CN112035611B - Target user recommendation method, device, computer equipment and storage medium - Google Patents
Target user recommendation method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112035611B CN112035611B CN202010887774.6A CN202010887774A CN112035611B CN 112035611 B CN112035611 B CN 112035611B CN 202010887774 A CN202010887774 A CN 202010887774A CN 112035611 B CN112035611 B CN 112035611B
- Authority
- CN
- China
- Prior art keywords
- user
- information
- historical
- portrait
- medical consultation
- 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
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
- G06F16/95—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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to user consumption portraits in the field of data analysis, in particular to a target user recommendation method, a target user recommendation device, computer equipment and a storage medium. According to the method, a user portrait is searched according to a medical consultation message sent by a receiving terminal, so as to obtain user portrait information; extracting user characteristic information corresponding to the medical consultation message and the user portrait information; acquiring user quality parameters corresponding to the user according to the user characteristic information; and recommending the target user to the medical service provider according to the user portrait information and the user quality parameter. According to the recommendation method and the recommendation device, the user characteristic information is mined through the consultation information of the user and the user portrait information mining, the user quality parameter is determined based on the user characteristic information, so that the target client is selected, the target user is recommended to the medical service provider, and the recommendation effective rate of the target user can be effectively improved.
Description
Technical Field
The present invention relates to consumer image processing in the field of data analysis, and in particular, to a target user recommendation method, apparatus, computer device, and storage medium.
Background
With the development of computer technology and artificial intelligence technology, user portrayal technology has emerged. User portraits are widely used in various fields as an effective tool for outlining target users, contacting user appeal and design directions. In the context of the big data age, user information is enriched in networks, each specific information of users is abstracted into labels, and the user images are materialized by using the labels, so that targeted services are provided for the users.
Currently, techniques for user portrayal analysis based on medical big data are mainly focused on analysis through specialized structured knowledge of patient personal population information, electronic health files, electronic medical records, and physical examination reports. However, this solution requires a lot of manpower and material costs, and the locality and universality of the obtained sample are often limited, so that the recommendation to the user cannot be effectively realized.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a target user recommendation method, apparatus, computer device, and storage medium that can improve recommendation efficiency.
A target user recommendation method, the method comprising:
receiving a medical consultation message sent by a terminal, and searching a user portrait according to the medical consultation message to obtain user portrait information;
Extracting user characteristic information corresponding to the medical consultation message and the user portrait information;
acquiring user quality parameters corresponding to the user according to the user characteristic information;
and recommending the target user to the medical service provider according to the user portrait information and the user quality parameter.
In one embodiment, the user image information includes real-time image features and offline interrogation features;
the receiving terminal sends the medical consultation message, searches the user portrait according to the medical consultation message, and obtains the user portrait information, which comprises the following steps:
receiving a medical consultation message sent by a terminal;
analyzing the medical consultation message to obtain a user identifier corresponding to the terminal;
and extracting the real-time portrait features from a preset online hive database platform according to the user identification, and extracting the offline inquiry features from a preset offline updating platform according to the user identification.
In one embodiment, the user image information includes real-time image features and offline interrogation features;
the medical consultation message sent by the receiving terminal searches the user portrait according to the medical consultation message, and before obtaining the user portrait information, the method further comprises the following steps:
Acquiring an image information update request;
searching user identity information, historical inquiry flow information and historical inquiry transaction information corresponding to the portrait information update request;
acquiring real-time portrait features according to the user identity information and the historical inquiry flow information, storing the real-time portrait features to a preset online hive database platform, acquiring offline inquiry features according to the historical inquiry transaction information, and storing the offline inquiry features to a preset offline updating platform.
In one embodiment, the receiving the medical consultation message sent by the terminal searches the user portrait according to the medical consultation message, and obtaining the user portrait information includes:
receiving a medical consultation message sent by a terminal;
inputting the medical consultation message into a preset semantic recognition model to obtain a recognition result;
and searching the user portrait according to the medical consultation information when the identification result represents that the medical consultation information is a valid message, so as to obtain user portrait information.
In one embodiment, the obtaining the user quality parameter corresponding to the user according to the user characteristic information includes:
constructing a multidimensional feature matrix according to the user feature information;
Inputting the multidimensional feature matrix into a preset user quality evaluation model to obtain user quality parameters corresponding to the user, wherein the preset user quality evaluation model is obtained by an initial xgboost model through supervised training based on labeled historical feature data.
In one embodiment, before the constructing the multidimensional feature matrix according to the user feature information, the method further includes:
acquiring a user type corresponding to a historical user and historical characteristic data;
determining the differentiation characteristics corresponding to each type of user according to the user type corresponding to the historical user and the historical characteristic data;
performing pearson correlation coefficient analysis on the differential features to obtain strong correlation feature types corresponding to the historical feature data;
the constructing a multidimensional feature matrix according to the user feature information comprises the following steps:
and constructing a multidimensional feature matrix according to the user feature information corresponding to the strong correlation feature type.
A target user recommendation device, the device comprising:
the information searching module is used for receiving the medical consultation message sent by the terminal, searching the user portrait according to the medical consultation message and obtaining user portrait information;
The feature extraction module is used for extracting the medical consultation message and the user feature information corresponding to the user portrait information;
the quality parameter evaluation module is used for acquiring user quality parameters corresponding to the user according to the user characteristic information;
and the target recommendation module is used for recommending target users to the medical service provider according to the user portrait information and the user quality parameters.
In one embodiment, the user image information includes a real-time image feature and an offline inquiry feature, and the information searching module is configured to:
receiving a medical consultation message sent by a terminal;
analyzing the medical consultation message to obtain a user identifier corresponding to the terminal;
and extracting the real-time portrait features from a preset online hive database platform according to the user identification, and extracting the offline inquiry features from a preset offline updating platform according to the user identification.
A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:
receiving a medical consultation message sent by a terminal, and searching a user portrait according to the medical consultation message to obtain user portrait information;
Extracting user characteristic information corresponding to the medical consultation message and the user portrait information;
acquiring user quality parameters corresponding to the user according to the user characteristic information;
and recommending the target user to the medical service provider according to the user portrait information and the user quality parameter.
A computer storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
receiving a medical consultation message sent by a terminal, and searching a user portrait according to the medical consultation message to obtain user portrait information;
extracting user characteristic information corresponding to the medical consultation message and the user portrait information;
acquiring user quality parameters corresponding to the user according to the user characteristic information;
and recommending the target user to the medical service provider according to the user portrait information and the user quality parameter.
The target user recommending method, the target user recommending device, the target user recommending computer equipment and the target user recommending storage medium are characterized in that the target user recommending storage medium is used for searching a user portrait according to the medical consultation message sent by the receiving terminal to obtain user portrait information; extracting user characteristic information corresponding to the medical consultation message and the user portrait information; acquiring user quality parameters corresponding to the user according to the user characteristic information; and recommending the target user to the medical service provider according to the user portrait information and the user quality parameter. According to the recommendation method and the recommendation device, the user characteristic information is mined through the consultation information of the user and the user portrait information mining, the user quality parameter is determined based on the user characteristic information, so that the target client is selected, the target user is recommended to the medical service provider, and the recommendation effective rate of the target user can be effectively improved.
Drawings
FIG. 1 is an application scenario diagram of a target user recommendation method in one embodiment;
FIG. 2 is a flow chart of a target user recommendation method in one embodiment;
FIG. 3 is a schematic flow chart illustrating a sub-process of step 201 in FIG. 2 according to one embodiment;
FIG. 4 is a flowchart illustrating steps for storing user profile information in one embodiment;
FIG. 5 is a schematic flow chart illustrating a sub-process of step 201 in FIG. 2 according to another embodiment;
FIG. 6 is a schematic flow chart illustrating a sub-process of step 205 in FIG. 2 according to one embodiment;
FIG. 7 is a block diagram of a target user recommendation device in one embodiment;
fig. 8 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The target user recommending method provided by the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the target recommendation server 104 via a network. When a user performs medical inquiry through an intelligent medical interaction platform, the target recommendation server 104 carrying the target user recommendation method can perform simulated inquiry and answer communication with the user through the medical interaction platform, so that corresponding user quality parameters of the user can be obtained through medical consultation information of the user and user portrait information. Specifically, the user may log into the medical interaction platform through the terminal 102. First, the terminal 102 transmits a medical advice message to the target recommendation server 104. The target recommendation server 104 receives the medical consultation message sent by the terminal 102, searches the user portrait according to the medical consultation message, and obtains user portrait information; extracting user characteristic information corresponding to the medical consultation message and the user image information; acquiring user quality parameters corresponding to a user according to the user characteristic information; and recommending the target user to the medical service provider according to the user portrait information and the user quality parameters. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smartphones, tablet computers, and portable wearable devices, and the server 104 may be implemented by a stand-alone server or a server cluster composed of a plurality of servers.
In one embodiment, as shown in fig. 2, a target user recommendation method is provided, and the method is applied to the target recommendation server 104 in fig. 1 for illustration, and includes the following steps:
The medical consultation message refers to a piece of inquiry information submitted by the user to the medical interactive platform. Specifically, the method comprises the following steps: inquiry information about what disease symptom a corresponds to, or whether a disease can be treated with medicine a. The user portrait information is a message stored in the system after the pointer images the user.
Specifically, the present invention relates to a method for manufacturing a semiconductor device. According to the scheme, the user recommendation server can add corresponding feature labels for the user based on the use of the medical interaction platform by the user and the identity information of the user, and construct a user portrait of the user, and when the user obtains medical services by using the online medical platform, the user can be analyzed through the user portrait information, so that the function of user recommendation is realized. The server can also feed back some information simulating inquiry to the user by the target recommendation server 104 during the consultation process, so as to extract data such as main complaints, template inquiry and diagnosis labels corresponding to the medical consultation information, and more completely supplement the medical self-selection information.
And 203, extracting user characteristic information corresponding to the medical consultation message and the user image information.
The user image information includes general specific features, corresponding user feature information needs to be extracted from the user image information in order to effectively perform subsequent user quality parameter extraction, and medical consultation information and user features available in the user image information can be extracted. In one embodiment, step S203 further includes a step of simplifying features, for example, for the historical inquiry transaction information included in the user portrait information, the historical inquiry transaction information of the user in different historical time periods may be obtained first, for example, the historical inquiry transaction information of 365 days, 180 days, 90 days and 60 days is directly used as features to perform calculation, and meanwhile, the historical inquiry transaction information is expressed in intervals, so that the longitudinal dimension of the feature vector is further reduced, and the space complexity required for constructing the feature vector is reduced. The characteristics of the mouth dimensions such as age, sex, province and the like can be expressed by one-dimensional digital characteristics, and the user characteristics are further simplified.
And step 205, acquiring user quality parameters corresponding to the user according to the user characteristic information.
Wherein the user quality parameter is an evaluation criterion for recommending the user. The user quality parameters corresponding to the user can be comprehensively obtained according to a plurality of different user characteristic information.
In particular, in one embodiment, the user quality parameter may be performed by a specific requirement of the medical service provider, for example, a higher user quality parameter may be allocated to the medical service provider according to a feature of high user yield, or a higher user quality parameter may be allocated to the medical service provider according to a feature of rich content of the user consultation message. In a specific embodiment, the user quality parameters corresponding to the user characteristic information may be extracted through a pre-built preset user quality evaluation model. The preset user quality evaluation model can be specifically an xgboost model, is obtained through supervised training, and evaluates the user quality by inputting a multidimensional feature matrix containing user feature information into the user quality evaluation model, for example, the purchase intention of an online user on a prescription can be embodied through user quality parameters, so that a platform user with higher quality is effectively extracted. In one embodiment, the user quality parameter may be performed by specific requirements of the medical service provider, for example, a higher user quality parameter may be allocated to the medical service provider according to a feature of high user success rate, or a higher user quality parameter may be allocated to the medical service provider according to a feature of rich content of the user consultation message.
The preset user quality evaluation model is used for evaluating the quality of the user, and specifically, the recommendation of the target user can be performed by quantifying the quality of the user into corresponding user quality parameters, and in one embodiment, the user quality parameters specifically may refer to the success rate of the user completing the prescription drug transaction through the online medical platform. The preset user quality evaluation model can be specifically an xgboost model, is obtained through supervised training, and evaluates the user quality by inputting a multidimensional feature matrix containing user feature information into the user quality evaluation model, so that the purchase intention of an online user on a prescription is stripped from massive inquiry, and a platform user with higher quality can be effectively extracted from massive users of the medical interaction platform.
The medical service provider is a processing party providing medical service for the user on the online medical platform, for example, the medical service provider can remotely inquire the user according to the medical consultation of the user, give prescriptions, take medicines and the like. Similar to the store of an e-commerce platform. The target user recommending method is used for recommending high-quality users to the medical service providers.
After determining the quality parameters of the user, the respective target user may be recommended to the medical service provider on the online medical platform based on the quality parameters of the user, in particular, the medical service provider of the online medical platform may set the respective user quality parameters online while setting up medical advice messages with which diagnostic tags may be accepted. After the user recommendation server obtains the user quality parameters corresponding to the user, the user recommendation server can determine which medical service providers the user meets the requirements on the basis of the diagnosis labels corresponding to the medical consultation messages and the user quality parameters, and then recommend the current user to the medical service providers.
According to the target user recommending method, the medical consultation message sent by the receiving terminal is used for searching the user portrait according to the medical consultation message to obtain user portrait information; extracting user characteristic information corresponding to the medical consultation message and the user image information; acquiring user quality parameters corresponding to a user according to the user characteristic information; and recommending the target user to the medical service provider according to the user portrait information and the user quality parameters. According to the recommendation method and the recommendation device, the user characteristic information is mined through the consultation information of the user and the user portrait information mining, the user quality parameter is determined based on the user characteristic information, so that the target client is selected, the target user is recommended to the medical service provider, and the recommendation effective rate of the target user can be effectively improved.
In one embodiment, the user image information includes real-time portrait features and offline consultation features, as shown in FIG. 3, step 201 includes:
and 302, receiving a medical consultation message sent by the terminal.
And 304, analyzing the medical consultation message to obtain the user identification corresponding to the terminal.
And 306, extracting real-time portrait features from a preset online hive database platform according to the user identification, and extracting offline inquiry features from a preset offline updating platform according to the user identification.
The user portrait information can be calculated and stored in a layered mode through an online hive database platform according to user identification. The storage system of the user portrait information is divided into an online real-time storage module and an offline update module. The online module corresponding to the real-time portrait features can respond to the portrait features of the user in real time, and the information contained in the features specifically comprises information such as user identity information, inquiry flow information and the like. And the offline module corresponding to the offline inquiry feature can update the historical inquiry transaction information and other features of the user at regular time.
Specifically, in order to improve the calculation efficiency in the target recommendation process, in the application, the portrait information related to the user is saved through two modes of offline storage and online updating. When the target user recommendation is required, the target recommendation server 104 firstly receives the medical consultation message sent by the terminal, and then analyzes the medical consultation message to acquire the user identification of the user portrait data in the user searching database; the user identification may be in the form of a UID, i.e. a user account number. Then the target recommendation server 104 extracts real-time portrait features from the preset online hive database platform according to the user identification, and extracts offline inquiry features from the preset offline update platform according to the user identification. In this embodiment, through the organic integration of the online module and the offline module, the storage of the user portrait information can be more accurately realized on the premise of not affecting the fluency of the processing environment, so that the accuracy of target user recommendation is improved.
In one embodiment, as shown in fig. 4, before step 201, the method further includes:
Wherein, the portrait information update request refers to that the corresponding portrait information update request is generated every time the user uses the medical interactive platform. The historical inquiry flow information refers to information generated in the process of carrying out online inquiry by a user through the medical interaction platform each time. The historical inquiry transaction information refers to whether the user receives a prescription issued by a doctor on line after on-line inquiry through the medical interaction platform, and purchases a corresponding historical record of the medicine according to the prescription.
Specifically, the user portrait information of the user can be stored through a pre-designed high-performance storage module to conveniently and quickly retrieve relevant portrait data of the user, for example, in one embodiment, 23 dimension online features can be input into a preset online hive database platform through a service party in the form of json character strings to be stored, and meanwhile, a 15 dimension offline feature cluster is stored and retrieved in a rediss storage unit (from the preset offline update platform) in a mode of background zeus timing task update. When the online model is called, the user identification is used as a key value for searching, and related features can be quickly called. At the system level, the comprehensive characteristics of the current user are stored in the form of key value pairs in redis for subsequent application calling. In this embodiment, the user image information of the user is stored by presetting the online hive database platform and presetting the offline update platform, so that when the target user recommends, image information extraction can be more efficiently realized, and the processing efficiency is ensured.
In one embodiment, as shown in fig. 5, step 201 includes:
The preset semantic recognition model can be specifically a classified neural network model, and is used for carrying out semantic classification on medical consultation information input by a user, and dividing the medical consultation information into effective consultation and ineffective consultation. When the medical consultation information input by the user is meaningless information such as 'hello' or 'thank you' which is not related to inquiry, the medical consultation information input by the user is determined to be effective consultation, and when the medical consultation information input by the user is specific symptom information, the medical consultation information input by the user can be judged to be ineffective consultation.
Specifically, the message sent by the user on the online medical platform is not necessarily effective medical information, and in order to not waste the computing resources of the user recommendation server 104, whether the message is an effective medical message may be determined before the medical consultation message is analyzed. This step may be specifically judged by a neural network model of semantic recognition. For the case that the medical consultation message is not a valid medical message, the server directly feeds back the consultation failure message to the user, and if the consultation failure message is a valid message, the subsequent analysis operation can be performed. By carrying out semantic recognition processing on the medical consultation message, invalid information is removed, the misoperation rate recommended by a target user can be effectively reduced, and the recommended processing efficiency is improved.
In one embodiment, as shown in FIG. 6, step 205 includes:
The multidimensional feature matrix is acquired based on all user feature information, and features of user identity dimensions such as age, gender, province and the like are expressed through one-dimensional digital features, so that user features are further simplified. Based on all features in the real-time portrait features and the offline consultation features, a multidimensional feature matrix corresponding to the feature type number can be constructed, so that the multidimensional feature matrix is used as a model input to estimate the user quality parameters. In addition, before step 603, a step of constructing a preset user quality assessment model is further included, specifically, historical data can be acquired, then historical feature information corresponding to the historical data is constructed based on predetermined feature parameters, corresponding labels are added to the historical feature information, then the initial xgboost model is subjected to supervised training based on the labeled historical feature information, the preset user quality assessment model is respectively trained and verified by dividing the labeled historical feature information into a training set and a verification set, and when the result obtained after verification is that the model is available, a trained model is output to serve as the preset user quality assessment model. In this embodiment, the xgboost model is used to extract the quality parameters of the user, so that the efficiency and accuracy of the quality parameter extraction process can be effectively improved.
In one embodiment, before step 601, the method further includes: acquiring a user type corresponding to a historical user and historical characteristic data; according to the user types corresponding to the historical users and the historical feature data, determining the differentiated features corresponding to the users of all types; and carrying out pearson correlation coefficient analysis on the differential features to obtain strong correlation feature types corresponding to the historical feature data. Step 601 comprises: and constructing a multidimensional feature matrix according to the user feature information corresponding to the strong correlation feature type.
The user recommendation server 104 may determine which users in the history users are high-quality users and which users are low-quality users in advance according to the requirements of the medical service provider, and add corresponding users with high success rate as high-quality users and low success rate as low-quality users for the users. The user recommendation server 104 may then perform computer statistical analysis on the real-time big data of the online medical platform to obtain the differentiated features of the high-quality user and the low-quality user piece. And then obtaining a strong correlation characteristic by analyzing the pearson correlation coefficient. The determined strong correlation characteristic is the available characteristic in the calculation process of the user quality parameter. In this embodiment, the multidimensional feature matrix is constructed by the strong correlation feature type correlated with the user quality, so that the validity of the user parameter in the user quality parameter can be ensured, and the calculation accuracy of the user quality parameter is improved.
It should be understood that, although the steps in the flowcharts of fig. 2-6 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-6 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the sub-steps or stages are performed necessarily occur in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
In one embodiment, as shown in fig. 7, there is provided a target user recommending apparatus, including:
the information searching module 702 is configured to receive a medical consultation message sent by the terminal, and search a user portrait according to the medical consultation message to obtain user portrait information.
And the feature extraction module 704 is configured to extract user feature information corresponding to the medical consultation message and the user image information.
The quality parameter evaluation module 706 is configured to obtain a user quality parameter corresponding to the user according to the user characteristic information.
A target recommendation module 708 for recommending a target user to the medical service provider based on the user profile information and the user quality parameters.
In one embodiment, the user image information includes real-time image features and offline interrogation features, and the information lookup module 702 is configured to: receiving a medical consultation message sent by a terminal; analyzing the medical consultation message to obtain a user identifier corresponding to the terminal; and extracting real-time portrait features from a preset online hive database platform according to the user identification, and extracting offline inquiry features from a preset offline updating platform according to the user identification.
In one embodiment, the user portrait information includes a real-time portrait feature and an offline consultation feature, and the apparatus further includes a user portrait module for: acquiring an image information update request; searching user identity information, historical inquiry flow information and historical inquiry transaction information corresponding to the portrait information update request; acquiring real-time portrait features according to user identity information and historical inquiry flow information, storing the real-time portrait features to a preset online hive database platform, acquiring offline inquiry features according to historical inquiry transaction information, and storing the offline inquiry features to a preset offline updating platform.
In one embodiment, the system further comprises a consultation message checking module for: receiving a medical consultation message sent by a terminal; inputting the medical consultation message into a preset semantic recognition model to obtain a recognition result; and when the identification result represents that the medical consultation message is a valid message, searching the user portrait according to the medical consultation message to obtain user portrait information.
In one embodiment, the quality parameter evaluation module is specifically configured to: constructing a multidimensional feature matrix according to the user feature information; inputting the multidimensional feature matrix into a preset user quality evaluation model to obtain user quality parameters corresponding to a user, wherein the preset user quality evaluation model is obtained by the initial xgboost model through supervised training based on labeled historical feature data.
In one embodiment, the method further comprises a feature screening unit for: acquiring a user type corresponding to a historical user and historical characteristic data; according to the user types corresponding to the historical users and the historical feature data, determining the differentiated features corresponding to the users of all types; and carrying out pearson correlation coefficient analysis on the differential features to obtain strong correlation feature types corresponding to the historical feature data.
For specific limitations on the target user recommendation device, reference may be made to the above limitation on the target user recommendation method, and no further description is given here. The respective modules in the above-described target user recommendation device may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing target user recommendation data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a target user recommendation method.
It will be appreciated by those skilled in the art that the structure shown in fig. 8 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory storing a computer program and a processor that when executing the computer program performs the steps of:
receiving a medical consultation message sent by the terminal, and searching a user portrait according to the medical consultation message to obtain user portrait information;
extracting user characteristic information corresponding to the medical consultation message and the user image information;
acquiring user quality parameters corresponding to a user according to the user characteristic information;
and recommending the target user to the medical service provider according to the user portrait information and the user quality parameters.
In one embodiment, the processor when executing the computer program further performs the steps of: receiving a medical consultation message sent by a terminal; analyzing the medical consultation message to obtain a user identifier corresponding to the terminal; and extracting real-time portrait features from a preset online hive database platform according to the user identification, and extracting offline inquiry features from a preset offline updating platform according to the user identification.
In one embodiment, the processor when executing the computer program further performs the steps of: acquiring an image information update request; searching user identity information, historical inquiry flow information and historical inquiry transaction information corresponding to the portrait information update request; acquiring real-time portrait features according to user identity information and historical inquiry flow information, storing the real-time portrait features to a preset online hive database platform, acquiring offline inquiry features according to historical inquiry transaction information, and storing the offline inquiry features to a preset offline updating platform.
In one embodiment, the processor when executing the computer program further performs the steps of: receiving a medical consultation message sent by a terminal; inputting the medical consultation message into a preset semantic recognition model to obtain a recognition result; and when the identification result represents that the medical consultation message is a valid message, searching the user portrait according to the medical consultation message to obtain user portrait information.
In one embodiment, the processor when executing the computer program further performs the steps of: constructing a multidimensional feature matrix according to the user feature information; inputting the multidimensional feature matrix into a preset user quality evaluation model to obtain user quality parameters corresponding to a user, wherein the preset user quality evaluation model is obtained by the initial xgboost model through supervised training based on labeled historical feature data.
In one embodiment, the processor when executing the computer program further performs the steps of: acquiring a user type corresponding to a historical user and historical characteristic data; according to the user types corresponding to the historical users and the historical feature data, determining the differentiated features corresponding to the users of all types; and carrying out pearson correlation coefficient analysis on the differential features to obtain strong correlation feature types corresponding to the historical feature data.
In one embodiment, a computer storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
receiving a medical consultation message sent by the terminal, and searching a user portrait according to the medical consultation message to obtain user portrait information;
extracting user characteristic information corresponding to the medical consultation message and the user image information;
acquiring user quality parameters corresponding to a user according to the user characteristic information;
and recommending the target user to the medical service provider according to the user portrait information and the user quality parameters.
In one embodiment, the computer program when executed by the processor further performs the steps of: receiving a medical consultation message sent by a terminal; analyzing the medical consultation message to obtain a user identifier corresponding to the terminal; and extracting real-time portrait features from a preset online hive database platform according to the user identification, and extracting offline inquiry features from a preset offline updating platform according to the user identification.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring an image information update request; searching user identity information, historical inquiry flow information and historical inquiry transaction information corresponding to the portrait information update request; acquiring real-time portrait features according to user identity information and historical inquiry flow information, storing the real-time portrait features to a preset online hive database platform, acquiring offline inquiry features according to historical inquiry transaction information, and storing the offline inquiry features to a preset offline updating platform.
In one embodiment, the computer program when executed by the processor further performs the steps of: receiving a medical consultation message sent by a terminal; inputting the medical consultation message into a preset semantic recognition model to obtain a recognition result; and when the identification result represents that the medical consultation message is a valid message, searching the user portrait according to the medical consultation message to obtain user portrait information.
In one embodiment, the computer program when executed by the processor further performs the steps of: constructing a multidimensional feature matrix according to the user feature information; inputting the multidimensional feature matrix into a preset user quality evaluation model to obtain user quality parameters corresponding to a user, wherein the preset user quality evaluation model is obtained by the initial xgboost model through supervised training based on labeled historical feature data.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring a user type corresponding to a historical user and historical characteristic data; according to the user types corresponding to the historical users and the historical feature data, determining the differentiated features corresponding to the users of all types; and carrying out pearson correlation coefficient analysis on the differential features to obtain strong correlation feature types corresponding to the historical feature data.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples represent only a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. A target user recommendation method, the method comprising:
receiving a medical consultation message sent by a terminal, and searching a user portrait according to the medical consultation message to obtain user portrait information;
extracting user characteristic information corresponding to the medical consultation message and the user portrait information, wherein the user characteristic information comprises a main complaint, a template inquiry and a diagnosis tag corresponding to the medical consultation message, and historical inquiry information, user identity information and historical inquiry transaction information in the user portrait information;
Acquiring user quality parameters corresponding to the user according to the user characteristic information;
recommending a target user according to the user portrait information and the user quality parameters;
the step of obtaining the user quality parameters corresponding to the user according to the user characteristic information comprises the following steps:
acquiring a user type corresponding to a historical user and historical characteristic data, wherein the user type corresponding to the historical user is determined based on the success rate of the historical user;
determining the differentiation characteristics corresponding to each type of user according to the user type corresponding to the historical user and the historical characteristic data;
performing pearson correlation coefficient analysis on the differential features to obtain strong correlation feature types corresponding to the historical feature data;
constructing a multidimensional feature matrix according to the user feature information corresponding to the strong correlation feature type;
inputting the multidimensional feature matrix into a preset user quality evaluation model to obtain user quality parameters corresponding to the user, wherein the preset user quality evaluation model is obtained by an initial xgboost model through supervised training based on labeled historical feature data;
the user image information comprises real-time image characteristics and offline inquiry characteristics;
The receiving terminal sends the medical consultation message, searches the user portrait according to the medical consultation message, and obtains the user portrait information, which comprises the following steps:
receiving a medical consultation message sent by a terminal;
analyzing the medical consultation message to obtain a user identifier corresponding to the terminal;
and extracting the real-time portrait features from a preset online hive database platform according to the user identification, and extracting the offline inquiry features from a preset offline updating platform according to the user identification.
2. The method of claim 1, wherein the user identification comprises a user account.
3. The method of claim 1, wherein the user image information includes real-time portrait features and offline consultation features;
the medical consultation message sent by the receiving terminal searches the user portrait according to the medical consultation message, and before obtaining the user portrait information, the method further comprises the following steps:
acquiring an image information update request;
searching user identity information, historical inquiry flow information and historical inquiry transaction information corresponding to the portrait information update request;
acquiring real-time portrait features according to the user identity information and the historical inquiry flow information, storing the real-time portrait features to a preset online hive database platform, acquiring offline inquiry features according to the historical inquiry transaction information, and storing the offline inquiry features to a preset offline updating platform.
4. The method of claim 3, wherein the receiving the medical advice message from the terminal, and searching for the user profile based on the medical advice message, and obtaining the user profile information comprises:
receiving a medical consultation message sent by a terminal;
inputting the medical consultation message into a preset semantic recognition model to obtain a recognition result;
and searching the user portrait according to the medical consultation information when the identification result represents that the medical consultation information is a valid message, so as to obtain user portrait information.
5. A target user recommendation device, the device comprising:
the information searching module is used for receiving the medical consultation message sent by the terminal, searching the user portrait according to the medical consultation message and obtaining user portrait information;
the feature extraction module is used for extracting the medical consultation information and the user feature information corresponding to the user portrait information, wherein the user feature information comprises a main complaint, a template inquiry and a diagnosis tag corresponding to the medical consultation information, and historical inquiry information, user identity information and historical inquiry transaction information in the user portrait information;
the quality parameter evaluation module is used for acquiring user quality parameters corresponding to the user according to the user characteristic information;
The target recommendation module is used for recommending target users to the medical service provider according to the user portrait information and the user quality parameters;
the quality parameter evaluation module is specifically used for: acquiring a user type corresponding to a historical user and historical characteristic data, wherein the user type corresponding to the historical user is determined based on the success rate of the historical user; determining the differentiation characteristics corresponding to each type of user according to the user type corresponding to the historical user and the historical characteristic data; performing pearson correlation coefficient analysis on the differential features to obtain strong correlation feature types corresponding to the historical feature data; constructing a multidimensional feature matrix according to the user feature information corresponding to the strong correlation feature type; inputting the multidimensional feature matrix into a preset user quality evaluation model to obtain user quality parameters corresponding to the user, wherein the preset user quality evaluation model is obtained by an initial xgboost model through supervised training based on labeled historical feature data;
the user image information comprises real-time image features and offline inquiry features, and the information searching module is used for: receiving a medical consultation message sent by a terminal; analyzing the medical consultation message to obtain a user identifier corresponding to the terminal; and extracting the real-time portrait features from a preset online hive database platform according to the user identification, and extracting the offline inquiry features from a preset offline updating platform according to the user identification.
6. The apparatus of claim 5, wherein the user identification comprises a user account.
7. The apparatus of claim 5, wherein the user image information includes real-time portrait features and offline consultation features;
the apparatus further comprises a user portrayal module for: acquiring an image information update request; searching user identity information, historical inquiry flow information and historical inquiry transaction information corresponding to the portrait information update request; acquiring real-time portrait features according to the user identity information and the historical inquiry flow information, storing the real-time portrait features to a preset online hive database platform, acquiring offline inquiry features according to the historical inquiry transaction information, and storing the offline inquiry features to a preset offline updating platform.
8. The apparatus of claim 7, further comprising a advisory message verification module for: receiving a medical consultation message sent by a terminal; inputting the medical consultation message into a preset semantic recognition model to obtain a recognition result; and searching the user portrait according to the medical consultation information when the identification result represents that the medical consultation information is a valid message, so as to obtain user portrait information.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 4 when the computer program is executed.
10. A computer storage medium having stored thereon a computer program, which when executed by a processor realizes the steps of the method according to any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010887774.6A CN112035611B (en) | 2020-08-28 | 2020-08-28 | Target user recommendation method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010887774.6A CN112035611B (en) | 2020-08-28 | 2020-08-28 | Target user recommendation method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112035611A CN112035611A (en) | 2020-12-04 |
| CN112035611B true CN112035611B (en) | 2023-05-30 |
Family
ID=73587687
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010887774.6A Active CN112035611B (en) | 2020-08-28 | 2020-08-28 | Target user recommendation method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112035611B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112925982B (en) * | 2021-03-12 | 2023-04-07 | 上海意略明数字科技股份有限公司 | User redirection method and device, storage medium and computer equipment |
| CN113221570A (en) * | 2021-05-31 | 2021-08-06 | 康键信息技术（深圳）有限公司 | Processing method, device, equipment and storage medium based on-line inquiry information |
| CN113360941A (en) * | 2021-06-04 | 2021-09-07 | 深圳市第二人民医院(深圳市转化医学研究院) | Medical data processing method and device based on digital twins and computer equipment |
| CN113486238A (en) * | 2021-06-29 | 2021-10-08 | 平安信托有限责任公司 | Information pushing method, device and equipment based on user portrait and storage medium |
| CN113722601B (en) * | 2021-09-07 | 2024-04-16 | 南方电网数字电网研究院股份有限公司 | Power measurement information recommendation method, device, computer equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245687A (en) * | 2019-05-17 | 2019-09-17 | 腾讯科技（上海）有限公司 | User classification method and device |
| CN111274380A (en) * | 2020-01-16 | 2020-06-12 | 平安银行股份有限公司 | Consultation complaint information processing method based on big data and related device |
| CN111368219A (en) * | 2020-02-27 | 2020-07-03 | 广州腾讯科技有限公司 | Information recommendation method and device, computer equipment and storage medium |
| CN111460323A (en) * | 2020-06-17 | 2020-07-28 | 腾讯科技（深圳）有限公司 | Focus user mining method and device based on artificial intelligence |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA3024682A1 (en) * | 2008-08-28 | 2010-03-04 | Fundacao D. Anna Sommer Champalimaud E Dr. Carlos Montez Champalimaud | Systems and methods for treating, diagnosing and predicting the occurrence of a medical condition |
| CN107220852A (en) * | 2017-05-26 | 2017-09-29 | 北京小度信息科技有限公司 | Method, device and server for determining target recommended user |
| CN109543863B (en) * | 2018-10-27 | 2024-06-18 | 深圳平安医疗健康科技服务有限公司 | Medical task management method, server and storage medium |
| CN110444297A (en) * | 2019-08-06 | 2019-11-12 | 重庆仙桃前沿消费行为大数据有限公司 | Medical information recommended method, device, equipment and readable storage medium storing program for executing |
| CN111009311A (en) * | 2019-11-05 | 2020-04-14 | 泰康保险集团股份有限公司 | Medical resource recommendation method, device, medium and equipment |
-
2020
- 2020-08-28 CN CN202010887774.6A patent/CN112035611B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245687A (en) * | 2019-05-17 | 2019-09-17 | 腾讯科技（上海）有限公司 | User classification method and device |
| CN111274380A (en) * | 2020-01-16 | 2020-06-12 | 平安银行股份有限公司 | Consultation complaint information processing method based on big data and related device |
| CN111368219A (en) * | 2020-02-27 | 2020-07-03 | 广州腾讯科技有限公司 | Information recommendation method and device, computer equipment and storage medium |
| CN111460323A (en) * | 2020-06-17 | 2020-07-28 | 腾讯科技（深圳）有限公司 | Focus user mining method and device based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112035611A (en) | 2020-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112035611B (en) | Target user recommendation method, device, computer equipment and storage medium | |
| CN108874992B (en) | Public opinion analysis method, system, computer equipment and storage medium | |
| CN110457431B (en) | Knowledge graph-based question and answer method and device, computer equipment and storage medium | |
| CN109829629B (en) | Risk analysis report generation method, apparatus, computer device and storage medium | |
| CN108897734B (en) | User portrait generation method, device, computer equipment and storage medium | |
| CN109036545B (en) | Medical information processing method, apparatus, computer device and storage medium | |
| CN110504028A (en) | A kind of disease way of inquisition, device, system, computer equipment and storage medium | |
| CN108766545B (en) | Online inquiry department distribution method, device, computer equipment and storage medium | |
| CN112035674B (en) | Diagnosis guiding data acquisition method, device, computer equipment and storage medium | |
| WO2020253357A1 (en) | Data product recommendation method and apparatus, computer device and storage medium | |
| CN110659298B (en) | Financial data processing method and device, computer equipment and storage medium | |
| CN111145910A (en) | Abnormal case identification method and device based on artificial intelligence and computer equipment | |
| CN110781379A (en) | Information recommendation method and device, computer equipment and storage medium | |
| CN112151141A (en) | Medical data processing method, device, computer equipment and storage medium | |
| CN112905876B (en) | Information pushing method and device based on deep learning and computer equipment | |
| CN108334625B (en) | User information processing method and device, computer equipment and storage medium | |
| CN113157863A (en) | Question and answer data processing method and device, computer equipment and storage medium | |
| WO2020034801A1 (en) | Medical feature screening method and apparatus, computer device, and storage medium | |
| CN112395500A (en) | Content data recommendation method and device, computer equipment and storage medium | |
| CN110674131A (en) | Financial statement data processing method and device, computer equipment and storage medium | |
| CN111710383A (en) | Medical record quality control method and device, computer equipment and storage medium | |
| CN112288279A (en) | Business risk assessment method and device based on natural language processing and linear regression | |
| CN112201359A (en) | Artificial intelligence-based critical illness inquiry data identification method and device | |
| CN114628001B (en) | Prescription recommendation method, system, equipment and storage medium based on neural network | |
| CN112035614A (en) | Test set generation method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |