WO2022062449A1 - Procédé et appareil de regroupement d'utilisateurs et dispositif électronique et support de stockage - Google Patents

Procédé et appareil de regroupement d'utilisateurs et dispositif électronique et support de stockage Download PDF

Info

Publication number
WO2022062449A1
WO2022062449A1 PCT/CN2021/096532 CN2021096532W WO2022062449A1 WO 2022062449 A1 WO2022062449 A1 WO 2022062449A1 CN 2021096532 W CN2021096532 W CN 2021096532W WO 2022062449 A1 WO2022062449 A1 WO 2022062449A1
Authority
WO
WIPO (PCT)
Prior art keywords
grouping
sample data
user
model
data
Prior art date
Application number
PCT/CN2021/096532
Other languages
English (en)
Chinese (zh)
Inventor
徐卓扬
赵惟
孙行智
胡岗
左磊
赵婷婷
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2022062449A1 publication Critical patent/WO2022062449A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/903—Querying
    • G06F16/9035—Filtering based on additional data, e.g. user or group profiles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"

Definitions

  • the present application relates to the technical field of artificial intelligence, and in particular, to a user grouping method, apparatus, electronic device, and computer-readable storage medium.
  • the inventor realized that the current user grouping methods are either knowledge-based user grouping methods or knowledge and data-based user grouping methods, both of which require professional guide knowledge, such as professional medical knowledge, to sort out , this sorting behavior requires a lot of human time, high cost, and low efficiency; and these two clustering methods are based on guide knowledge rather than pure data-driven models, which lack scalability.
  • a user grouping method is applied to an electronic device, and includes:
  • optimization loss function use the sample data to train the user grouping model to obtain an optimized user grouping model
  • the user data to be grouped is grouped by using the optimized user grouping model, a grouping result is obtained, and the grouping result is output through the display screen of the electronic device.
  • a user grouping device comprising:
  • the sample data acquisition module is used to acquire the user's return visit data from the database communicatively connected with the electronic device, and organize the return visit data to obtain the sample data;
  • a grouping prediction model training module configured to use the sample data to train a pre-built grouping prediction model, and use the trained grouping prediction model to obtain an output result of the sample data
  • a loss function improvement module configured to adjust the loss function of the pre-built user grouping model based on the output result to obtain an optimized loss function
  • the user grouping model training module uses the sample data to train the user grouping model to obtain an optimized user grouping model
  • the grouping module is configured to use the optimized user grouping model to group the user data to be grouped, obtain a grouping result, and output the grouping result through the display screen of the electronic device.
  • An electronic device comprising:
  • a processor that executes computer program instructions stored in the memory to achieve the following steps:
  • optimization loss function use the sample data to train the user grouping model to obtain an optimized user grouping model
  • the user data to be grouped is grouped by using the optimized user grouping model, a grouping result is obtained, and the grouping result is output through the display screen of the electronic device.
  • a computer-readable storage medium storing a computer program, the computer program being executed by a processor to implement the following steps:
  • optimization loss function use the sample data to train the user grouping model to obtain an optimized user grouping model
  • the user data to be grouped is grouped by using the optimized user grouping model, a grouping result is obtained, and the grouping result is output through the display screen of the electronic device.
  • the present application can achieve the purpose of more efficient, scalable, and purely data-driven user grouping.
  • FIG. 1 is a schematic flowchart of a user grouping method provided by an embodiment of the present application.
  • FIG. 2 is a schematic flowchart of a method for generating sample data according to an embodiment of the present application
  • FIG. 3 is a schematic flowchart of a model training method provided by an embodiment of the present application.
  • FIG. 4 is a schematic flowchart of a method for improving a loss function provided by an embodiment of the present application
  • FIG. 5 is a schematic flowchart of a method for generating an optimized user grouping model according to an embodiment of the present application
  • FIG. 6 is a schematic flowchart of a grouping method provided by an embodiment of the present application.
  • FIG. 7 is a schematic block diagram of a user grouping device according to an embodiment of the present application.
  • FIG. 8 is a schematic diagram of an internal structure of an electronic device for implementing a user grouping method provided by an embodiment of the present application.
  • the execution subject of the user grouping method provided by the embodiment of the present application includes, but is not limited to, at least one of the electronic devices that can be configured to execute the method provided by the embodiment of the present application, such as a server and a terminal.
  • the user grouping method can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform.
  • the server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
  • the user grouping method includes:
  • the database is connected in communication with the electronic device that executes the user grouping method described in this solution.
  • the user is a patient who has suffered from a disease. Therefore, the return visit data of the user includes long-term follow-up records of multiple patients, including but not limited to demographic information. , Inspection and inspection indicators, medication history, expert prescription and other indicator data.
  • the expert prescribing medicine can be considered as expert grouping, as the standard grouping result of user grouping.
  • the return visit data can be obtained from the database of the medical platform.
  • the return visit data can also be obtained from a preset blockchain node.
  • the re-visit data is sorted to obtain sample data, including:
  • the grouping prediction model described in this application is a deep neural network (Deep Neural Networks, DNN) model for predicting multi-classification problems.
  • the DNN model includes an input layer, a hidden layer, an output layer and a softmax function.
  • the input layer is used to receive data;
  • the hidden layer is used to calculate the data and enhance the classification capability of the model;
  • the output layer includes a plurality of output nodes, each output node outputs the corresponding category of the node
  • the softmax function is used to convert the output score to a probability value.
  • the grouping prediction model needs to be trained to improve the accuracy of the grouping prediction model.
  • the use of the sample data to train the pre-built grouping prediction model includes:
  • the preset stop condition means that the loss value no longer decreases.
  • H(p,q) is the loss function value
  • n is the total number of clustering schemes
  • p(x i ) is the true probability value of the i-th clustering scheme
  • q(x i ) is the predicted probability value of the i-th clustering scheme .
  • the sample data is input into the trained grouping prediction model, and the output result of the sample data is obtained.
  • the pre-built user grouping model is a DQN (Deep Q-learning, deep Q-value learning) model based on a deep reinforcement learning algorithm, which can optimize the long-term goal of the sequence decision problem.
  • DQN Deep Q-learning, deep Q-value learning
  • the input of the DQN model is state
  • the output is the Q (expected reward) value corresponding to each action
  • reward participates in training to optimize the model's selection of actions.
  • the input state of the user grouping model is the sample data
  • the action is the unique code of the grouping scheme
  • the loss function needs to be improved.
  • the loss function of the pre-built user grouping model is improved based on the output result, including:
  • the method for modifying the selection of the grouping scheme in the loss function includes:
  • a"' is the grouping scheme corresponding to the maximum Q value of the output after the sample data s' is input into the user grouping model; is the corresponding grouping scheme output by the user grouping model when the input is sample data s'
  • the Q value of , A′ DNN is the n clustering schemes with the highest output prediction probability value when the clustering prediction model inputs sample data s′, n is a preset constant, and can be 1/3 of the total number of all clustering schemes.
  • the preset penalty item is the penalty item that the current grouping scheme is higher than the expert grouping scheme, including:
  • P(s) is the penalty value
  • Q(s,a) is the Q value of the corresponding grouping scheme a output by the user grouping model when the input is sample data s
  • a DNN is the input sample of the grouping prediction model
  • the n clustering schemes with the highest predicted probability output when the data is s, n is a preset constant, and the value can be 1/3 of the total number of all clustering schemes; is the average of the Q values of all the grouping schemes output by the user grouping model when the input is the sample data s belonging to the A DNN .
  • the embodiment of the present application improves the loss function through the above steps to obtain an optimized loss function.
  • the optimized loss function includes:
  • the loss function is improved to limit the model's tendency to adopt a grouping scheme that is most likely to be decided by experts, thereby improving the credibility of the grouping scheme.
  • the S4 includes:
  • the present application utilizes a large amount of user return visit data collected for training and learning, and the data utilization rate is relatively high.
  • the user data to be grouped is grouped by using the optimized user grouping model to obtain a grouping scheme, including:
  • the optimized user grouping model is used to group patients, and the obtained grouping results can help doctors to quickly understand the treatment conditions of the patients, so as to carry out the next treatment plan.
  • a large amount of return visit data is collected as sample data, which is conducive to the subsequent optimization of the grouping model; the sample data is used to train a pre-built grouping prediction model, and the trained grouping prediction model is used to obtain the
  • the output result of the sample data uses the grouping prediction model to perform grouping prediction, which improves the work efficiency; adjusts the loss function of the pre-built user grouping model based on the output result to obtain an optimized loss function, and restricts the user grouping by improving the loss function.
  • the model adopts the grouping scheme most likely to be decided by experts to improve the accuracy of the grouping scheme; according to the optimization loss function, use the sample data to train the user grouping model to obtain an optimized user grouping model, and use the collected sample data for training.
  • the user grouping method, device and computer-readable storage medium proposed in this application can achieve the purpose of more efficient, scalable, and purely data-driven user grouping.
  • FIG. 7 it is a functional block diagram of the user grouping device of the present application.
  • the user grouping apparatus 100 described in this application may be installed in an electronic device. According to the implemented functions, the user grouping apparatus 100 may include a sample data acquisition module 101 , a grouping prediction model training module 102 , a loss function improvement module 103 , a user grouping model training module 104 and a grouping module 105 .
  • the modules described in the present invention can also be called units, which refer to a series of computer program segments that can be executed by the electronic device processor and can perform fixed functions, and are stored in the memory of the electronic device.
  • each module/unit is as follows:
  • the sample data acquisition module 101 is configured to acquire the user's return visit data from a database, and organize the return visit data to obtain sample data.
  • the sample data acquisition module 101 specifically performs the following operations:
  • the grouping prediction model training module 102 is configured to use the sample data to train a pre-built grouping prediction model, and use the trained grouping prediction model to obtain an output result of the sample data.
  • the grouping prediction model training module 102 specifically performs the following operations:
  • the parameters of the grouping prediction model are modified according to the loss function, and the grouping operation is performed again on the sample data by using the modified grouping prediction model until a preset stopping condition is reached.
  • the loss function improvement module 103 is configured to adjust the loss function of the pre-built user grouping model based on the output result to obtain an optimized loss function.
  • the method for modifying the selection of the grouping scheme in the loss function includes:
  • a"' is the grouping scheme corresponding to the maximum Q value of the output after the sample data s' is input into the user grouping model; is the corresponding grouping scheme output by the user grouping model when the input is sample data s'
  • the Q value of , A′ DNN is the n clustering schemes with the highest output prediction probability value when the clustering prediction model inputs sample data s′, n is a preset constant, and can be 1/3 of the total number of all clustering schemes.
  • the optimized loss function includes:
  • the loss function is improved to limit the model's tendency to adopt a grouping scheme that is most likely to be decided by experts, thereby improving the credibility of the grouping scheme.
  • the user grouping model training module 104 is configured to use the sample data to train the user grouping model according to the optimization loss function to obtain an optimized user grouping model.
  • the user grouping model training module 104 is specifically used for:
  • the optimized user grouping model is obtained.
  • the grouping module 105 is configured to use the optimized user grouping model to group the user data to be grouped, obtain a grouping result, and output the grouping result.
  • the grouping module 105 specifically performs the following operations:
  • the grouping scheme with the largest expected reward value (Q value) is selected as the grouping result of the user data to be grouped.
  • FIG. 8 it is a schematic structural diagram of an electronic device implementing the user grouping method of the present application.
  • the electronic device 1 may include a processor 10, a memory 11 and a bus, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a user grouping program 12.
  • the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, magnetic disk, CD etc.
  • the memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a mobile hard disk of the electronic device 1 .
  • the memory 11 may also be an external storage device of the electronic device 1, such as a pluggable mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital) equipped on the electronic device 1. , SD) card, flash memory card (Flash Card), etc.
  • the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device.
  • the memory 11 can not only be used to store application software installed in the electronic device 1 and various types of data, such as the code of the user grouping program 12, etc., but also can be used to temporarily store data that has been output or will be output.
  • the processor 10 may be composed of integrated circuits, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits packaged with the same function or different functions, including one or more integrated circuits.
  • Central Processing Unit CPU
  • microprocessor digital processing chip
  • graphics processor and combination of various control chips, etc.
  • the processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect the various components of the entire electronic device, by running or executing the program or module (for example, executing the program) stored in the memory 11. User grouping program, etc.), and call the data stored in the memory 11 to execute various functions of the electronic device 1 and process data.
  • the bus may be a peripheral component interconnect (PCI for short) bus or an extended industry standard architecture (Extended industry standard architecture, EISA for short) bus or the like.
  • PCI peripheral component interconnect
  • EISA Extended industry standard architecture
  • the bus can be divided into address bus, data bus, control bus and so on.
  • the bus is configured to implement connection communication between the memory 11 and at least one processor 10 and the like.
  • FIG. 8 only shows an electronic device with components. Those skilled in the art can understand that the structure shown in FIG. 8 does not constitute a limitation on the electronic device 1, and may include fewer or more components than those shown in the figure. components, or a combination of certain components, or a different arrangement of components.
  • the electronic device 1 may also include a power supply (such as a battery) for powering the various components, preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that the power management
  • the device implements functions such as charge management, discharge management, and power consumption management.
  • the power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and any other components.
  • the electronic device 1 may further include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.
  • the electronic device 1 may also include a network interface, optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used in the electronic device 1 Establish a communication connection with other electronic devices.
  • a network interface optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used in the electronic device 1 Establish a communication connection with other electronic devices.
  • the electronic device 1 may further include a user interface, and the user interface may be a display (Display), an input unit (eg, a keyboard (Keyboard)), optionally, the user interface may also be a standard wired interface or a wireless interface.
  • the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, and the like.
  • the display may also be appropriately called a display screen or a display unit, which is used for displaying information processed in the electronic device 1 and for displaying a visualized user interface.
  • the user grouping program 12 stored in the memory 11 in the electronic device 1 is a combination of multiple instructions, and when running in the processor 10, can realize:
  • optimization loss function use the sample data to train the user grouping model to obtain an optimized user grouping model
  • the user data to be grouped is grouped by using the optimized user grouping model, a grouping result is obtained, and the grouping result is output through the display screen of the electronic device.
  • the modules/units integrated by the electronic device 1 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium, and the computer-readable storage medium can be stored in a computer-readable storage medium. Can be volatile or non-volatile.
  • the computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory) .
  • the computer-readable medium stores a computer program, and the computer program is executed by the processor to realize the following steps:
  • optimization loss function use the sample data to train the user grouping model to obtain an optimized user grouping model
  • the user data to be grouped is grouped by using the optimized user grouping model, a grouping result is obtained, and the grouping result is output through the display screen of the electronic device.
  • modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional module in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units can be implemented in the form of hardware, or can be implemented in the form of hardware plus software function modules.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Strategic Management (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Economics (AREA)
  • Databases & Information Systems (AREA)
  • Human Resources & Organizations (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

L'invention concerne un procédé et un appareil de regroupement d'utilisateurs et un dispositif électronique et un support de stockage lisible par ordinateur. Le procédé consiste : à acquérir, dans une base de données, des données de visite de retour d'un utilisateur et à organiser ces données de visite de retour pour obtenir des données d'échantillon (S1) ; à entraîner un modèle de prédiction de regroupement préconstruit de manière à obtenir un résultat de sortie des données d'échantillon (S2) ; à ajuster une fonction de perte d'un modèle de regroupement d'utilisateurs préconstruit sur la base du résultat de sortie de manière à obtenir une fonction de perte optimisée (S3) ; à entraîner le modèle de regroupement d'utilisateurs d'après la fonction de perte optimisée de façon à obtenir un modèle de regroupement d'utilisateurs optimisé (S4) ; et au moyen du modèle de regroupement d'utilisateurs optimisé, à regrouper les données d'utilisateurs à regrouper pour obtenir un résultat de regroupement, et à fournir le résultat de regroupement au moyen d'un écran d'affichage (S5). L'efficacité et l'extensibilité du regroupement d'utilisateurs sont améliorées. Les données de visite de retour peuvent également être stockées dans une chaîne de blocs.
PCT/CN2021/096532 2020-09-25 2021-05-27 Procédé et appareil de regroupement d'utilisateurs et dispositif électronique et support de stockage WO2022062449A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011021840.8A CN112115322B (zh) 2020-09-25 2020-09-25 用户分群方法、装置、电子设备及存储介质
CN202011021840.8 2020-09-25

Publications (1)

Publication Number Publication Date
WO2022062449A1 true WO2022062449A1 (fr) 2022-03-31

Family

ID=73796783

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/096532 WO2022062449A1 (fr) 2020-09-25 2021-05-27 Procédé et appareil de regroupement d'utilisateurs et dispositif électronique et support de stockage

Country Status (2)

Country Link
CN (1) CN112115322B (fr)
WO (1) WO2022062449A1 (fr)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112115322B (zh) * 2020-09-25 2024-05-07 平安科技（深圳）有限公司 用户分群方法、装置、电子设备及存储介质
CN113112346A (zh) * 2021-04-30 2021-07-13 平安普惠企业管理有限公司 用户分类方法、装置、电子设备及存储介质
CN113782192A (zh) * 2021-09-30 2021-12-10 平安科技（深圳）有限公司 基于因果推断的分群模型构建方法和医疗数据处理方法
CN114742238B (zh) * 2022-06-14 2022-09-09 四川省郫县豆瓣股份有限公司 豆瓣酱的原料筛选方法、装置、设备及介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108364131A (zh) * 2018-02-09 2018-08-03 合不合（厦门）网络科技有限公司 利用类神经网络进行人格类型的自动识别与分群的方法
CN109086787A (zh) * 2018-06-06 2018-12-25 平安科技（深圳）有限公司 用户画像获取方法、装置、计算机设备以及存储介质
CN109451523A (zh) * 2018-11-23 2019-03-08 南京邮电大学 基于流量识别技术和q学习的快速切换方法
CN109447685A (zh) * 2018-09-26 2019-03-08 中国平安人寿保险股份有限公司 基于机器学习的产品数据推送方法、装置和计算机设备
CN110473147A (zh) * 2018-05-09 2019-11-19 腾讯科技（深圳）有限公司 一种视频去模糊方法和装置
CN110706303A (zh) * 2019-10-15 2020-01-17 西南交通大学 基于GANs的人脸图像生成方法
CN111199240A (zh) * 2018-11-16 2020-05-26 马上消费金融股份有限公司 银行卡识别模型的训练方法、银行卡识别方法以及装置
CN112115322A (zh) * 2020-09-25 2020-12-22 平安科技（深圳）有限公司 用户分群方法、装置、电子设备及存储介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102106684B1 (ko) * 2018-02-22 2020-05-04 한국과학기술원 동적인 피쳐 획득과 분류를 위한 공동 학습 프레임워크
CN111062491B (zh) * 2019-12-13 2024-06-14 陕西国王的朋友教育科技有限公司 一种基于强化学习的智能体探索未知环境方法
CN111091710A (zh) * 2019-12-18 2020-05-01 上海天壤智能科技有限公司 交通信号控制方法、系统及介质
CN111666494B (zh) * 2020-05-13 2022-08-12 平安科技（深圳）有限公司 分群决策模型生成、分群处理方法、装置、设备及介质
CN111683010B (zh) * 2020-05-26 2022-07-05 广东省电信规划设计院有限公司 基于光缆网光路的双路由的生成方法及装置
CN111651220B (zh) * 2020-06-04 2023-08-18 上海电力大学 一种基于深度强化学习的Spark参数自动优化方法及系统

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108364131A (zh) * 2018-02-09 2018-08-03 合不合（厦门）网络科技有限公司 利用类神经网络进行人格类型的自动识别与分群的方法
CN110473147A (zh) * 2018-05-09 2019-11-19 腾讯科技（深圳）有限公司 一种视频去模糊方法和装置
CN109086787A (zh) * 2018-06-06 2018-12-25 平安科技（深圳）有限公司 用户画像获取方法、装置、计算机设备以及存储介质
CN109447685A (zh) * 2018-09-26 2019-03-08 中国平安人寿保险股份有限公司 基于机器学习的产品数据推送方法、装置和计算机设备
CN111199240A (zh) * 2018-11-16 2020-05-26 马上消费金融股份有限公司 银行卡识别模型的训练方法、银行卡识别方法以及装置
CN109451523A (zh) * 2018-11-23 2019-03-08 南京邮电大学 基于流量识别技术和q学习的快速切换方法
CN110706303A (zh) * 2019-10-15 2020-01-17 西南交通大学 基于GANs的人脸图像生成方法
CN112115322A (zh) * 2020-09-25 2020-12-22 平安科技（深圳）有限公司 用户分群方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN112115322A (zh) 2020-12-22
CN112115322B (zh) 2024-05-07

Similar Documents

Publication Publication Date Title
WO2022062449A1 (fr) Procédé et appareil de regroupement d'utilisateurs et dispositif électronique et support de stockage
WO2021151306A1 (fr) Procédé et appareil d'analyse intelligente de matériel linguistique de questions-réponses, dispositif électronique et support d'enregistrement lisible
WO2022160449A1 (fr) Procédé et appareil de classification de texte, dispositif électronique et support de stockage
WO2021208703A1 (fr) Procédé et appareil d'analyse de question, dispositif électronique et support d'enregistrement
WO2021151271A1 (fr) Procédé et appareil de réponse textuelle à des questions faisant appel à des entités nommées, ainsi que dispositif et support d'enregistrement
WO2022222943A1 (fr) Procédé et appareil de recommandation de département, dispositif électronique et support de stockage
WO2022222300A1 (fr) Procédé et appareil d'extraction de relation ouverte, dispositif électronique et support de stockage
WO2023029511A1 (fr) Procédé et appareil d'inspection intelligente pour un médicament sur ordonnance médicale en ligne, et dispositif ainsi que support de stockage
WO2021238563A1 (fr) Procédé et appareil d'analyse de données de fonctionnement d'entreprise basés sur un algorithme de configuration, et dispositif électronique et support
CN113626606B (zh) 信息分类方法、装置、电子设备及可读存储介质
WO2021114635A1 (fr) Procédé de construction de modèle de regroupement de patients, procédé de regroupement de patients et dispositif associé
WO2022141840A1 (fr) Procédé et appareil de recherche d'architecture de réseau, dispositif électronique et support
US20240112807A1 (en) Modular data system for processing multimodal data and enabling parallel recommendation system processing
CN116860935A (zh) 基于提示词问答交互的内容管理方法、装置、设备及介质
WO2022227171A1 (fr) Procédé et appareil d'extraction d'informations clés, dispositif électronique et support
WO2021139223A1 (fr) Procédé et appareil d'interprétation d'un modèle de regroupement, dispositif informatique et support d'enregistrement
WO2019085464A1 (fr) Procédé et dispositif de notation de document d'infraction, et support d'informations lisible par ordinateur
CN116719891A (zh) 中医信息分组聚类方法、装置、设备及计算机存储介质
CN116720525A (zh) 基于问诊数据的疾病辅助分析方法、装置、设备及介质
WO2023178979A1 (fr) Procédé et appareil d'étiquetage de question, dispositif électronique et support de stockage
US20220309404A1 (en) Method of and system for identifying and enumerating cross-body degradations
US20230068453A1 (en) Methods and systems for determining and displaying dynamic patient readmission risk and intervention recommendation
CN112259254B (zh) 基于交互反馈的病例搜索方法、装置及可读存储介质
CN112232408B (zh) 目标推荐方法、装置、电子设备及计算机可读存储介质
WO2022141838A1 (fr) Procédé et appareil d'analyse de confiance de modèle, dispositif électronique et support de stockage informatique

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21870836

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21870836

Country of ref document: EP

Kind code of ref document: A1