conversation model.
Step 306, in the case that the state information of the user for the target source identifier is a hit state, obtaining the service information of the target source identifier.
Step 307, determining a reply text corresponding to the current question text according to the service information, the current question text and the context text.
In the embodiment of the present disclosure, the man-machine conversation system performs the process of step 307, for example, by inputting service information, current question text and context text into the conversation model, and obtaining a reply text output by the conversation model. The dialogue model can be obtained by training data, the training data comprises samples larger than a preset number, and the samples can comprise: sample push information/service information, sample question text, sample context text, sample reply text.
In an embodiment of the present disclosure, after determining the reply text corresponding to the current question text, the man-machine interaction system may further perform the following procedure: acquiring a response text of a user aiming at the response text; under the condition that the response text is a positive response text, acquiring information to be pushed or service information related to the response text; and carrying out multi-round dialogue processing with the user according to the information to be pushed or the service information.
In addition, in the case where the response text is a message response text, the process goes to step 301, and the steps 301 and the following steps are re-executed.
According to whether the response text of the user aiming at the response text is a positive response text or not, whether multiple rounds of dialogue are carried out with the user or not is further determined according to the information to be pushed or the service information, multiple rounds of dialogue processing can be carried out according to the requirement of the user, and dialogue efficiency is further improved.
In the following description, taking the target source identifier as the brand a as an example, the industry to which the brand a belongs is the identifier xiaowang@google.com of the user in the automobile industry, the preference information and/or the status information of the user for the brand a are shown in table 1, the information to be pushed and/or the service information of the brand a are shown in table 2, and the conversation process between the man-machine conversation system and the user can be shown in the following table 3, for example.
Table 3 man-machine conversation system and conversation content table of user
Wherein in table 3, bot represents a human-machine dialog system. In Table 3, the current question text may be, for example, "drive without me going out, not afraid-! "; the context text may be, for example, "user: what air temperature is today? Bot: the highest temperature is 1 ℃, and the lowest temperature is 7 ℃ below zero. Today weather true cold-! "; the reply text corresponding to the current question text may be, for example, "enter winter, your loving car of brand A should be regularly maintained-! "; the positive answer text for the reply text may be, for example, "thank you alert-! You don't say this, I don't remember-! ".
In the embodiment of the disclosure, according to the information to be pushed or the service information, in the process of performing multi-round dialogue processing with the user, the man-machine dialogue system can also perform dialogue with the user, acquire feedback information of the user on the hit product under the target source identifier, and provide the feedback information for the corresponding product source identifier merchant. The feedback information is, for example, "the recent fuel consumption is somewhat high, and the automobile starts without power after stepping on the accelerator" or the like.
It should be noted that, for details of steps 301 to 303, reference may be made to steps 101 to 103 in the embodiment shown in fig. 1, and detailed description thereof will not be provided here.
According to the man-machine conversation method, the identification of the user, the current problem text of the user and the context text in the conversation process are obtained; based on the identification, preference information and/or state information of a user aiming at least one product source identification are obtained; selecting a target source identifier from at least one product source identifier according to the current question text and the context text; under the condition that the preference information of the user aiming at the target source identifier is forward preference information and the state information is in a miss state, obtaining information to be pushed of the target source identifier; determining a reply text corresponding to the current question text according to the information to be pushed, the current question text and the context text; under the condition that the state information is hit, acquiring service information of a target source identifier; according to the service information, the current question text and the context text, a reply text corresponding to the current question text is determined, so that the requirement of a user for the product source identifier can be determined by combining preference information and/or state information of the user for at least one product source identifier in the man-machine conversation process, the requirement of the user for the product source identifier is prevented from being acquired through multiple rounds, conversation rounds are reduced, accurate requirements can be acquired, and conversation efficiency of a man-machine conversation system is improved.
In order to implement the above embodiment, the present disclosure further provides a human-machine interaction device. As shown in fig. 4, fig. 4 is a schematic diagram according to a fourth embodiment of the present disclosure. The man-machine conversation device 40 may be applied to a man-machine conversation system, and may include: a first acquisition module 401, a second acquisition module 402, a selection module 403, and a first determination module 404.
The first obtaining module 401 is configured to obtain an identifier of a user, a current question text of the user, and a context text in a session;
a second obtaining module 402, configured to obtain preference information and/or status information of the user for at least one product source identifier based on the identifier;
a selection module 403, configured to select a target source identifier from at least one of the product source identifiers according to the current question text and the context text;
a first determining module 404, configured to determine a reply text corresponding to the current question text according to preference information and/or status information of the user for the target source identifier, the current question text, and the context text.
