CN111177330A - Personal intelligent assistant system and data processing method - Google Patents

Personal intelligent assistant system and data processing method Download PDF

Info

Publication number
CN111177330A
CN111177330A CN201911139931.9A CN201911139931A CN111177330A CN 111177330 A CN111177330 A CN 111177330A CN 201911139931 A CN201911139931 A CN 201911139931A CN 111177330 A CN111177330 A CN 111177330A
Authority
CN
China
Prior art keywords
data
input data
user
knowledge
recommendation
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.)
Pending
Application number
CN201911139931.9A
Other languages
Chinese (zh)
Inventor
章劲秋
赵洪莹
朱君
贾静
王清琛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing Yunwen Network Technology Co ltd
Electric Power Research Institute of State Grid Jiangsu Electric Power Co Ltd
Original Assignee
Nanjing Yunwen Network Technology Co ltd
Electric Power Research Institute of State Grid Jiangsu Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing Yunwen Network Technology Co ltd, Electric Power Research Institute of State Grid Jiangsu Electric Power Co Ltd filed Critical Nanjing Yunwen Network Technology Co ltd
Priority to CN201911139931.9A priority Critical patent/CN111177330A/en
Publication of CN111177330A publication Critical patent/CN111177330A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G06F16/3329—Natural language query formulation or dialogue systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3343—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
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9536—Search customisation based on social or collaborative filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
    • 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
    • G06Q30/01—Customer relationship services
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Mathematical Physics (AREA)
  • Economics (AREA)
  • Computational Linguistics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Human Computer Interaction (AREA)
  • Artificial Intelligence (AREA)
  • Game Theory and Decision Science (AREA)
  • Health & Medical Sciences (AREA)
  • Acoustics & Sound (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

The invention discloses a personal intelligent assistant system and a data processing method, wherein the system comprises an intelligent search module, a knowledge scene recommendation module and an individualized knowledge recommendation module, wherein the intelligent search module retrieves and feeds back data related to input data according to the received input data; the knowledge scene recommending module is used for scene-based pushing of knowledge content based on a user tag content recommending technology by combining service content transacted by a user and user intention identification according to received input data; and the personalized knowledge recommendation module completes personalized recommendation based on collaborative filtering according to the received input data and the user tag system. The invention realizes the fragmentation application of knowledge, provides fast-digestion knowledge service and provides each employee with a virtual intelligent assistant by various modes such as intelligent retrieval, voice input, accurate matching acquisition, intelligent recommendation, personalized recommendation, active push and the like.

