WO2021164205A1 - Identity identification-based data auditing method and apparatus, and computer device - Google Patents

Identity identification-based data auditing method and apparatus, and computer device Download PDF

Info

Publication number
WO2021164205A1
WO2021164205A1 PCT/CN2020/106052 CN2020106052W WO2021164205A1 WO 2021164205 A1 WO2021164205 A1 WO 2021164205A1 CN 2020106052 W CN2020106052 W CN 2020106052W WO 2021164205 A1 WO2021164205 A1 WO 2021164205A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
asset
user
review
character recognition
Prior art date
Application number
PCT/CN2020/106052
Other languages
French (fr)
Chinese (zh)
Inventor
刘丽珍
Original Assignee
深圳壹账通智能科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳壹账通智能科技有限公司 filed Critical 深圳壹账通智能科技有限公司
Publication of WO2021164205A1 publication Critical patent/WO2021164205A1/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/5846Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using extracted text
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/10Office automation; Time management
    • G06Q10/103Workflow collaboration or project management

Definitions

  • This application relates to the field of big data technology, and in particular to a data verification method, device and computer equipment based on identity recognition.
  • the inventor realizes that at present, the data uploaded by the customer is directly reviewed, and among the materials to be reviewed, there are still more information that is not related to the user's purchase qualification review, which leads to an increase in the workload of information review processing. , A large amount of computer resources are consumed, and the audit efficiency cannot be improved.
  • a data verification method, device and computer equipment based on identity recognition are provided.
  • a data audit method based on identity recognition includes:
  • the identification character recognition result and the asset character recognition result corresponding to the user identification are obtained, and the identification character recognition result is compared with the pre-stored user identity information;
  • the data types include numeric data, text data, and byte data;
  • the data review method includes a first review method corresponding to the digital behavior history data and a second review method corresponding to the text type behavior history data, And the third audit method corresponding to byte-type behavior historical data;
  • the behavior history data passes the data review, obtain the first user identification corresponding to the behavior history data, and push the first user identification to the priority queue in the queuing system;
  • the asset data is audited on the asset character recognition result corresponding to the first user identification, and the audit result is generated and returned to the user terminal.
  • a data verification device based on identity recognition comprising:
  • the detection module is used to obtain the identification character recognition result and asset character identification result corresponding to the user identification when the data review request sent by the user is detected, and compare the identification character identification result with pre-stored user identification information ;
  • a behavior history data extraction module configured to extract behavior history data corresponding to the user identification when the identification character recognition result matches the pre-stored user identification information
  • the classification module is configured to classify the behavior history data according to preset data classification rules to obtain behavior history data of different data types; the data types include digital data, text data, and byte data;
  • the data review method determining module is used to determine the data review method corresponding to each of the different data types of behavior history data; the data review method includes the first review method corresponding to the digital behavior history data and the text type behavior history The second review method corresponding to the data, and the third review method corresponding to the byte-type behavior historical data;
  • the data review module is used to conduct data review on the behavior history data of the corresponding data type according to the review method
  • a push module configured to obtain a first user identification corresponding to the behavior history data when the behavior history data passes the data review, and push the first user identification to the priority queue in the queuing system;
  • a polling module configured to poll the queuing system to obtain the first user identification from the priority queue
  • the audit result generation module is used to audit asset data on the asset character recognition result corresponding to the first user identification, generate an audit result, and return it to the user terminal.
  • a computer device including a memory and one or more processors, the memory stores computer readable instructions, and when the computer readable instructions are executed by the processor, the one or more processors execute The following steps:
  • the identification character recognition result and the asset character recognition result corresponding to the user identification are obtained, and the identification character recognition result is compared with the pre-stored user identity information;
  • the data types include numeric data, text data, and byte data;
  • the data review method includes a first review method corresponding to the digital behavior history data and a second review method corresponding to the text type behavior history data, And the third audit method corresponding to byte-type behavior historical data;
  • the behavior history data passes the data review, obtain the first user identification corresponding to the behavior history data, and push the first user identification to the priority queue in the queuing system;
  • One or more computer-readable storage media storing computer-readable instructions.
  • the one or more processors perform the following steps:
  • the identification character recognition result and the asset character recognition result corresponding to the user identification are obtained, and the identification character recognition result is compared with the pre-stored user identity information;
  • the data types include numeric data, text data, and byte data;
  • the data review method includes a first review method corresponding to the digital behavior history data and a second review method corresponding to the text type behavior history data, And the third audit method corresponding to byte-type behavior historical data;
  • the behavior history data passes the data review, obtain the first user identification corresponding to the behavior history data, and push the first user identification to the priority queue in the queuing system;
  • the above-mentioned data verification method, device, computer equipment and storage medium based on identity recognition when the data verification request sent by the user is detected, obtain the identity character recognition result and asset character recognition result corresponding to the user identity, and then compare the identity character recognition result Compare with pre-stored user identity information.
  • the identification character recognition result matches the pre-stored user identity information
  • the behavior history data corresponding to the user ID is extracted, and the behavior history data is classified according to the preset data classification rules to obtain the behavior history data of different data types, and then determine the Data review methods corresponding to different data types of behavioral historical data. According to the review method, conduct data review on the behavior history data of the corresponding data type.
  • the behavior history data passes the data review, obtain the first user ID corresponding to the behavior history data, and push the first user ID to the queue in the queuing system.
  • Priority queue The queuing system is polled, the first user identification is obtained from the priority queue, the asset data is audited on the asset character recognition result corresponding to the first user identification, and the audit result is generated and returned to the user terminal.
  • the user By confirming the customer’s identity information, and after the identity information is confirmed, the user’s behavior history data is audited, avoiding confusion caused by directly auditing all the information submitted by the user, and it can also be used to check the historical behavior data.
  • the first audited asset data information of the user is prioritized and the audit result is returned to the user in a timely manner, which improves the efficiency of data auditing.
  • Figure 1 is an application scenario diagram of a data audit method based on identity recognition according to one or more embodiments
  • FIG. 2 is a schematic flowchart of a data verification method based on identity recognition according to one or more embodiments
  • Fig. 3 is a block diagram of a data verification device based on identity recognition according to one or more embodiments
  • Figure 4 is a block diagram of a computer device according to one or more embodiments.
  • the data verification method based on identity recognition can be applied to the application environment as shown in FIG. 1.
  • the user terminal 102 and the server 104 communicate through the network.
  • the server 104 detects the data review request sent by the user at the user terminal 102
  • the server 104 obtains the character recognition result and the asset character recognition result corresponding to the user identification, and compares the character recognition result with the pre-stored user identity information.
  • the identification character recognition result matches the pre-stored user identity information
  • the behavior history data corresponding to the user ID is extracted, and the behavior history data is classified according to the preset data classification rules to obtain the behavior history data of different data types, and then determine the Data review methods corresponding to different data types of behavioral historical data.
  • the review method conduct data review on the behavior history data of the corresponding data type.
  • the behavior history data passes the data review, obtain the first user ID corresponding to the behavior history data, and push the first user ID to the queue in the queuing system.
  • Priority queue Priority queue.
  • the server 104 obtains the first user identification from the priority queue by polling the queuing system, conducts asset data audit on the asset character recognition result corresponding to the first user identification, generates the audit result, and returns it to the user terminal 102.
  • the user terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices.
  • the server 104 may be implemented by an independent server or a server cluster composed of multiple servers.
  • a data audit method based on identity recognition is provided. Taking the method applied to the server in FIG. 1 as an example, the method includes the following steps:
  • S202 When a data review request sent by the user is detected, obtain an identification character recognition result and an asset character recognition result corresponding to the user identification, and compare the identification character recognition result with pre-stored user identity information.
  • the server detects the data review request sent by the user at the terminal, by acquiring the identity certification image file and asset certification image file uploaded by the user, and extracting character recognition information from the identity certification image file and asset certification image file, Obtain identification character recognition results and asset character recognition results. Obtain the user identity information pre-stored during user registration from the system, and compare the identification character recognition result with the pre-stored user identity information.
  • the user uploads his ID card image file and asset certification image file to the server while the terminal sends a data review request to the server, the server receives the data review request sent by the terminal, and obtains the identity ID image file and image file uploaded by the user.
  • Asset proof image file includes income certificates, bank records, deposit certificates, other certificates of purchase of financial products, and image files such as stocks, funds, futures, bonds, trusts, insurance, and current passbooks.
  • the pre-stored user information is the identity information entered by the user at the terminal, including the user's ID number and name.
  • the server can obtain the ID number and name on the ID image file by analyzing the user's identification information character recognition result, and compare the ID information character recognition result with the ID number and name pre-entered by the user on the terminal. Yes, it is judged whether the character recognition result of the identity information matches the ID number and name entered by the user in the terminal in advance.
  • the result of the audit failure needs to be returned.
  • the results of the audit failure include identity non-conformance and image file format errors. When the image file format is incorrect, character recognition information cannot be extracted, and the information for re-uploading the image file needs to be returned.
  • the name in the asset certificate needs to be extracted from the name and ID in the image file. After the image character is recognized, there will be a series of text information, and then The extracted name is compared with the user name in the pre-stored user information. If it is not the same, the ID number is compared. After matching the ID card, compare it. If the ID number is also inconsistent, it can be explained that the uploaded asset certificate is not the person, and the review fails.
  • the behavior history data corresponding to the user ID includes browsing records, favorite records, and product purchase records corresponding to the user ID.
  • the browsing records can be the user's access records to products and promotion activities in the system or in the mall.
  • the favorite records include the user After browsing the product, select the record of collecting one or more of the products.
  • the purchase record of the product includes the different types of products purchased by the user and the value of the corresponding product.
  • browsing record related data includes the product category browsed by the user, the product value of the corresponding product and the number of views
  • the favorite record related data includes the user's favorite product category and the product value of the corresponding product
  • the purchase record related data includes the product purchased by the user.
  • the server obtains the user's browsing records, favorite records, product purchase records, and promotion activity participation records in the system or in the mall.
  • the type of wealth management product or insurance product purchased by the user is obtained, including the value of the product and the time of purchase.
  • S206 Classify the behavior history data according to preset data classification rules, and obtain behavior history data of different data types.
  • the data types include numeric data, text data, and byte data.
  • the preset data classification rules are used to classify behavior history data, and the classification basis corresponds to the data type, where the data types include numeric data, text data, and byte data.
  • the behavior history data is classified into digital behavior history data, text behavior history data, and byte behavior history data.
  • S208 Determine the data review method corresponding to the behavior history data of each different data type; the data review method includes the first review method corresponding to the digital behavior historical data, the second review method corresponding to the text-based behavior historical data, and The third audit method corresponding to byte-type behavior historical data.
  • the behavior history data of the corresponding data types can be reviewed by obtaining the data review methods corresponding to the behavior history data of different data types.
  • the data review method includes a first review method corresponding to digital behavior historical data, a second review method corresponding to text-based behavior historical data, and a third review method corresponding to byte-type behavior historical data.
  • the first review method can be used to review digital behavior historical data
  • the second review method can be used to review text-based behavior historical data
  • the third review method can be used to review byte-type historical data.
  • S210 Perform data audit on the behavior history data corresponding to the data type according to the audit mode.
  • the data can be reviewed using the corresponding data review method.
  • the server reviews the different categories of products the user browses and the number of corresponding product views. The number of times the product is viewed determines the user’s purchase tendency.
  • users have a greater tendency to purchase products that have been viewed multiple times, and products that have not been browsed and understood will not be easily purchased. Therefore, it can be based on the user’s browsing history. Preliminarily judge whether the user passes the preliminary data review, that is, whether the data related to the browsing record can pass the data review.
  • the server needs to review the different categories of products collected by the user, the number of products in the same category, and the product value of the respective products, and can determine whether the product that the user has a purchase tendency meets the asset type in the subsequent asset review. At the same time, the number of purchases of different types of products purchased by the user and the product value of the corresponding product are reviewed.
  • the product purchased by the user meets the acceptable asset type in the subsequent asset review, and the product value is accumulated, it can pass the preset review Standard means that the user’s collection record-related data and purchase record data have passed the data review. Further, after passing the data review with the identified behavior data, it indicates that the user corresponding to the user identification is the first user. The system will prioritize the audit for the first user, and is in the priority queue in the queuing system.
  • the behavior history data passes the data review, it indicates that the user ID corresponding to the changed behavior history data is the first user ID.
  • the server can obtain the first user ID corresponding to the first user and push the first user ID to the queue.
  • the user identification also includes a second user identification, that is, when the behavior data corresponding to the user identification fails the data review, the user corresponding to the user identification is the second user, and the second user identification corresponding to the second user can be pushed To the second queue in the queuing system.
  • the data audit of the second user in the second queue is after the priority queue.
  • S214 Polling the queuing system to obtain the first user identifier from the priority queue.
  • the server uses a polling mechanism to poll the queuing system to determine whether the first user identification exists in the priority queue in the queuing system, and when the first user identification is recognized in the queuing system, the first user identification is acquired.
  • S216 Perform asset data review on the asset character recognition result corresponding to the first user identifier, generate the review result, and return it to the user terminal.
  • the server parses the asset information character recognition result corresponding to the first user ID, and extracts the asset keyword from it.
  • the asset keyword includes the asset type corresponding to the first user identifier.
  • the server obtains the preset review criteria and compares the asset keyword with the preset review criteria, and when the asset keyword meets the preset review criteria, it returns the first user's successful review result.
  • the server obtains the preset audit criteria, and compares the asset keyword with the preset audit criteria, which specifically includes: the server obtains the preset audit criteria, where the preset audit criteria is the preset total asset threshold corresponding to the user ID .
  • the preset audit criteria is the preset total asset threshold corresponding to the user ID .
  • Obtain the asset value size corresponding to each asset type accumulate the asset value size of each asset type, obtain the total asset value, and compare the total asset value with the preset total asset threshold to determine the total asset value and the preset total asset value The difference between the thresholds. Furthermore, it can be judged whether the audit is passed or not based on the difference between the total asset value and the preset total asset threshold.
  • the server performs template matching through the results returned by asset information character recognition, matches the corresponding value through regular rules, and then performs templateization.
  • character recognition can extract keywords such as the amount and account number from the asset certificate submitted by the user, and extract After the keywords are reached, the total asset value is summarized, and then it is judged whether the total asset value can meet the predetermined standard for review. When the standard is met, the review is passed. If the standard is not met, the review is not passed, or the user is reminded to provide other asset certification documents.
  • the summary of the total asset value means the sum of all the amounts in the multiple asset certificates submitted by the user.
  • the set audit standard can be fixed or adjustable, but the user audit standard for all sent data audits needs to be kept consistent.
  • the general audit standard is that the total assets reach 1 million or more, then the approval can be passed, and then it can be judged whether the total amount exceeds 1 million to judge whether the audit is passed.
  • the reason for the failure of the audit is the inability to meet the asset requirements of the corresponding wealth management products based on identification.
  • the identity character recognition result and asset character recognition result corresponding to the user identity are obtained, and the identity character recognition result is combined with the pre-stored user identity information Compare.
  • the identification character recognition result matches the pre-stored user identity information
  • the behavior history data corresponding to the user ID is extracted, and the behavior history data is classified according to the preset data classification rules to obtain the behavior history data of different data types, and then determine the Data review methods corresponding to different data types of behavioral historical data. According to the review method, conduct data review on the behavior history data of the corresponding data type.
  • the behavior history data passes the data review, obtain the first user ID corresponding to the behavior history data, and push the first user ID to the queue in the queuing system.
  • Priority queue The queuing system is polled, the first user identification is obtained from the priority queue, the asset data is audited on the asset character recognition result corresponding to the first user identification, and the audit result is generated and returned to the user terminal.
  • the user By confirming the customer’s identity information, and after the identity information is confirmed, the user’s behavior history data is audited, avoiding confusion caused by directly auditing all the information submitted by the user, and it can also be used to check the historical behavior data.
  • the first audited asset data information of the user is prioritized and the audit result is returned to the user in a timely manner, which improves the efficiency of data auditing.
  • the step of performing asset data audit on the asset character recognition result corresponding to the first user identification, generating the audit result and returning it to the user terminal further includes:
  • the preset audit standard is a preset total asset threshold corresponding to the first user identification
  • the result generated by the audit is generated and returned to the user terminal; when the total asset value is less than the preset total asset threshold, the audit failed result is generated and returned to the user terminal.
  • the server obtains a preset audit standard, where the preset audit standard is a preset total asset threshold corresponding to the user identification.
  • the preset audit standard is a preset total asset threshold corresponding to the user identification.
  • Obtain the asset value size corresponding to each asset type accumulate the asset value size of each asset type, obtain the total asset value, and compare the total asset value with the preset total asset threshold to determine the total asset value and the preset total asset value The difference between the thresholds.
  • it can be judged whether the audit is passed or not based on the difference between the total asset value and the preset total asset threshold.
  • the difference is a positive number, that is, when the total asset value is greater than the preset total asset threshold, it means that the review is passed.
  • the difference is a negative number that is, when the total asset value is less than the preset total asset threshold, the review fails, and the user is reminded to provide other asset certification documents.
  • asset types include income, financial products, including stocks, funds, futures, bonds, trusts, and insurance, etc.
  • the value of the asset amount corresponding to each asset type is not fixed.
  • the summary of the total asset value means the sum of all the amounts in the multiple asset certificates submitted by the user.
  • the set audit standard can be fixed or adjustable, but the user audit standard for all sent data audits needs to be kept consistent.
  • the general audit standard is that the total assets reach 1 million or more, then the approval can be passed, and then it can be judged whether the total amount exceeds 1 million to judge whether the audit is passed.
  • the reason for the failure of the audit is the inability to meet the asset requirements of the corresponding wealth management products based on identification.
  • the asset keyword is extracted from the asset information character recognition result corresponding to the first user ID, and the asset keyword is audited using the preset audit standard.
  • the asset keyword meets the preset audit standard, return to the first user for audit Successful results. It realizes the priority to review the asset information character recognition of the first user identification, the review result can be obtained in time, the time for the user to wait for the review result is reduced, and the user experience is improved.
  • a data audit method based on identity recognition which further includes:
  • the server obtains the corresponding second user; pushes the second user ID corresponding to the second user to the second queue in the queuing system; when the polling queuing system fails to obtain When the first user ID is reached, the second user ID is obtained from the second queue; the asset character recognition result corresponding to the second user ID is checked by using preset audit criteria, and the audit result is generated and returned to the user terminal.
  • the server parses the asset information character recognition result corresponding to the second user ID, and extracts the asset keyword therefrom.
  • the asset keyword includes the asset type corresponding to the second user identifier.
  • the server obtains the preset review criteria and compares the asset keyword with the preset review criteria, and when the asset keyword meets the preset review criteria, it returns the result of successful review by the second user.
  • the server obtains the preset audit criteria, and compares the asset keyword with the preset audit criteria, which specifically includes: the server obtains the preset audit criteria, where the preset audit criteria is the preset total assets corresponding to the user ID Threshold.
  • the preset audit criteria is the preset total assets corresponding to the user ID Threshold.
  • Obtain the asset value size corresponding to each asset type accumulate the asset value size of each asset type, obtain the total asset value, and compare the total asset value with the preset total asset threshold to determine the total asset value and the preset total asset value The difference between the thresholds. Furthermore, it can be judged whether the audit is passed or not based on the difference between the total asset value and the preset total asset threshold.
  • the second user ID in the front position is obtained from the queuing system, and the preset audit criteria are used to check the asset information characters corresponding to the second user ID.
  • the identification results are reviewed and the corresponding review results are obtained. Since the priority review of the first user relative to the second user is realized, the use experience of the first user is improved, and more first users are attracted.
  • the identification character recognition result and the asset character recognition result corresponding to the user identification are obtained, and the identification character recognition result is compared with the pre-stored user identification information
  • the steps include:
  • the server obtains the identity certification image file and asset certification image file uploaded by the user; extracts the character recognition information of the identity certification image file and the asset certification image file to obtain the identity character recognition result and the asset character recognition result; obtains the pre-stored user identity information; The identification character recognition result is compared with the pre-stored user identification information.
  • the user uploads his ID card image file and asset certification image file to the server while the terminal sends a data review request to the server, the server receives the data review request sent by the terminal, and obtains the ID ID image file uploaded by the user And asset proof image files.
  • the image files of asset certification include income certificates, bank records, deposit certificates, other certificates of purchase of financial products, and image files such as stocks, funds, futures, bonds, trusts, insurance, and current passbooks.
  • the pre-stored user information is the identity information entered by the user at the terminal, including the user's ID number and name.
  • the server can obtain the ID number and name on the ID image file by analyzing the user's identification information character recognition result, and compare the ID information character recognition result with the ID number and name pre-entered by the user on the terminal. Yes, it is judged whether the character recognition result of the identity information matches the ID number and name entered by the user in the terminal in advance.
  • the result of the audit failure needs to be returned.
  • the results of the audit failure include identity non-conformance and image file format errors. When the image file format is incorrect, character recognition information cannot be extracted, and the information for re-uploading the image file needs to be returned.
  • the server extracts the character recognition information from the identity certification image file and asset certification image file uploaded by the user to obtain the identity character recognition result and the asset character recognition result, and compare the identity character recognition result with the pre-stored user identity information. Comparison. It realizes the automatic review of user identity information, avoids manual offline verification, and improves the accuracy and speed of identity information verification.
  • steps in the flowchart of FIG. 2 are displayed in sequence as indicated by the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless specifically stated in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least part of the steps in FIG. 2 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution of these sub-steps or stages The sequence is not necessarily performed sequentially, but may be performed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.
  • a data review device based on identity recognition includes: a detection module 302, a behavior history data extraction module 304, a classification module 306, a data review method determination module 308, and a data review module 308.
  • the audit module 310, the push module 312, the polling module 314, and the audit result generation module 316 wherein:
  • the detection module 302 is configured to obtain the identification character recognition result and the asset character recognition result corresponding to the user identification when the data review request sent by the user is detected, and compare the identification character recognition result with pre-stored user identification information.
  • the behavior history data extraction module 304 is configured to extract behavior history data corresponding to the user identification when the identification character recognition result matches the pre-stored user identification information.
  • the classification module 306 is configured to classify behavior history data according to preset data classification rules to obtain behavior history data of different data types; the data types include digital data, text data, and byte data.
  • the data review method determining module 308 is used to determine the data review method corresponding to the behavior history data of different data types; the data review method includes the first review method corresponding to the digital behavior history data and the data review method corresponding to the text type behavior history data. The second review method, and the third review method corresponding to byte-type behavior historical data.
  • the data audit module 310 is used to perform data audit on the behavior history data of the corresponding data type according to the audit mode.
  • the pushing module 312 is configured to obtain the first user identifier corresponding to the behavior historical data when the behavior historical data passes the data review, and push the first user identifier to the priority queue in the queuing system.
  • the polling module 314 is configured to poll the queuing system and obtain the first user identification from the priority queue.
  • the audit result generation module 316 is configured to perform asset data audit on the asset character recognition result corresponding to the first user identification, generate an audit result, and return it to the user terminal.
  • the above-mentioned data verification device when detecting a data verification request sent by a user, obtains the identity character recognition result and asset character recognition result corresponding to the user ID, and compares the identity character recognition result with the pre-stored user identity information Comparison.
  • the identification character recognition result matches the pre-stored user identity information
  • the behavior history data corresponding to the user ID is extracted, and the behavior history data is classified according to the preset data classification rules to obtain the behavior history data of different data types, and then determine the Data review methods corresponding to different data types of behavioral historical data. According to the review method, conduct data review on the behavior history data of the corresponding data type.
  • the behavior history data passes the data review, obtain the first user ID corresponding to the behavior history data, and push the first user ID to the queue in the queuing system.
  • Priority queue The queuing system is polled, the first user identification is obtained from the priority queue, the asset data is audited on the asset character recognition result corresponding to the first user identification, and the audit result is generated and returned to the user terminal.
  • the user By confirming the customer’s identity information, and after the identity information is confirmed, the user’s behavior history data is audited, avoiding confusion caused by directly auditing all the information submitted by the user, and it can also be used to check the historical behavior data.
  • the first audited asset data information of the user is prioritized and the audit result is returned to the user in a timely manner, which improves the efficiency of data auditing.
  • the audit result generation module is also used to:
  • the above-mentioned review module realizes the priority review of the asset information character recognition of the first user identification, the review result can be obtained in time, the time for the user to wait for the review result is reduced, and the user experience is improved.
  • the audit result generation module is also used to:
  • the preset audit standard is the preset total asset threshold corresponding to the first user ID; obtain the asset value size corresponding to each asset type corresponding to the first user ID; accumulate each asset The type of asset value size, the total asset value obtained; compare the total asset value with the preset total asset threshold; when the total asset value is greater than or equal to the preset total asset threshold, the result generated by the audit is generated and returned to the user terminal ; When the total asset value is less than the preset total asset threshold, the result of the audit failure is generated and returned to the user terminal.
  • the aforementioned audit result generation module extracts asset keywords from the asset information character recognition result corresponding to the first user ID, and uses preset audit criteria to audit the asset keywords. When the asset keyword meets the preset audit criteria, it returns to the first The result of a successful user review. It realizes the priority to review the asset information character recognition of the first user identification, the review result can be obtained in time, the time for the user to wait for the review result is reduced, and the user experience is improved.
  • a data verification device based on identity recognition is provided, and further includes a second user verification module for:
  • the corresponding second user is obtained; the second user ID corresponding to the second user is pushed to the second queue in the queuing system; when the polling queuing system does not obtain the first user ID At the time, obtain the second user ID from the second queue; use the preset audit criteria to audit the asset character recognition result corresponding to the second user ID, and return the audit result.
  • the above-mentioned data verification device based on identity recognition, when the first user ID is not obtained, obtains the second user ID in the front position from the queuing system, and uses preset audit criteria to determine the asset information characters corresponding to the second user ID The identification results are reviewed and the corresponding review results are obtained. Since the first user's priority review relative to the second user is realized, the first user's experience is improved and more first users are attracted.
  • the detection module is also used to:
  • the above-mentioned acquisition module realizes automatic verification of user identity information, avoids manual offline verification, and improves the accuracy and speed of identity information verification.
  • Each module in the above-mentioned identity recognition-based data auditing device can be implemented in whole or in part by software, hardware, and a combination thereof.
  • the above-mentioned modules may be embedded in the form of hardware or independent of the processor in the computer equipment, or may be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.
  • a computer device is provided.
  • the computer device may be a server, and its internal structure diagram may be as shown in FIG. 4.
  • the computer equipment includes a processor, a memory, a network interface, and a database connected through a system bus.
  • the processor of the computer device is used to provide calculation and control capabilities.
  • the memory of the computer device includes a non-volatile or volatile storage medium and internal memory.
  • the non-volatile or volatile storage medium stores an operating system, computer readable instructions, and a database.
  • the internal memory provides an environment for the operation of the operating system and computer-readable instructions in the non-volatile storage medium.
  • the database of the computer equipment is used to store data audit data.
  • the network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer readable instruction is executed by the processor, a data audit method based on identification is realized.
  • FIG. 4 is only a block diagram of part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied.
  • the specific computer device may Including more or fewer parts than shown in the figure, or combining some parts, or having a different arrangement of parts.
  • One or more computer-readable storage media storing computer-readable instructions.
  • the one or more processors perform the following steps:
  • the identification character recognition result and the asset character recognition result corresponding to the user identification are obtained, and the identification character recognition result is compared with the pre-stored user identity information;
  • Classify behavior history data according to preset data classification rules to obtain behavior history data of different data types; data types include numeric data, text data, and byte data;
  • the data review method includes the first review method corresponding to the digital behavior historical data, the second review method corresponding to the text-based behavior historical data, and the byte
  • the third review method corresponding to historical data of type behavior
  • the behavior history data passes the data review, obtain the first user identification corresponding to the behavior history data, and push the first user identification to the priority queue in the queuing system;
  • the asset data is audited on the asset character recognition result corresponding to the first user identification, and the audit result is generated and returned to the user terminal.
  • the asset keyword includes the asset type corresponding to the first user ID
  • the preset audit standard is a preset total asset threshold corresponding to the first user identification
  • the result generated by the audit is generated and returned to the user terminal; when the total asset value is less than the preset total asset threshold, the audit failed result is generated and returned to the user terminal.
  • the asset data is audited on the asset character recognition result corresponding to the second user ID, and the audit result is generated and returned to the user terminal.
  • the identification character recognition result is compared with the pre-stored user identification information.
  • the browsing record related data, the favorite record related data and the purchase record related data corresponding to the user identification are obtained respectively;
  • the browsing record related data includes the product category browsed by the user and the corresponding product information.
  • purchase record related data includes the user's product category purchased, the number of purchases of the corresponding product, purchase time, and product value.
  • One or more computer-readable storage media storing computer-readable instructions.
  • the one or more processors perform the following steps:
  • the identification character recognition result and the asset character recognition result corresponding to the user identification are obtained, and the identification character recognition result is compared with the pre-stored user identity information;
  • Classify behavior history data according to preset data classification rules to obtain behavior history data of different data types; data types include numeric data, text data, and byte data;
  • the data review method includes the first review method corresponding to the digital behavior historical data, the second review method corresponding to the text-based behavior historical data, and the byte
  • the third review method corresponding to historical data of type behavior
  • the behavior history data passes the data review, obtain the first user identification corresponding to the behavior history data, and push the first user identification to the priority queue in the queuing system;
  • the asset data is audited on the asset character recognition result corresponding to the first user identification, and the audit result is generated and returned to the user terminal.
  • the computer-readable storage medium may be non-volatile or volatile.
  • the asset keyword includes the asset type corresponding to the first user ID
  • the preset audit standard is a preset total asset threshold corresponding to the first user identification
  • the result generated by the audit is generated and returned to the user terminal; when the total asset value is less than the preset total asset threshold, the audit failed result is generated and returned to the user terminal.
  • the asset data is audited on the asset character recognition result corresponding to the second user ID, and the audit result is generated and returned to the user terminal.
  • the identification character recognition result is compared with the pre-stored user identification information.
  • the browsing record related data, the favorite record related data and the purchase record related data corresponding to the user identification are obtained respectively;
  • the browsing record related data includes the product category browsed by the user and the corresponding product information.
  • purchase record related data includes the user's product category purchased, the number of purchases of the corresponding product, purchase time, and product value.
  • Non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory may include random access memory (RAM) or external cache memory.
  • RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
  • SRAM static RAM
  • DRAM dynamic RAM
  • SDRAM synchronous DRAM
  • DDRSDRAM double data rate SDRAM
  • ESDRAM enhanced SDRAM
  • SLDRAM synchronous chain Channel
  • memory bus Radbus direct RAM
  • RDRAM direct memory bus dynamic RAM
  • RDRAM memory bus dynamic RAM

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Library & Information Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Operations Research (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

An identity identification-based data auditing method and apparatus, and a computer device, relating to big data. The method comprises: when a data auditing request is detected, comparing an identity character identification result corresponding to a user identifier with user identity information; when the identity character identification result corresponds to the user identity information, extracting corresponding behavior historical data; determining data auditing modes corresponding to the behavior historical data of different data types; when the behavior historical data passes the data auditing of a corresponding auditing mode, obtaining a first user identifier corresponding to the behavior historical data, and pushing the first user identifier to a priority queue; performing polling on a queuing system and obtaining the first user identifier from the priority queue; and performing asset data auditing on an asset character identification result corresponding to the first user identifier to generate an auditing result, and returning the auditing result to a user terminal.

Description

基于身份识别的数据审核方法、装置和计算机设备Data verification method, device and computer equipment based on identity recognition
相关申请的交叉引用Cross-references to related applications
本申请要求于2020年2月18日提交中国专利局,申请号为2020100994722,申请名称为″基于身份识别的数据审核方法、装置和计算机设备″的中国专利申请的优先权,其全部内容通过引用结合在本申请中。This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on February 18, 2020. The application number is 2020100994722 and the application name is "identification-based data verification methods, devices and computer equipment". The entire content is by reference Incorporated in this application.
技术领域Technical field
本申请涉及大数据技术领域,特别是涉及一种基于身份识别的数据审核方法、装置和计算机设备。This application relates to the field of big data technology, and in particular to a data verification method, device and computer equipment based on identity recognition.
背景技术Background technique
随着计算技术的发展,关于资产信息的处理活动越发频繁,人们可将自己的资产用于投资理财,以收到更高价值的回报。对于有理财产品购买需求的用户,相关企业需要对用户的购买资格进行审核,其中,合格投资者认证是对用户购买理财产品时,银行或企业对基于身份识别的进行认证的过程。目前企业大多通过对基于身份识别的的相关数据进行审核,来判定该用户是否具备理财产品的购买资格。待客户上传资料后,通过对客户上传的资料进行审核,来判断该客户是否可购买相关产品。With the development of computing technology, the processing activities of asset information become more frequent, and people can use their assets for investment and financial management to receive higher value returns. For users who need to purchase wealth management products, relevant companies need to review the purchase qualifications of users. Among them, qualified investor certification is the process of identification-based authentication by banks or companies when users purchase wealth management products. At present, most companies judge whether the user is eligible to purchase wealth management products by reviewing relevant data based on identification. After the customer uploads the information, review the information uploaded by the customer to determine whether the customer can purchase the relevant product.
然而,发明人意识到,目前是通过对客户上传的资料进行直接审核,而在待进行审核的资料中,仍存在较多与用户购买资格审核不相关的信息,导致出现信息审核处理工作量上升,大量消耗计算机资源,且审核效率并不能得到提高的问题。However, the inventor realizes that at present, the data uploaded by the customer is directly reviewed, and among the materials to be reviewed, there are still more information that is not related to the user's purchase qualification review, which leads to an increase in the workload of information review processing. , A large amount of computer resources are consumed, and the audit efficiency cannot be improved.
发明内容Summary of the invention
根据本申请公开的各种实施例,提供一种基于身份识别的数据审核方法、装置和计算机设备。According to various embodiments disclosed in the present application, a data verification method, device and computer equipment based on identity recognition are provided.
一种基于身份识别的数据审核方法包括:A data audit method based on identity recognition includes:
当检测到用户发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将所述身份字符识别结果与预先存储的用户身份信息进行比对;When the data review request sent by the user is detected, the identification character recognition result and the asset character recognition result corresponding to the user identification are obtained, and the identification character recognition result is compared with the pre-stored user identity information;
当所述身份字符识别结果符合所述预先存储的用户身份信息时,提取所述用户标识对应的行为历史数据;When the identification character recognition result matches the pre-stored user identification information, extracting the behavior history data corresponding to the user identification;
根据预设数据分类规则对所述行为历史数据进行分类,获得不同数据类型的行为历史数据;所述数据类型包括数字型数据、文本型数据以及字节型数据;Classify the behavior history data according to preset data classification rules to obtain behavior history data of different data types; the data types include numeric data, text data, and byte data;
确定与各所述不同数据类型的行为历史数据对应的数据审核方式;所述数据审核方式包括与数字型行为历史数据对应的第一审核方式、与文本型行为历史数据对应的第二审核 方式,以及与字节型行为历史数据对应的第三审核方式;Determine the data review method corresponding to each of the different data types of behavior history data; the data review method includes a first review method corresponding to the digital behavior history data and a second review method corresponding to the text type behavior history data, And the third audit method corresponding to byte-type behavior historical data;
根据所述审核方式,分别对对应数据类型的行为历史数据进行数据审核;According to the review method, conduct a data review on the behavior history data of the corresponding data type;
当所述行为历史数据通过所述数据审核时,获取与所述行为历史数据对应的第一用户标识,并将所述第一用户标识推送至排队***中的优先队列;When the behavior history data passes the data review, obtain the first user identification corresponding to the behavior history data, and push the first user identification to the priority queue in the queuing system;
轮询所述排队***,从所述优先队列中获取所述第一用户标识;及Polling the queuing system to obtain the first user identification from the priority queue; and
对与所述第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。The asset data is audited on the asset character recognition result corresponding to the first user identification, and the audit result is generated and returned to the user terminal.
一种基于身份识别的数据审核装置,所述装置包括:A data verification device based on identity recognition, the device comprising:
检测模块,用于当检测到用户发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将所述身份字符识别结果与预先存储的用户身份信息进行比对;The detection module is used to obtain the identification character recognition result and asset character identification result corresponding to the user identification when the data review request sent by the user is detected, and compare the identification character identification result with pre-stored user identification information ;
行为历史数据提取模块,用于当所述身份字符识别结果符合所述预先存储的用户身份信息时,提取所述用户标识对应的行为历史数据;A behavior history data extraction module, configured to extract behavior history data corresponding to the user identification when the identification character recognition result matches the pre-stored user identification information;
分类模块,用于根据预设数据分类规则对所述行为历史数据进行分类,获得不同数据类型的行为历史数据;所述数据类型包括数字型数据、文本型数据以及字节型数据;The classification module is configured to classify the behavior history data according to preset data classification rules to obtain behavior history data of different data types; the data types include digital data, text data, and byte data;
数据审核方式确定模块,用于确定与各所述不同数据类型的行为历史数据对应的数据审核方式;所述数据审核方式包括与数字型行为历史数据对应的第一审核方式、与文本型行为历史数据对应的第二审核方式,以及与字节型行为历史数据对应的第三审核方式;The data review method determining module is used to determine the data review method corresponding to each of the different data types of behavior history data; the data review method includes the first review method corresponding to the digital behavior history data and the text type behavior history The second review method corresponding to the data, and the third review method corresponding to the byte-type behavior historical data;
数据审核模块,用于根据所述审核方式,分别对对应数据类型的行为历史数据进行数据审核;The data review module is used to conduct data review on the behavior history data of the corresponding data type according to the review method;
推送模块,用于当所述行为历史数据通过所述数据审核时,获取与所述行为历史数据对应的第一用户标识,并将所述第一用户标识推送至排队***中的优先队列;A push module, configured to obtain a first user identification corresponding to the behavior history data when the behavior history data passes the data review, and push the first user identification to the priority queue in the queuing system;
轮询模块,用于轮询所述排队***,从所述优先队列中获取所述第一用户标识;及A polling module, configured to poll the queuing system to obtain the first user identification from the priority queue; and
审核结果生成模块,用于对与所述第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。The audit result generation module is used to audit asset data on the asset character recognition result corresponding to the first user identification, generate an audit result, and return it to the user terminal.
一种计算机设备,包括存储器和一个或多个处理器,所述存储器中储存有计算机可读指令,所述计算机可读指令被所述处理器执行时,使得所述一个或多个处理器执行以下步骤:A computer device, including a memory and one or more processors, the memory stores computer readable instructions, and when the computer readable instructions are executed by the processor, the one or more processors execute The following steps:
当检测到用户发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将所述身份字符识别结果与预先存储的用户身份信息进行比对;When the data review request sent by the user is detected, the identification character recognition result and the asset character recognition result corresponding to the user identification are obtained, and the identification character recognition result is compared with the pre-stored user identity information;
当所述身份字符识别结果符合所述预先存储的用户身份信息时,提取所述用户标识对应的行为历史数据;When the identification character recognition result matches the pre-stored user identification information, extracting the behavior history data corresponding to the user identification;
根据预设数据分类规则对所述行为历史数据进行分类,获得不同数据类型的行为历史数据;所述数据类型包括数字型数据、文本型数据以及字节型数据;Classify the behavior history data according to preset data classification rules to obtain behavior history data of different data types; the data types include numeric data, text data, and byte data;
确定与各所述不同数据类型的行为历史数据对应的数据审核方式;所述数据审核方式 包括与数字型行为历史数据对应的第一审核方式、与文本型行为历史数据对应的第二审核方式,以及与字节型行为历史数据对应的第三审核方式;Determine the data review method corresponding to each of the different data types of behavior history data; the data review method includes a first review method corresponding to the digital behavior history data and a second review method corresponding to the text type behavior history data, And the third audit method corresponding to byte-type behavior historical data;
根据所述审核方式,分别对对应数据类型的行为历史数据进行数据审核;According to the review method, conduct a data review on the behavior history data of the corresponding data type;
当所述行为历史数据通过所述数据审核时,获取与所述行为历史数据对应的第一用户标识,并将所述第一用户标识推送至排队***中的优先队列;When the behavior history data passes the data review, obtain the first user identification corresponding to the behavior history data, and push the first user identification to the priority queue in the queuing system;
轮询所述排队***,从所述优先队列中获取所述第一用户标识;及Polling the queuing system to obtain the first user identification from the priority queue; and
对与所述第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端.Perform asset data audit on the asset character recognition result corresponding to the first user ID, generate the audit result and return it to the user terminal.
一个或多个存储有计算机可读指令的计算机可读存储介质,计算机可读指令被一个或多个处理器执行时,使得一个或多个处理器执行以下步骤:One or more computer-readable storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors perform the following steps:
当检测到用户发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将所述身份字符识别结果与预先存储的用户身份信息进行比对;When the data review request sent by the user is detected, the identification character recognition result and the asset character recognition result corresponding to the user identification are obtained, and the identification character recognition result is compared with the pre-stored user identity information;
当所述身份字符识别结果符合所述预先存储的用户身份信息时,提取所述用户标识对应的行为历史数据;When the identification character recognition result matches the pre-stored user identification information, extracting the behavior history data corresponding to the user identification;
根据预设数据分类规则对所述行为历史数据进行分类,获得不同数据类型的行为历史数据;所述数据类型包括数字型数据、文本型数据以及字节型数据;Classify the behavior history data according to preset data classification rules to obtain behavior history data of different data types; the data types include numeric data, text data, and byte data;
确定与各所述不同数据类型的行为历史数据对应的数据审核方式;所述数据审核方式包括与数字型行为历史数据对应的第一审核方式、与文本型行为历史数据对应的第二审核方式,以及与字节型行为历史数据对应的第三审核方式;Determine the data review method corresponding to each of the different data types of behavior history data; the data review method includes a first review method corresponding to the digital behavior history data and a second review method corresponding to the text type behavior history data, And the third audit method corresponding to byte-type behavior historical data;
根据所述审核方式,分别对对应数据类型的行为历史数据进行数据审核;According to the review method, conduct a data review on the behavior history data of the corresponding data type;
当所述行为历史数据通过所述数据审核时,获取与所述行为历史数据对应的第一用户标识,并将所述第一用户标识推送至排队***中的优先队列;When the behavior history data passes the data review, obtain the first user identification corresponding to the behavior history data, and push the first user identification to the priority queue in the queuing system;
轮询所述排队***,从所述优先队列中获取所述第一用户标识;及Polling the queuing system to obtain the first user identification from the priority queue; and
对与所述第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端Perform asset data audit on the asset character recognition result corresponding to the first user ID, generate the audit result and return it to the user terminal
上述基于身份识别的数据审核方法、装置、计算机设备和存储介质,当检测到用户发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将身份字符识别结果与预先存储的用户身份信息进行比对。当身份字符识别结果符合预先存储的用户身份信息时,提取用户标识对应的行为历史数据,并根据预设数据分类规则对行为历史数据进行分类,获得不同数据类型的行为历史数据,进而确定与各不同数据类型的行为历史数据对应的数据审核方式。根据审核方式,分别对对应数据类型的行为历史数据进行数据审核,当行为历史数据通过数据审核时,获取与行为历史数据对应的第一用户标识,并将第一用户标识推送至排队***中的优先队列。轮询排队***,从优先队列中获取第一用户标识,对与第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。通过对客户的身份信息进行确认,并在身份信息确认后对用 户的行为历史数据进行审核,避免直接对用户提交的所有信息进行审核导致混乱的情况,且还可对通过针对历史行为数据进行的审核的第一用户的资产数据信息,进行优先审核,及时向用户返回审核结果,提高了数据审核的工作效率。The above-mentioned data verification method, device, computer equipment and storage medium based on identity recognition, when the data verification request sent by the user is detected, obtain the identity character recognition result and asset character recognition result corresponding to the user identity, and then compare the identity character recognition result Compare with pre-stored user identity information. When the identification character recognition result matches the pre-stored user identity information, the behavior history data corresponding to the user ID is extracted, and the behavior history data is classified according to the preset data classification rules to obtain the behavior history data of different data types, and then determine the Data review methods corresponding to different data types of behavioral historical data. According to the review method, conduct data review on the behavior history data of the corresponding data type. When the behavior history data passes the data review, obtain the first user ID corresponding to the behavior history data, and push the first user ID to the queue in the queuing system. Priority queue. The queuing system is polled, the first user identification is obtained from the priority queue, the asset data is audited on the asset character recognition result corresponding to the first user identification, and the audit result is generated and returned to the user terminal. By confirming the customer’s identity information, and after the identity information is confirmed, the user’s behavior history data is audited, avoiding confusion caused by directly auditing all the information submitted by the user, and it can also be used to check the historical behavior data. The first audited asset data information of the user is prioritized and the audit result is returned to the user in a timely manner, which improves the efficiency of data auditing.
本申请的一个或多个实施例的细节在下面的附图和描述中提出。本申请的其它特征和优点将从说明书、附图以及权利要求书变得明显。The details of one or more embodiments of the present application are set forth in the following drawings and description. Other features and advantages of this application will become apparent from the description, drawings and claims.
附图说明Description of the drawings
图1为根据一个或多个实施例中基于身份识别的数据审核方法的应用场景图;Figure 1 is an application scenario diagram of a data audit method based on identity recognition according to one or more embodiments;
图2为根据一个或多个实施例中基于身份识别的数据审核方法的流程示意图;FIG. 2 is a schematic flowchart of a data verification method based on identity recognition according to one or more embodiments;
图3为根据一个或多个实施例中基于身份识别的数据审核装置的框图;Fig. 3 is a block diagram of a data verification device based on identity recognition according to one or more embodiments;
图4为根据一个或多个实施例中计算机设备的框图。Figure 4 is a block diagram of a computer device according to one or more embodiments.
具体实施方式Detailed ways
为了使本申请的技术方案及优点更加清楚明白,以下结合附图及实施例,对本申请进行进一步详细说明。应当理解,此处描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。In order to make the technical solutions and advantages of the present application clearer, the following further describes the present application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.
本申请提供的基于身份识别的数据审核方法,可以应用于如图1所示的应用环境中。其中,用户终端102与服务器104通过网络进行通信。当服务器104检测到用户在用户终端102发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将身份字符识别结果与预先存储的用户身份信息进行比对。当身份字符识别结果符合预先存储的用户身份信息时,提取用户标识对应的行为历史数据,并根据预设数据分类规则对行为历史数据进行分类,获得不同数据类型的行为历史数据,进而确定与各不同数据类型的行为历史数据对应的数据审核方式。根据审核方式,分别对对应数据类型的行为历史数据进行数据审核,当行为历史数据通过数据审核时,获取与行为历史数据对应的第一用户标识,并将第一用户标识推送至排队***中的优先队列。服务器104通过轮询排队***,从优先队列中获取第一用户标识,并对与第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端102。其中,用户终端102可以但不限于是各种个人计算机、笔记本电脑、智能手机、平板电脑和便携式可穿戴设备,服务器104可以用独立的服务器或者是多个服务器组成的服务器集群来实现。The data verification method based on identity recognition provided in this application can be applied to the application environment as shown in FIG. 1. Among them, the user terminal 102 and the server 104 communicate through the network. When the server 104 detects the data review request sent by the user at the user terminal 102, the server 104 obtains the character recognition result and the asset character recognition result corresponding to the user identification, and compares the character recognition result with the pre-stored user identity information. When the identification character recognition result matches the pre-stored user identity information, the behavior history data corresponding to the user ID is extracted, and the behavior history data is classified according to the preset data classification rules to obtain the behavior history data of different data types, and then determine the Data review methods corresponding to different data types of behavioral historical data. According to the review method, conduct data review on the behavior history data of the corresponding data type. When the behavior history data passes the data review, obtain the first user ID corresponding to the behavior history data, and push the first user ID to the queue in the queuing system. Priority queue. The server 104 obtains the first user identification from the priority queue by polling the queuing system, conducts asset data audit on the asset character recognition result corresponding to the first user identification, generates the audit result, and returns it to the user terminal 102. The user terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server 104 may be implemented by an independent server or a server cluster composed of multiple servers.
在其中一个实施例中,如图2所示,提供了一种基于身份识别的数据审核方法,以该方法应用于图1中的服务器为例进行说明,包括以下步骤:In one of the embodiments, as shown in FIG. 2, a data audit method based on identity recognition is provided. Taking the method applied to the server in FIG. 1 as an example, the method includes the following steps:
S202,当检测到用户发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将身份字符识别结果与预先存储的用户身份信息进行比对。S202: When a data review request sent by the user is detected, obtain an identification character recognition result and an asset character recognition result corresponding to the user identification, and compare the identification character recognition result with pre-stored user identity information.
具体地,当服务器检测到用户在终端发送的数据审核请求时,通过获取用户上传的身份证明图像文件和资产证明图像文件,并对身份证明图像文件和资产证明图像文件进行字 符识别信息提取,可获得身份字符识别结果和资产字符识别结果。从***中获取用户注册时预先存储的用户身份信息,并将身份字符识别结果,与预先存储的用户身份信息进行比对。Specifically, when the server detects the data review request sent by the user at the terminal, by acquiring the identity certification image file and asset certification image file uploaded by the user, and extracting character recognition information from the identity certification image file and asset certification image file, Obtain identification character recognition results and asset character recognition results. Obtain the user identity information pre-stored during user registration from the system, and compare the identification character recognition result with the pre-stored user identity information.
其中,用户在终端向服务器发送数据审核请求的同时,将自己的身份证图像文件和资产证明图像文件上传至服务器,服务器接收终端发送的数据审核请求,并获取用户上传的身份身份证图像文件和资产证明图像文件。其中,资产证明图像文件包括收入证明、银行流水、存款证明、其他购买理财产品的证明,以及股票、基金、期货、债券、信托、保险和活期存折等图像文件。预先存储的用户信息为用户在终端输入的身份信息,包括用户的身份证号和姓名。Among them, the user uploads his ID card image file and asset certification image file to the server while the terminal sends a data review request to the server, the server receives the data review request sent by the terminal, and obtains the identity ID image file and image file uploaded by the user. Asset proof image file. Among them, the image files of asset certification include income certificates, bank records, deposit certificates, other certificates of purchase of financial products, and image files such as stocks, funds, futures, bonds, trusts, insurance, and current passbooks. The pre-stored user information is the identity information entered by the user at the terminal, including the user's ID number and name.
进一步地,服务器通过解析用户的身份信息字符识别结果,可以得到身份证图像文件上的身份证号和姓名,通过将身份信息字符识别结果,和用户在终端预先输入的身份证号和姓名进行比对,判断身份信息字符识别结果是否和用户在终端预先输入的身份证号和姓名是否匹配。当身份信息字符识别结果和用户在终端预先输入的身份证号和姓名不匹配时,需要返回审核失败的结果。其中,审核失败的结果包括身份不符合,以及图像文件格式错误,图像文件格式错误时,无法实现字符识别信息提取,需要返回重新上传图像文件的信息。Further, the server can obtain the ID number and name on the ID image file by analyzing the user's identification information character recognition result, and compare the ID information character recognition result with the ID number and name pre-entered by the user on the terminal. Yes, it is judged whether the character recognition result of the identity information matches the ID number and name entered by the user in the terminal in advance. When the character recognition result of the identity information does not match the ID number and name entered by the user in the terminal in advance, the result of the audit failure needs to be returned. Among them, the results of the audit failure include identity non-conformance and image file format errors. When the image file format is incorrect, character recognition information cannot be extracted, and the information for re-uploading the image file needs to be returned.
其中,在资产证明中需要验证用户所上传的资产是否是本人,可资产证明中的姓名,需要将图像文件中的姓名和身份证等信息提取出来,图片字符识别后会有一大串文字信息,然后提取出来的姓名,再与预先存储的用户信息中的用户姓名进行对比,如果不一样,再去比身份证号。匹配到身份证后再对比,如果身份证号也不一致,可以说明上传的资产证明非本人,审核不通过。Among them, in the asset certificate, it is necessary to verify whether the asset uploaded by the user is the person. The name in the asset certificate needs to be extracted from the name and ID in the image file. After the image character is recognized, there will be a series of text information, and then The extracted name is compared with the user name in the pre-stored user information. If it is not the same, the ID number is compared. After matching the ID card, compare it. If the ID number is also inconsistent, it can be explained that the uploaded asset certificate is not the person, and the review fails.
S204,当身份字符识别结果符合预先存储的用户身份信息时,提取用户标识对应的行为历史数据。S204: When the identification character recognition result matches the pre-stored user identification information, extract the behavior history data corresponding to the user identification.
其中,用户标识对应的行为历史数据包括与用户标识对应的浏览记录、收藏记录和产品购买记录,浏览记录可以是用户在***或在商城内,对产品和推广活动的访问记录,收藏记录包括用户对产品进行浏览后,选择对其中某个或多个产品进行收藏的记录,产品的购买记录包括用户所购买的不同类型的产品,以及相应产品的价值等。具体来说,浏览记录相关数据包括用户浏览的产品类别、对应产品的产品价值和浏览次数,收藏记录相关数据包括用户收藏的产品类别以及对应产品的产品价值,购买记录相关数据包括用户购买的产品类别、对应产品的购买次数、购买时间以及产品价值。Among them, the behavior history data corresponding to the user ID includes browsing records, favorite records, and product purchase records corresponding to the user ID. The browsing records can be the user's access records to products and promotion activities in the system or in the mall. The favorite records include the user After browsing the product, select the record of collecting one or more of the products. The purchase record of the product includes the different types of products purchased by the user and the value of the corresponding product. Specifically, browsing record related data includes the product category browsed by the user, the product value of the corresponding product and the number of views, the favorite record related data includes the user's favorite product category and the product value of the corresponding product, and the purchase record related data includes the product purchased by the user. The category, the number of purchases of the corresponding product, the time of purchase, and the value of the product.
具体地,当身份信息字符识别结果符合预先存储的身份信息,也就是说,用户上传的身份证图像文件上的身份证号和姓名,与用户在终端预先输入的身份证号和姓名匹配时,服务器根据用户的注册信息,获取用户在***内或商城内的浏览记录、收藏记录、产品购买记录以及推广活动参与记录。同时,在用户的产品购买记录中,通过获取用户所购买的理财产品或保险产品的类别,包括产品价值以及购买时间等。Specifically, when the identity information character recognition result matches the pre-stored identity information, that is, the ID number and name on the ID card image file uploaded by the user match the ID number and name pre-input by the user on the terminal, According to the user's registration information, the server obtains the user's browsing records, favorite records, product purchase records, and promotion activity participation records in the system or in the mall. At the same time, in the user's product purchase record, the type of wealth management product or insurance product purchased by the user is obtained, including the value of the product and the time of purchase.
S206,根据预设数据分类规则对行为历史数据进行分类,获得不同数据类型的行为历史数据,数据类型包括数字型数据、文本型数据以及字节型数据。S206: Classify the behavior history data according to preset data classification rules, and obtain behavior history data of different data types. The data types include numeric data, text data, and byte data.
具体地,预设数据分类规则用于对行为历史数据进行分类,且分类依据与数据类型对应,其中数据类型包括数字型数据、文本型数据和字节型数据,通过预设数据分类规则,可将行为历史数据分类为数字型行为历史数据、文本型行为历史数据和字节型行为历史数据。Specifically, the preset data classification rules are used to classify behavior history data, and the classification basis corresponds to the data type, where the data types include numeric data, text data, and byte data. Through the preset data classification rules, The behavior history data is classified into digital behavior history data, text behavior history data, and byte behavior history data.
S208,确定与各不同数据类型的行为历史数据对应的数据审核方式;数据审核方式包括与数字型行为历史数据对应的第一审核方式、与文本型行为历史数据对应的第二审核方式,以及与字节型行为历史数据对应的第三审核方式。S208: Determine the data review method corresponding to the behavior history data of each different data type; the data review method includes the first review method corresponding to the digital behavior historical data, the second review method corresponding to the text-based behavior historical data, and The third audit method corresponding to byte-type behavior historical data.
具体地,由于不同数据类型的行为历史数据设置了相应的数据审核方式,可通过获取与不同数据类型的行为历史数据对应的数据审核方式,对对应数据类型的行为历史数据进行审核。其中,数据审核方式包括与数字型行为历史数据对应的第一审核方式、与文本型行为历史数据对应的第二审核方式,以及与字节型行为历史数据对应的第三审核方式。可利用第一审核方式对数字型行为历史数据进行审核,利用第二审核方式对文本型行为历史数据进行审核,同样地,可利用第三审核方式对字节型行为历史数据进行数据审核。Specifically, since the behavior history data of different data types has corresponding data review methods, the behavior history data of the corresponding data types can be reviewed by obtaining the data review methods corresponding to the behavior history data of different data types. Among them, the data review method includes a first review method corresponding to digital behavior historical data, a second review method corresponding to text-based behavior historical data, and a third review method corresponding to byte-type behavior historical data. The first review method can be used to review digital behavior historical data, the second review method can be used to review text-based behavior historical data, and the third review method can be used to review byte-type historical data.
S210,根据审核方式,分别对对应数据类型的行为历史数据进行数据审核。S210: Perform data audit on the behavior history data corresponding to the data type according to the audit mode.
具体地,可分别对浏览记录相关数据、收藏记录相关数据以及购买记录相关数据进行数据分类后,利用对应的数据审核方式进行数据审核。针对用户在商城或***内的浏览记录相关数据,包括用户浏览的产品类别、对应产品的产品价值和浏览次数,服务器通过对用户浏览的不同类别的产品以及相应产品的浏览次数进行审核,根据不同产品的浏览次数的多少判断用户的购买倾向,通常来说,用户对进行多次浏览的产品更加具有购买倾向,而未进行浏览和了解的产品不会轻易购买,也因此可根据用户的浏览记录初步判断该用户是否通过初步数据审核,即其浏览记录相关数据是否可通过数据审核。Specifically, after data classification is performed on browsing record-related data, favorite record-related data, and purchase record-related data, the data can be reviewed using the corresponding data review method. Regarding the user's browsing record related data in the mall or system, including the product category browsed by the user, the product value of the corresponding product and the number of views, the server reviews the different categories of products the user browses and the number of corresponding product views. The number of times the product is viewed determines the user’s purchase tendency. Generally speaking, users have a greater tendency to purchase products that have been viewed multiple times, and products that have not been browsed and understood will not be easily purchased. Therefore, it can be based on the user’s browsing history. Preliminarily judge whether the user passes the preliminary data review, that is, whether the data related to the browsing record can pass the data review.
进一步地,针对在商城或***内的浏览收藏相关数据和购买记录相关数据,包括用户收藏的产品类别和对应产品的产品价值,以及用户购买的产品类别、对应产品的购买次数、购买时间以及产品价值。服务器需要对用户收藏的不同类别的产品,以及相同类别下产品的个数,以及各自产品的产品价值进行审核,可判定用户所具有购买倾向的产品,是否符合后续资产审核中资产类型。同时针对用户购买的不同类别的产品的购买次数和相应产品的产品价值进行审核,当用户购买的产品符合后续资产审核中可接受的资产类型,且其产品价值进行累计后,可通过预设审核标准,则表示该用户的收藏记录相关数据和购买记录数据,通过数据审核。进一步地,用标识的行为数据通过数据审核后,表示对应用户标识的用户为第一用户。***针对第一用户会优先进行审核,在排队***中处于优先队列。Further, for browsing collection related data and purchase record related data in the mall or system, including the user's favorite product category and the product value of the corresponding product, as well as the product category purchased by the user, the number of purchases of the corresponding product, the time of purchase, and the product value. The server needs to review the different categories of products collected by the user, the number of products in the same category, and the product value of the respective products, and can determine whether the product that the user has a purchase tendency meets the asset type in the subsequent asset review. At the same time, the number of purchases of different types of products purchased by the user and the product value of the corresponding product are reviewed. When the product purchased by the user meets the acceptable asset type in the subsequent asset review, and the product value is accumulated, it can pass the preset review Standard means that the user’s collection record-related data and purchase record data have passed the data review. Further, after passing the data review with the identified behavior data, it indicates that the user corresponding to the user identification is the first user. The system will prioritize the audit for the first user, and is in the priority queue in the queuing system.
S212,当行为历史数据通过数据审核时,获取与行为历史数据对应的第一用户标识,并将第一用户标识推送至排队***中的优先队列。S212: When the behavior history data passes the data review, obtain the first user identification corresponding to the behavior history data, and push the first user identification to the priority queue in the queuing system.
具体地,当行为历史数据通过数据审核时,表明改行为历史数据对应的用户标识为第 一用户标识,服务器可通过获取第一用户对应的第一用户标识,并将第一用户标识推送至排队***中的优先队列。其中,用户标识还包括第二用户标识,即对应用户标识的行为数据未通过数据审核时,得到用户标识对应的的用户为第二用户,可将与第二用户对应的第二用户标识,推送至排队***中的第二队列中。对第二队列中的第二用户的数据审核,在优先队列之后。Specifically, when the behavior history data passes the data review, it indicates that the user ID corresponding to the changed behavior history data is the first user ID. The server can obtain the first user ID corresponding to the first user and push the first user ID to the queue. The priority queue in the system. The user identification also includes a second user identification, that is, when the behavior data corresponding to the user identification fails the data review, the user corresponding to the user identification is the second user, and the second user identification corresponding to the second user can be pushed To the second queue in the queuing system. The data audit of the second user in the second queue is after the priority queue.
S214,轮询排队***,从优先队列中获取第一用户标识。S214: Polling the queuing system to obtain the first user identifier from the priority queue.
具体地,服务器利用轮询机制,对排队***进行轮询,判断排队***中优先队列是否存在第一用户标识,当在排队***中识别到第一用户标识时,获取该第一用户标识。Specifically, the server uses a polling mechanism to poll the queuing system to determine whether the first user identification exists in the priority queue in the queuing system, and when the first user identification is recognized in the queuing system, the first user identification is acquired.
S216,对与第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。S216: Perform asset data review on the asset character recognition result corresponding to the first user identifier, generate the review result, and return it to the user terminal.
具体地,服务器通过解析第一用户标识对应的资产信息字符识别结果,并从中提取资产关键字。其中,资产关键字,包括与第一用户标识对应的资产类型。服务器通过获取预设审核标准,并将资产关键字和预设审核标准进行比对,当资产关键字符合预设审核标准时,返回第一用户审核成功的结果。Specifically, the server parses the asset information character recognition result corresponding to the first user ID, and extracts the asset keyword from it. Among them, the asset keyword includes the asset type corresponding to the first user identifier. The server obtains the preset review criteria and compares the asset keyword with the preset review criteria, and when the asset keyword meets the preset review criteria, it returns the first user's successful review result.
其中,服务器获取预设审核标准,并将资产关键字和预设审核标准进行比对,具体包括:服务器获取预设审核标准,其中,预设审核标准为与用户标识对应的预设总资产阈值。获取与各资产类型对应的资产数值大小,累计各资产类型的资产数值大小,获得的总资产数值,并将总资产数值与预设总资产阈值进行比对,判断总资产数值与预设总资产阈值的差值。进而可根据总资产数值与预设总资产阈值的差值,判断是否通过审核。Among them, the server obtains the preset audit criteria, and compares the asset keyword with the preset audit criteria, which specifically includes: the server obtains the preset audit criteria, where the preset audit criteria is the preset total asset threshold corresponding to the user ID . Obtain the asset value size corresponding to each asset type, accumulate the asset value size of each asset type, obtain the total asset value, and compare the total asset value with the preset total asset threshold to determine the total asset value and the preset total asset value The difference between the thresholds. Furthermore, it can be judged whether the audit is passed or not based on the difference between the total asset value and the preset total asset threshold.
进一步地,服务器通过资产信息字符识别返回的结果进行模板匹配,通过正则匹配到相应的值,然后进行模板化,目前字符识别可从用户提交的资产证明中提取出金额,账号等关键字,提取到关键字后,对总资产数值进行汇总,然后判断资产总值是否可以达到审核预定的标准。当达到标准,则审核通过,如果不达标,则审核不通过,或是提醒用户再提供其他资产证明的文件。Further, the server performs template matching through the results returned by asset information character recognition, matches the corresponding value through regular rules, and then performs templateization. At present, character recognition can extract keywords such as the amount and account number from the asset certificate submitted by the user, and extract After the keywords are reached, the total asset value is summarized, and then it is judged whether the total asset value can meet the predetermined standard for review. When the standard is met, the review is passed. If the standard is not met, the review is not passed, or the user is reminded to provide other asset certification documents.
其中,总资产数值的汇总表示用户提交的多份资产证明中所有金额的进行加总,设置的审核标准可以固定,也可调整,但需要保持对所有发送数据审核的用户审核标准一致。比如一般的审核标准是总资产达到100万以上,就可以审批通过,则可判断加总后的总额是否超过100万,来判断是否通过审核。其中审核失败的原因为基于身份识别的无法满足对应理财产品对资产的要求。Among them, the summary of the total asset value means the sum of all the amounts in the multiple asset certificates submitted by the user. The set audit standard can be fixed or adjustable, but the user audit standard for all sent data audits needs to be kept consistent. For example, the general audit standard is that the total assets reach 1 million or more, then the approval can be passed, and then it can be judged whether the total amount exceeds 1 million to judge whether the audit is passed. The reason for the failure of the audit is the inability to meet the asset requirements of the corresponding wealth management products based on identification.
上述基于身份识别的数据审核方法中,当检测到用户发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将身份字符识别结果与预先存储的用户身份信息进行比对。当身份字符识别结果符合预先存储的用户身份信息时,提取用户标识对应的行为历史数据,并根据预设数据分类规则对行为历史数据进行分类,获得不同数据类型的行为历史数据,进而确定与各不同数据类型的行为历史数据对应的数据审核方式。根据审核方式,分别对对应数据类型的行为历史数据进行数据审核,当行为历 史数据通过数据审核时,获取与行为历史数据对应的第一用户标识,并将第一用户标识推送至排队***中的优先队列。轮询排队***,从优先队列中获取第一用户标识,对与第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。通过对客户的身份信息进行确认,并在身份信息确认后对用户的行为历史数据进行审核,避免直接对用户提交的所有信息进行审核导致混乱的情况,且还可对通过针对历史行为数据进行的审核的第一用户的资产数据信息,进行优先审核,及时向用户返回审核结果,提高了数据审核的工作效率。In the above-mentioned data verification method based on identity recognition, when a data verification request sent by a user is detected, the identity character recognition result and asset character recognition result corresponding to the user identity are obtained, and the identity character recognition result is combined with the pre-stored user identity information Compare. When the identification character recognition result matches the pre-stored user identity information, the behavior history data corresponding to the user ID is extracted, and the behavior history data is classified according to the preset data classification rules to obtain the behavior history data of different data types, and then determine the Data review methods corresponding to different data types of behavioral historical data. According to the review method, conduct data review on the behavior history data of the corresponding data type. When the behavior history data passes the data review, obtain the first user ID corresponding to the behavior history data, and push the first user ID to the queue in the queuing system. Priority queue. The queuing system is polled, the first user identification is obtained from the priority queue, the asset data is audited on the asset character recognition result corresponding to the first user identification, and the audit result is generated and returned to the user terminal. By confirming the customer’s identity information, and after the identity information is confirmed, the user’s behavior history data is audited, avoiding confusion caused by directly auditing all the information submitted by the user, and it can also be used to check the historical behavior data. The first audited asset data information of the user is prioritized and the audit result is returned to the user in a timely manner, which improves the efficiency of data auditing.
在其中一个实施例中,对与第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端的步骤,还包括:In one of the embodiments, the step of performing asset data audit on the asset character recognition result corresponding to the first user identification, generating the audit result and returning it to the user terminal, further includes:
获取与第一用户标识对应的预设审核标准;预设审核标准为与第一用户标识对应的预设总资产阈值;Obtaining a preset audit standard corresponding to the first user identification; the preset audit standard is a preset total asset threshold corresponding to the first user identification;
获取第一用户标识对应的各资产类型对应的资产数值大小;Acquiring the asset value size corresponding to each asset type corresponding to the first user identifier;
累计各资产类型的资产数值大小,获得的总资产数值;Accumulate the size of the asset value of each asset type, and the total asset value obtained;
将总资产数值与预设总资产阈值进行比对;Compare the total asset value with the preset total asset threshold;
当总资产数值大于或等于预设总资产阈值时,生成审核生成的结果并返回给用户终端;当总资产数值小于预设总资产阈值时,生成审核失败的结果并返回给用户终端。When the total asset value is greater than or equal to the preset total asset threshold, the result generated by the audit is generated and returned to the user terminal; when the total asset value is less than the preset total asset threshold, the audit failed result is generated and returned to the user terminal.
具体地,服务器获取预设审核标准,其中,预设审核标准为与用户标识对应的预设总资产阈值。获取与各资产类型对应的资产数值大小,累计各资产类型的资产数值大小,获得的总资产数值,并将总资产数值与预设总资产阈值进行比对,判断总资产数值与预设总资产阈值的差值。进而可根据总资产数值与预设总资产阈值的差值,判断是否通过审核。当差值为正数,即总资产数值大于预设总资产阈值时,表示审核通过。当差值为负数,即总资产数值小于预设总资产阈值时,则审核不通过,提醒用户需要再提供其他资产证明的文件。Specifically, the server obtains a preset audit standard, where the preset audit standard is a preset total asset threshold corresponding to the user identification. Obtain the asset value size corresponding to each asset type, accumulate the asset value size of each asset type, obtain the total asset value, and compare the total asset value with the preset total asset threshold to determine the total asset value and the preset total asset value The difference between the thresholds. Furthermore, it can be judged whether the audit is passed or not based on the difference between the total asset value and the preset total asset threshold. When the difference is a positive number, that is, when the total asset value is greater than the preset total asset threshold, it means that the review is passed. When the difference is a negative number, that is, when the total asset value is less than the preset total asset threshold, the review fails, and the user is reminded to provide other asset certification documents.
其中,资产类型包括收入、理财产品,包括以及股票、基金、期货、债券、信托和保险等,各资产类型对应的资产金额的取值不固定。总资产数值的汇总表示用户提交的多份资产证明中所有金额的进行加总,设置的审核标准可以固定,也可调整,但需要保持对所有发送数据审核的用户审核标准一致。比如一般的审核标准是总资产达到100万以上,就可以审批通过,则可判断加总后的总额是否超过100万,来判断是否通过审核。其中审核失败的原因为基于身份识别的无法满足对应理财产品对资产的要求。Among them, asset types include income, financial products, including stocks, funds, futures, bonds, trusts, and insurance, etc. The value of the asset amount corresponding to each asset type is not fixed. The summary of the total asset value means the sum of all the amounts in the multiple asset certificates submitted by the user. The set audit standard can be fixed or adjustable, but the user audit standard for all sent data audits needs to be kept consistent. For example, the general audit standard is that the total assets reach 1 million or more, then the approval can be passed, and then it can be judged whether the total amount exceeds 1 million to judge whether the audit is passed. The reason for the failure of the audit is the inability to meet the asset requirements of the corresponding wealth management products based on identification.
上述步骤,通过从第一用户标识对应的资产信息字符识别结果中,提取资产关键字,利用预设审核标准对资产关键字进行审核,当资产关键字符合预设审核标准时,返回第一用户审核成功的结果。实现了优先对第一用户标识的资产信息字符识别进行审核,可及时得到审核结果,减少用户等待审核结果的时间,提高了用户体验。In the above steps, the asset keyword is extracted from the asset information character recognition result corresponding to the first user ID, and the asset keyword is audited using the preset audit standard. When the asset keyword meets the preset audit standard, return to the first user for audit Successful results. It realizes the priority to review the asset information character recognition of the first user identification, the review result can be obtained in time, the time for the user to wait for the review result is reduced, and the user experience is improved.
在其中一个实施例中,提供了一种基于身份识别的数据审核方法,还包括:In one of the embodiments, a data audit method based on identity recognition is provided, which further includes:
当对应用户标识的行为数据未通过数据审核时,服务器得到对应的第二用户;将与 第二用户对应的第二用户标识,推送至排队***中的第二队列;当轮询排队***未获取到第一用户标识时,从第二队列中获取第二用户标识;利用预设审核标准,对与第二用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。When the behavior data corresponding to the user ID fails the data review, the server obtains the corresponding second user; pushes the second user ID corresponding to the second user to the second queue in the queuing system; when the polling queuing system fails to obtain When the first user ID is reached, the second user ID is obtained from the second queue; the asset character recognition result corresponding to the second user ID is checked by using preset audit criteria, and the audit result is generated and returned to the user terminal.
具体地,服务器通过解析第二用户标识对应的资产信息字符识别结果,并从中提取资产关键字。其中,资产关键字,包括与第二用户标识对应的资产类型。服务器通过获取预设审核标准,并将资产关键字和预设审核标准进行比对,当资产关键字符合预设审核标准时,返回第二用户审核成功的结果。Specifically, the server parses the asset information character recognition result corresponding to the second user ID, and extracts the asset keyword therefrom. Among them, the asset keyword includes the asset type corresponding to the second user identifier. The server obtains the preset review criteria and compares the asset keyword with the preset review criteria, and when the asset keyword meets the preset review criteria, it returns the result of successful review by the second user.
进一步地,服务器获取预设审核标准,并将资产关键字和预设审核标准进行比对,具体包括:服务器获取预设审核标准,其中,预设审核标准为与用户标识对应的预设总资产阈值。获取与各资产类型对应的资产数值大小,累计各资产类型的资产数值大小,获得的总资产数值,并将总资产数值与预设总资产阈值进行比对,判断总资产数值与预设总资产阈值的差值。进而可根据总资产数值与预设总资产阈值的差值,判断是否通过审核。Further, the server obtains the preset audit criteria, and compares the asset keyword with the preset audit criteria, which specifically includes: the server obtains the preset audit criteria, where the preset audit criteria is the preset total assets corresponding to the user ID Threshold. Obtain the asset value size corresponding to each asset type, accumulate the asset value size of each asset type, obtain the total asset value, and compare the total asset value with the preset total asset threshold to determine the total asset value and the preset total asset value The difference between the thresholds. Furthermore, it can be judged whether the audit is passed or not based on the difference between the total asset value and the preset total asset threshold.
上述基于身份识别的数据审核方法,在未获取到第一用户标识时,从排队***中获取靠前位置的第二用户标识,并利用预设审核标准,对第二用户标识对应的资产信息字符识别结果进行审核,获得对应的审核结果。由于实现了第一用户相对于第二用户的优先审核,提高第一用户的使用体验度,并吸引更多第一用户。In the above-mentioned data audit method based on identity recognition, when the first user ID is not obtained, the second user ID in the front position is obtained from the queuing system, and the preset audit criteria are used to check the asset information characters corresponding to the second user ID. The identification results are reviewed and the corresponding review results are obtained. Since the priority review of the first user relative to the second user is realized, the use experience of the first user is improved, and more first users are attracted.
在其中一个实施例中,当检测到用户发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将身份字符识别结果与预先存储的用户身份信息进行比对的步骤,包括:In one of the embodiments, when the data review request sent by the user is detected, the identification character recognition result and the asset character recognition result corresponding to the user identification are obtained, and the identification character recognition result is compared with the pre-stored user identification information The steps include:
服务器获取用户上传的身份证明图像文件和资产证明图像文件;对身份证明图像文件和资产证明图像文件进行字符识别信息提取,获得身份字符识别结果和资产字符识别结果;获取预先存储的用户身份信息;将身份字符识别结果,与预先存储的用户身份信息进行比对。The server obtains the identity certification image file and asset certification image file uploaded by the user; extracts the character recognition information of the identity certification image file and the asset certification image file to obtain the identity character recognition result and the asset character recognition result; obtains the pre-stored user identity information; The identification character recognition result is compared with the pre-stored user identification information.
具体地,用户在终端向服务器发送数据审核请求的同时,将自己的身份证图像文件和资产证明图像文件上传至服务器,服务器接收终端发送的数据审核请求,并获取用户上传的身份身份证图像文件和资产证明图像文件。其中,资产证明图像文件包括收入证明、银行流水、存款证明、其他购买理财产品的证明,以及股票、基金、期货、债券、信托、保险和活期存折等图像文件。预先存储的用户信息为用户在终端输入的身份信息,包括用户的身份证号和姓名。Specifically, the user uploads his ID card image file and asset certification image file to the server while the terminal sends a data review request to the server, the server receives the data review request sent by the terminal, and obtains the ID ID image file uploaded by the user And asset proof image files. Among them, the image files of asset certification include income certificates, bank records, deposit certificates, other certificates of purchase of financial products, and image files such as stocks, funds, futures, bonds, trusts, insurance, and current passbooks. The pre-stored user information is the identity information entered by the user at the terminal, including the user's ID number and name.
进一步地,服务器通过解析用户的身份信息字符识别结果,可以得到身份证图像文件上的身份证号和姓名,通过将身份信息字符识别结果,和用户在终端预先输入的身份证号和姓名进行比对,判断身份信息字符识别结果是否和用户在终端预先输入的身份证号和姓名是否匹配。当身份信息字符识别结果和用户在终端预先输入的身份证号和姓名不匹配时,需要返回审核失败的结果。其中,审核失败的结果包括身份不符合,以及图像文件格式错误,图像文件格式错误时,无法实现字符识别信息提取,需要返回重新上传图像文件 的信息。Further, the server can obtain the ID number and name on the ID image file by analyzing the user's identification information character recognition result, and compare the ID information character recognition result with the ID number and name pre-entered by the user on the terminal. Yes, it is judged whether the character recognition result of the identity information matches the ID number and name entered by the user in the terminal in advance. When the character recognition result of the identity information does not match the ID number and name entered by the user in the terminal in advance, the result of the audit failure needs to be returned. Among them, the results of the audit failure include identity non-conformance and image file format errors. When the image file format is incorrect, character recognition information cannot be extracted, and the information for re-uploading the image file needs to be returned.
上述步骤,服务器通过对用户上传的身份证明图像文件和资产证明图像文件进行字符识别信息提取,得到身份字符识别结果和资产字符识别结果,并将身份字符识别结果,与预先存储的用户身份信息进行比对。实现了对用户身份信息的自动审核,避免人工线下核对,提高身份信息审核的正确率和审核速度。In the above steps, the server extracts the character recognition information from the identity certification image file and asset certification image file uploaded by the user to obtain the identity character recognition result and the asset character recognition result, and compare the identity character recognition result with the pre-stored user identity information. Comparison. It realizes the automatic review of user identity information, avoids manual offline verification, and improves the accuracy and speed of identity information verification.
应该理解的是,虽然图2的流程图中的各个步骤按照箭头的指示依次显示,但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明,这些步骤的执行并没有严格的顺序限制,这些步骤可以以其它的顺序执行。而且,图2中的至少一部分步骤可以包括多个子步骤或者多个阶段,这些子步骤或者阶段并不必然是在同一时刻执行完成,而是可以在不同的时刻执行,这些子步骤或者阶段的执行顺序也不必然是依次进行,而是可以与其它步骤或者其它步骤的子步骤或者阶段的至少一部分轮流或者交替地执行。It should be understood that although the various steps in the flowchart of FIG. 2 are displayed in sequence as indicated by the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless specifically stated in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least part of the steps in FIG. 2 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution of these sub-steps or stages The sequence is not necessarily performed sequentially, but may be performed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.
在其中一个实施例中,如图3所示,提供了一种基于身份识别的数据审核装置,包括:检测模块302、行为历史数据提取模块304、分类模块306、数据审核方式确定模块308、数据审核模块310、推送模块312、轮询模块314以及审核结果生成模块316,其中:In one of the embodiments, as shown in FIG. 3, a data review device based on identity recognition is provided, which includes: a detection module 302, a behavior history data extraction module 304, a classification module 306, a data review method determination module 308, and a data review module 308. The audit module 310, the push module 312, the polling module 314, and the audit result generation module 316, wherein:
检测模块302,用于当检测到用户发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将身份字符识别结果与预先存储的用户身份信息进行比对。The detection module 302 is configured to obtain the identification character recognition result and the asset character recognition result corresponding to the user identification when the data review request sent by the user is detected, and compare the identification character recognition result with pre-stored user identification information.
行为历史数据提取模块304,用于当身份字符识别结果符合预先存储的用户身份信息时,提取用户标识对应的行为历史数据。The behavior history data extraction module 304 is configured to extract behavior history data corresponding to the user identification when the identification character recognition result matches the pre-stored user identification information.
分类模块306,用于根据预设数据分类规则对行为历史数据进行分类,获得不同数据类型的行为历史数据;数据类型包括数字型数据、文本型数据以及字节型数据。The classification module 306 is configured to classify behavior history data according to preset data classification rules to obtain behavior history data of different data types; the data types include digital data, text data, and byte data.
数据审核方式确定模块308,用于确定与各不同数据类型的行为历史数据对应的数据审核方式;数据审核方式包括与数字型行为历史数据对应的第一审核方式、与文本型行为历史数据对应的第二审核方式,以及与字节型行为历史数据对应的第三审核方式。The data review method determining module 308 is used to determine the data review method corresponding to the behavior history data of different data types; the data review method includes the first review method corresponding to the digital behavior history data and the data review method corresponding to the text type behavior history data. The second review method, and the third review method corresponding to byte-type behavior historical data.
数据审核模块310,用于根据审核方式,分别对对应数据类型的行为历史数据进行数据审核。The data audit module 310 is used to perform data audit on the behavior history data of the corresponding data type according to the audit mode.
推送模块312,用于当行为历史数据通过数据审核时,获取与行为历史数据对应的第一用户标识,并将第一用户标识推送至排队***中的优先队列。The pushing module 312 is configured to obtain the first user identifier corresponding to the behavior historical data when the behavior historical data passes the data review, and push the first user identifier to the priority queue in the queuing system.
轮询模块314,用于轮询排队***,从优先队列中获取第一用户标识。The polling module 314 is configured to poll the queuing system and obtain the first user identification from the priority queue.
审核结果生成模块316,用于对与第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。The audit result generation module 316 is configured to perform asset data audit on the asset character recognition result corresponding to the first user identification, generate an audit result, and return it to the user terminal.
上述基于身份识别的数据审核装置,当检测到用户发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将身份字符识别结果与预先存储的用户身份信息进行比对。当身份字符识别结果符合预先存储的用户身份信息时,提取 用户标识对应的行为历史数据,并根据预设数据分类规则对行为历史数据进行分类,获得不同数据类型的行为历史数据,进而确定与各不同数据类型的行为历史数据对应的数据审核方式。根据审核方式,分别对对应数据类型的行为历史数据进行数据审核,当行为历史数据通过数据审核时,获取与行为历史数据对应的第一用户标识,并将第一用户标识推送至排队***中的优先队列。轮询排队***,从优先队列中获取第一用户标识,对与第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。通过对客户的身份信息进行确认,并在身份信息确认后对用户的行为历史数据进行审核,避免直接对用户提交的所有信息进行审核导致混乱的情况,且还可对通过针对历史行为数据进行的审核的第一用户的资产数据信息,进行优先审核,及时向用户返回审核结果,提高了数据审核的工作效率。The above-mentioned data verification device based on identity recognition, when detecting a data verification request sent by a user, obtains the identity character recognition result and asset character recognition result corresponding to the user ID, and compares the identity character recognition result with the pre-stored user identity information Comparison. When the identification character recognition result matches the pre-stored user identity information, the behavior history data corresponding to the user ID is extracted, and the behavior history data is classified according to the preset data classification rules to obtain the behavior history data of different data types, and then determine the Data review methods corresponding to different data types of behavioral historical data. According to the review method, conduct data review on the behavior history data of the corresponding data type. When the behavior history data passes the data review, obtain the first user ID corresponding to the behavior history data, and push the first user ID to the queue in the queuing system. Priority queue. The queuing system is polled, the first user identification is obtained from the priority queue, the asset data is audited on the asset character recognition result corresponding to the first user identification, and the audit result is generated and returned to the user terminal. By confirming the customer’s identity information, and after the identity information is confirmed, the user’s behavior history data is audited, avoiding confusion caused by directly auditing all the information submitted by the user, and it can also be used to check the historical behavior data. The first audited asset data information of the user is prioritized and the audit result is returned to the user in a timely manner, which improves the efficiency of data auditing.
在其中一个实施例中,审核结果生成模块还用于:In one of the embodiments, the audit result generation module is also used to:
解析第一用户标识对应的资产信息字符识别结果,并从中提取资产关键字;资产关键字,包括与第一用户标识对应的资产类型;获取预设审核标准,并将资产关键字和预设审核标准进行比对;当资产关键字符合预设审核标准时,返回第一用户审核成功的结果。Analyze the character recognition result of the asset information corresponding to the first user ID, and extract the asset keyword from it; the asset keyword, including the asset type corresponding to the first user ID; obtain the preset review criteria, and compare the asset keyword with the preset review Standards are compared; when the asset keyword meets the preset review standard, the result of successful review by the first user is returned.
上述审核模块,实现了优先对第一用户标识的资产信息字符识别进行审核,可及时得到审核结果,减少用户等待审核结果的时间,提高了用户体验。The above-mentioned review module realizes the priority review of the asset information character recognition of the first user identification, the review result can be obtained in time, the time for the user to wait for the review result is reduced, and the user experience is improved.
在其中一个实施例中,审核结果生成模块还用于:In one of the embodiments, the audit result generation module is also used to:
获取与第一用户标识对应的预设审核标准;预设审核标准为与第一用户标识对应的预设总资产阈值;获取第一用户标识对应的各资产类型对应的资产数值大小;累计各资产类型的资产数值大小,获得的总资产数值;将总资产数值与预设总资产阈值进行比对;当总资产数值大于或等于预设总资产阈值时,生成审核生成的结果并返回给用户终端;当总资产数值小于预设总资产阈值时,生成审核失败的结果并返回给用户终端。Obtain the preset audit standard corresponding to the first user ID; the preset audit standard is the preset total asset threshold corresponding to the first user ID; obtain the asset value size corresponding to each asset type corresponding to the first user ID; accumulate each asset The type of asset value size, the total asset value obtained; compare the total asset value with the preset total asset threshold; when the total asset value is greater than or equal to the preset total asset threshold, the result generated by the audit is generated and returned to the user terminal ; When the total asset value is less than the preset total asset threshold, the result of the audit failure is generated and returned to the user terminal.
上述审核结果生成模块,通过从第一用户标识对应的资产信息字符识别结果中,提取资产关键字,利用预设审核标准对资产关键字进行审核,当资产关键字符合预设审核标准时,返回第一用户审核成功的结果。实现了优先对第一用户标识的资产信息字符识别进行审核,可及时得到审核结果,减少用户等待审核结果的时间,提高了用户体验。The aforementioned audit result generation module extracts asset keywords from the asset information character recognition result corresponding to the first user ID, and uses preset audit criteria to audit the asset keywords. When the asset keyword meets the preset audit criteria, it returns to the first The result of a successful user review. It realizes the priority to review the asset information character recognition of the first user identification, the review result can be obtained in time, the time for the user to wait for the review result is reduced, and the user experience is improved.
在其中一个实施例中,提供了一种基于身份识别的数据审核装置,还包括第二用户审核模块,用于:In one of the embodiments, a data verification device based on identity recognition is provided, and further includes a second user verification module for:
当行为数据未通过数据审核时,得到对应的第二用户;将与第二用户对应的第二用户标识,推送至排队***中的第二队列;当轮询排队***未获取到第一用户标识时,从第二队列中获取第二用户标识;利用预设审核标准,对与第二用户标识对应的资产字符识别结果进行审核,返回审核结果。When the behavior data fails the data review, the corresponding second user is obtained; the second user ID corresponding to the second user is pushed to the second queue in the queuing system; when the polling queuing system does not obtain the first user ID At the time, obtain the second user ID from the second queue; use the preset audit criteria to audit the asset character recognition result corresponding to the second user ID, and return the audit result.
上述基于身份识别的数据审核装置,在未获取到第一用户标识时,从排队***中获取靠前位置的第二用户标识,并利用预设审核标准,对第二用户标识对应的资产信息字符识别结果进行审核,获得对应的审核结果。由于实现了第一用户相对于第二用户的优先审 核,提高第一用户的使用体验度,并吸引更多第一用户。The above-mentioned data verification device based on identity recognition, when the first user ID is not obtained, obtains the second user ID in the front position from the queuing system, and uses preset audit criteria to determine the asset information characters corresponding to the second user ID The identification results are reviewed and the corresponding review results are obtained. Since the first user's priority review relative to the second user is realized, the first user's experience is improved and more first users are attracted.
在其中一个实施例中,检测模块还用于:In one of the embodiments, the detection module is also used to:
获取用户上传的身份证明图像文件和资产证明图像文件;对身份证明图像文件和资产证明图像文件进行字符识别信息提取,获得身份字符识别结果和资产字符识别结果;获取预先存储的用户身份信息;将身份字符识别结果,与预先存储的用户身份信息进行比对。Obtain the identity certification image file and asset certification image file uploaded by the user; extract the character recognition information from the identity certification image file and the asset certification image file to obtain the identity character recognition result and the asset character recognition result; obtain the pre-stored user identity information; The identification character recognition result is compared with the pre-stored user identification information.
上述获取模块,实现了对用户身份信息的自动审核,避免人工线下核对,提高身份信息审核的正确率和审核速度。The above-mentioned acquisition module realizes automatic verification of user identity information, avoids manual offline verification, and improves the accuracy and speed of identity information verification.
关于基于身份识别的数据审核装置的具体限定可以参见上文中对于基于身份识别的数据审核方法的限定,在此不再赘述。上述基于身份识别的数据审核装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中,也可以以软件形式存储于计算机设备中的存储器中,以便于处理器调用执行以上各个模块对应的操作。For the specific definition of the data verification device based on identity recognition, please refer to the above definition of the data verification method based on identity recognition, which will not be repeated here. Each module in the above-mentioned identity recognition-based data auditing device can be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules may be embedded in the form of hardware or independent of the processor in the computer equipment, or may be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.
在一个实施例中,提供了一种计算机设备,该计算机设备可以是服务器,其内部结构图可以如图4所示。该计算机设备包括通过***总线连接的处理器、存储器、网络接口和数据库。其中,该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性或易失性存储介质、内存储器。该非易失性或易失性存储介质存储有操作***、计算机可读指令和数据库。该内存储器为非易失性存储介质中的操作***和计算机可读指令的运行提供环境。该计算机设备的数据库用于存储数据审核数据。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机可读指令被处理器执行时以实现一种基于身份识别的数据审核方法。In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. 4. The computer equipment includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile or volatile storage medium and internal memory. The non-volatile or volatile storage medium stores an operating system, computer readable instructions, and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the non-volatile storage medium. The database of the computer equipment is used to store data audit data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer readable instruction is executed by the processor, a data audit method based on identification is realized.
本领域技术人员可以理解,图4中示出的结构,仅仅是与本申请方案相关的部分结构的框图,并不构成对本申请方案所应用于其上的计算机设备的限定,具体的计算机设备可以包括比图中所示更多或更少的部件,或者组合某些部件,或者具有不同的部件布置。Those skilled in the art can understand that the structure shown in FIG. 4 is only a block diagram of part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may Including more or fewer parts than shown in the figure, or combining some parts, or having a different arrangement of parts.
一个或多个存储有计算机可读指令的计算机可读存储介质,计算机可读指令被一个或多个处理器执行时,使得一个或多个处理器执行以下步骤:One or more computer-readable storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors perform the following steps:
当检测到用户发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将身份字符识别结果与预先存储的用户身份信息进行比对;When the data review request sent by the user is detected, the identification character recognition result and the asset character recognition result corresponding to the user identification are obtained, and the identification character recognition result is compared with the pre-stored user identity information;
当身份字符识别结果符合预先存储的用户身份信息时,提取用户标识对应的行为历史数据;When the identification character recognition result matches the pre-stored user identification information, extract the behavior history data corresponding to the user identification;
根据预设数据分类规则对行为历史数据进行分类,获得不同数据类型的行为历史数据;数据类型包括数字型数据、文本型数据以及字节型数据;Classify behavior history data according to preset data classification rules to obtain behavior history data of different data types; data types include numeric data, text data, and byte data;
确定与各不同数据类型的行为历史数据对应的数据审核方式;数据审核方式包括与数字型行为历史数据对应的第一审核方式、与文本型行为历史数据对应的第二审核方式,以及与字节型行为历史数据对应的第三审核方式;Determine the data review method corresponding to the behavior history data of each different data type; the data review method includes the first review method corresponding to the digital behavior historical data, the second review method corresponding to the text-based behavior historical data, and the byte The third review method corresponding to historical data of type behavior;
根据审核方式,分别对对应数据类型的行为历史数据进行数据审核;According to the review method, conduct data review on the behavioral historical data of the corresponding data type;
当行为历史数据通过数据审核时,获取与行为历史数据对应的第一用户标识,并将第一用户标识推送至排队***中的优先队列;When the behavior history data passes the data review, obtain the first user identification corresponding to the behavior history data, and push the first user identification to the priority queue in the queuing system;
轮询排队***,从优先队列中获取第一用户标识;及Polling the queuing system to obtain the first user ID from the priority queue; and
对与第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。The asset data is audited on the asset character recognition result corresponding to the first user identification, and the audit result is generated and returned to the user terminal.
在一个实施例中,计算机可读指令被处理器执行时还实现以下步骤:In one embodiment, when the computer-readable instructions are executed by the processor, the following steps are further implemented:
解析第一用户标识对应的资产信息字符识别结果,并从中提取资产关键字;资产关键字,包括与第一用户标识对应的资产类型;Analyze the asset information character recognition result corresponding to the first user ID, and extract the asset keyword from it; the asset keyword includes the asset type corresponding to the first user ID;
获取预设审核标准,并将资产关键字和预设审核标准进行比对;及Obtain preset review criteria and compare asset keywords with preset review criteria; and
当资产关键字符合预设审核标准时,返回第一用户审核成功的结果。When the asset keyword meets the preset review criteria, the result of successful review by the first user is returned.
在一个实施例中,计算机可读指令被处理器执行时还实现以下步骤:In one embodiment, when the computer-readable instructions are executed by the processor, the following steps are further implemented:
获取与第一用户标识对应的预设审核标准;预设审核标准为与第一用户标识对应的预设总资产阈值;Obtaining a preset audit standard corresponding to the first user identification; the preset audit standard is a preset total asset threshold corresponding to the first user identification;
获取第一用户标识对应的各资产类型对应的资产数值大小;Acquiring the asset value size corresponding to each asset type corresponding to the first user identifier;
累计各资产类型的资产数值大小,获得的总资产数值;Accumulate the size of the asset value of each asset type, and the total asset value obtained;
将总资产数值与预设总资产阈值进行比对;及Compare the total asset value with the preset total asset threshold; and
当总资产数值大于或等于预设总资产阈值时,生成审核生成的结果并返回给用户终端;当总资产数值小于预设总资产阈值时,生成审核失败的结果并返回给用户终端。When the total asset value is greater than or equal to the preset total asset threshold, the result generated by the audit is generated and returned to the user terminal; when the total asset value is less than the preset total asset threshold, the audit failed result is generated and returned to the user terminal.
在一个实施例中,计算机可读指令被处理器执行时还实现以下步骤:In one embodiment, when the computer-readable instructions are executed by the processor, the following steps are further implemented:
当行为数据未通过数据审核时,得到对应的第二用户;When the behavior data fails the data review, the corresponding second user is obtained;
将与第二用户对应的第二用户标识,推送至排队***中的普通队列;Push the second user ID corresponding to the second user to the ordinary queue in the queuing system;
当轮询排队***未获取到第一用户标识时,从普通队列中获取第二用户标识;及When the polling queuing system does not obtain the first user ID, obtain the second user ID from the ordinary queue; and
利用预设审核标准,对与第二用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。Using the preset audit criteria, the asset data is audited on the asset character recognition result corresponding to the second user ID, and the audit result is generated and returned to the user terminal.
在一个实施例中,计算机可读指令被处理器执行时还实现以下步骤:In one embodiment, when the computer-readable instructions are executed by the processor, the following steps are further implemented:
获取用户上传的身份证明图像文件和资产证明图像文件;Obtain the image file of the identity certificate and the image file of the asset certificate uploaded by the user;
对身份证明图像文件和资产证明图像文件进行字符识别信息提取,获得身份字符识别结果和资产字符识别结果;Extract the character recognition information from the image file of the identity certificate and the image file of the asset certificate, and obtain the result of identity character recognition and asset character recognition;
获取预先存储的用户身份信息;及Obtain pre-stored user identification information; and
将身份字符识别结果,与预先存储的用户身份信息进行比对。The identification character recognition result is compared with the pre-stored user identification information.
在一个实施例中,计算机可读指令被处理器执行时还实现以下步骤:In one embodiment, when the computer-readable instructions are executed by the processor, the following steps are further implemented:
当身份字符识别结果符合预先存储的用户身份信息时,分别获取与用户标识对应的浏览记录相关数据、收藏记录相关数据以及购买记录相关数据;浏览记录相关数据包括用户浏览的产品类别、对应产品的产品价值和浏览次数;收藏记录相关数据包括用户收藏的产品类别以及对应产品的产品价值;购买记录相关数据包括用户购买的产品类别、对应产品 的购买次数、购买时间以及产品价值。When the identification character recognition result matches the pre-stored user identity information, the browsing record related data, the favorite record related data and the purchase record related data corresponding to the user identification are obtained respectively; the browsing record related data includes the product category browsed by the user and the corresponding product information. Product value and number of views; collection record related data includes the user's favorite product category and the product value of the corresponding product; purchase record related data includes the user's product category purchased, the number of purchases of the corresponding product, purchase time, and product value.
一个或多个存储有计算机可读指令的计算机可读存储介质,计算机可读指令被一个或多个处理器执行时,使得一个或多个处理器执行以下步骤:One or more computer-readable storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors perform the following steps:
当检测到用户发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将身份字符识别结果与预先存储的用户身份信息进行比对;When the data review request sent by the user is detected, the identification character recognition result and the asset character recognition result corresponding to the user identification are obtained, and the identification character recognition result is compared with the pre-stored user identity information;
当身份字符识别结果符合预先存储的用户身份信息时,提取用户标识对应的行为历史数据;When the identification character recognition result matches the pre-stored user identification information, extract the behavior history data corresponding to the user identification;
根据预设数据分类规则对行为历史数据进行分类,获得不同数据类型的行为历史数据;数据类型包括数字型数据、文本型数据以及字节型数据;Classify behavior history data according to preset data classification rules to obtain behavior history data of different data types; data types include numeric data, text data, and byte data;
确定与各不同数据类型的行为历史数据对应的数据审核方式;数据审核方式包括与数字型行为历史数据对应的第一审核方式、与文本型行为历史数据对应的第二审核方式,以及与字节型行为历史数据对应的第三审核方式;Determine the data review method corresponding to the behavior history data of each different data type; the data review method includes the first review method corresponding to the digital behavior historical data, the second review method corresponding to the text-based behavior historical data, and the byte The third review method corresponding to historical data of type behavior;
根据审核方式,分别对对应数据类型的行为历史数据进行数据审核;According to the review method, conduct data review on the behavioral historical data of the corresponding data type;
当行为历史数据通过数据审核时,获取与行为历史数据对应的第一用户标识,并将第一用户标识推送至排队***中的优先队列;When the behavior history data passes the data review, obtain the first user identification corresponding to the behavior history data, and push the first user identification to the priority queue in the queuing system;
轮询排队***,从优先队列中获取第一用户标识;及Polling the queuing system to obtain the first user ID from the priority queue; and
对与第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。The asset data is audited on the asset character recognition result corresponding to the first user identification, and the audit result is generated and returned to the user terminal.
其中,该计算机可读存储介质可以是非易失性,也可以是易失性的。Wherein, the computer-readable storage medium may be non-volatile or volatile.
在一个实施例中,计算机可读指令被处理器执行时还实现以下步骤:In one embodiment, when the computer-readable instructions are executed by the processor, the following steps are further implemented:
解析第一用户标识对应的资产信息字符识别结果,并从中提取资产关键字;资产关键字,包括与第一用户标识对应的资产类型;Analyze the asset information character recognition result corresponding to the first user ID, and extract the asset keyword from it; the asset keyword includes the asset type corresponding to the first user ID;
获取预设审核标准,并将资产关键字和预设审核标准进行比对;及Obtain preset review criteria and compare asset keywords with preset review criteria; and
当资产关键字符合预设审核标准时,返回第一用户审核成功的结果。在一个实施例中,计算机可读指令被处理器执行时还实现以下步骤:When the asset keyword meets the preset review criteria, the result of successful review by the first user is returned. In one embodiment, when the computer-readable instructions are executed by the processor, the following steps are further implemented:
获取与第一用户标识对应的预设审核标准;预设审核标准为与第一用户标识对应的预设总资产阈值;Obtaining a preset audit standard corresponding to the first user identification; the preset audit standard is a preset total asset threshold corresponding to the first user identification;
获取第一用户标识对应的各资产类型对应的资产数值大小;Acquiring the asset value size corresponding to each asset type corresponding to the first user identifier;
累计各资产类型的资产数值大小,获得的总资产数值;Accumulate the size of the asset value of each asset type, and the total asset value obtained;
将总资产数值与预设总资产阈值进行比对;及Compare the total asset value with the preset total asset threshold; and
当总资产数值大于或等于预设总资产阈值时,生成审核生成的结果并返回给用户终端;当总资产数值小于预设总资产阈值时,生成审核失败的结果并返回给用户终端。When the total asset value is greater than or equal to the preset total asset threshold, the result generated by the audit is generated and returned to the user terminal; when the total asset value is less than the preset total asset threshold, the audit failed result is generated and returned to the user terminal.
在一个实施例中,计算机可读指令被处理器执行时还实现以下步骤:In one embodiment, when the computer-readable instructions are executed by the processor, the following steps are further implemented:
当行为数据未通过数据审核时,得到对应的第二用户;When the behavior data fails the data review, the corresponding second user is obtained;
将与第二用户对应的第二用户标识,推送至排队***中的普通队列;Push the second user ID corresponding to the second user to the ordinary queue in the queuing system;
当轮询排队***未获取到第一用户标识时,从普通队列中获取第二用户标识;及When the polling queuing system does not obtain the first user ID, obtain the second user ID from the ordinary queue; and
利用预设审核标准,对与第二用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。Using the preset audit criteria, the asset data is audited on the asset character recognition result corresponding to the second user ID, and the audit result is generated and returned to the user terminal.
在一个实施例中,计算机可读指令被处理器执行时还实现以下步骤:In one embodiment, when the computer-readable instructions are executed by the processor, the following steps are further implemented:
获取用户上传的身份证明图像文件和资产证明图像文件;Obtain the image file of the identity certificate and the image file of the asset certificate uploaded by the user;
对身份证明图像文件和资产证明图像文件进行字符识别信息提取,获得身份字符识别结果和资产字符识别结果;Extract the character recognition information from the image file of the identity certificate and the image file of the asset certificate, and obtain the result of identity character recognition and asset character recognition;
获取预先存储的用户身份信息;及Obtain pre-stored user identification information; and
将身份字符识别结果,与预先存储的用户身份信息进行比对。The identification character recognition result is compared with the pre-stored user identification information.
在一个实施例中,计算机可读指令被处理器执行时还实现以下步骤:In one embodiment, when the computer-readable instructions are executed by the processor, the following steps are further implemented:
当身份字符识别结果符合预先存储的用户身份信息时,分别获取与用户标识对应的浏览记录相关数据、收藏记录相关数据以及购买记录相关数据;浏览记录相关数据包括用户浏览的产品类别、对应产品的产品价值和浏览次数;收藏记录相关数据包括用户收藏的产品类别以及对应产品的产品价值;购买记录相关数据包括用户购买的产品类别、对应产品的购买次数、购买时间以及产品价值。When the identification character recognition result matches the pre-stored user identity information, the browsing record related data, the favorite record related data and the purchase record related data corresponding to the user identification are obtained respectively; the browsing record related data includes the product category browsed by the user and the corresponding product information. Product value and number of views; collection record related data includes the user's favorite product category and the product value of the corresponding product; purchase record related data includes the user's product category purchased, the number of purchases of the corresponding product, purchase time, and product value.
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程,是可以通过计算机可读指令来指令相关的硬件来完成,的计算机可读指令可存储于一计算机可读取存储介质中,该计算机可读指令在执行时,可包括如上述各方法的实施例的流程。其中,本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用,均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限,RAM以多种形式可得,诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing relevant hardware through computer-readable instructions. The computer-readable instructions can be stored in a computer-readable storage medium. When the computer-readable instructions are executed, they may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and/or volatile memory. Non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not a limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
以上实施例的各技术特征可以进行任意的组合,为使描述简洁,未对上述实施例中的各个技术特征所有可能的组合都进行描述,然而,只要这些技术特征的组合不存在矛盾,都应当认为是本说明书记载的范围。The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered as the range described in this specification.
以上实施例仅表达了本申请的几种实施方式,其描述较为具体和详细,但并不能因此而理解为对发明专利范围的限制。应当指出的是,对于本领域的普通技术人员来说,在不脱离本申请构思的前提下,还可以做出若干变形和改进,这些都属于本申请的保护范围。因此,本申请专利的保护范围应以所附权利要求为准。The above examples only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can be made, and these all fall within the protection scope of this application. Therefore, the scope of protection of the patent of this application shall be subject to the appended claims.

Claims (20)

  1. 一种基于身份识别的数据审核方法,包括:A data audit method based on identity recognition, including:
    当检测到用户发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将所述身份字符识别结果与预先存储的用户身份信息进行比对;When the data review request sent by the user is detected, the identification character recognition result and the asset character recognition result corresponding to the user identification are obtained, and the identification character recognition result is compared with the pre-stored user identity information;
    当所述身份字符识别结果符合所述预先存储的用户身份信息时,提取所述用户标识对应的行为历史数据;When the identification character recognition result matches the pre-stored user identification information, extracting the behavior history data corresponding to the user identification;
    根据预设数据分类规则对所述行为历史数据进行分类,获得不同数据类型的行为历史数据;所述数据类型包括数字型数据、文本型数据以及字节型数据;Classify the behavior history data according to preset data classification rules to obtain behavior history data of different data types; the data types include numeric data, text data, and byte data;
    确定与各所述不同数据类型的行为历史数据对应的数据审核方式;所述数据审核方式包括与数字型行为历史数据对应的第一审核方式、与文本型行为历史数据对应的第二审核方式,以及与字节型行为历史数据对应的第三审核方式;Determine the data review method corresponding to each of the different data types of behavior history data; the data review method includes a first review method corresponding to the digital behavior history data and a second review method corresponding to the text type behavior history data, And the third audit method corresponding to byte-type behavior historical data;
    根据所述审核方式,分别对对应数据类型的行为历史数据进行数据审核;According to the review method, conduct a data review on the behavior history data of the corresponding data type;
    当所述行为历史数据通过所述数据审核时,获取与所述行为历史数据对应的第一用户标识,并将所述第一用户标识推送至排队***中的优先队列;When the behavior history data passes the data review, obtain the first user identification corresponding to the behavior history data, and push the first user identification to the priority queue in the queuing system;
    轮询所述排队***,从所述优先队列中获取所述第一用户标识;及Polling the queuing system to obtain the first user identification from the priority queue; and
    对与所述第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。The asset data is audited on the asset character recognition result corresponding to the first user identification, and the audit result is generated and returned to the user terminal.
  2. 根据权利要求1所述的方法,其中,所述对与所述第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端,包括:The method according to claim 1, wherein the reviewing asset data on the asset character recognition result corresponding to the first user identification, generating the review result and returning it to the user terminal comprises:
    解析所述第一用户标识对应的资产信息字符识别结果,并从中提取资产关键字;所述资产关键字,包括与所述第一用户标识对应的资产类型;Parse the asset information character recognition result corresponding to the first user ID, and extract asset keywords therefrom; the asset keyword includes the asset type corresponding to the first user ID;
    获取预设审核标准,并将所述资产关键字和所述预设审核标准进行比对;及Obtain a preset review standard, and compare the asset keyword with the preset review standard; and
    当所述资产关键字符合所述预设审核标准时,返回所述第一用户审核成功的结果。When the asset keyword meets the preset review standard, the result of the successful review of the first user is returned.
  3. 根据权利要求1所述的方法,其中,所述对与所述第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端,还包括:The method according to claim 1, wherein said performing an asset data audit on the asset character recognition result corresponding to the first user identification, generating the audit result and returning it to the user terminal, further comprises:
    获取与所述第一用户标识对应的所述预设审核标准;所述预设审核标准为与所述第一用户标识对应的预设总资产阈值;Acquiring the preset audit standard corresponding to the first user identification; the preset audit standard is a preset total asset threshold corresponding to the first user identification;
    获取所述第一用户标识对应的各所述资产类型对应的资产数值大小;Acquiring the asset value size corresponding to each asset type corresponding to the first user identifier;
    累计各所述资产类型的资产数值大小,获得的总资产数值;Accumulate the size of the asset value of each asset type, and obtain the total asset value;
    将所述总资产数值与所述预设总资产阈值进行比对;及Compare the total asset value with the preset total asset threshold; and
    当所述总资产数值大于或等于所述预设总资产阈值时,生成审核生成的结果并返回给用户终端;当所述总资产数值小于所述预设总资产阈值时,生成审核失败的结果并返回给用户终端。When the total asset value is greater than or equal to the preset total asset threshold, the result generated by the audit is generated and returned to the user terminal; when the total asset value is less than the preset total asset threshold, a result of audit failure is generated And return to the user terminal.
  4. 根据权利要求1至3任意一项所述的方法,其中,所述用户标识还包括第二用户标识;所述方法还包括:The method according to any one of claims 1 to 3, wherein the user identification further comprises a second user identification; the method further comprises:
    当所述行为数据未通过所述数据审核时,得到对应的第二用户;When the behavior data fails the data review, obtain the corresponding second user;
    将与所述第二用户对应的第二用户标识,推送至所述排队***中的普通队列;Pushing the second user identifier corresponding to the second user to the normal queue in the queuing system;
    当轮询所述排队***未获取到所述第一用户标识时,从所述普通队列中获取所述第二用户标识;及When the first user identification is not obtained by polling the queuing system, obtain the second user identification from the normal queue; and
    利用所述预设审核标准,对与所述第二用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。Using the preset review criteria, the asset data is reviewed on the asset character recognition result corresponding to the second user identification, and the review result is generated and returned to the user terminal.
  5. 根据权利要求1至3任意一项所述的方法,其中,所述当检测到用户发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将所述身份字符识别结果与预先存储的用户身份信息进行比对,包括:The method according to any one of claims 1 to 3, wherein when the data review request sent by the user is detected, the identification character recognition result and the asset character recognition result corresponding to the user identification are obtained, and the identity The character recognition results are compared with pre-stored user identity information, including:
    获取用户上传的身份证明图像文件和资产证明图像文件;Obtain the image file of the identity certificate and the image file of the asset certificate uploaded by the user;
    对所述身份证明图像文件和所述资产证明图像文件进行字符识别信息提取,获得身份字符识别结果和资产字符识别结果;Performing character recognition information extraction on the identity certification image file and the asset certification image file to obtain an identity character recognition result and an asset character recognition result;
    获取预先存储的用户身份信息;及Obtain pre-stored user identification information; and
    将所述身份字符识别结果,与所述预先存储的用户身份信息进行比对。The identification character recognition result is compared with the pre-stored user identification information.
  6. 根据权利要求1至3任意一项所述的方法,其中,所述当所述身份字符识别结果符合所述预先存储的用户身份信息时,提取所述用户标识对应的行为历史数据,包括:The method according to any one of claims 1 to 3, wherein said extracting behavior history data corresponding to said user identification when said identification character recognition result matches said pre-stored user identification information comprises:
    当所述身份字符识别结果符合所述预先存储的用户身份信息时,分别获取与用户标识对应的浏览记录相关数据、收藏记录相关数据以及购买记录相关数据;所述浏览记录相关数据包括用户浏览的产品类别、对应产品的产品价值和浏览次数;所述收藏记录相关数据包括用户收藏的产品类别以及对应产品的产品价值;所述购买记录相关数据包括用户购买的产品类别、对应产品的购买次数、购买时间以及产品价值。When the identification character recognition result matches the pre-stored user identity information, the browsing record related data, the favorite record related data, and the purchase record related data corresponding to the user identification are obtained respectively; the browsing record related data includes the user's browsing history The product category, the product value of the corresponding product, and the number of views; the collection record related data includes the user’s favorite product category and the product value of the corresponding product; the purchase record related data includes the product category purchased by the user, the number of purchases of the corresponding product, Purchase time and product value.
  7. 一种基于身份识别的数据审核装置,包括:A data verification device based on identity recognition includes:
    检测模块,用于当检测到用户发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将所述身份字符识别结果与预先存储的用户身份信息进行比对;The detection module is used to obtain the identification character recognition result and asset character identification result corresponding to the user identification when the data review request sent by the user is detected, and compare the identification character identification result with pre-stored user identification information ;
    行为历史数据提取模块,用于当所述身份字符识别结果符合所述预先存储的用户身份信息时,提取所述用户标识对应的行为历史数据;A behavior history data extraction module, configured to extract behavior history data corresponding to the user identification when the identification character recognition result matches the pre-stored user identification information;
    分类模块,用于根据预设数据分类规则对所述行为历史数据进行分类,获得不同数据类型的行为历史数据;所述数据类型包括数字型数据、文本型数据以及字节型数据;The classification module is configured to classify the behavior history data according to preset data classification rules to obtain behavior history data of different data types; the data types include digital data, text data, and byte data;
    数据审核方式确定模块,用于确定与各所述不同数据类型的行为历史数据对应的数据审核方式;所述数据审核方式包括与数字型行为历史数据对应的第一审核方式、与文本型行为历史数据对应的第二审核方式,以及与字节型行为历史数据对应的第三审核方式;The data review method determining module is used to determine the data review method corresponding to each of the different data types of behavior history data; the data review method includes the first review method corresponding to the digital behavior history data and the text type behavior history The second review method corresponding to the data, and the third review method corresponding to the byte-type behavior historical data;
    数据审核模块,用于根据所述审核方式,分别对对应数据类型的行为历史数据进行数据审核;The data review module is used to conduct data review on the behavior history data of the corresponding data type according to the review method;
    推送模块,用于当所述行为历史数据通过所述数据审核时,获取与所述行为历史数据 对应的第一用户标识,并将所述第一用户标识推送至排队***中的优先队列;A push module, configured to obtain a first user identification corresponding to the behavior history data when the behavior history data passes the data review, and push the first user identification to the priority queue in the queuing system;
    轮询模块,用于轮询所述排队***,从所述优先队列中获取所述第一用户标识;及A polling module, configured to poll the queuing system to obtain the first user identification from the priority queue; and
    审核结果生成模块,用于对与所述第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。The audit result generation module is used to audit asset data on the asset character recognition result corresponding to the first user identification, generate an audit result, and return it to the user terminal.
  8. 根据权利要求7所述的基于身份识别的数据审核装置,其中,所述审核结果生成模块还用于:The data verification device based on identity recognition according to claim 7, wherein the verification result generation module is further used for:
    解析所述第一用户标识对应的资产信息字符识别结果,并从中提取资产关键字;所述资产关键字,包括与所述第一用户标识对应的资产类型;Parse the asset information character recognition result corresponding to the first user ID, and extract asset keywords therefrom; the asset keyword includes the asset type corresponding to the first user ID;
    获取预设审核标准,并将所述资产关键字和所述预设审核标准进行比对;Obtain a preset review standard, and compare the asset keyword with the preset review standard;
    当所述资产关键字符合所述预设审核标准时,返回所述第一用户审核成功的结果。When the asset keyword meets the preset review standard, the result of the successful review of the first user is returned.
  9. 一种计算机设备,包括存储器及一个或多个处理器,所述存储器中储存有计算机可读指令,所述计算机可读指令被所述一个或多个处理器执行时,使得所述一个或多个处理器执行以下步骤:A computer device includes a memory and one or more processors. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the one or more processors, the one or more Each processor performs the following steps:
    当检测到用户发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将所述身份字符识别结果与预先存储的用户身份信息进行比对;When the data review request sent by the user is detected, the identification character recognition result and the asset character recognition result corresponding to the user identification are obtained, and the identification character recognition result is compared with the pre-stored user identity information;
    当所述身份字符识别结果符合所述预先存储的用户身份信息时,提取所述用户标识对应的行为历史数据;When the identification character recognition result matches the pre-stored user identification information, extracting the behavior history data corresponding to the user identification;
    根据预设数据分类规则对所述行为历史数据进行分类,获得不同数据类型的行为历史数据;所述数据类型包括数字型数据、文本型数据以及字节型数据;Classify the behavior history data according to preset data classification rules to obtain behavior history data of different data types; the data types include numeric data, text data, and byte data;
    确定与各所述不同数据类型的行为历史数据对应的数据审核方式;所述数据审核方式包括与数字型行为历史数据对应的第一审核方式、与文本型行为历史数据对应的第二审核方式,以及与字节型行为历史数据对应的第三审核方式;Determine the data review method corresponding to each of the different data types of behavior history data; the data review method includes a first review method corresponding to the digital behavior history data and a second review method corresponding to the text type behavior history data, And the third audit method corresponding to byte-type behavior historical data;
    根据所述审核方式,分别对对应数据类型的行为历史数据进行数据审核;According to the review method, conduct a data review on the behavior history data of the corresponding data type;
    当所述行为历史数据通过所述数据审核时,获取与所述行为历史数据对应的第一用户标识,并将所述第一用户标识推送至排队***中的优先队列;When the behavior history data passes the data review, obtain the first user identification corresponding to the behavior history data, and push the first user identification to the priority queue in the queuing system;
    轮询所述排队***,从所述优先队列中获取所述第一用户标识;及Polling the queuing system to obtain the first user identification from the priority queue; and
    对与所述第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。The asset data is audited on the asset character recognition result corresponding to the first user identification, and the audit result is generated and returned to the user terminal.
  10. 根据权利要求9所述的计算机设备,其中,所述处理器执行所述计算机可读指令时还执行以下步骤:The computer device according to claim 9, wherein the processor further executes the following steps when executing the computer readable instruction:
    解析所述第一用户标识对应的资产信息字符识别结果,并从中提取资产关键字;所述资产关键字,包括与所述第一用户标识对应的资产类型;Parse the asset information character recognition result corresponding to the first user ID, and extract asset keywords therefrom; the asset keyword includes the asset type corresponding to the first user ID;
    获取预设审核标准,并将所述资产关键字和所述预设审核标准进行比对;及Obtain a preset review standard, and compare the asset keyword with the preset review standard; and
    当所述资产关键字符合所述预设审核标准时,返回所述第一用户审核成功的结果。When the asset keyword meets the preset review standard, the result of the successful review of the first user is returned.
  11. 根据权利要求9所述的计算机设备,其中,所述处理器执行所述计算机可读指令 时还执行以下步骤:The computer device according to claim 9, wherein the processor further executes the following steps when executing the computer-readable instructions:
    获取与所述第一用户标识对应的所述预设审核标准;所述预设审核标准为与所述第一用户标识对应的预设总资产阈值;Acquiring the preset audit standard corresponding to the first user identification; the preset audit standard is a preset total asset threshold corresponding to the first user identification;
    获取所述第一用户标识对应的各所述资产类型对应的资产数值大小;Acquiring the asset value size corresponding to each asset type corresponding to the first user identifier;
    累计各所述资产类型的资产数值大小,获得的总资产数值;Accumulate the size of the asset value of each asset type, and obtain the total asset value;
    将所述总资产数值与所述预设总资产阈值进行比对;及Compare the total asset value with the preset total asset threshold; and
    当所述总资产数值大于或等于所述预设总资产阈值时,生成审核生成的结果并返回给用户终端;当所述总资产数值小于所述预设总资产阈值时,生成审核失败的结果并返回给用户终端。When the total asset value is greater than or equal to the preset total asset threshold, the result generated by the audit is generated and returned to the user terminal; when the total asset value is less than the preset total asset threshold, a result of audit failure is generated And return to the user terminal.
  12. 根据权利要求9至11任一项所述的计算机设备,其中,所述处理器执行所述计算机可读指令时还执行以下步骤:The computer device according to any one of claims 9 to 11, wherein the processor further executes the following steps when executing the computer readable instruction:
    当所述行为数据未通过所述数据审核时,得到对应的第二用户;When the behavior data fails the data review, obtain the corresponding second user;
    将与所述第二用户对应的第二用户标识,推送至所述排队***中的普通队列;Pushing the second user identifier corresponding to the second user to the normal queue in the queuing system;
    当轮询所述排队***未获取到所述第一用户标识时,从所述普通队列中获取所述第二用户标识;及When the first user identification is not obtained by polling the queuing system, obtain the second user identification from the normal queue; and
    利用所述预设审核标准,对与所述第二用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。Using the preset review criteria, the asset data is reviewed on the asset character recognition result corresponding to the second user identification, and the review result is generated and returned to the user terminal.
  13. 根据权利要求9至11任一项所述的计算机设备,其中,所述处理器执行所述计算机可读指令时还执行以下步骤:The computer device according to any one of claims 9 to 11, wherein the processor further executes the following steps when executing the computer readable instruction:
    获取用户上传的身份证明图像文件和资产证明图像文件;Obtain the image file of the identity certificate and the image file of the asset certificate uploaded by the user;
    对所述身份证明图像文件和所述资产证明图像文件进行字符识别信息提取,获得身份字符识别结果和资产字符识别结果;Performing character recognition information extraction on the identity certification image file and the asset certification image file to obtain an identity character recognition result and an asset character recognition result;
    获取预先存储的用户身份信息;及Obtain pre-stored user identification information; and
    将所述身份字符识别结果,与所述预先存储的用户身份信息进行比对。The identification character recognition result is compared with the pre-stored user identification information.
  14. 根据权利要求9至11任一项所述的计算机设备,其中,所述处理器执行所述计算机可读指令时还执行以下步骤:The computer device according to any one of claims 9 to 11, wherein the processor further executes the following steps when executing the computer readable instruction:
    当所述身份字符识别结果符合所述预先存储的用户身份信息时,分别获取与用户标识对应的浏览记录相关数据、收藏记录相关数据以及购买记录相关数据;所述浏览记录相关数据包括用户浏览的产品类别、对应产品的产品价值和浏览次数;所述收藏记录相关数据包括用户收藏的产品类别以及对应产品的产品价值;所述购买记录相关数据包括用户购买的产品类别、对应产品的购买次数、购买时间以及产品价值。When the identification character recognition result matches the pre-stored user identity information, the browsing record related data, the favorite record related data, and the purchase record related data corresponding to the user identification are obtained respectively; the browsing record related data includes the user's browsing history The product category, the product value of the corresponding product, and the number of views; the collection record related data includes the user’s favorite product category and the product value of the corresponding product; the purchase record related data includes the product category purchased by the user, the number of purchases of the corresponding product, Purchase time and product value.
  15. 一个或多个存储有计算机可读指令的计算机可读存储介质,所述计算机可读指令被一个或多个处理器执行时,使得所述一个或多个处理器执行以下步骤:One or more computer-readable storage media storing computer-readable instructions, when the computer-readable instructions are executed by one or more processors, cause the one or more processors to perform the following steps:
    当检测到用户发送的数据审核请求时,获取与用户标识对应的身份字符识别结果和资产字符识别结果,并将所述身份字符识别结果与预先存储的用户身份信息进行比对;When the data review request sent by the user is detected, the identification character recognition result and the asset character recognition result corresponding to the user identification are obtained, and the identification character recognition result is compared with the pre-stored user identity information;
    当所述身份字符识别结果符合所述预先存储的用户身份信息时,提取所述用户标识对应的行为历史数据;When the identification character recognition result matches the pre-stored user identification information, extracting the behavior history data corresponding to the user identification;
    根据预设数据分类规则对所述行为历史数据进行分类,获得不同数据类型的行为历史数据;所述数据类型包括数字型数据、文本型数据以及字节型数据;Classify the behavior history data according to preset data classification rules to obtain behavior history data of different data types; the data types include numeric data, text data, and byte data;
    确定与各所述不同数据类型的行为历史数据对应的数据审核方式;所述数据审核方式包括与数字型行为历史数据对应的第一审核方式、与文本型行为历史数据对应的第二审核方式,以及与字节型行为历史数据对应的第三审核方式;Determine the data review method corresponding to each of the different data types of behavior history data; the data review method includes a first review method corresponding to the digital behavior history data and a second review method corresponding to the text type behavior history data, And the third audit method corresponding to byte-type behavior historical data;
    根据所述审核方式,分别对对应数据类型的行为历史数据进行数据审核;According to the review method, conduct a data review on the behavior history data of the corresponding data type;
    当所述行为历史数据通过所述数据审核时,获取与所述行为历史数据对应的第一用户标识,并将所述第一用户标识推送至排队***中的优先队列;When the behavior history data passes the data review, obtain the first user identification corresponding to the behavior history data, and push the first user identification to the priority queue in the queuing system;
    轮询所述排队***,从所述优先队列中获取所述第一用户标识;及Polling the queuing system to obtain the first user identification from the priority queue; and
    对与所述第一用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。The asset data is audited on the asset character recognition result corresponding to the first user identification, and the audit result is generated and returned to the user terminal.
  16. 根据权利要求15所述的存储介质,其中,所述计算机可读指令被所述处理器执行时还执行以下步骤:The storage medium according to claim 15, wherein the following steps are further performed when the computer-readable instructions are executed by the processor:
    解析所述第一用户标识对应的资产信息字符识别结果,并从中提取资产关键字;所述资产关键字,包括与所述第一用户标识对应的资产类型;Parse the asset information character recognition result corresponding to the first user ID, and extract asset keywords therefrom; the asset keyword includes the asset type corresponding to the first user ID;
    获取预设审核标准,并将所述资产关键字和所述预设审核标准进行比对;及Obtain a preset review standard, and compare the asset keyword with the preset review standard; and
    当所述资产关键字符合所述预设审核标准时,返回所述第一用户审核成功的结果。When the asset keyword meets the preset review standard, the result of the successful review of the first user is returned.
  17. 根据权利要求15所述的存储介质,其中,所述计算机可读指令被所述处理器执行时还执行以下步骤:The storage medium according to claim 15, wherein the following steps are further performed when the computer-readable instructions are executed by the processor:
    获取与所述第一用户标识对应的所述预设审核标准;所述预设审核标准为与所述第一用户标识对应的预设总资产阈值;Acquiring the preset audit standard corresponding to the first user identification; the preset audit standard is a preset total asset threshold corresponding to the first user identification;
    获取所述第一用户标识对应的各所述资产类型对应的资产数值大小;Acquiring the asset value size corresponding to each asset type corresponding to the first user identifier;
    累计各所述资产类型的资产数值大小,获得的总资产数值;Accumulate the size of the asset value of each asset type, and obtain the total asset value;
    将所述总资产数值与所述预设总资产阈值进行比对;及Compare the total asset value with the preset total asset threshold; and
    当所述总资产数值大于或等于所述预设总资产阈值时,生成审核生成的结果并返回给用户终端;当所述总资产数值小于所述预设总资产阈值时,生成审核失败的结果并返回给用户终端。When the total asset value is greater than or equal to the preset total asset threshold, the result generated by the audit is generated and returned to the user terminal; when the total asset value is less than the preset total asset threshold, a result of audit failure is generated And return to the user terminal.
  18. 根据权利要求15至17所述的存储介质,其中,所述计算机可读指令被所述处理器执行时还执行以下步骤:The storage medium according to claims 15 to 17, wherein the following steps are further performed when the computer-readable instructions are executed by the processor:
    当所述行为数据未通过所述数据审核时,得到对应的第二用户;When the behavior data fails the data review, obtain the corresponding second user;
    将与所述第二用户对应的第二用户标识,推送至所述排队***中的普通队列;Pushing the second user identifier corresponding to the second user to the normal queue in the queuing system;
    当轮询所述排队***未获取到所述第一用户标识时,从所述普通队列中获取所述第二用户标识;及When the first user identification is not obtained by polling the queuing system, obtain the second user identification from the normal queue; and
    利用所述预设审核标准,对与所述第二用户标识对应的资产字符识别结果进行资产数据审核,生成审核结果并返回给用户终端。Using the preset review criteria, the asset data is reviewed on the asset character recognition result corresponding to the second user identification, and the review result is generated and returned to the user terminal.
  19. 根据权利要求15至17所述的存储介质,其中,所述计算机可读指令被所述处理器执行时还执行以下步骤:The storage medium according to claims 15 to 17, wherein the following steps are further performed when the computer-readable instructions are executed by the processor:
    获取用户上传的身份证明图像文件和资产证明图像文件;Obtain the image file of the identity certificate and the image file of the asset certificate uploaded by the user;
    对所述身份证明图像文件和所述资产证明图像文件进行字符识别信息提取,获得身份字符识别结果和资产字符识别结果;Performing character recognition information extraction on the identity certification image file and the asset certification image file to obtain an identity character recognition result and an asset character recognition result;
    获取预先存储的用户身份信息;及Obtain pre-stored user identification information; and
    将所述身份字符识别结果,与所述预先存储的用户身份信息进行比对。The identification character recognition result is compared with the pre-stored user identification information.
  20. 根据权利要求15至17所述的存储介质,其中,所述计算机可读指令被所述处理器执行时还执行以下步骤:The storage medium according to claims 15 to 17, wherein the following steps are further performed when the computer-readable instructions are executed by the processor:
    当所述身份字符识别结果符合所述预先存储的用户身份信息时,分别获取与用户标识对应的浏览记录相关数据、收藏记录相关数据以及购买记录相关数据;所述浏览记录相关数据包括用户浏览的产品类别、对应产品的产品价值和浏览次数;所述收藏记录相关数据包括用户收藏的产品类别以及对应产品的产品价值;所述购买记录相关数据包括用户购买的产品类别、对应产品的购买次数、购买时间以及产品价值。When the identification character recognition result matches the pre-stored user identity information, the browsing record related data, the favorite record related data, and the purchase record related data corresponding to the user identification are obtained respectively; the browsing record related data includes the user's browsing history The product category, the product value of the corresponding product, and the number of views; the collection record related data includes the user’s favorite product category and the product value of the corresponding product; the purchase record related data includes the product category purchased by the user, the number of purchases of the corresponding product, Purchase time and product value.
PCT/CN2020/106052 2020-02-18 2020-07-31 Identity identification-based data auditing method and apparatus, and computer device WO2021164205A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010099472.2A CN111324802A (en) 2020-02-18 2020-02-18 Data auditing method and device based on identity recognition and computer equipment
CN202010099472.2 2020-02-18

Publications (1)

Publication Number Publication Date
WO2021164205A1 true WO2021164205A1 (en) 2021-08-26

Family

ID=71167086

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/106052 WO2021164205A1 (en) 2020-02-18 2020-07-31 Identity identification-based data auditing method and apparatus, and computer device

Country Status (2)

Country Link
CN (1) CN111324802A (en)
WO (1) WO2021164205A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113744048A (en) * 2021-09-14 2021-12-03 中国银行股份有限公司 Loan transaction processing method and device
CN115329156A (en) * 2022-10-14 2022-11-11 北京云成金融信息服务有限公司 Data management method and system based on historical data

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111324802A (en) * 2020-02-18 2020-06-23 深圳壹账通智能科技有限公司 Data auditing method and device based on identity recognition and computer equipment
CN113761854A (en) * 2021-08-27 2021-12-07 北京和利时***工程有限公司 Method and device for realizing train control data processing
CN113743902A (en) * 2021-09-08 2021-12-03 未鲲(上海)科技服务有限公司 Information auditing method and device based on artificial intelligence, terminal equipment and medium

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100305977A1 (en) * 2009-05-29 2010-12-02 Hyperquest, Inc. Automation of auditing claims
CN105005982A (en) * 2014-04-04 2015-10-28 影像搜索者公司 Image processing including object selection
CN106101138A (en) * 2016-07-29 2016-11-09 深圳市银雁金融服务有限公司 Method for processing business based on mobile terminal and device
CN106572100A (en) * 2016-10-25 2017-04-19 中国建设银行股份有限公司 Service data transfer audit method, device and system
CN108257027A (en) * 2017-06-16 2018-07-06 平安科技(深圳)有限公司 Declaration form data checking method, device, computer equipment and storage medium
CN108764994A (en) * 2018-05-24 2018-11-06 深圳前海桔子信息技术有限公司 A kind of user behavior guidance method, device, server and storage medium
CN108921510A (en) * 2018-06-27 2018-11-30 中国建设银行股份有限公司 Banking remote auto checking method and system
CN109800639A (en) * 2018-12-14 2019-05-24 深圳壹账通智能科技有限公司 Insurance checking method and server based on big data
CN110648224A (en) * 2019-09-27 2020-01-03 中国工商银行股份有限公司 Method, apparatus, computer system, and medium for matching financial products
CN111324802A (en) * 2020-02-18 2020-06-23 深圳壹账通智能科技有限公司 Data auditing method and device based on identity recognition and computer equipment

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100305977A1 (en) * 2009-05-29 2010-12-02 Hyperquest, Inc. Automation of auditing claims
CN105005982A (en) * 2014-04-04 2015-10-28 影像搜索者公司 Image processing including object selection
CN106101138A (en) * 2016-07-29 2016-11-09 深圳市银雁金融服务有限公司 Method for processing business based on mobile terminal and device
CN106572100A (en) * 2016-10-25 2017-04-19 中国建设银行股份有限公司 Service data transfer audit method, device and system
CN108257027A (en) * 2017-06-16 2018-07-06 平安科技(深圳)有限公司 Declaration form data checking method, device, computer equipment and storage medium
CN108764994A (en) * 2018-05-24 2018-11-06 深圳前海桔子信息技术有限公司 A kind of user behavior guidance method, device, server and storage medium
CN108921510A (en) * 2018-06-27 2018-11-30 中国建设银行股份有限公司 Banking remote auto checking method and system
CN109800639A (en) * 2018-12-14 2019-05-24 深圳壹账通智能科技有限公司 Insurance checking method and server based on big data
CN110648224A (en) * 2019-09-27 2020-01-03 中国工商银行股份有限公司 Method, apparatus, computer system, and medium for matching financial products
CN111324802A (en) * 2020-02-18 2020-06-23 深圳壹账通智能科技有限公司 Data auditing method and device based on identity recognition and computer equipment

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113744048A (en) * 2021-09-14 2021-12-03 中国银行股份有限公司 Loan transaction processing method and device
CN115329156A (en) * 2022-10-14 2022-11-11 北京云成金融信息服务有限公司 Data management method and system based on historical data

Also Published As

Publication number Publication date
CN111324802A (en) 2020-06-23

Similar Documents

Publication Publication Date Title
WO2021164205A1 (en) Identity identification-based data auditing method and apparatus, and computer device
CN108876133B (en) Risk assessment processing method, device, server and medium based on business information
WO2020077895A1 (en) Signing intention determining method and apparatus, computer device, and storage medium
WO2021004132A1 (en) Abnormal data detection method, apparatus, computer device, and storage medium
CN110443692B (en) Enterprise credit auditing method, device, equipment and computer readable storage medium
WO2019218699A1 (en) Fraud transaction determining method and apparatus, computer device, and storage medium
WO2020000688A1 (en) Financial risk verification processing method and apparatus, computer device, and storage medium
CN109783338A (en) Recording method, device and computer equipment based on business information
US20140258169A1 (en) Method and system for automated verification of customer reviews
WO2021043076A1 (en) Method and apparatus for processing network data to be published, and computer device and storage medium
CN110751533B (en) Product portrait generation method and device, computer equipment and storage medium
CN110362799B (en) On-line arbitration-based method and device for generating and processing resolution book and computer equipment
CN109801151B (en) Financial falsification risk monitoring method, device, computer equipment and storage medium
CN110472114B (en) Abnormal data early warning method and device, computer equipment and storage medium
CN110717650A (en) Receipt data processing method and device, computer equipment and storage medium
US20210042343A1 (en) Techniques and components to find new instances of text documents and identify known response templates
CN110674131A (en) Financial statement data processing method and device, computer equipment and storage medium
WO2020077876A1 (en) Method and apparatus for generating company supply and marketing relationship map, and computer device
CN112559526A (en) Data table export method and device, computer equipment and storage medium
CN110378811B (en) Arbitration information processing method, apparatus, computer device and storage medium
CN112288279A (en) Business risk assessment method and device based on natural language processing and linear regression
CN111813946A (en) Medical information feedback method, device, equipment and readable storage medium
CN110750619A (en) Chat record keyword extraction method and device, computer equipment and storage medium
CN110533381B (en) Case jurisdiction auditing method, device, computer equipment and storage medium
CN115994232B (en) Online multi-version document identity authentication method, system and computer equipment

Legal Events

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

Ref document number: 20919703

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 09/12/2022)

122 Ep: pct application non-entry in european phase

Ref document number: 20919703

Country of ref document: EP

Kind code of ref document: A1