As one possible implementation manner of the embodiment of the present disclosure, the selecting module 403 is specifically configured to determine a text source feature according to the current question text and the context text; acquiring source characteristics of at least one product source identifier; and selecting the target source identifier from at least one product source identifier according to the text source characteristics and the source characteristics of the at least one product source identifier.
As one possible implementation manner of the embodiment of the present disclosure, the selecting module 403 is specifically further configured to determine, according to the text source feature and the source feature of at least one of the product source identifiers, a similarity between the text source feature and at least one of the source features; acquiring a first source feature with the corresponding similarity larger than a preset similarity threshold value in at least one source feature; and determining the product source identifier corresponding to the first source characteristic as the target source identifier.
As one possible implementation of the embodiment of the present disclosure, the first determining module 404 includes: a first acquisition unit and a first determination unit; the first obtaining unit is configured to obtain information to be pushed of the target source identifier, where preference information of the user for the target source identifier is forward preference information, and the state information is a miss state; the first determining unit is configured to determine a reply text corresponding to the current question text according to the information to be pushed, the current question text and the context text.
As one possible implementation of the embodiment of the present disclosure, the first determining module 404 further includes: a second acquisition unit and a second determination unit; the second obtaining unit is configured to obtain service information of the target source identifier in a case that the state information is in a hit state; the second determining unit is configured to determine a reply text corresponding to the current question text according to the service information, the current question text and the context text.
As a possible implementation manner of the embodiment of the present disclosure, the first obtaining module 401 is specifically configured to obtain a registered user identifier on the man-machine interaction system; in the case that the number of registered user identifications is single, taking the registered user identifications as the user identifications in the conversation process; and acquiring the current question text of the user and the context text.
As a possible implementation manner of the embodiment of the present disclosure, the first obtaining module 401 is specifically further configured to obtain, in a case where the number of registered user identities is plural, registered voiceprint information corresponding to the plural registered user identities, and current voiceprint information of the user in a session; determining first registered voiceprint information matched with the current voiceprint information according to registered voiceprint information corresponding to a plurality of registered user identifications and the current voiceprint information of the user in the conversation process; and taking the registered user identification corresponding to the first registered voiceprint information as the identification of the user in the conversation process.
As one possible implementation manner of the embodiments of the present disclosure, the apparatus further includes: a third acquisition module and a second determination module; the third acquisition module is used for acquiring hit behavior data of a plurality of users, wherein the hit behavior data comprises hit behavior records of the users aiming at a plurality of product source identifiers; the second determining module is configured to determine, for each user, preference information and/or status information of the user for at least one product source identifier according to hit behavior records of the user for a plurality of product source identifiers.
As one possible implementation manner of the embodiments of the present disclosure, the third obtaining module is specifically configured to determine an identifier of at least one hit database; aiming at each hit database, acquiring sub-hit behavior data of a plurality of users in the hit database based on the identification of the hit database; and determining hit behavior data of a plurality of users according to sub-hit behavior data of the plurality of users in at least one hit database.
As one possible implementation manner of the embodiments of the present disclosure, the apparatus further includes: the system comprises a fourth acquisition module, a fifth acquisition module and a dialogue processing module; the fourth obtaining module is used for obtaining a response text of the user aiming at the response text; the fifth obtaining module is configured to obtain information to be pushed or service information related to the reply text, where the reply text is a positive reply text; and the dialogue processing module is used for carrying out multi-round dialogue processing with the user according to the information to be pushed or the service information.
As one possible implementation of the embodiments of the present disclosure, the human-machine dialogue system is disposed on at least one of the following devices: mobile terminal, intelligent audio amplifier.
The man-machine conversation device of the embodiment of the disclosure obtains the user identification, the current problem text and the context text of the user in the conversation process; based on the identification, preference information and/or state information of a user aiming at least one product source identification are obtained; selecting a target source identifier from at least one product source identifier according to the current question text and the context text; according to preference information and/or state information of a user aiming at a target source identifier, a current question text and a context text, a reply text corresponding to the current question text is determined, so that the requirement of the user aiming at the product source identifier can be determined by combining the preference information and/or state information of the user aiming at least one product source identifier in the man-machine conversation process, the requirement of the user aiming at the product source identifier is avoided being acquired through multiple times, conversation times are reduced, accurate requirements can be acquired, and conversation efficiency of a man-machine conversation system is improved.
In the technical scheme of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user are performed on the premise of proving the consent of the user, and all the processes accord with the regulations of related laws and regulations, and the public welfare is not violated.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
Fig. 5 illustrates a schematic block diagram of an example electronic device 500 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 5, the apparatus 500 includes a computing unit 501 that can perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM) 502 or a computer program loaded from a storage unit 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, ROM 502, and RAM 503 are connected to each other by a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
Various components in the device 500 are connected to the I/O interface 505, including: an input unit 506 such as a keyboard, a mouse, etc.; an output unit 507 such as various types of displays, speakers, and the like; a storage unit 508 such as a magnetic disk, an optical disk, or the like; and a communication unit 509 such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The computing unit 501 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 501 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as a human-machine conversation method. For example, in some embodiments, the human-machine interaction method may be implemented as a computer software program tangibly embodied on a machine-readable medium, e.g., storage unit 508. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 500 via the ROM 502 and/or the communication unit 509. When the computer program is loaded into RAM 503 and executed by computing unit 501, one or more steps of the human-machine interaction method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the human-machine dialog method by any other suitable means (e.g. by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (25)
1. A human-machine conversation method applied to a human-machine conversation system, the method comprising:
acquiring an identification of a user, a current problem text of the user and a context text in a dialogue process;
based on the identification, preference information and/or state information of the user for at least one product source identification are obtained;
selecting a target source identifier from at least one of the product source identifiers according to the current question text and the context text;
And determining a reply text corresponding to the current question text according to preference information and/or state information of the user aiming at the target source identification, the current question text and the context text.
2. The method of claim 1, wherein the selecting a target source identifier from at least one of the product source identifiers based on the current question text and the context text comprises:
determining text source characteristics according to the current question text and the context text;
acquiring source characteristics of at least one product source identifier;
and selecting the target source identifier from at least one product source identifier according to the text source characteristics and the source characteristics of the at least one product source identifier.
3. The method of claim 2, wherein the selecting the target source identifier from at least one of the product source identifiers based on the text source characteristics and source characteristics of at least one of the product source identifiers comprises:
determining a similarity between the text source feature and at least one of the source features according to the text source feature and the source feature of at least one of the product source identifiers;
Acquiring a first source feature with the corresponding similarity larger than a preset similarity threshold value in at least one source feature;
and determining the product source identifier corresponding to the first source characteristic as the target source identifier.
4. The method of claim 1, wherein the determining the reply text corresponding to the current question text according to the preference information and/or status information of the user for the target source identification, the current question text, and the context text comprises:
acquiring information to be pushed of the target source identifier under the condition that the preference information of the user aiming at the target source identifier is forward preference information and the state information is in a miss state;
and determining a reply text corresponding to the current question text according to the information to be pushed, the current question text and the context text.
5. The method of claim 4, wherein the determining the reply text corresponding to the current question text according to preference information and/or status information of the user for the target source identification, the current question text, and the context text further comprises:
Acquiring service information of the target source identifier under the condition that the state information is in a hit state;
and determining a reply text corresponding to the current question text according to the service information, the current question text and the context text.
6. The method of claim 1, wherein the obtaining the identity of the user, the current question text of the user, and the context text during the conversation comprises:
acquiring a registered user identifier on the man-machine conversation system;
in the case that the number of registered user identifications is single, taking the registered user identifications as the user identifications in the conversation process;
and acquiring the current question text of the user and the context text.
7. The method of claim 6, wherein the obtaining the identity of the user, the current question text of the user, and the context text during the conversation further comprises:
under the condition that the number of the registered user identifications is a plurality of, acquiring registered voiceprint information corresponding to the registered user identifications and current voiceprint information of the user in the conversation process;
determining first registered voiceprint information matched with the current voiceprint information according to registered voiceprint information corresponding to a plurality of registered user identifications and the current voiceprint information of the user in the conversation process;
And taking the registered user identification corresponding to the first registered voiceprint information as the identification of the user in the conversation process.
8. The method of claim 1, wherein prior to obtaining preference information and/or status information for the user for at least one product source identification based on the identification, the method further comprises:
acquiring hit behavior data of a plurality of users, wherein the hit behavior data comprises hit behavior records of the users aiming at a plurality of product source identifiers;
for each user, determining preference information and/or status information of the user for at least one product source identifier according to hit behavior records of the user for a plurality of product source identifiers.