Description

Personal intelligent assistant system and data processing method
Technical Field
The invention belongs to the technical field of natural language processing in the technical field of computers, and particularly relates to a personal intelligent assistant system and a data processing method.
Background
National network companies have preliminarily established a unified 95598 knowledge management platform intended to provide knowledge services for operators and work order processors. Along with the application depth, knowledge base users put forward higher requirements on the aspect of knowledge base use, the problems that the scene engagement degree with users is not high enough, the details are embodied in that the knowledge display channel is single, the knowledge display mode only has text content at present and does not have a rich media display mode, personalized active recommendation cannot be realized, the knowledge base cannot be inquired in field operation and the like exist, and a set of adaptive and expandable electric power marketing knowledge service system needs to be designed urgently to provide more natural and barrier-free knowledge service for the users.
Disclosure of Invention
The invention provides a personal intelligent assistant system and a data processing method aiming at the problems.
In order to achieve the technical purpose and achieve the technical effects, the invention is realized by the following technical scheme:
in a first aspect, the present invention provides a personal intelligent assistant system, comprising:
the intelligent search module retrieves data related to the input data according to the received input data and feeds back the data;
the knowledge scene recommending module is used for carrying out scene pushing on the knowledge content based on a user tag content recommending technology by combining the service content transacted by the user and the user intention identification according to the received input data;
and the personalized knowledge recommendation module is used for completing personalized recommendation based on collaborative filtering according to the received input data and the user tag system.
Optionally, the intelligent search module includes:
the first processing unit is used for retrieving data related to the input data based on the received voice input data and a tag content recommendation technology and feeding back the data;
and/or the second processing unit is used for retrieving data related to the input data based on the received text input data and the label content recommendation technology and feeding back the data.
Optionally, the knowledge scenario recommendation module includes:
the tag forming unit is used for collecting real data of a user according to the received input data and forming a first tag by applying a Chinese semantic analysis technology;
the system comprises a label modification unit, a label analysis unit and a label analysis unit, wherein the label modification unit is used for manually checking labels, and a service expert screens/modifies related first labels aiming at the relevance of a real scene to form second labels;
and the first recommending unit is used for performing reverse association on the knowledge with the same second label and recommending the unread knowledge with the same second label to the user.
Optionally, the personalized knowledge recommendation module includes:
the data collection unit is used for collecting the on-line interactive behavior data of the user according to the received input data;
the characteristic extraction unit is used for extracting user characteristics from the collected user online interactive behavior data by utilizing a characteristic extraction related technology;
the computing unit is used for computing the user similarity based on the extracted user features to obtain similar users of the users;
and the second recommending unit is used for recommending the related content of the similar users to a certain user.
Optionally, the personal intelligent assistant system further comprises a multimedia interactive question and answer module for implementing multimedia interaction based on the acquired input data and a group intelligent collaborative filtering technology.
In a second aspect, the present invention provides a data processing method for a personal intelligent assistant, including:
acquiring input data;
and selecting a proper data processing rule based on the type of the input data, processing the input data based on the selected data processing rule, and finally performing data feedback or scene-based knowledge content pushing or completing personalized recommendation based on collaborative filtering.
Optionally, the selecting a suitable data processing rule based on the type of the input data, processing the input data based on the selected data processing rule, and finally performing data feedback specifically includes:
when the input data is voice input data, retrieving data related to the input data based on a tag content recommendation technology, and feeding back the data;
and/or when the received text input data is received, retrieving data related to the input data based on the tag content recommendation technology and feeding back the data.
Optionally, the selecting a suitable data processing rule based on the type of the input data, processing the input data based on the selected data processing rule, and finally performing scene-based knowledge content pushing specifically includes:
collecting real data of a user, and forming a first label by applying a Chinese semantic analysis technology;
manually checking the tags, and screening/modifying related first tags by a service expert aiming at the relevance of a real scene to form second tags;
and performing reverse association on the knowledge with the same second label, and recommending the unread knowledge with the same second label to the user.
Optionally, the selecting a suitable data processing rule based on the type of the input data, processing the input data based on the selected data processing rule, and finally performing personalized recommendation based on collaborative filtering specifically includes:
collecting online interactive behavior data of a user;
extracting user characteristics from the collected online interactive behavior data of the user by using a characteristic extraction related technology;
calculating user similarity based on the extracted user features to obtain similar users of the users;
and recommending the related content of the similar users to a certain user.
Optionally, the data processing method further includes: and realizing multimedia interaction based on the acquired input data and a group intelligent collaborative filtering technology.
Compared with the prior art, the invention has the beneficial effects that:
the method fuses text data, voice data and online behavior data, and processes the data and extracts relevant characteristics by applying the related technology of natural language processing (named entity recognition and syntactic analysis); the characteristic layer is modeled in a mode of separating user characteristics, scene characteristics and product characteristics; considering the deviation of the extracted features of the machine, a module for manually checking and modifying the features is added to correct the features; a personal intelligent assistant system is designed by applying relevant characteristics, the knowledge search which is convenient, intelligent and close to the business is provided, the new and old employees are helped to learn knowledge, the business cooperation assists in working, experts participate in sharing experience, the fragmented application of knowledge is realized through various modes such as intelligent retrieval, voice input, accurate matching acquisition, intelligent recommendation, personalized recommendation and active push, the fast-dissolving knowledge service is provided, and each employee is provided with a virtual intelligent assistant.
Drawings
In order that the present disclosure may be more readily and clearly understood, reference is now made to the following detailed description of the present disclosure taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a flow chart of a method according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the scope of the invention.
The following detailed description of the principles of the invention is provided in connection with the accompanying drawings.
Example 1
The embodiment of the invention provides a personal intelligent assistant system, which comprises:
the intelligent search module retrieves data related to the input data according to the received input data and feeds back the data;
the knowledge scene recommending module is used for carrying out scene pushing on the knowledge content based on a user tag content recommending technology by combining the service content transacted by the user and the user intention identification according to the received input data;
and the personalized knowledge recommendation module is used for completing personalized recommendation based on collaborative filtering according to the received input data and the user tag system.
In a specific implementation manner of the embodiment of the present invention, the intelligent search module includes:
the first processing unit is used for retrieving data related to the input data based on the received voice input data and a tag content recommendation technology and feeding back the data; the retrieval can be completed by adopting a retrieval module based on natural language understanding enhancement, and compared with a general retrieval module, the invention adopts the related technology (word segmentation, named entity identification and the like) based on the existing Chinese natural language understanding to effectively retrieve a plurality of semantic elements such as time, number words, places, prices, number intervals and the like.
And/or the second processing unit is used for retrieving data related to the input data based on the received text input data and the tag content recommendation technology and feeding back the data; in a specific implementation process, the text input data comprises Chinese characters, English characters, phrases, sentences and the like; the retrieval can be completed by adopting a retrieval module based on natural language understanding enhancement, and compared with a general retrieval module, the invention adopts the related technology (word segmentation, named entity identification and the like) based on the existing Chinese natural language understanding to effectively retrieve a plurality of semantic elements such as time, number words, places, prices, number intervals and the like.
The first processing unit and the second processing unit finish the extraction of text features, including product features and scene features.
In a specific implementation manner of the embodiment of the present invention, the knowledge scene recommendation module includes:
the tag forming unit is used for collecting real data of a user according to the received input data and forming a first tag by applying a Chinese semantic analysis technology;
the system comprises a label modification unit, a label analysis unit and a label analysis unit, wherein the label modification unit is used for manually checking labels, and a service expert screens/modifies related first labels aiming at the relevance of a real scene to form second labels;
and the first recommending unit is used for performing reverse association on the knowledge with the same second label and recommending the unread knowledge with the same second label to the user.
The knowledge unread with the same second tag includes:
Figure BDA0002280633050000041
in a specific implementation manner of the embodiment of the present invention, the personalized knowledge recommendation module includes:
the data collection unit is used for collecting the on-line interactive behavior data of the user according to the received input data;
the characteristic extraction unit is used for extracting user characteristics from the collected user online interactive behavior data by utilizing a characteristic extraction related technology, namely completing the extraction of non-text characteristics;
the computing unit is used for computing the user similarity based on the extracted user features to obtain similar users of the users;
and the second recommending unit is used for recommending the related content of the similar users to a certain user.
In a specific implementation manner of the embodiment of the present invention, the personal intelligent assistant system further includes a multimedia interactive question-answering module, configured to implement multimedia interaction based on the acquired input data and a group intelligent collaborative filtering technology.
Example 2
The embodiment of the invention provides a data processing method of a personal intelligent assistant, which specifically comprises the following steps as shown in fig. 1:
(1) acquiring input data;
(2) and selecting a proper data processing rule based on the type of the input data, processing the input data based on the selected data processing rule, and finally performing data feedback or scene-based knowledge content pushing or completing personalized recommendation based on collaborative filtering.
In a specific implementation manner of the embodiment of the present invention, the selecting a suitable data processing rule based on the type of the input data, processing the input data based on the selected data processing rule, and finally performing data feedback specifically includes:
when the input data is voice input data, retrieving data related to the input data based on a tag content recommendation technology, and feeding back the data; the retrieval can be completed by adopting a retrieval module based on natural language understanding enhancement, and compared with a general retrieval module, the invention adopts the relevant technology (word segmentation, named entity identification and the like) based on the existing Chinese natural language understanding to effectively retrieve a plurality of semantic elements such as time, number words, places, prices, number intervals and the like;
and/or when the received text input data is input, retrieving data related to the input data based on a tag content recommendation technology, and feeding back the data; in a specific implementation process, the text input data comprises Chinese characters, English characters, phrases, sentences and the like; the retrieval can be completed by adopting a retrieval module based on natural language understanding enhancement, compared with a general retrieval module, the invention adopts the related technology (word segmentation, named entity identification and the like) based on the existing Chinese natural language understanding to effectively retrieve a plurality of semantic elements such as time, quantity words, places, prices, quantity intervals and the like, and completes the extraction of text characteristics including product characteristics and scene characteristics.
In a specific implementation manner of the embodiment of the present invention, the selecting a suitable data processing rule based on the type of the input data, processing the input data based on the selected data processing rule, and finally performing scene-based knowledge content pushing specifically includes:
collecting real data of a user, and forming a first label by applying a Chinese semantic analysis technology;
manually checking the tags, and screening/modifying related first tags by a service expert aiming at the relevance of a real scene to form second tags;
and performing reverse association on the knowledge with the same second label, and recommending the unread knowledge with the same second label to the user.
The knowledge unread with the same second tag includes:
Figure BDA0002280633050000061
in a specific implementation manner of the embodiment of the present invention, the selecting a suitable data processing rule based on the type of the input data, processing the input data based on the selected data processing rule, and finally performing personalized recommendation based on collaborative filtering specifically includes:
collecting online interactive behavior data of a user;
extracting user characteristics from the collected online interactive behavior data of the user by using a characteristic extraction related technology;
calculating user similarity based on the extracted user features to obtain similar users of the users;
and recommending the related content of the similar users to a certain user.
In a specific implementation process of the embodiment of the present invention, the following steps are specifically performed:
an item-based collaborative filtering algorithm ItemCF;
and (3) evaluating the similarity between the items through the scores of different items by the user based on the collaborative filtering of the items, and making a recommendation based on the similarity between the items.
The method is as follows simply: the user is recommended knowledge content similar to the knowledge points he likes before.
User/knowledge Knowledge point A Knowledge point B Knowledge point C
User A √ √
User B √ √ √
User C √ Recommending
The implementation steps are shown in FIG. 1:
step 1, collecting user online interactive behavior data, preprocessing the user online interactive behavior data, completing preprocessing work of original user text data by using related technologies such as Chinese word segmentation, part of speech tagging, syntactic analysis and the like, and cleaning impurity content in the data;
and 2, a user characteristic acquisition process, namely extracting the characteristic character characteristics of the user, such as field entities, operation phenomena and the like, by utilizing the preprocessing result of the step 1 aiming at each user behavior data.
And 3, manually checking the user characteristic extraction condition, and manually checking related characteristics according to the scene real condition.
And 4, judging whether the user characteristic collection is finished or not, and returning to the step 2 to continuously discover new user characteristics if the user characteristic collection is not finished.
Step 5, recommending knowledge points with similar characteristics for the users according to the characteristics of the users, wherein the similarity calculation of the knowledge points adopts a Pearson correlation coefficient;
step 6, calculating a recommended knowledge point of each user according to the calculation result in the step 5;
the calculation formula of the Pearson correlation coefficient is as follows:
where p (x, y) represents the relevance of user x to knowledge point y, xiRepresenting the ith-dimensional numerical characteristic, y, of user xiThe ith dimension of the numerical feature representing the knowledge point y.
The recommendation algorithm based on Item-CF needs to reduce the influence of the active User on data, and the algorithm judges that the contribution of the active User to the similarity of the article should be smaller than that of an inactive User, so an IUF (Inverse User frequency) parameter is added to modify a calculation formula of the similarity of the article:
Figure BDA0002280633050000072
wherein N (u) represents the total number of items owned by user u, N (i) represents the total number of persons owning item i, N (j) represents the total number of items owned by item j, wijRepresenting the similarity of item i to item j.
In a specific implementation manner of the embodiment of the present invention, the data processing method further includes: and realizing multimedia interaction based on the acquired input data and a group intelligent collaborative filtering technology.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.

Claims (10)

1. A personal intelligent assistant system, comprising:
the intelligent search module retrieves data related to the input data according to the received input data and feeds back the data;
the knowledge scene recommending module is used for carrying out scene pushing on the knowledge content based on a user tag content recommending technology by combining the service content transacted by the user and the user intention identification according to the received input data;
and the personalized knowledge recommendation module is used for completing personalized recommendation based on collaborative filtering according to the received input data and the user tag system.
2. The personal intelligent assistant system according to claim 1, wherein the intelligent search module comprises:
the first processing unit is used for retrieving data related to the input data based on the received voice input data and a tag content recommendation technology and feeding back the data;
and/or the second processing unit is used for retrieving data related to the input data based on the received text input data and the label content recommendation technology and feeding back the data.
3. The personal intelligent assistant system according to claim 1, wherein the knowledge scene recommendation module comprises:
the tag forming unit is used for collecting real data of a user according to the received input data and forming a first tag by applying a Chinese semantic analysis technology;
the system comprises a label modification unit, a label analysis unit and a label analysis unit, wherein the label modification unit is used for manually checking labels, and a service expert screens/modifies related first labels aiming at the relevance of a real scene to form second labels;
and the first recommending unit is used for performing reverse association on the knowledge with the same second label and recommending the unread knowledge with the same second label to the user.
4. The personal intelligent assistant system according to claim 1, wherein the personalized knowledge recommendation module comprises:
the data collection unit is used for collecting the on-line interactive behavior data of the user according to the received input data;
the characteristic extraction unit is used for extracting user characteristics from the collected user online interactive behavior data by utilizing a characteristic extraction related technology;
the computing unit is used for computing the user similarity based on the extracted user features to obtain similar users of the users;
and the second recommending unit is used for recommending the related content of the similar users to a certain user.
5. The personal intelligent assistant system as claimed in claim 1, further comprising a multimedia interactive question and answer module for implementing multimedia interaction based on the acquired input data and crowd-sourced intelligent collaborative filtering technology.
6. A data processing method of a personal intelligent assistant is characterized by comprising the following steps:
acquiring input data;
and selecting a proper data processing rule based on the type of the input data, processing the input data based on the selected data processing rule, and finally performing data feedback or scene-based knowledge content pushing or completing personalized recommendation based on collaborative filtering.
7. The data processing method of the personal intelligent assistant as claimed in claim 6, wherein the selecting of the appropriate data processing rule based on the type of the input data, the processing of the input data based on the selected data processing rule, and the final data feedback are specifically:
when the input data is voice input data, retrieving data related to the input data based on a tag content recommendation technology, and feeding back the data;
and/or when the received text input data is received, retrieving data related to the input data based on the tag content recommendation technology and feeding back the data.
8. The data processing method of the personal intelligent assistant according to claim 6, wherein: selecting a proper data processing rule based on the type of the input data, processing the input data based on the selected data processing rule, and finally performing scene-based knowledge content pushing, wherein the method specifically comprises the following steps:
collecting real data of a user, and forming a first label by applying a Chinese semantic analysis technology;
manually checking the tags, and screening/modifying related first tags by a service expert aiming at the relevance of a real scene to form second tags;
and performing reverse association on the knowledge with the same second label, and recommending the unread knowledge with the same second label to the user.
9. The data processing method of the personal intelligent assistant according to claim 6, wherein: selecting a proper data processing rule based on the type of the input data, processing the input data based on the selected data processing rule, and finally performing personalized recommendation based on collaborative filtering, wherein the specific steps are as follows:
collecting online interactive behavior data of a user;
extracting user characteristics from the collected online interactive behavior data of the user by using a characteristic extraction related technology;
calculating user similarity based on the extracted user features to obtain similar users of the users;
and recommending the related content of the similar users to a certain user.
10. The data processing method of the personal intelligent assistant according to claim 6, wherein: the data processing method further comprises: and realizing multimedia interaction based on the acquired input data and a group intelligent collaborative filtering technology.
CN201911139931.9A 2019-11-20 2019-11-20 Personal intelligent assistant system and data processing method Pending CN111177330A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911139931.9A CN111177330A (en) 2019-11-20 2019-11-20 Personal intelligent assistant system and data processing method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911139931.9A CN111177330A (en) 2019-11-20 2019-11-20 Personal intelligent assistant system and data processing method

Publications (1)

Publication Number Publication Date
CN111177330A true CN111177330A (en) 2020-05-19

Family

ID=70648747

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911139931.9A Pending CN111177330A (en) 2019-11-20 2019-11-20 Personal intelligent assistant system and data processing method

Country Status (1)

Country Link
CN (1) CN111177330A (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106448670A (en) * 2016-10-21 2017-02-22 竹间智能科技（上海）有限公司 Dialogue automatic reply system based on deep learning and reinforcement learning
CN107193883A (en) * 2017-04-27 2017-09-22 北京拓尔思信息技术股份有限公司 A kind of data processing method and system
CN110188169A (en) * 2019-05-27 2019-08-30 深圳宇诺智能有限公司 A kind of knowledge matching process, system and equipment based on simplified label

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106448670A (en) * 2016-10-21 2017-02-22 竹间智能科技（上海）有限公司 Dialogue automatic reply system based on deep learning and reinforcement learning
CN107193883A (en) * 2017-04-27 2017-09-22 北京拓尔思信息技术股份有限公司 A kind of data processing method and system
CN110188169A (en) * 2019-05-27 2019-08-30 深圳宇诺智能有限公司 A kind of knowledge matching process, system and equipment based on simplified label

Similar Documents

Publication Publication Date Title
CN107705066B (en) Information input method and electronic equipment during commodity warehousing
CN109189901B (en) Method for automatically discovering new classification and corresponding corpus in intelligent customer service system
CN110427563B (en) Professional field system cold start recommendation method based on knowledge graph
CN106570708B (en) Management method and system of intelligent customer service knowledge base
CN109960786A (en) Chinese Measurement of word similarity based on convergence strategy
CN110472017A (en) A kind of analysis of words art and topic point identify matched method and system
CN110019703B (en) Data marking method and device and intelligent question-answering method and system
CN108363748B (en) Topic portrait system and topic portrait method based on knowledge
CN107436916B (en) Intelligent answer prompting method and device
CN112559684A (en) Keyword extraction and information retrieval method
CN108182605A (en) A kind of user's behavior prediction method and system based on user's portrait
CN113627797B (en) Method, device, computer equipment and storage medium for generating staff member portrait
CN109086265A (en) A kind of semanteme training method, multi-semantic meaning word disambiguation method in short text
CN111462752A (en) Client intention identification method based on attention mechanism, feature embedding and BI-L STM
CN107291755A (en) A kind of terminal method for pushing and device
CN112115712B (en) Topic-based group emotion analysis method
CN110929007A (en) Electric power marketing knowledge system platform and application method
CN114266443A (en) Data evaluation method and device, electronic equipment and storage medium
CN112149422B (en) Dynamic enterprise news monitoring method based on natural language
CN112667815A (en) Text processing method and device, computer readable storage medium and processor
CN107908749B (en) Character retrieval system and method based on search engine
CN106708932A (en) Abstract extraction method and apparatus for reply of question and answer website
CN111680505B (en) Method for extracting unsupervised keywords of MarkDown feature perception
CN112597273A (en) Power distribution automation chart generation method based on NL2SQL technology
CN112330387A (en) Virtual broker applied to house-watching software

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20200519

RJ01 Rejection of invention patent application after publication