CN112446741B - User portrayal method and system based on probability knowledge graph - Google Patents
User portrayal method and system based on probability knowledge graph Download PDFInfo
- Publication number
- CN112446741B CN112446741B CN202011455170.0A CN202011455170A CN112446741B CN 112446741 B CN112446741 B CN 112446741B CN 202011455170 A CN202011455170 A CN 202011455170A CN 112446741 B CN112446741 B CN 112446741B
- Authority
- CN
- China
- Prior art keywords
- user
- regression coefficient
- similarity
- behavior
- normalized
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000006399 behavior Effects 0.000 claims abstract description 112
- 238000010606 normalization Methods 0.000 claims abstract description 16
- 238000012417 linear regression Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 8
- 230000008569 process Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 2
- 238000003384 imaging method Methods 0.000 claims 4
- 241000282414 Homo sapiens Species 0.000 abstract description 6
- 230000006872 improvement Effects 0.000 description 8
- 230000007547 defect Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000009182 swimming Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (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 method and a system based on a probability knowledge graph, which comprises the following steps: acquiring questionnaire personality information and user behavior data of a user; obtaining regression coefficients of the behavior about the personality by utilizing linear regression based on the questionnaire personality information and the user behavior data; carrying out normalization processing on the regression coefficient to obtain a normalized regression coefficient; calculating the similarity between the behaviors based on the normalized regression coefficients of the two behaviors; and storing the behaviors and the similarity between the behaviors into a graph database to construct a probabilistic knowledge graph. The invention utilizes the probabilistic knowledge graph to portray the user, not only can solve the limitation that the traditional knowledge graph lacks human dynamics and uncertainty representation, but also has the capability of reasoning uncertain facts under the condition of insufficient information and computing resources, thereby portraying the user more effectively.
Description
Technical Field
The invention relates to the technical field of user portrayal, in particular to a user portrayal method and a user portrayal system based on a probability knowledge graph.
Background
Knowledge Graph (also known as Knowledge domain visualization or Knowledge domain mapping map) is a series of different graphs displaying the relationship between the Knowledge development process and the structure, and uses visualization technology to describe Knowledge resources and their carriers, and to mine, analyze, construct, draw and display Knowledge and the mutual relation between them.
The limitations of the traditional knowledge graph are mainly reflected in that the knowledge is mechanically depicted, and the dynamic and uncertainty representation of the knowledge by human beings is lacked, which is mainly reflected in two aspects:
firstly, the knowledge depicted in the knowledge map is static, and in the real human society, the knowledge is dynamic and can be correspondingly changed along with the change of the environment;
the second is that human representation of knowledge is not a deterministic fact of "yes or no", but rather contains a large number of uncertain facts that we attribute to "probably yes".
Disclosure of Invention
In order to solve the above problems in the prior art, the present invention provides a method and system for user portrayal based on probabilistic knowledge domain.
The invention discloses a user portrait method based on a probability knowledge graph, which comprises the following steps:
acquiring questionnaire personality information and user behavior data of a user;
obtaining regression coefficients of the behaviors about the personality by utilizing linear regression based on the questionnaire personality information and the user behavior data;
carrying out normalization processing on the regression coefficient to obtain a normalized regression coefficient;
calculating the similarity between the behaviors based on the normalized regression coefficients of the two behaviors;
and storing the behaviors and the similarity between the behaviors into a graph database to construct a probabilistic knowledge graph.
As a further improvement of the invention, the method also comprises the following steps:
creating a user personality information table, a user multi-dimensional behavior data table, a regression coefficient table, a normalized regression coefficient table and a behavior similarity table;
inputting the questionnaire personality information into the user personality information table, and inputting the user behavior data into the user multi-dimensional behavior data table;
storing the regression coefficients into the regression coefficient table;
storing the normalized regression coefficients into the normalized regression coefficient table;
and storing the similarity between the behaviors into the behavior similarity table.
As a further improvement of the present invention,
the questionnaire personality information comprises demographic information and personality information, wherein the demographic information comprises gender, age and region, and the personality information comprises openness and accountability; in the process of inputting the user personality information table, if information is missing, a missing value is stored;
the user behavior data comprises consumption preferences, music preferences, movie preferences, and color preferences; and if the information is missing, a missing value is stored in the process of inputting the information into the user multi-dimensional behavior data table.