9. The method of claim 8, wherein the obtaining hit behavior data for a plurality of users comprises:
determining an identity of at least one hit database;
aiming at each hit database, acquiring sub-hit behavior data of a plurality of users in the hit database based on the identification of the hit database;
and determining hit behavior data of a plurality of users according to sub-hit behavior data of the plurality of users in at least one hit database.
10. The method of claim 1, wherein the method further comprises:
acquiring a response text of the user aiming at the response text;
under the condition that the response text is a positive response text, acquiring information to be pushed or service information related to the response text;
and carrying out multi-round dialogue processing with the user according to the information to be pushed or the service information.
11. The method of any of claims 1-10, wherein the human-machine dialog system is provided on at least one of: mobile terminal, intelligent audio amplifier.
12. A human-machine interaction device for use in a human-machine interaction system, the device comprising:
the first acquisition module is used for acquiring the identification of the user, the current problem text of the user and the context text in the dialogue process;
the second acquisition module is used for acquiring preference information and/or state information of the user aiming at least one product source identifier based on the identifier;
a selection module, configured to select a target source identifier from at least one of the product source identifiers according to the current question text and the context text;
and the first determining module is used for determining a reply text corresponding to the current question text according to preference information and/or state information of the user aiming at the target source identification, the current question text and the context text.
13. The apparatus of claim 12, wherein the selection module is configured to,
determining text source characteristics according to the current question text and the context text;
acquiring source characteristics of at least one product source identifier;
and selecting the target source identifier from at least one product source identifier according to the text source characteristics and the source characteristics of the at least one product source identifier.
14. The apparatus of claim 13, wherein the selection module is further configured to,
determining a similarity between the text source feature and at least one of the source features according to the text source feature and the source feature of at least one of the product source identifiers;
acquiring a first source feature with the corresponding similarity larger than a preset similarity threshold value in at least one source feature;
and determining the product source identifier corresponding to the first source characteristic as the target source identifier.
15. The apparatus of claim 12, wherein the first determination module comprises: a first acquisition unit and a first determination unit;
the first obtaining unit is configured to obtain information to be pushed of the target source identifier, where preference information of the user for the target source identifier is forward preference information, and the state information is a miss state;
The first determining unit is configured to determine a reply text corresponding to the current question text according to the information to be pushed, the current question text and the context text.
16. The apparatus of claim 15, wherein the first determination module further comprises: a second acquisition unit and a second determination unit;
the second obtaining unit is configured to obtain service information of the target source identifier in a case that the state information is in a hit state;
the second determining unit is configured to determine a reply text corresponding to the current question text according to the service information, the current question text and the context text.
17. The apparatus of claim 12, wherein the first acquisition module is configured to,
acquiring a registered user identifier on the man-machine conversation system;
in the case that the number of registered user identifications is single, taking the registered user identifications as the user identifications in the conversation process;
and acquiring the current question text of the user and the context text.
18. The apparatus of claim 17, wherein the first acquisition module is further configured to,
Under the condition that the number of the registered user identifications is a plurality of, acquiring registered voiceprint information corresponding to the registered user identifications and current voiceprint information of the user in the conversation process;
determining first registered voiceprint information matched with the current voiceprint information according to registered voiceprint information corresponding to a plurality of registered user identifications and the current voiceprint information of the user in the conversation process;
and taking the registered user identification corresponding to the first registered voiceprint information as the identification of the user in the conversation process.
19. The apparatus of claim 12, wherein the apparatus further comprises: a third acquisition module and a second determination module;
the third acquisition module is used for acquiring hit behavior data of a plurality of users, wherein the hit behavior data comprises hit behavior records of the users aiming at a plurality of product source identifiers;
the second determining module is configured to determine, for each user, preference information and/or status information of the user for at least one product source identifier according to hit behavior records of the user for a plurality of product source identifiers.
20. The apparatus of claim 19, wherein the third acquisition module is configured to,
Determining an identity of at least one hit database;
aiming at each hit database, acquiring sub-hit behavior data of a plurality of users in the hit database based on the identification of the hit database;
and determining hit behavior data of a plurality of users according to sub-hit behavior data of the plurality of users in at least one hit database.
21. The apparatus of claim 12, wherein the apparatus further comprises: the system comprises a fourth acquisition module, a fifth acquisition module and a dialogue processing module;
the fourth obtaining module is used for obtaining a response text of the user aiming at the response text;
the fifth obtaining module is configured to obtain information to be pushed or service information related to the reply text, where the reply text is a positive reply text;
and the dialogue processing module is used for carrying out multi-round dialogue processing with the user according to the information to be pushed or the service information.
22. The apparatus of any of claims 12 to 21, wherein the human-machine dialog system is provided on at least one of: mobile terminal, intelligent audio amplifier.
23. An electronic device, comprising:
At least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 11.
24. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1 to 11.
25. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310124978.8A CN116049372B (en) | 2023-02-07 | 2023-02-07 | Man-machine conversation method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310124978.8A CN116049372B (en) | 2023-02-07 | 2023-02-07 | Man-machine conversation method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116049372A true CN116049372A (en) | 2023-05-02 |
| CN116049372B CN116049372B (en) | 2023-11-28 |
Family
ID=86120055
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310124978.8A Active CN116049372B (en) | 2023-02-07 | 2023-02-07 | Man-machine conversation method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116049372B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140257792A1 (en) * | 2013-03-11 | 2014-09-11 | Nuance Communications, Inc. | Anaphora Resolution Using Linguisitic Cues, Dialogue Context, and General Knowledge |
| CN112925894A (en) * | 2021-03-26 | 2021-06-08 | 支付宝(杭州)信息技术有限公司 | Method, system and device for matching bid-asking questions in conversation |
| CN114391143A (en) * | 2019-08-26 | 2022-04-22 | 三星电子株式会社 | Electronic device and method for providing conversation service |
| CN115150501A (en) * | 2021-03-30 | 2022-10-04 | 华为技术有限公司 | Voice interaction method and electronic equipment |
-
2023
- 2023-02-07 CN CN202310124978.8A patent/CN116049372B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140257792A1 (en) * | 2013-03-11 | 2014-09-11 | Nuance Communications, Inc. | Anaphora Resolution Using Linguisitic Cues, Dialogue Context, and General Knowledge |
| CN114391143A (en) * | 2019-08-26 | 2022-04-22 | 三星电子株式会社 | Electronic device and method for providing conversation service |
| CN112925894A (en) * | 2021-03-26 | 2021-06-08 | 支付宝(杭州)信息技术有限公司 | Method, system and device for matching bid-asking questions in conversation |
| CN115150501A (en) * | 2021-03-30 | 2022-10-04 | 华为技术有限公司 | Voice interaction method and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116049372B (en) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104951428B (en) | User's intension recognizing method and device | |
| CN110019742B (en) | Method and device for processing information | |
| CN113239295A (en) | Search method, search device, electronic equipment and storage medium | |
| CN112506359A (en) | Method and device for providing candidate long sentences in input method and electronic equipment | |
| CN114244795B (en) | Information pushing method, device, equipment and medium | |
| CN113904943B (en) | Account detection method and device, electronic equipment and storage medium | |
| CN113326450B (en) | Point-of-interest recall method and device, electronic equipment and storage medium | |
| CN116049372B (en) | Man-machine conversation method and device and electronic equipment | |
| CN117171296A (en) | Information acquisition method and device and electronic equipment | |
| CN116204624A (en) | Response method, response device, electronic equipment and storage medium | |
| CN114490969B (en) | Question and answer method and device based on table and electronic equipment | |
| CN116049370A (en) | Information query method and training method and device of information generation model | |
| CN114444514A (en) | Semantic matching model training method, semantic matching method and related device | |
| CN113360590A (en) | Method and device for updating point of interest information, electronic equipment and storage medium | |
| CN112817463A (en) | Method, equipment and storage medium for acquiring audio data by input method | |
| CN113377921B (en) | Method, device, electronic equipment and medium for matching information | |
| CN116244413B (en) | New intention determining method, apparatus and storage medium | |
| CN113377922B (en) | Method, device, electronic equipment and medium for matching information | |
| CN115965018B (en) | Training method of information generation model, information generation method and device | |
| CN116069914B (en) | Training data generation method, model training method and device | |
| CN116244740B (en) | Log desensitization method and device, electronic equipment and storage medium | |
| CN113238765B (en) | Method, device, equipment and storage medium for distributing small program | |
| CN117421400A (en) | Dialogue interaction method and device and electronic equipment | |
| CN117421402A (en) | Dialogue processing method and device and electronic equipment | |
| CN113919365A (en) | Method and device for processing question reply, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |