CN111798279A - Dialog-based user portrait generation method and apparatus - Google Patents
Dialog-based user portrait generation method and apparatus Download PDFInfo
- Publication number
- CN111798279A CN111798279A CN202010693513.0A CN202010693513A CN111798279A CN 111798279 A CN111798279 A CN 111798279A CN 202010693513 A CN202010693513 A CN 202010693513A CN 111798279 A CN111798279 A CN 111798279A
- Authority
- CN
- China
- Prior art keywords
- user
- topic
- portrait
- intention
- chat
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a user portrait generation method and device based on conversation, wherein the user portrait generation method based on the conversation comprises the following steps: responding to a query sentence of a user, and judging whether the query sentence corresponds to a preset portrait intention; if the query statement corresponds to the preset portrait intention, generating an associated chat topic at least based on the query statement and the preset portrait intention; the user portrait is constructed by performing voice interaction with the user based on the chat topic, mutual understanding is deepened through the chat and the conversation, the portrait of the user can be established, the user is selected to ask questions, the continuity of the current conversation is ensured by ensuring the relevance and consistency of the question content and the current conversation topic and the time of asking the questions is ensured to be right, the pertinence of the questions is ensured, the user portrait which is as complete as possible is constructed by using the least questions, and therefore the real-time performance of the user portrait, the dynamic updating of the user portrait and the complete no perception of the user can be ensured.
Description
Technical Field
The invention belongs to the technical field of voice interaction, and particularly relates to a user portrait generation method and device based on conversation.
Background
In the related art, the existing user portrait construction method in the market is divided into an offline method and an online method, and the user portrait is constructed through member management, questionnaire survey, shopping cart analysis and the like in the traditional offline method. Online is based primarily on the user's search, browse, purchase logs.
Generally comprising the steps of: collecting a user log, and acquiring the user behavior according to the user log;
analyzing the user behavior, and establishing a user discrimination model;
and constructing a user portrait according to the reading interest, region and income information of the user and the user distinguishing degree model.
Disclosure of Invention
An embodiment of the present invention provides a method and an apparatus for generating a user portrait based on a dialog, which are used to solve at least one of the above technical problems.
In a first aspect, an embodiment of the present invention provides a dialog-based user representation generation method, including: responding to a query sentence of a user, and judging whether the query sentence corresponds to a preset portrait intention; if the query statement corresponds to the preset portrait intention, generating an associated chat topic at least based on the query statement and the preset portrait intention; performing voice interaction with the user based on the chat topic to construct a user representation.
In a second aspect, an embodiment of the present invention provides a user representation generating apparatus based on a dialog, including: the judging module is configured to respond to a query sentence of a user and judge whether the query sentence corresponds to a preset portrait intention; a first generation module configured to generate an associated chat topic based at least on the query statement and the preset portrait intent if the query statement corresponds to the preset portrait intent; and a construction module configured to perform voice interaction with the user based on the chat topic to construct a user representation.
In a third aspect, there is provided a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, cause the computer to perform the steps of the dialog based user representation generation method of the first aspect.
In a fourth aspect, an embodiment of the present invention further provides an electronic device, which includes: 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 steps of the method of the first aspect.
The method provided by the embodiment of the application deepens mutual understanding through chatting and conversation, the portrait of the user can be established in conversation interaction, the user can be asked questions opportunistically in the user portrait establishing method based on the conversation interaction, the user cannot feel hesitant by ensuring the relevance and consistency of the question content and the current conversation theme, secondly, the time for asking the questions is ensured to be right, the continuity of the current conversation is ensured, finally, the pertinence of the questions is ensured, and the user portrait which is as complete as possible is established by using the fewest questions, so that the real-time property of the portrait of the user, the dynamic updating of the portrait of the user and the complete no perception of the user can be ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
FIG. 1 is a flow chart of a method for generating a user representation based on a dialog according to an embodiment of the present invention;
FIG. 2 is a flowchart of another dialog-based user representation generation method according to an embodiment of the present invention;
FIG. 3 is a system flow diagram of one embodiment of a dialog-based user representation generation arrangement in accordance with an embodiment of the present invention;
FIG. 4 is a schematic diagram of a user representation structure of an embodiment of a dialog-based user representation generation arrangement of the present invention;
FIG. 5 is a diagram illustrating an example of a dialog with an intent to move and a representation construction in accordance with an embodiment of the present invention;
FIG. 6 is a diagram illustrating a music intent dialog example and representation construction in accordance with a particular embodiment of a dialog-based user representation generation arrangement in accordance with an embodiment of the present invention;
FIG. 7 is a block diagram of an apparatus for generating a user representation based on a dialog according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a flow chart of an embodiment of a dialog-based user representation generation method of the present invention is shown, wherein the UID of the user can be determined by the device ID of the user interaction, the user account and the voiceprint identification module, and the UID of the user is guaranteed to be unique, so as to guarantee the user representation of each person to be unique.