As a further improvement of the present invention,
column names of the regression coefficient table and the normalization coefficient table are behavior names and personality names;
the column names of the behavior similarity table are 3 columns, namely behavior 1, behavior 2 and similarity.
As a further improvement of the present invention,
and the user personality information table, the user multi-dimensional behavior data table, the regression coefficient table, the normalized regression coefficient table and the behavior similarity table are created in the Hive database.
As a further improvement of the present invention, the obtaining of the regression coefficient of the behavior with respect to the personality by using linear regression includes:
and taking the personality value as an explanation variable and the behavior value as an explained variable, and obtaining a regression coefficient of the behavior about the personality by utilizing linear regression.
As a further improvement of the present invention, the formula of the normalization process is:
in the formula,is normalized regression coefficient, beta is regression coefficient, betaiIs the i-th component of the regression coefficient β, and n is the vector length.
8. A user portrayal method according to claim 1 or 2, wherein the similarity between the activities is calculated by the formula:
where sim (x, y) is the similarity between the normalized regression coefficient x and the normalized regression coefficient y, xiIs the i-th component, y, of the normalized regression coefficient xiIs the i-th component of the normalized regression coefficient y.
As a further improvement of the present invention, said graph database is a neo4j graph database.
The invention also discloses a user portrait system based on the probability knowledge map, which is used for realizing the user portrait method and comprises the following steps:
the system comprises a creating module, a judging module and a judging module, wherein the creating module is used for creating a user personality information table, a user multi-dimensional behavior data table, a regression coefficient table, a normalized regression coefficient table and a behavior similarity table;
the input module is used for inputting questionnaire personality information of a user into the user personality information table and inputting user behavior data into the user multi-dimensional behavior data table;
the regression coefficient calculation module is used for respectively calling data from the user personality information table and the user multi-dimensional behavior data table, obtaining a regression coefficient of the behavior about the personality by utilizing linear regression, and storing the regression coefficient into the regression coefficient table;
the normalization module is used for calling data from the regression coefficient table, carrying out normalization processing on the regression coefficient to obtain a normalized regression coefficient, and storing the normalized regression coefficient into the normalized regression coefficient table;
the similarity calculation module is used for calling data from the normalized regression coefficient table, calculating the similarity between the behaviors based on the normalized regression coefficients of the two behaviors and storing the similarity into the behavior similarity table;
and the construction module is used for calling data from the behavior similarity table, storing the behaviors and the similarity between the behaviors into a graph database and constructing a probabilistic knowledge graph.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention can overcome the defect that the traditional knowledge graph mechanically describes things, and realizes effective representation of fuzzy facts;
2. the invention has the capability of reasoning uncertain facts under the condition of insufficient information and computing resources;
3. the invention has the ability of small sample learning and cross-modal knowledge, deeply insights the internal driving force of the user and realizes personalized image.
Drawings
FIG. 1 is a flowchart of a probabilistic knowledgegraph-based user portrayal method according to an embodiment of the present invention;
FIG. 2 is a block diagram of a probabilistic knowledgegraph-based user representation system according to an embodiment of the disclosure.
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 obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
The invention is described in further detail below with reference to the attached drawing figures:
the invention provides a user portrait method and a system based on a probability knowledge graph, which comprises the following steps: acquiring questionnaire personality information and user behavior data of a user; obtaining regression coefficients of the behavior about the personality by utilizing linear regression based on the questionnaire personality information and the user behavior data; carrying out normalization processing on the regression coefficient to obtain a normalized regression coefficient; calculating the similarity between the behaviors based on the normalized regression coefficients of the two behaviors; and storing the behaviors and the similarity between the behaviors into a graph database to construct a probabilistic knowledge graph.
The probability is introduced into the traditional knowledge graph, and the probability knowledge graph is used for expressing knowledge, so that the fuzzy fact can be effectively represented; meanwhile, a Non-Axiomatic Reasoning System NARS (Non-axial Reasoning System) is combined to enable the machine to have the capability of Reasoning uncertain facts under the condition of insufficient information and computing resources. In the knowledge reasoning process, a meta-knowledge network is extracted from the facet data through a meta-learning method and an internal drive mechanism based on a feature extraction and modal fusion method, so that the system has the capabilities of small sample learning, learning and cross-modal knowledge, realizes small data, cross-domain and personalized inference and prediction, and covers various fields of dimension including human consumption, social contact, entertainment and the like.
The method specifically comprises the following steps:
as shown in FIG. 1, the invention provides a user portrayal method based on a probability knowledge graph, which comprises the following steps:
step 1, creating a user personality information table, a user multi-dimensional behavior data table, a regression coefficient table, a normalized regression coefficient table and a behavior similarity table;
wherein,
a user personality information table, a user multi-dimensional behavior data table, a regression coefficient table, a normalized regression coefficient table and a behavior similarity table are created in a Hive database;
the questionnaire personality information comprises demographic information and personality information, wherein the demographic information comprises gender, age and region, and the personality information comprises openness and accountability; in the process of inputting the information into the personality information table of the user, if the information is missing, a missing value is stored;
user behavior data includes consumption preferences, music preferences, movie preferences, and color preferences; in the process of inputting the information into the user multi-dimensional behavior data table, if the information is missing, a missing value is stored;
the column names of the regression coefficient table and the normalization coefficient table are a behavior name and a personality name;
the column names of the behavior similarity table are 3 columns, which are behavior 1, behavior 2 and similarity, respectively.
And 2, inputting the questionnaire personality information of the user into a personality information table of the user, and inputting the user behavior data into a multi-dimensional behavior data table of the user.
Step 3, data are respectively retrieved from the user personality information table and the user multi-dimensional behavior data table, regression coefficients of behaviors about the personality are obtained through linear regression, and the regression coefficients are stored in the regression coefficient table;
wherein,
and taking the personality value as an explanation variable and the behavior value as an explained variable, and obtaining a regression coefficient of the behavior about the personality by utilizing linear regression.
Step 4, calling data from the regression coefficient table, carrying out normalization processing on the regression coefficients to obtain normalized regression coefficients, and storing the normalized regression coefficients into the normalized regression coefficient table;
wherein,
the formula of the normalization processing is as follows:
in the formula,for normalizing the regression coefficient, beta is the regression coefficient obtained above, betaiIs the i-th component of the regression coefficient β, and n is the vector length.
Step 5, calling the normalized regression coefficients of the two behaviors from the normalized regression coefficient table, calculating the similarity between the two behaviors based on the normalized regression coefficients of the two behaviors, and storing the similarity into the behavior similarity table;
wherein,
the formula for calculating the similarity between behaviors is:
where sim (x, y) is the similarity between the normalized regression coefficient x and the normalized regression coefficient y, xiIs the i-th component, y, of the normalized regression coefficient xiIs the i-th component of the normalized regression coefficient y.
And 6, constructing a neo4j graph database, calling data from the behavior similarity table, storing the similarity between behaviors into the graph database, and constructing a probabilistic knowledge graph.
As shown in FIG. 2, the present invention provides a user portrayal system based on probability knowledge mapping, for implementing the user portrayal method, comprising:
a creating module for implementing the step 1;
the recording module is used for realizing the step 2;
a regression coefficient calculation module for implementing the step 3;
a normalization module for implementing the step 4;
a similarity calculation module for implementing the step 5;
and a building module for realizing the step 6.
Based on the method and the system, the construction of the probabilistic knowledge graph about the human behavior characterization is completed, when the user is portrayed based on the method and the system, behavior nodes corresponding to the client need to be found out from a database, then the relation (coefficient) is used as the transition probability, and the preference of the user on other behaviors can be deduced by utilizing a random swimming model, so that the user portrait is constructed; the method mainly realizes the fuzzy depiction of subjective facts in a mode of combining a machine learning algorithm and personality analysis of behaviors.
The invention has the advantages that:
1. the invention can overcome the defect that the traditional knowledge graph mechanically describes things, and realizes effective representation of fuzzy facts;
2. the invention has the capability of reasoning uncertain facts under the condition of insufficient information and computing resources;
3. the invention has the ability of small sample learning and cross-modal knowledge, deeply insights the internal driving force of the user and realizes personalized image.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. A user portrait method based on probability knowledge graph is characterized by comprising the following steps:
acquiring questionnaire personality information and user behavior data of a user;
based on the questionnaire personality information and the user behavior data, taking the personality value as an explanation variable and the behavior value as an explained variable, and obtaining a regression coefficient of the behavior about the personality by utilizing linear regression;
carrying out normalization processing on the regression coefficient to obtain a normalized regression coefficient;
calculating the similarity between the behaviors based on the normalized regression coefficients of the two behaviors;
and storing the behaviors and the similarity between the behaviors into a graph database to construct a probabilistic knowledge graph.
2. A user representation method as claimed in claim 1, further comprising:
creating a user personality information table, a user multi-dimensional behavior data table, a regression coefficient table, a normalized regression coefficient table and a behavior similarity table;
inputting the questionnaire personality information into the user personality information table, and inputting the user behavior data into the user multi-dimensional behavior data table;
storing the regression coefficients into the regression coefficient table;
storing the normalized regression coefficients into the normalized regression coefficient table;
and storing the similarity between the behaviors into the behavior similarity table.
3. The user imaging method according to claim 2,
the questionnaire personality information comprises demographic information and personality information, wherein the demographic information comprises gender, age and region, and the personality information comprises openness and accountability; in the process of inputting the user personality information table, if information is missing, a missing value is stored;
the user behavior data comprises consumption preferences, music preferences, movie preferences, and color preferences; and if the information is missing, a missing value is stored in the process of inputting the information into the user multi-dimensional behavior data table.
4. The user imaging method according to claim 2,
column names of the regression coefficient table and the normalization coefficient table are behavior names and personality names;
the column names of the behavior similarity table are 3 columns, namely behavior 1, behavior 2 and similarity.
5. The user imaging method according to claim 2,
and the user personality information table, the user multi-dimensional behavior data table, the regression coefficient table, the normalized regression coefficient table and the behavior similarity table are created in the Hive database.
7. A user portrayal method according to claim 1 or 2, wherein the similarity between the activities is calculated by the formula:
where sim (x, y) is the similarity between the normalized regression coefficient x and the normalized regression coefficient y, xiIs the i-th component, y, of the normalized regression coefficient xiIs the i-th component of the normalized regression coefficient y.
8. The user imaging method according to claim 1 or 2, wherein said map database is a neo4j map database.
9. A probabilistic knowledge graph-based user portrayal system for implementing a user portrayal method as claimed in any one of claims 1 to 8, comprising:
the system comprises a creating module, a judging module and a judging module, wherein the creating module is used for creating a user personality information table, a user multi-dimensional behavior data table, a regression coefficient table, a normalized regression coefficient table and a behavior similarity table;
the input module is used for inputting questionnaire personality information of a user into the user personality information table and inputting user behavior data into the user multi-dimensional behavior data table;
the regression coefficient calculation module is used for respectively calling data from the user personality information table and the user multi-dimensional behavior data table, taking the personality value as an explanation variable and the behavior value as an explained variable, obtaining a regression coefficient of the behavior about the personality by utilizing linear regression, and storing the regression coefficient into the regression coefficient table;
the normalization module is used for calling data from the regression coefficient table, carrying out normalization processing on the regression coefficient to obtain a normalized regression coefficient, and storing the normalized regression coefficient into the normalized regression coefficient table;
the similarity calculation module is used for calling data from the normalized regression coefficient table, calculating the similarity between the behaviors based on the normalized regression coefficients of the two behaviors and storing the similarity into the behavior similarity table;
and the construction module is used for calling data from the behavior similarity table, storing the behaviors and the similarity between the behaviors into a graph database and constructing a probabilistic knowledge graph.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011455170.0A CN112446741B (en) | 2020-12-10 | 2020-12-10 | User portrayal method and system based on probability knowledge graph |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011455170.0A CN112446741B (en) | 2020-12-10 | 2020-12-10 | User portrayal method and system based on probability knowledge graph |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112446741A CN112446741A (en) | 2021-03-05 |
CN112446741B true CN112446741B (en) | 2022-02-15 |
Family
ID=74740399
