Information collection method, system and device, storage medium and computer program product

Abstract

The invention provides an information collection method, system and device, a storage medium and a computer program product, and relates to the technical field of computer application. The information acquisition method comprises the following steps: acquiring basic information of a customer; obtaining an expression label and an expression score according to the basic information of the customer; obtaining question type codes according to the expression labels and the expression scores, and generating a question collection list and question collection timeliness according to the question type codes and the basic information of the customers; generating problem information according to the collection problem list and the problem collection timeliness; and acquiring a supplementary acquisition information list according to the problem information. By adopting the method and the system, the information points needing additional attention or supplement can be identified in a personalized manner by combining the basic information and the micro-expression information of the customer, so that necessary supplement information is actively collected in advance, the collection accuracy of the approval information can be improved, the approval process is seamlessly jointed, and the approval period is remarkably shortened.

Description

Technical Field

[0001] The present invention relates to the field of computer application technology, and more specifically, to an information collection method, system, device, storage medium and computer program product. Background Art

[0002] In recent years, the Internet loan industry has gradually established a standardized information collection process including registration and login, automatic OCR recognition of ID cards, facial recognition verification, contact information and personal information collection. These links effectively gather key information and image data of customers, thus serving as an important basis for credit decision-making in the approval system. However, the current information collection methods tend to be mechanized, lacking sufficient flexibility and humanized design, and there is no difference in the information collected between individuals. More importantly, the existing information collection model fails to fully explore and utilize the effective information provided by customers (customer information and customer image data), but instead transmits the collected information to the approval system without any personalization, and uses the approval system and the experience of the approval personnel to identify and judge the supplementary collected information. At the same time, in order to supplement the information and maintain its accuracy, it may be necessary to revisit the customer many times, which seriously affects the customer experience and limits the accuracy of approval information collection and the development space of personalized services. Summary of the invention

[0003] In order to solve the problems or at least part of the problems existing in the above-mentioned prior art, the embodiments of the present invention provide an information collection method, system, device, storage medium and computer program product, which combine the customer's basic information and micro-expression information to personalize the identification of information points that require extra attention or supplementation, thereby actively collecting necessary supplementary information in advance, improving the accuracy of approval information collection, and being able to seamlessly connect the approval process, significantly shortening the approval cycle.

[0004] According to a first aspect of the present invention, an embodiment of the present invention provides an information collection method, which includes: obtaining basic customer information; obtaining expression labels and expression scores based on the basic customer information; obtaining question type codes based on the expression labels and expression scores, and generating a collection question list and question collection time limit based on the question type codes and basic customer information; generating question information based on the collection question list and question collection time limit; and obtaining a supplementary collection information list based on the question information.

[0005] According to the above-mentioned implementation mode of the present invention, on the basis of the basic information of the customer, the potential micro-expression information is finely mined, and the micro-expression data including expression labels and expression scores are integrated into the information collection algorithm. Combined with the customer information, the information points that need extra attention or supplementation are personalized and identified. The necessary supplementary information can be actively collected in advance, the approval process can be seamlessly connected, the approval cycle can be significantly shortened, and at the same time, the customer waiting time can be reduced, and the customer experience can be optimized.

[0006] In some embodiments of the present invention, obtaining the question type code according to the expression label and expression score includes: obtaining the collection information in the emotion collection information table according to the expression label and expression score; and parsing the collection information to obtain the question type code and the number of questions.

[0007] In some embodiments of the present invention, generating a collection question list and a question collection time limit based on the question type code and the customer's basic information includes: obtaining configuration information in the question type time limit table based on the question type code and the number of questions, the configuration information including a basic question answering time limit and a time limit offset range; calculating the question collection time limit based on the basic question answering time limit and the time limit offset range.

[0008] In some embodiments of the present invention, generating a list of collected questions and a time limit for question collection based on the question type code and the basic information of the customer also includes: obtaining a question bank ID in a question bank table based on the emotional tag and the question type code; generating question content based on the question bank ID and the basic information of the customer; and generating the list of collected questions based on the question content.

[0009] According to the above-mentioned embodiment of the present invention, personalized questions and question collection timeliness are dynamically generated based on micro-expression data including expression labels and expression scores and basic customer information, thereby ensuring the diversity and timeliness of information collection. This not only effectively increases the difficulty of identifying fraudulent behavior, but also greatly reduces the cost of fraud detection, thereby improving the security and stability of information collection and approval.

[0010] According to the second aspect of the present invention, an embodiment of the present invention provides an information collection system, which includes: a basic information acquisition module, used to obtain basic customer information; a micro-expression recognition module, used to obtain expression labels and expression scores based on the basic customer information; a supplementary information acquisition module, used to perform the following operations: obtain question type codes according to the expression labels and expression scores, generate a collection question list and question collection time limit according to the question type code and the basic customer information; generate question information according to the collection question list and the question collection time limit; obtain a supplementary collection information list according to the question information.

[0011] According to the above-mentioned implementation mode of the present invention, on the basis of the basic information of the customer, the potential micro-expression information is finely mined, and the micro-expression data including expression labels and expression scores are integrated into the information collection algorithm. Combined with the customer information, the information points that need extra attention or supplementation are personalized and identified. The necessary supplementary information can be actively collected in advance, the approval process can be seamlessly connected, the approval cycle can be significantly shortened, and at the same time, the customer waiting time can be reduced, and the customer experience can be optimized.

[0012] In some embodiments of the present invention, obtaining the question type code according to the expression label and expression score includes: obtaining the collection information in the emotion collection information table according to the expression label and expression score; and parsing the collection information to obtain the question type code and the number of questions.

[0013] In some embodiments of the present invention, generating a collection question list and a question collection time limit based on the question type code and the customer's basic information includes: obtaining configuration information in the question type time limit table based on the question type code and the number of questions, the configuration information including a basic question answering time limit and a time limit offset range; calculating the question collection time limit based on the basic question answering time limit and the time limit offset range.

[0014] In some embodiments of the present invention, generating a list of collected questions and a time limit for question collection based on the question type code and the basic information of the customer also includes: obtaining a question bank ID in a question bank table based on the emotional tag and the question type code; generating question content based on the question bank ID and the basic information of the customer; and generating the list of collected questions based on the question content.

[0015] According to the above-mentioned embodiment of the present invention, personalized questions and question collection timeliness are dynamically generated based on micro-expression data including expression labels and expression scores and basic customer information, thereby ensuring the diversity and timeliness of information collection. This not only effectively increases the difficulty of identifying fraudulent behavior, but also greatly reduces the cost of fraud detection, thereby improving the security and stability of information collection and approval.

[0016] According to the third aspect of the present invention, an embodiment of the present invention provides a computer-readable storage medium having computer-readable instructions stored thereon. When the computer-readable instructions are executed by a processor, the computer performs the following operations: the operations include the steps included in the information collection method described in any one of the above embodiments.

[0017] According to the fourth aspect of the present invention, an embodiment of the present invention provides a computer device including a memory and a processor, wherein the memory is used to store one or more computer-readable instructions, wherein the one or more computer-readable instructions, when executed by the processor, can implement the information collection method described in any one of the above embodiments.

[0018] According to a fifth aspect of the present invention, an embodiment of the present invention provides a computer program product including a computer program, and when the computer program is executed by a processor, the information collection method described in any one of the above embodiments is implemented.

[0019] From the above, it can be seen that the information collection method, system, device, storage medium and computer program product provided in the embodiments of the present invention, based on the basic information of the customer, finely mines the potential micro-expression information, and integrates the micro-expression data including expression labels and expression scores into the information collection algorithm, and combines customer information to personalize the identification of information points that require extra attention or supplementation. It can actively collect necessary supplementary information in advance, seamlessly connect the approval process, significantly shorten the approval cycle, and at the same time reduce customer waiting time and optimize customer experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flow chart of the information collection method according to Embodiment 1 of the present invention;

[0021] Figure 2 is a flow chart of an information collection method according to Embodiment 2 of the present invention;

[0022] Figure 3 It is a schematic diagram of the architecture of the information collection system according to Example 3 of the present invention. DETAILED DESCRIPTION

[0023] The various aspects of the present invention are described in detail below in conjunction with the accompanying drawings and specific embodiments. Among them, well-known modules, units and their connections, links, communications or operations are not shown or described in detail. In addition, the described features, architectures or functions can be combined in any way in one or more embodiments. It should be understood by those skilled in the art that the various embodiments described below are only used for illustration and are not intended to limit the scope of protection of the present invention. It can also be easily understood that the modules or units or processing methods in each embodiment described herein and shown in the accompanying drawings can be combined and designed in various different configurations.

[0024] The following is a brief description of the terms used in this article.

[0025] LLM: Large Language Model, large language model.

[0026] OCR: Optical Character Recognition. OCR refers to the process by which an electronic device (such as a scanner or digital camera) examines characters printed on paper, determines their shape by detecting dark and light patterns, and then uses character recognition methods to translate the shape into computer text.

[0027] Liveness score: After the liveness recognition system conducts a comprehensive analysis of the input face image or video stream, it gives a score to measure whether the face is real or not. The higher the score, the more likely the system thinks the face is real or not; conversely, the lower the score, the more likely it is a fake face attack. Liveness score is an important indicator for quantitatively evaluating liveness detection results, and can accurately determine whether the user is real or not.

[0028] User ID: The unique identifier of the registered mobile phone number, that is, after a mobile phone number is registered and logged in, it corresponds to a unique user ID in the system.

[0029] Customer ID: The unique identification of the ID number, that is, one ID number corresponds to one unique customer ID in the system. N user IDs correspond to one customer ID.

[0030] filekey: The unique identifier or index of the file.

[0031] API: Application Programming Interface, application programming interface.

[0032] MTCNN: Multi-task Cascaded Convolutional Networks, multi-task cascaded convolutional neural network.

[0033] CNN: Convolutional Neural Network, convolutional neural network.

[0034] OpenFace: A powerful open source facial recognition and expression analysis tool.

[0035] [Example 1]

[0036] Figure 1 It is a flowchart of the information collection method according to Example 1 of the present invention.

[0037] like Figure 1 As shown, in Embodiment 1 of the present invention, the information collection method may include: step S11, step S12, step S13, step S14 and step S15, and the above steps are described in detail below.

[0038] In step S11, basic customer information is obtained.

[0039] In some embodiments, the basic information of the customer is obtained through the existing standardized collection process. Specifically, the basic information of the customer is obtained through the existing standardized collection process of "registration and login - ID card OCR automatic recognition - face recognition verification - contact information - personal information collection", such as: ID card information (name, gender, ethnicity, date of birth, ID card address information, ID card number, ID card validity period, ID card issuing authority, ID card portrait image data, ID card front image data), live body points, live body photo image data, live body video image data, contact information (contact name, contact relationship, contact mobile phone number), personal information (education, marriage, residential address, industry, occupation, monthly income, work unit), letter of commitment and authorization and other related image data.

[0040] In step S12, expression labels and expression scores are obtained according to the basic information of the customer. In this embodiment, expression labels and expression scores are obtained according to the facial information in the basic information of the customer combined with the micro-expression recognition system / module.

[0041] In some embodiments, a channel for identifying micro-expressions based on a facial photo is determined by inputting a facial photo and identifying a channel identifier (01 self-built identification module, 02 external identification module), and then the micro-expression recognition system processes and outputs expression labels and expression scores, wherein the expression labels include but are not limited to: angry, disgust, scared, happy, sad, surprised, and neutral; the expression score ranges from 0 to 100, and a higher score represents a higher recognition accuracy.

[0042] In step S13, the question type code is obtained according to the expression label and expression score, and the collection question list and question collection time limit are generated according to the question type code and the basic information of the customer. In this embodiment, by inputting the expression information (the aforementioned expression label and expression score), and then using the algorithm to process the random question type (for example, verification type, upload type, video dual recording type, large language model LLM random question type), and then combining the basic information of the customer collected in step S11 to generate the collection question list and the corresponding question collection time limit.

[0043] In some implementations, obtaining the question type code according to the expression label and the expression score includes: obtaining collection information in an emotion collection information table according to the expression label and the expression score; and parsing the collection information to obtain the question type code and the number of questions.

[0044] In a further embodiment, generating a collected question list and a question collection time limit according to the question type code and the basic information of the customer includes: obtaining configuration information in the question type time limit table according to the question type code and the number of questions, the configuration information including a basic question answering time limit and a time limit offset range; calculating the question collection time limit according to the basic question answering time limit and the time limit offset range; obtaining a question bank ID in a question bank table according to the emotional tag and the question type code; generating question content according to the question bank ID and the basic information of the customer; and generating the collected question list according to the question content.

[0045] In step S14, problem information is generated according to the collection problem list and the problem collection timeliness.

[0046] In step S15, a supplementary collection information list is obtained according to the problem information.

[0047] In some implementations, the system outputs question information based on the collection algorithm and dynamically displays it on the customer display page through the interface, thereby performing differentiated data collection on the customer and storing the customer's answer information in a structured manner. The question information includes, but is not limited to, question type, question title, question options, answer time limit, and other information.

[0048] By adopting the above-mentioned information collection method of Example 1 of the present invention, on the basis of the basic information of the customer, the potential micro-expression information is finely mined, and the micro-expression data including expression labels and expression scores are integrated into the information collection algorithm. Combined with the customer information, the information points that need extra attention or supplementation are personalized identified. The necessary supplementary information can be actively collected in advance, the approval process can be seamlessly connected, the approval cycle can be significantly shortened, and at the same time, the customer waiting time can be reduced, and the customer experience can be optimized.

[0049] [Example 2]

[0050] Figure 2 It is a flowchart of the information collection method according to Example 2 of the present invention.

[0051] like Figure 2 As shown, the information collection method includes the following steps:

[0052] Step 1. Basic information collection process: The customer completes registration and login, ID card OCR automatic recognition, face recognition verification, contact information, personal information collection and other page interactions on the loan application process page of the financial institution. The customer's relevant basic information is synchronously saved to the institution's business system through the interface and stored in the relevant business table to form the customer's relevant basic information data.

[0053] In this embodiment, the business table includes but is not limited to the following tables:

[0054] ①Registered user table, used to store registered mobile phone number, user ID, registration channel, etc.;

[0055] ② ID card information table, used to store user ID, customer ID, name, gender, ethnicity, date of birth, ID card address information, ID card number, ID card validity period, ID card issuing authority, ID card portrait image filekey, ID card front image data filekey, etc.;

[0056] ③ Liveness information table, used to store user ID, customer ID, liveness score, liveness photo image filekey, liveness video image filekey, etc.;

[0057] ④Contact information table, used to store user ID, customer ID, contact name, contact relationship, contact phone number, etc.;

[0058] ⑤ Personal information table, used to store user ID, customer ID, education, marriage, residential address, industry, occupation, monthly income, work unit, etc.

[0059] Step 2: The micro-expression recognition system processing process includes the following steps:

[0060] The face photo fileKey (i.e., live photo image filekey) is input through the recognition interface. The micro-expression recognition system calls the file system interface through the fileKey to obtain the face image photo and gives it to the recognition module. The recognition module outputs the emotion label and emotion score according to the internal recognition process. The expression labels include but are not limited to: angry, disgust, scared, happy, sad, surprised, neutral; the expression score is in the range of 0-100, and the higher the score, the higher the recognition accuracy.

[0061] Among them, the file system is a storage system for files (such as photos, videos, PDFs, etc.), which is developed based on the open source distributed file system FastDFS (Fast Distributed File System), and mainly provides file upload storage and file download functions. The storage process of the file system includes: the business system calls the file system API upload interface, the file system initializes the uploaded file information to the file table (file name, fileKey, file size, file suffix, upload time), and then calls the FastDFS client (client) to request the tracker server (trackerserver) to upload the target storage server (storage server), the tracker server selects the storage server according to the policy and returns the address to the client, and then the client communicates with the selected storage server to store the file data and may synchronize it to other servers in the same group. The file system stores the file_id (storage path and file information) responded by FastDFS in the corresponding field of the corresponding record "FastDFS file id" in the file table and responds to the business end. The facial photo acquisition / download process includes: the business end requests the download interface of the file system and passes in the fileKey of the facial photo; after receiving the request, the file system queries the fileKey in the file table, obtains the file record corresponding to the facial photo, and thus obtains the value of the corresponding record "FastDFS file id"; the FastDFS client requests the storage server address of the downloaded file from the tracking server and provides file identification information (file_id); after the tracking server returns the storage server address, the client establishes a connection with the storage server, sends a download request and receives file data; the file system synchronously responds to the received file data to the business end.

[0062] In this embodiment, the external interface of the micro-expression recognition system includes: ① recognition application interface and ② recognition query interface. Among them, the input parameters of the recognition application interface include: request unique identifier, face photo fileKey, recognition module identifier (01 self-built recognition module / 02 external recognition module); the output parameters of the recognition application interface include: response code resultCode, response content resultMsg, processing status handleStatus, emotion label, emotion score; the input parameters of the recognition query interface include: request unique identifier; the output parameters of the recognition query interface include: response code resultCode, response content resultMsg, processing status handleStatus, emotion label, emotion score.

[0063] The present invention provides an example of a recognition record table of a micro-expression recognition system, as shown in Table 1 below:

[0064] Table 1

[0065]

[0066]

[0067] According to Table 1 above, this recognition record example uses a self-built recognition module, and the recognized emotion label is angry and the emotion score is 80 points.

[0068] In this embodiment, the recognition module of the micro-expression recognition system includes ① an external recognition module and ② a self-built recognition module. The external recognition module directly connects to the external channel recognition interface through an API interface; the self-built recognition module performs efficient face detection through MTCNN, extracts features using the powerful capabilities of CNN, and uses the OpenFace face recognition model for emotion recognition, realizing a complete processing flow from input image to final expression and action unit recognition. The recognition module mainly consists of three parts: face detection, feature extraction, and feature classification.

[0069] Among them, the face detection stage uses the MTCNN detector backend, and through its three cascaded network structures P-Net (Proposal Network), R-Net (Refine Network), and O-Net (Output Network), it gradually filters out non-face areas and combines the key technology of graphic pyramid to solve the multi-scale problem of the target, and finally obtains accurate face position, bounding box and face key point information.

[0070] The feature extraction stage uses the powerful capabilities of CNN to automatically learn and extract features from face images. CNN gradually extracts feature representations from low-level to high-level through multiple convolutional layers, pooling layers, and fully connected layers. These features include edges, textures, shapes, etc., which together constitute a rich representation of face images.

[0071] The OpenFace face recognition model is used in the feature classification stage to realize emotion and action unit recognition.

[0072] Step 3: Supplement the information collection system processing process, which specifically includes the following steps:

[0073] 3.1 Use the emotion label and emotion score to match the collected information in the emotion collection information table, and then parse the collected question type code and the number of corresponding questions. If it does not match, choose to read the default (preset) emotion label's backup information for subsequent operations.

[0074] In an exemplary embodiment, the emotion collection information table includes: emotion label (there is a default label default), emotion score range, collection information situation (for example {"question type code":"collection number"}). In addition, the present invention provides an example of an emotion collection information table, as shown in Table 2 below:

[0075] Table 2

[0076]

[0077] According to Table 2 above, when the sentiment label is angry and the sentiment score x is between 80 and 100, the information that needs to be collected includes: 2 questions with question type code "01" and 1 question with question type code "02".

[0078] 3.2 According to the selected question type codes and the number of corresponding questions, the configuration information is obtained in the question type timeliness table through the question type code, and the basic answer timeliness and deviation of the question type are obtained. By inputting the maximum and minimum answer timeliness parameters, the Mersenne Twister (MT) algorithm encapsulates the custom algorithm mtRandom to calculate the true answer timeliness value. Among them, the maximum timeliness formula is as follows: maximum timeliness = (standard answer time + offset value) × (1 + 5%); minimum timeliness = (standard answer time - offset value) × (1 + 10%), and the calculation result is rounded to an integer. For example, (30 + 5) × (1 + 5%) = 36.75, the value is 36. Based on the answer timeliness algorithm, the corresponding answer timeliness is determined according to different question types and different customers, and corresponding time management can be performed for each type of question and each customer, ensuring that high-quality questions are asked to users within a reasonable time, meeting the needs of diversified information collection of different users, and improving the user experience.

[0079] In an exemplary embodiment, the question type timeliness table includes: question type code, question type name, standard answering time (in seconds), offset range, and status (1 valid, 0 invalid). In addition, the present invention provides an example of a question type timeliness table, as shown in Table 3 below:

[0080] Table 3

[0081]

[0082] According to Table 3 above, there are four types of questions: basic information type, dual video recording type, image acquisition type, and large language model question type.

[0083] 3.3 According to the combination of sentiment label and question type coding, the corresponding question type in the question bank table is obtained and / or the supplementary question information is obtained according to the large language model system, and then the final generated collection question information is stored in the collection question table and provided to the front end through the interface for display. The supplementary collection information obtained by algorithm analysis is presented to customers in a friendly and easy-to-understand form, which can enhance the customer's sense of participation through page interaction.

[0084] The question bank is a dynamic question bank, which is a continuously evolving dynamic resource pool rather than a static model. The question bank adjusts its content in real time according to business feedback, knowledge updates, and changes in approval processes to ensure the effectiveness of collected information. By accurately selecting the most matching question resources from the question bank, a perfect combination of personalization and efficiency can be achieved.

[0085] In this embodiment, when the corresponding question type in the question bank table is taken according to the combination of the emotional label and the question type code, the question bank only supports the question type code of 01 / 02 / 03, and the qualified question ID is extracted to generate a question set, and the sequence identifier in the question set is used to form the minimum value (the minimum value of the set is 1) and the maximum value (the maximum value of the set is the number of elements in the set) of the random number algorithm, and then the random set sequence identifier is calculated based on the Mattset rotation algorithm encapsulation custom algorithm mtRandom, and the corresponding question ID is taken out according to the identifier to obtain the question content. When the question type code is 04 (large language model question type), the collected customer text information (such as name, address, income, marriage, etc.) is extracted from the business system according to the customer ID to form a personal profile and pass it to the large language model system for supplementary question asking, and the large language model questions are collected to further form mapping information. Among them, the large language model system is based on the general large model, combined with the industry model and characteristics to form a domain large model, and then based on the domain large model, the enterprise-specific large model system is formed by using the enterprise's exclusive model, enterprise characteristics, preferences, etc. By integrating expert experience questions with advanced large-model questioning technology, a diversified and three-dimensional questioning framework has been constructed, which can enrich the dimensions of question collection, ensure the diversity and depth of questions, and thus respond to various complex situations more flexibly.

[0086] In an exemplary embodiment, the question bank table includes: question bank ID, question content, question type code (01 / 02 / 03), applicable emotion label, and status (1 valid, 0 invalid). In addition, the present invention provides an example of a question bank table, as shown in Table 4 below:

[0087] Table 4

[0088]

[0089] In an exemplary embodiment, when the question type code is 04 (large language model question type), the collected customer text information (such as name, address, income, marital status, etc.) is extracted from the business system according to the customer ID to form a personal profile and transmitted to the large language model system for supplementary questions as follows: "The borrower is male, with a monthly income of 4,000, married, a doctor, and a residential address in Shijiazhuang, Hebei. Please ask one additional question about his information?", thereby obtaining the following question content: "In addition to your monthly income, do you and your spouse have other stable sources of income or investment channels to further enhance the overall financial stability and repayment ability?".

[0090] In this embodiment, the interfaces provided by the supplementary information collection system include ① application interface and ② query interface. The input parameters of the application interface include: request unique identifier, customer ID, emotion tag, emotion score; the output parameters of the application interface include: response code resultCode, response content resultMsg, processing status handleStatus; the input parameters of the query interface include: request unique identifier, customer ID, emotion tag, emotion score; the output parameters of the query interface include: response code resultCode, response content resultMsg, processing status handleStatus.

[0091] In an exemplary embodiment, the collection question table includes: request unique identifier, customer ID, question content, question type code, and answer time limit (in seconds). In addition, the present invention provides an example of a question type time limit table, as shown in Table 5 below:

[0092] Table 5

[0093]

[0094] Step 4, supplementary collection and storage, specifically includes the following steps: the business system obtains the supplementary collection information list by calling the relevant interfaces of the micro-expression recognition system and the personalized information collection algorithm system (i.e., the supplementary information collection system), renders the question type through the business front-end system, supplements the collection of customer information by combining the question with the time limit of the answer, and stores the collected information in the risk application information of the business system. In this way, more customer information can be transmitted when applying for risk decision-making for the risk system to make decisions.

[0095] The above-mentioned information collection method of Example 2 of the present invention is adopted. On the basis of the basic information of the customer, the potential micro-expression information is carefully mined, and the micro-expression data including expression labels and expression scores are integrated into the information collection algorithm. The information points that need extra attention or supplementation are personalized and identified in combination with the customer information. The necessary supplementary information can be collected in advance, the approval process can be seamlessly connected, and the approval cycle can be significantly shortened. At the same time, the customer waiting time is reduced and the customer experience is optimized. At the same time, based on a flexible and dynamic answering mechanism, personalized questions and question types are randomly generated according to customer portraits and risk assessments to ensure the diversity and timeliness of information collection, which not only effectively increases the difficulty of identifying fraudulent behavior, but also greatly reduces the cost of fraud detection, and improves the security and stability of information collection and approval.

[0096] At the same time, the present invention provides an example of using the information collection method of the above-mentioned embodiment 2 to obtain supplementary question information, which is as follows:

[0097] First, obtain the request information for collecting supplementary question information and store the request information in a request log table, wherein the request log table includes: a request unique identifier, a request message, and a processing status. For example, the request log table is shown in Table 6 below:

[0098] Table 6

[0099]

[0100] Secondly, based on the collected basic customer information and request information, the collection question list and question collection time limit are obtained as shown in Table 7 below:

[0101] Table 7

[0102]

[0103] Then, the problem information is generated according to the collection problem list and the problem collection time limit, and then the supplementary collection information list is obtained according to the problem information as shown in Table 8 below:

[0104] Table 8

[0105]

[0106]

[0107] Finally, the content of each question in Table 8 above is provided to the front-end for display to obtain additional collection information.

[0108] [Example 3]

[0109] Figure 3 It is a schematic diagram of the architecture of the information collection system according to Example 3 of the present invention.

[0110] like Figure 3 As shown, the information acquisition system includes: a basic information acquisition module 310, a micro-expression recognition module 320, and a supplementary information acquisition module 330.

[0111] The basic information acquisition module 310 is used to acquire basic customer information.

[0112] In some embodiments, the basic information of the customer is obtained through the existing standardized collection process. Specifically, the basic information of the customer is obtained through the existing standardized collection process of "registration and login - ID card OCR automatic recognition - face recognition verification - contact information - personal information collection", such as: ID card information (name, gender, ethnicity, date of birth, ID card address information, ID card number, ID card validity period, ID card issuing authority, ID card portrait image data, ID card front image data), live body points, live body photo image data, live body video image data, contact information (contact name, contact relationship, contact mobile phone number), personal information (education, marriage, residential address, industry, occupation, monthly income, work unit), letter of commitment and authorization and other related image data.

[0113] The micro-expression recognition module 320 is used to obtain expression labels and expression scores according to the basic information of the customer. In this embodiment, expression labels and expression scores are obtained according to the facial information in the basic information of the customer combined with the micro-expression recognition system / module.

[0114] The supplementary information acquisition module 330 is used to perform the following operations: obtain the question type code according to the expression label and expression score, generate a collection question list and question collection time limit according to the question type code and customer basic information; generate question information according to the collection question list and question collection time limit; obtain a supplementary collection information list according to the question information.

[0115] In some implementations, obtaining the question type code according to the expression label and the expression score includes: obtaining collection information in an emotion collection information table according to the expression label and the expression score; and parsing the collection information to obtain the question type code and the number of questions.

[0116] In a further embodiment, generating a collected question list and a question collection time limit according to the question type code and the basic information of the customer includes: obtaining configuration information in the question type time limit table according to the question type code and the number of questions, the configuration information including a basic question answering time limit and a time limit offset range; calculating the question collection time limit according to the basic question answering time limit and the time limit offset range; obtaining a question bank ID in a question bank table according to the emotional tag and the question type code; generating question content according to the question bank ID and the basic information of the customer; and generating the collected question list according to the question content.

[0117] The above-mentioned information collection system of Example 3 of the present invention can mine potential micro-expression information on the basis of basic customer information, integrate micro-expression data including expression labels and expression scores into the information collection algorithm, and combine customer information to personalize and identify information points that require extra attention or supplementation. It can actively collect necessary supplementary information in advance, seamlessly connect the approval process, significantly shorten the approval cycle, and at the same time reduce customer waiting time and optimize customer experience.

[0118] Through the description of the above implementation modes, those skilled in the art can clearly understand that the present invention can be implemented by combining software with a hardware platform. Based on such an understanding, all or part of the contribution of the technical solution of the present invention to the background technology can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation modes of the present invention or some parts of the implementation modes.

[0119] Correspondingly, an embodiment of the present invention further provides a computer-readable storage medium on which computer-readable instructions or programs are stored. When the computer-readable instructions or programs are executed by a processor, the computer performs the following operations: the operations include the steps included in the information collection method described in any of the above embodiments, which are not repeated here. The storage medium may include, for example, a CD, a hard disk, a floppy disk, a flash memory, a magnetic tape, etc.

[0120] In addition, an embodiment of the present invention further provides a computer device including a memory and a processor, wherein the memory is used to store one or more computer-readable instructions or programs, wherein the one or more computer-readable instructions or programs can implement the information collection method described in any of the above embodiments when executed by the processor. The computer device can be, for example, a server, a desktop computer, a notebook computer, a tablet computer, etc.

[0121] The present invention also provides a computer program product including a computer program, wherein the computer program includes a program code for executing the information collection method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the information collection method provided by the embodiment of the present disclosure.

[0122] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0123] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention is described in detail with reference to the above embodiments, a person skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention. Therefore, the protection scope of the present invention shall be subject to the claims.

Claims

1. An information collection method, characterized in that: The information collection method comprises: Obtain basic customer information; Obtaining expression labels and expression scores according to the basic information of the customer; Acquire a question type code according to the expression label and the expression score, and generate a collection question list and question collection time limit according to the question type code and the basic information of the customer; Generate problem information according to the collection problem list and problem collection time limit; A supplementary collection information list is obtained according to the problem information.

2. The information collection method according to claim 1, characterized in that: The obtaining of the question type code according to the expression label and the expression score comprises: Acquire the collected information in the emotion collection information table according to the expression label and the expression score; The collected information is parsed to obtain the question type code and the number of questions.

3. The information collection method according to claim 2, characterized in that: The collection question list and question collection time limit are generated according to the question type code and the basic information of the customer, including: Acquire configuration information in the question type timeliness table according to the question type code and the number of questions, wherein the configuration information includes a basic question answering timeliness and a timeliness offset range; The question collection time limit is calculated according to the basic question answering time limit and the time limit offset range.

4. The information collection method according to claim 3, characterized in that: Generating a collection question list and question collection time limit according to the question type code and the basic information of the customer also includes: Obtaining the question bank ID in the question bank table according to the emotion label and question type code; Generate question content according to the question bank ID and basic customer information; The collection question list is generated according to the question content.

5. An information collection system, characterized in that: The information collection system comprises: Basic information acquisition module, used to obtain basic customer information; A micro-expression recognition module is used to obtain expression labels and expression scores according to the basic information of the customer; The supplementary information acquisition module is used to perform the following operations: Acquire a question type code according to the expression label and the expression score, and generate a collection question list and question collection time limit according to the question type code and the basic information of the customer; Generate problem information according to the collection problem list and problem collection time limit; A supplementary collection information list is obtained according to the problem information.

6. The information collection system according to claim 5, characterized in that: The obtaining of the question type code according to the expression label and the expression score comprises: Acquire the collected information in the emotion collection information table according to the expression label and the expression score; The collected information is parsed to obtain the question type code and the number of questions.

7. The information collection system according to claim 6, characterized in that: The collection question list and question collection time limit are generated according to the question type code and the basic information of the customer, including: Acquire configuration information in the question type timeliness table according to the question type code and the number of questions, wherein the configuration information includes a basic question answering timeliness and a timeliness offset range; Calculate the question collection time limit according to the basic question answering time limit and the time limit offset range; Obtaining the question bank ID in the question bank table according to the emotion label and question type code; Generate question content according to the question bank ID and basic customer information; The collection question list is generated according to the question content.

8. A computer-readable storage medium storing computer-readable instructions, characterized in that: The computer-readable instructions are executed by a processor to implement the information collection method according to any one of claims 1 to 4.

9. A computer device comprising a memory and a processor, The memory stores computer-readable instructions, characterized in that: The processor executes the computer-readable instructions to implement the information collection method according to any one of claims 1 to 4.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by the processor, the information collection method according to any one of claims 1 to 4 is implemented.

Images