As shown in fig. 1, in step 101, in response to a query sentence of a user, determining whether the query sentence corresponds to a preset portrait intention;
in step 102, if the query statement corresponds to the preset portrait intention, generating an associated chat topic at least based on the query statement and the preset portrait intention;
in step 103, voice interaction is performed with the user based on the chat topic to construct a user representation.
In this embodiment, for step 101, the dialog-based user representation generation apparatus determines whether a query statement corresponds to a preset representation intent in response to a query statement of a user, e.g., the user has a dialog with a smart speaker, e.g., "I25 years old, how big are you? The intelligent sound box can determine that the intention of the user is an age intention through intention classification, and then the intelligent sound box judges whether the age intention exists in the preset image or not;
then, for step 102, if the query statement corresponds to the preset portrait intention, generating a related chat topic at least based on the query statement and the preset portrait intention, for example, the smart speaker may generate a chat topic related to age according to age intention, such as a constellation, a birthday, or an equivalent, and of course, besides generating the chat topic by referring to the above information, the present application may also refer to historical portrait information of the user, which is not limited herein;
finally, for step 103, the user representation generation device based on the conversation performs voice interaction with the user based on the chat topic to construct a user representation, for example, the user has a conversation with a smart speaker, wherein the conversation may also be a mobile phone voice assistant or a voice assistant in APP, and the application is not limited herein;
the dialog scenario is as follows:
the user: i am 25 years old, how big are you?
Intelligent sound box: i have been two years old soon, have a birthday of 2 months and 3 days, how much do you birthday of the owner?
The user: i'm birthday is 4 months 17.
Intelligent sound box: 4, 17 days, the owner should not know the constellation and the fortune?
The smart speaker would construct a user portrait based on the above dialog, with an age of 25 years, a birthday of 4 months and a day of 17 days, and a constellation of bulls.
In the scheme of the embodiment, the user can be created with pictures in conversation interaction by deepening mutual understanding through chatting and conversation.
In the method of the above embodiment, after determining whether the query statement corresponds to a preset portrait intent, the method further includes: if the query statement does not correspond to the preset portrait intention, generating a chat topic associated with the intention corresponding to the query statement;
for example, the smart speaker receives a certain intention of the user, but has no specific information, for example, the dialog content given by the user is "i am boring", then the user is identified as "intention boring" through the intention classification, and then chat topics such as motion, movie, music, and game are generated according to boring, for example, one dialog scenario is as follows:
the user: i are bored.
Intelligent sound box: now that we feel bored we get to chat about the concert, we discuss the singer bar, do you have a favorite singer?
The user: i like Zhou Ji Lun, am o.
Intelligent sound box: what were you originally liked Zhou Jiereno, what you liked your song?
The user: i prefer his balloon.
Intelligent sound box: is his song really straight, is that Zhou Jieren the favorite star?
The user: is.
Intelligent sound box: it seems that the Zhou Jie's charm is not general and can be appreciated by small owners.
For example, another dialog scenario is as follows:
the user: i starve.
Intelligent sound box: what is the owner you want to eat?
The user: i want to eat water boiled fish.
Intelligent sound box: do I know that there is a home of boiled fish in the vicinity, do not help you to place an order?
In the scheme of the embodiment, a large number of dialog logs are used, so that more user figures can be constructed, and the user figures can be communicated with an offline store to guide offline store flow.
In some optional embodiments, the chat topics include at least a first level topic and a second level topic, the first level topic includes the second level topic, and the priority of the second level topic is higher than that of the first level topic in the chat topics, for example, if the first topic of the chat topics of the user is sports, the second topics such as running, volleyball and basketball related to sports are generated, and if the first topic of the chat topics of the user is a movie, the second topics such as comedy films, war films, antique films, modern films related to movies are generated.
In the scheme of the embodiment, the problem content and the relevance and consistency of the current conversation theme are ensured, so that the user can not feel the conflict.
Referring to fig. 2, in the method of the above embodiment, the chat topic is a first level topic, and the flowchart of the embodiment of constructing the user representation if the user interacts with the chat topic in a voice manner based on the chat topic is shown.
As shown in fig. 2, in step 201, it is determined whether there is a second level topic associated with the first level topic;
in step 202, if yes, performing voice interaction with the user based on the second level topic;
in step 203, extracting a first answer of the user to the first level topic and a second answer of the user to the second level topic based on voice interaction with the user;
in step 204, a user representation is constructed based on the first answer, the second answer, the first level topic, and the second level topic.
In this embodiment, in step 201, the user image generation device based on the dialog determines whether there is a second level topic associated with the first level topic, for example, if the first topic is sports, then second topics such as running, volleyball, basketball and the like related to sports are generated, which have been described in detail in the above embodiments and will not be described again;
then, for step 202, if a second topic, such as running, volleyball, and basketball, exists, then generating a question based on the topics such as running, volleyball, and basketball, and performing dialogue interaction with the user, where the dialogue interaction may be voice interaction or text interaction, and the application is not limited herein and is not described herein again;
thereafter, for step 203, the dialog-based user representation generating means extracts, based on the voice interaction with the user, a first answer of the user to the first level topic and a second answer of the user to the second level topic, for example, a dialog scenario as follows:
intelligent sound box: we discuss an exercise bar, do you have a favorite sport?
The user: i like volleyball sometime.
Intelligent sound box: now that you like volleyball, remember to practice much more, build up the body, do you have disliked sports?
The user: i do not like running.
Intelligent sound box: originally, little owner dislikes to run, and little owner participates in some exercises that oneself likes more, and body building is Ha.
According to the conversation scene, the first answer volleyball and the second answer running of the user can be extracted;
finally, for step 204, the dialog-based user representation generating means constructs a user representation based on the first answer, the second answer, the first level topic, and the second level topic, e.g., a user representation created from the topics of the dialog scene and the user answers is sports, likes volleyball, and dislikes running;
in the scheme of the embodiment, the relevance and consistency of the problem content and the current conversation theme are ensured, so that a user does not feel a great sense, the time for asking questions is ensured to be right, the continuity of the current conversation is ensured, finally, the pertinence of the problems is ensured, and the user portrait which is as complete as possible is constructed by using the fewest problems, so that the real-time property of the user portrait, the dynamic updating of the user portrait and the complete no perception of the user can be ensured.
In some optional embodiments, the user portrait is composed of an intention tree and knowledge points, for example, the portrait of the user includes basic information, diet and games, then the knowledge points of the basic information include gender and age, and the knowledge points of the diet include fruits, vegetables and meat, wherein the knowledge points in the fruits include favorite apples, favorite pears and dislike apricots, so that the information retrieval can be realized according to a certain category classification system, and the successive viewing and the brief retrieval can be realized, therefore, the purpose is strong for the user, the precision is high, further, the information resources are organized by adopting a tree directory structure, and the information resources have good expandability and strict systematicness.
In the method of the above embodiment, after the voice interacting with the user based on the chat topic to construct a user representation, the method further comprises: if the user portrait constructed through voice interaction conflicts with the historical user portrait, the conflicting knowledge points in the historical user portrait are deleted or updated, for example, the fruit liked by the user has an apple, and the user does not like to eat the apple any more in a later period of time, then after the obtained user portrait conflicts with the historical user portrait, the historical portrait is updated timely, the fruit liked by the user portrait is changed into the apple not liked, and therefore the user portrait can be deleted or updated timely.
The following description is provided to enable those skilled in the art to better understand the present disclosure by describing some of the problems encountered by the inventors in implementing the present disclosure and by describing one particular embodiment of the finally identified solution.
In the process of implementing the present application, the inventors found that the following defects exist in the similar technologies:
firstly, the real-time performance of data is not enough, and a lot of time is spent from collection and analysis to modeling, so that the portrait of a user is not updated timely, the latest interest point of the user cannot be captured, and secondly, the specific interest point of the user cannot be accurately positioned, because the user browses too many pages every day, the real interest point is submerged in a large amount of logs, just like a sea fishing needle. Third, it is difficult to verify the quality of the image after the traditional user image is constructed.
The reason why is not easily conceivable:
it is common practice to collect basic data, such as browsing, purchasing, searching records, and then analyze and model, mine key information from them, and store the key information as a user representation.
The technical problem existing in the prior art is solved through the following scheme:
the embodiment of the invention provides a user portrait construction method based on conversation interaction, wherein human beings deepen mutual understanding through conversation and chatting, if a robot can imitate the conversation of the human beings, the two people are similar to strengthen mutual understanding in the chatting process, and in the conversation interaction, the robot can also establish portrait of human customers. In the user portrait construction method based on the dialogue interaction, the robot can choose to ask a user with a choice, and as long as three points are met, the relevance and consistency of the question content and the current dialogue theme are ensured, so that the user does not feel glancing; secondly, ensuring that the question asking time is right to ensure the continuity of the current conversation; finally, it is ensured that the user portrait is as complete as possible with the least number of problems. The method has the following advantages: firstly, the real-time performance of a user portrait is guaranteed; secondly, dynamically updating the user portrait; third, the user is completely unaware.
The technical innovation points of the embodiment of the invention are as follows:
a user portrait construction method based on dialogue interaction;
an intention slot position modeling method in a user portrait;
a generation method of the dialogue content;
a method for selecting conversation opportunities.
As shown in fig. 3, the flow of the method is to classify the intentions of the input query of the user, and the category of the intentions corresponds to the category of the intentions in the user image library (shown in fig. 4).
If the intention of the query corresponds to a certain intention in the portrait of the user, then the query is extracted, for example, "i 25 years old, how big are you? "it can be determined by the intention classification to be" intention of age ", then < UID, age, 25 years > can be obtained by information extraction. The extracted information is added to the user image library as shown in fig. 4.
The UID of the user is determined by the equipment ID interacted by the user, the user account and the voiceprint recognition module, so that the UID of the user is unique, and the user portrait of each person is unique.
FIG. 4 is a schematic diagram of a user representation consisting of an intent tree and knowledge points, such as basic information, diet, games, sports, books, music, etc., all being sub-intents. < UID, age, 25 years >, < UID, sex, male > are all knowledge points. Common basic information knowledge points are shown in table 1. The user portrait organization structure of FIG. 4 is advantageous in that it is convenient to add and delete user portraits, and to establish the association between knowledge points. And related intentions can be conveniently found in the conversation, and related chat topics are further generated.
TABLE 1 general basic information
| Name (I) | Language(s) | Sex | Mailbox |
| Birthday | Height of a person | Nationality | Telephone set |
| Dried rehmannia root | Body weight | Constellation | Study calendar |
| Place of living | The animal joining together | Age (age) | Occupation of the world |
Note that some knowledge points are related to each other, for example, knowing the birthday, the constellation and age can be deduced. Therefore, when asking questions, the user needs to chat with birthday topics preferentially, so that birthday information is captured in the conversation, and the age and the constellation of the user are inferred. On the contrary, if the user says that the user is the golden ox, the user can tell me the constellation situation that the user can be acquired first, and the birthday of the user is inferred to be 4 months or 5 months.
If the query of the user belongs to a certain intention, but has no specific information, such as query is boring, the system can identify the user as boring through intention classification, and generate a chat topic such as movie, music, game and the like according to boring, such as 'do not recommend movie to the owner'. If the user says "good", then one can ask what kind of movie is liked "is the host like comedy or war? "or who likes" the movie "how do the movie sung? "from this dialogue, the user's favorite stars, the subject of the movie, etc. can be further known.
The chat topics such as movies, music, games and the like can be generated according to the 'intention ═ chatting', the association strength between the intention and the topics can be determined, the association strength can be obtained by statistically mining a large number of dialog logs, such as movie and television dialogue, microblog forum postback, and the association strength can also be constructed in advance according to scene knowledge or common knowledge.
For another example, the user says "i hungry", the system recognizes "intention as food", and can ask "what do you want to eat by the owner? "the user says" i want to eat water and boil fish ", the system replies" i know that there is family water and boil fish nearby and do not help i get a bill ". Therefore, the device can be communicated with an offline store to drain the offline store.
Fig. 5 is an example of a sports intent dialog from which we can obtain the user portrait knowledge points < UID likes sports volleyball >, < UID likes sports volleyball >.
Fig. 6 is an example of a music intent dialog from which we can obtain user portrait knowledge points < UID likes singer jieren >, < UID likes song billow balloon >.
Referring to FIG. 7, a block diagram of a dialog-based user representation generation apparatus according to an embodiment of the present invention is shown.
As shown in fig. 7, a user profile generation apparatus 700 for generating a user profile based on a dialog includes: a determination module 710, a first generation module 720, and a construction module 730.
The judging module 710 is configured to respond to a query statement of a user, and judge whether the query statement corresponds to a preset portrait intention; a first generating module 720, configured to generate an associated chat topic based on at least the query statement and the preset portrait intent if the query statement corresponds to the preset portrait intent; and a construction module 730 configured to perform voice interaction with the user based on the chat topic to construct a user representation.
It should be understood that the modules depicted in fig. 7 correspond to various steps in the methods described with reference to fig. 1 and 2. Thus, the operations and features described above for the method and the corresponding technical effects are also applicable to the modules in fig. 7, and are not described again here.
It should be noted that the modules in the embodiments of the present application are not limited to the scheme of the present application, for example, the determining module may be described as responding to a query statement of a user to determine whether the query statement corresponds to a preset portrait intention, and in addition, the related functional modules may also be implemented by a hardware processor, for example, the determining module may also be implemented by a processor, and details are not described herein.
In other embodiments, the present invention further provides a non-volatile computer storage medium, where the computer storage medium stores computer-executable instructions, and the computer-executable instructions may perform the dialog-based user representation generation method in any of the above method embodiments;
as one embodiment, a non-volatile computer storage medium of the present invention stores computer-executable instructions configured to:
responding to a query sentence of a user, and judging whether the query sentence corresponds to a preset portrait intention;
if the query statement corresponds to the preset portrait intention, generating an associated chat topic at least based on the query statement and the preset portrait intention;
performing voice interaction with the user based on the chat topic to construct a user representation.
The non-volatile computer-readable storage medium may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created in accordance with use of the dialog-based user representation generating apparatus, and the like. Further, the non-volatile computer-readable storage medium may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the non-transitory computer readable storage medium optionally includes memory remotely located from the processor, which may be connected to the dialog-based user representation generation apparatus over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Embodiments of the present invention also provide a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, where the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes any one of the above methods for generating a user profile based on a dialog.
Fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 8, the electronic device includes: one or more processors 810 and a memory 820, with one processor 810 being an example in FIG. 8. The apparatus for a dialog-based user representation generation method may further include: an input device 830 and an output device 840. The processor 810, the memory 820, the input device 830, and the output device 840 may be connected by a bus or other means, such as the bus connection in fig. 8. The memory 820 is a non-volatile computer-readable storage medium as described above. The processor 810 implements the above-described method embodiments for a dialog-based user representation generation method by executing non-volatile software programs, instructions, and modules stored in the memory 820 to perform various functional applications of the server and data processing. The input device 830 may receive input numeric or character information and generate key signal inputs related to user settings and function controls for a dialog-based user representation generation device. The output device 840 may include a display device such as a display screen.
The product can execute the method provided by the embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the method provided by the embodiment of the present invention.
In one embodiment, the electronic device is applied to a user profile generation apparatus based on a dialog, and includes:
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 cause the at least one processor to:
responding to a query sentence of a user, and judging whether the query sentence corresponds to a preset portrait intention;
if the query statement corresponds to the preset portrait intention, generating an associated chat topic at least based on the query statement and the preset portrait intention;
performing voice interaction with the user based on the chat topic to construct a user representation.
The electronic device of the embodiments of the present application exists in various forms, including but not limited to:
(1) a mobile communication device: such devices are characterized by mobile communications capabilities and are primarily targeted at providing voice, data communications. Such terminals include smart phones, multimedia phones, functional phones, and low-end phones, among others.
(2) Ultra mobile personal computer device: the equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include: PDA, MID, and UMPC devices, etc.
(3) A portable entertainment device: such devices can display and play multimedia content. The devices comprise audio and video players, handheld game consoles, electronic books, intelligent toys and portable vehicle-mounted navigation devices.
(4) The server is similar to a general computer architecture, but has higher requirements on processing capability, stability, reliability, safety, expandability, manageability and the like because of the need of providing highly reliable services.
(5) And other electronic devices with data interaction functions.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method of dialog-based user representation generation, comprising:
responding to a query sentence of a user, and judging whether the query sentence corresponds to a preset portrait intention;
if the query statement corresponds to the preset portrait intention, generating an associated chat topic at least based on the query statement and the preset portrait intention;
performing voice interaction with the user based on the chat topic to construct a user representation.
2. The method of claim 1, wherein after said determining whether the query statement corresponds to a preset portrait intent, the method further comprises:
and if the query sentence does not correspond to the preset portrait intention, generating a chat topic associated with the intention corresponding to the query sentence.
3. The method of claim 1, wherein the chat topics include at least a first level topic and a second level topic, the first level topic including the second level topic,
in the chat topic, the second level topic has a higher priority than the first level topic.
4. The method of claim 3, wherein the chat topic is a first level topic, and wherein the constructing a user representation if voice interaction is performed with the user based on the chat topic comprises:
judging whether a second level topic related to the first level topic exists or not;
if yes, performing voice interaction with the user based on the second-level topic;
extracting a first answer of the user to the first level topic and a second answer of the user to the second level topic based on voice interaction with the user;
constructing a user representation based on the first answer, the second answer, the first level topic, and the second level topic.
5. The method of any of claims 1-4, wherein the user representation is comprised of an intent tree and knowledge points.
6. The method of claim 5, wherein after the voice interacting with the user based on the chat topic to construct a user representation, the method further comprises:
and if the user portrait constructed by voice interaction conflicts with the historical user portrait, deleting or updating the conflicting knowledge points in the historical user portrait.
7. A dialog-based user representation generation apparatus, comprising:
the judging module is configured to respond to a query sentence of a user and judge whether the query sentence corresponds to a preset portrait intention;
a first generation module configured to generate an associated chat topic based at least on the query statement and the preset portrait intent if the query statement corresponds to the preset portrait intent;
a construction module configured to perform voice interaction with the user based on the chat topic to construct a user representation.
8. The apparatus of claim 7, further comprising:
and the second generation module is configured to generate a chat topic associated with the intention corresponding to the query sentence if the query sentence does not correspond to the preset portrait intention.
9. A computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, cause the computer to perform the steps of the method of any of claims 1-6.
10. An electronic device, comprising: 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 steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010693513.0A CN111798279A (en) | 2020-07-17 | 2020-07-17 | Dialog-based user portrait generation method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010693513.0A CN111798279A (en) | 2020-07-17 | 2020-07-17 | Dialog-based user portrait generation method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111798279A true CN111798279A (en) | 2020-10-20 |
Family
ID=72807747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010693513.0A Withdrawn CN111798279A (en) | 2020-07-17 | 2020-07-17 | Dialog-based user portrait generation method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111798279A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112256943A (en) * | 2020-10-22 | 2021-01-22 | 上海适享文化传播有限公司 | Portal portrait extraction method based on combination of natural language processing and knowledge graph |
| CN112417110A (en) * | 2020-10-27 | 2021-02-26 | 联想(北京)有限公司 | Information processing method and device |
| CN112866088A (en) * | 2021-01-19 | 2021-05-28 | 北京秒针人工智能科技有限公司 | User portrait method and system in instant communication application |
| CN112948565A (en) * | 2021-04-16 | 2021-06-11 | 北京小米移动软件有限公司 | Man-machine conversation method, device, electronic equipment and storage medium |
| CN112989011A (en) * | 2021-04-26 | 2021-06-18 | 广州思迈特软件有限公司 | Data query method, data query device and electronic equipment |
| WO2022141862A1 (en) * | 2020-12-30 | 2022-07-07 | 平安科技（深圳）有限公司 | User portrait generation method and apparatus, computer device and storage medium |
| CN115392937A (en) * | 2022-10-25 | 2022-11-25 | 成都新希望金融信息有限公司 | User fraud risk identification method and device, electronic equipment and storage medium |
| CN113127750B (en) * | 2021-05-19 | 2024-04-02 | 同盾科技有限公司 | Information list generation method and device, storage medium and electronic equipment |
| CN118132736A (en) * | 2024-05-08 | 2024-06-04 | 青岛国创智能家电研究院有限公司 | Training method, control device and storage medium for user portrait identification system |
-
2020
- 2020-07-17 CN CN202010693513.0A patent/CN111798279A/en not_active Withdrawn
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112256943A (en) * | 2020-10-22 | 2021-01-22 | 上海适享文化传播有限公司 | Portal portrait extraction method based on combination of natural language processing and knowledge graph |
| CN112256943B (en) * | 2020-10-22 | 2024-01-23 | 上海适享文化传播有限公司 | Portal store image extraction method based on natural language processing combined with knowledge graph |
| CN112417110A (en) * | 2020-10-27 | 2021-02-26 | 联想(北京)有限公司 | Information processing method and device |
| WO2022141862A1 (en) * | 2020-12-30 | 2022-07-07 | 平安科技（深圳）有限公司 | User portrait generation method and apparatus, computer device and storage medium |
| CN112866088A (en) * | 2021-01-19 | 2021-05-28 | 北京秒针人工智能科技有限公司 | User portrait method and system in instant communication application |
| CN112948565A (en) * | 2021-04-16 | 2021-06-11 | 北京小米移动软件有限公司 | Man-machine conversation method, device, electronic equipment and storage medium |
| CN112989011A (en) * | 2021-04-26 | 2021-06-18 | 广州思迈特软件有限公司 | Data query method, data query device and electronic equipment |
| CN112989011B (en) * | 2021-04-26 | 2021-08-24 | 广州思迈特软件有限公司 | Data query method, data query device and electronic equipment |
| CN113127750B (en) * | 2021-05-19 | 2024-04-02 | 同盾科技有限公司 | Information list generation method and device, storage medium and electronic equipment |
| CN115392937A (en) * | 2022-10-25 | 2022-11-25 | 成都新希望金融信息有限公司 | User fraud risk identification method and device, electronic equipment and storage medium |
| CN118132736A (en) * | 2024-05-08 | 2024-06-04 | 青岛国创智能家电研究院有限公司 | Training method, control device and storage medium for user portrait identification system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111798279A (en) | Dialog-based user portrait generation method and apparatus | |
| US20200301954A1 (en) | Reply information obtaining method and apparatus | |
| CN107507612B (en) | Voiceprint recognition method and device | |
| US10061985B2 (en) | Video understanding platform | |
| CN110209897B (en) | Intelligent dialogue method, device, storage medium and equipment | |
| US20150243279A1 (en) | Systems and methods for recommending responses | |
| CN108520046B (en) | Method and device for searching chat records | |
| CN109284490B (en) | Text similarity calculation method and device, electronic equipment and storage medium | |
| CN109284502B (en) | Text similarity calculation method and device, electronic equipment and storage medium | |
| US9684908B2 (en) | Automatically generated comparison polls | |
| CN109992781B (en) | Text feature processing method and device and storage medium | |
| CN110929045B (en) | Construction method and system of poetry-semantic knowledge map | |
| CN103488787B (en) | A kind of method for pushing and device of the online broadcasting entrance object based on video search | |
| CN111159382B (en) | Method and device for constructing and using session system knowledge model | |
| CN110895656B (en) | Text similarity calculation method and device, electronic equipment and storage medium | |
| US20170272476A1 (en) | Systems and methods for virtual interaction | |
| TW201508522A (en) | Social snippet augmenting | |
| EP3834162A1 (en) | Dynamic and continous onboarding of service providers in an online expert marketplace | |
| CN109190116B (en) | Semantic analysis method, system, electronic device and storage medium | |
| CN109472032A (en) | A kind of determination method, apparatus, server and the storage medium of entity relationship diagram | |
| CN111767386B (en) | Dialogue processing method, device, electronic equipment and computer readable storage medium | |
| CN109063127A (en) | A kind of searching method, device, server and storage medium | |
| CN116910201A (en) | Dialogue data generation method and related equipment thereof | |
| CN109145261B (en) | Method and device for generating label | |
| CN113010664B (en) | Data processing method and device and computer equipment |
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 | ||
| CB02 | Change of applicant information |
Address after: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province Applicant after: Sipic Technology Co.,Ltd. Address before: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province Applicant before: AI SPEECH Ltd. |
|
| CB02 | Change of applicant information | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201020 |
|
| WW01 | Invention patent application withdrawn after publication |