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011455170.0A Active CN112446741B (en) | 2020-12-10 | 2020-12-10 | User portrayal method and system based on probability knowledge graph |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112446741B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114242235A (en) * | 2021-12-16 | 2022-03-25 | 北京阿叟阿巴科技有限公司 | Autism patient portrait method based on multi-level key characteristic behaviors |
CN118469679A (en) * | 2024-07-12 | 2024-08-09 | 暗物智能科技(广州)有限公司 | Financial product recommendation method and device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109903117A (en) * | 2019-01-04 | 2019-06-18 | 苏宁易购集团股份有限公司 | A kind of knowledge mapping processing method and processing device for commercial product recommending |
CN110019837A (en) * | 2017-12-22 | 2019-07-16 | 百度在线网络技术(北京)有限公司 | The generation method and device, computer equipment and readable medium of user's portrait |
CN110110094A (en) * | 2019-04-22 | 2019-08-09 | 华侨大学 | Across a network personage's correlating method based on social networks knowledge mapping |
CN110309316A (en) * | 2018-06-08 | 2019-10-08 | 腾讯科技(深圳)有限公司 | A kind of determination method, apparatus, terminal device and the medium of knowledge mapping vector |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150012471A1 (en) * | 2013-07-02 | 2015-01-08 | SenseGon Technologies Ltd. | System for user psychosocial profiling |
CN111090683B (en) * | 2019-11-29 | 2023-12-22 | 上海勘察设计研究院(集团)股份有限公司 | Knowledge graph construction method and generation device thereof in engineering field |
-
2020
- 2020-12-10 CN CN202011455170.0A patent/CN112446741B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110019837A (en) * | 2017-12-22 | 2019-07-16 | 百度在线网络技术(北京)有限公司 | The generation method and device, computer equipment and readable medium of user's portrait |
CN110309316A (en) * | 2018-06-08 | 2019-10-08 | 腾讯科技(深圳)有限公司 | A kind of determination method, apparatus, terminal device and the medium of knowledge mapping vector |
CN109903117A (en) * | 2019-01-04 | 2019-06-18 | 苏宁易购集团股份有限公司 | A kind of knowledge mapping processing method and processing device for commercial product recommending |
CN110110094A (en) * | 2019-04-22 | 2019-08-09 | 华侨大学 | Across a network personage's correlating method based on social networks knowledge mapping |
Also Published As
Publication number | Publication date |
---|---|
CN112446741A (en) | 2021-03-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108287864A (en) | A kind of interest group division methods, device, medium and computing device | |
Algan et al. | Well-being through the lens of the internet | |
CN112446741B (en) | User portrayal method and system based on probability knowledge graph | |
CN111949886B (en) | Sample data generation method and related device for information recommendation | |
US20190026637A1 (en) | Method and virtual data agent system for providing data insights with artificial intelligence | |
Mukkamala et al. | Towards a formal model of social data | |
CN117237574A (en) | Task-driven geographical digital twin scene enhancement visualization method and system | |
US9875443B2 (en) | Unified attractiveness prediction framework based on content impact factor | |
Khan et al. | Comparative analysis on Facebook post interaction using DNN, ELM and LSTM | |
CN116764236A (en) | Game prop recommending method, game prop recommending device, computer equipment and storage medium | |
US20060149614A1 (en) | Dynamic brand evaluation information processing apparatus and method | |
CN112819154B (en) | Method and device for generating pre-training model applied to graph learning field | |
Lin et al. | A comprehensive survey on deep learning techniques in educational data mining | |
CN117540703A (en) | Text generation method, model training method, device and electronic equipment | |
CN113392200A (en) | Recommendation method and device based on user learning behaviors | |
Liu et al. | The design of a moral education evaluation system for college students based on a deep learning model | |
Mahalle et al. | Foundations of data science for engineering problem solving | |
CN111797856A (en) | Modeling method, modeling device, storage medium and electronic equipment | |
Leung et al. | Theoretical and practical data science and analytics: challenges and solutions | |
CN113010772B (en) | Data processing method, related equipment and computer readable storage medium | |
Horstmann et al. | Alexa, What's Inside of You: A Qualitative Study to Explore Users' Mental Models of Intelligent Voice Assistants | |
Chandrasekar et al. | Data Exploratory Analysis for Classification in Machine Learning Algorithms | |
Le et al. | Improving deep matrix factorization with normalized cross entropy loss function for graph-based MOOC recommendation | |
CN115482019A (en) | Activity attention prediction method and device, electronic equipment and storage medium | |
Pargent et al. | An introduction to machine learning for psychologists in R |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 200040 9th floor, block a, 1256 and 1258 Wanrong Road, Jing'an District, Shanghai Applicant after: Huayuan computing technology (Shanghai) Co.,Ltd. Address before: 200040 9 / F, 1256, 1258, Wanrong Road, Jing'an District, Shanghai Applicant before: UNIDT TECHNOLOGY (SHANGHAI) Co.,Ltd. |
|
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |