Financial institution fault early warning method and device

Abstract

The invention discloses a financial institution fault early warning method and device, which can be used in the technical field of artificial intelligence, and the method comprises the steps: detecting the announcement information of a target website based on the link of the target website, and determining whether the announcement information is fault announcement information; if yes, obtaining a text image corresponding to the announcement information; identifying character information in the text image, forming early warning information based on the character information, and sending the early warning information to a user terminal to enable the user terminal to control the transaction of the user terminal based on the early warning information. According to the application, the fault announcement information can be automatically detected and early warning can be carried out, so that the user terminal can timely control the transaction when the fault occurs, the occurrence of the abnormal transaction is avoided, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of financial institution failure early warning technology, in particular to the field of artificial intelligence technology, and more particularly to a financial institution failure early warning method and device. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the present application as recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] At present, mobile network payment platforms have penetrated into thousands of households. Financial institution application software installed on user terminals of banks and other financial institutions can provide users with transaction payment functions. For example, when using mobile network payment to take the subway, the "pay first and pay later" delayed deduction form is adopted. When scanning the boarding code at the exit, the gate automatically opens and the passenger exits the station. At this time, the payment information is sent to the bank server and confirmed before the deduction can be made, so there is a delay of several seconds in the deduction. However, sometimes, due to network failures, system downtime and upgrade of the issuing bank, etc., the subway system cannot send the deduction information to UnionPay in time. Only when the network information of the card machine is restored or the bank starts external services can the recovery deduction information be sent to the system. In addition, the recovery deduction cannot enjoy the fare deduction discount, resulting in poor customer experience.

[0004] Therefore, existing financial institutions cannot fully grasp the situation of financial institutions actively suspending services due to system upgrades and other reasons. Existing technical methods cannot further automatically obtain the specific reasons why financial institutions refuse transactions, and can only be determined by manual telephone consultation or website announcements by customer service posts. In addition, financial institutions may also passively suspend services due to natural disasters, sudden communication failures, etc. Existing customer service posts cannot grasp the information of service suspension caused by emergencies at any time, which will also lead to abnormal transactions and reduced user experience. Summary of the invention

[0005] One object of the present application is to provide a financial institution fault warning method, which automatically detects fault announcement information and issues a warning, so that the user terminal can promptly control transactions during a fault, avoid abnormal transactions, and improve user experience. Another object of the present application is to provide a financial institution fault warning device. Another object of the present application is to provide a computer device. Another object of the present application is to provide a readable medium.

[0006] In order to achieve the above objectives, the present application discloses a method for early warning of failures in financial institutions, including:

[0007] Detecting the announcement information of the target website based on the link of the target website to determine whether the announcement information is fault announcement information;

[0008] If so, obtaining a text image corresponding to the announcement information;

[0009] The text information in the text image is identified and warning information is formed based on the text information, and the warning information is sent to the user terminal so that the user terminal controls the transaction of the user terminal based on the warning information.

[0010] Optionally, the target website includes an official website and a social networking website;

[0011] The detecting of the announcement information of the target website based on the link of the target website includes:

[0012] Detecting announcement information of the official website based on the link of the official website through a first detection rule;

[0013] The announcement information of the social networking site is detected based on the link of the social networking site through the second detection rule.

[0014] Optionally, the step of detecting keywords of the announcement information of the target website based on the link of the target website to determine whether the announcement information is fault announcement information includes:

[0015] Accessing the target website based on the link of the target website;

[0016] Detecting target keywords in the announcement information of the target website that are present in preset keywords;

[0017] Based on the target keyword, it is determined whether the announcement information is fault announcement information.

[0018] Optionally, determining whether the announcement information is fault announcement information based on the target keyword includes:

[0019] Determine a total weight based on each of the target keywords and the corresponding preset weight;

[0020] If the total weight is greater than the preset weight standard value, the announcement information is fault announcement information.

[0021] Optionally, the acquiring of the text image corresponding to the announcement information includes:

[0022] The text image corresponding to the announcement information is obtained based on preset screenshot setting information through crawler technology.

[0023] Optionally, the identifying text information in the text image and forming warning information based on the text information includes:

[0024] Processing the text image to obtain local features and global features;

[0025] Recognize the local features and the global features through OCR technology to obtain text information;

[0026] A warning message is generated according to the text message and the current time.

[0027] Optionally, the warning information includes the current fault status;

[0028] The sending of the warning information to the user terminal comprises:

[0029] If the current fault status is effective, the warning information is sent to the user terminal.

[0030] The present application also discloses a financial institution fault warning device, comprising:

[0031] A fault detection module, used to detect the announcement information of the target website based on the link of the target website to determine whether the announcement information is fault announcement information;

[0032] An image acquisition module, used for acquiring a text image corresponding to the announcement information;

[0033] The fault warning module is used to identify the text information in the text image and form warning information based on the text information, and send the warning information to the user terminal so that the user terminal controls the transaction of the user terminal based on the warning information.

[0034] The present application also discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the computer program.

[0035] The present application also discloses a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0036] The fault warning method of the financial institution of the present application detects the announcement information of the target website based on the link of the target website to determine whether the announcement information is fault announcement information; if so, obtain the text image corresponding to the announcement information; identify the text information in the text image and form warning information based on the text information, and send the warning information to the user terminal so that the user terminal controls the transaction of the user terminal based on the warning information. The present application can automatically detect the announcement information of the target website and determine whether the announcement information is fault announcement information. If it is fault announcement information, by obtaining the text image, identifying the text information in the text image to form warning information and send it to the user terminal, the user terminal can control the transaction of the user terminal according to the warning information, avoiding the problem of transaction abnormality caused by transactions in the fault stage, reducing labor costs, and improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0038] Figure 1 This is a flowchart of a specific embodiment of the method for early warning of failures in financial institutions according to an embodiment of the present application;

[0039] Figure 2 This is a flowchart of a specific embodiment S100 of the method for early warning of failures in financial institutions according to an embodiment of the present application;

[0040] Figure 3 This is a flowchart of a specific embodiment of the financial institution fault warning method according to the present application embodiment S100 determining whether the announcement information is fault announcement information;

[0041] Figure 4 This is a flowchart of a specific embodiment S123 of the method for early warning of failure of a financial institution according to an embodiment of the present application;

[0042] Figure 5 This is a flowchart of a specific embodiment S300 of the method for early warning of failures in financial institutions according to an embodiment of the present application;

[0043] Figure 6 This is a structural diagram of a specific embodiment of the financial institution fault warning device of the present application embodiment;

[0044] Figure 7 A schematic diagram showing the structure of a computer device suitable for implementing an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the embodiments of the present application more clear, the embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. Here, the illustrative embodiments of the present application and their descriptions are used to explain the present application, but are not intended to limit the present application.

[0046] It should be noted that the method and device for early warning of financial institution faults disclosed in the present application can be used in the field of artificial intelligence technology, and can also be used in any field other than the field of artificial intelligence technology. The application field of the method and device for early warning of financial institution faults disclosed in the present application is not limited.

[0047] According to one aspect of the present application, this embodiment discloses a method for early warning of failures in financial institutions. Figure 1 As shown, in this embodiment, the method includes:

[0048] S100: Detecting announcement information of the target website based on a link of the target website to determine whether the announcement information is fault announcement information.

[0049] S200: If yes, obtain the text image corresponding to the announcement information.

[0050] S300: Identify text information in the text image and form warning information based on the text information, and send the warning information to the user terminal so that the user terminal controls the transaction of the user terminal based on the warning information.

[0051] This application can automatically detect the announcement information of the target website and determine whether the announcement information is a fault announcement information. If it is a fault announcement information, by obtaining a text image, identifying the text information in the text image to form an early warning message and send it to the user terminal, so that the user terminal can control the transaction of the user terminal according to the early warning information, avoiding the problem of transaction abnormality caused by transactions in the fault stage, reducing labor costs and improving user experience.

[0052] In an optional embodiment, the target website includes an official website and a social networking website. Figure 2 As shown, the step S100 of detecting the announcement information of the target website based on the link of the target website includes:

[0053] S111: Detecting announcement information of the official website based on the link of the official website through a first detection rule.

[0054] S112: Detect announcement information of the social networking site based on the link of the social networking site by using a second detection rule.

[0055] Specifically, it is understandable that financial institutions usually issue fault announcement information through official websites when the system upgrades and actively stops service or fails. These announcement information are closely related to the transaction services provided by financial institutions and are regular. Based on this, a first detection rule targeted at the official website can be set to regularly detect the announcement information released by the official website. In addition, due to other reasons such as natural disasters and sudden communication failures, related social networking sites will also release fault announcement information. Based on this, a second detection rule corresponding to the social networking site can be set to regularly detect the announcement information released by the social networking site. Among them, the official website may include websites such as financial institutions and transaction parties, and the social networking site may include websites such as news and social platforms.

[0056] Among them, different detection rules can be set for different websites according to the importance of the target website and the accuracy of the announcement information. For example, for official websites, the importance of their announcement information is high, the information accuracy is high, and the release of announcement information is usually regular and notified in advance. It can be set to detect once a day at 20:00 to provide early warning. Of course, in actual applications, the corresponding first detection rule can be set according to the release regularity of announcement information on different websites, and this application does not limit this.

[0057] The update time of information on social networking sites is uncertain and unpredictable, so a second detection rule can be set to detect at regular intervals 24 hours a day. Optionally, the importance of the collected social networking sites can be classified to increase the detection frequency of social networking sites with high importance. For example, a second detection rule can be set to detect once every 10 minutes for social networking sites with high importance levels, and a second detection rule can be set to detect once an hour for social networking sites with low importance levels.

[0058] In an optional embodiment, if Figure 3 As shown, the step S100 detects keywords of the announcement information of the target website based on the link of the target website to determine whether the announcement information is fault announcement information, including:

[0059] S121: Accessing the target website based on the link of the target website.

[0060] S122: Detecting target keywords in preset keywords in the announcement information of the target website.

[0061] S123: Determine whether the announcement information is fault announcement information based on the target keyword.

[0062] Specifically, the target website to be detected can be collected in advance, and the link of the target website can be collected to automatically access the target website to detect the announcement information on the target website. Among them, the link of the target website can be the URL of the target website. Of course, in actual application, other link forms of the target website can be determined according to actual conditions to achieve automatic access to the target website and keyword detection.

[0063] Among them, the keywords may include keywords of target website announcement information such as system version upgrade, system failure or network failure. In specific examples, the keywords may include about, respect, customer, bank, our bank, system, communication, failure, upgrade, maintenance, shutdown, suspension, service, time, year, month, day, personal online banking, personal mobile banking, corporate online banking, corporate mobile banking, telephone banking, bank-enterprise interconnection, counter, self-service equipment, business outlets, inconvenience, question, call, please understand and hereby announce, etc.

[0064] In an optional embodiment, if Figure 4 As shown, the step S123 determines whether the announcement information is fault announcement information based on the target keyword, including:

[0065] S1231: Determine a total weight based on each of the target keywords and the corresponding preset weight.

[0066] S1232: If the total weight is greater than the preset weight standard value, the announcement information is fault announcement information.

[0067] Specifically, it is understandable that the necessary keywords included in different fault announcement information can be obtained by analyzing the characteristics of historical fault announcement information, and at least one necessary keyword corresponding to different fault announcement information can be set as a target keyword to form a corresponding judgment standard. When determining whether the announcement information is fault announcement information, it can be determined whether the announcement information is fault announcement information by detecting whether the announcement information includes all the target keywords in the judgment standard.

[0068] However, the flexibility of the judgment standard of this fault announcement information is not high, which may cause some fault announcement information with some changes in the description to be unable to be recognized. Therefore, in this optional implementation, in order to improve the recognition rate of fault announcement information, a corresponding preset weight can be set for each target keyword, and the corresponding weight can be set according to the importance of different target keywords and whether they can be changed into target keywords. When determining whether the announcement information is fault announcement information, the target keyword detected is multiplied by the corresponding preset weight and the sum is obtained to obtain the total weight, and whether the announcement information is fault announcement information is determined based on whether the total weight is greater than the preset weight standard value. Among them, in actual applications, those skilled in the art can set the target keyword, its weight and weight standard value according to actual conditions, and this application does not limit this.

[0069] In an optional implementation manner, the step S200 of acquiring the text image corresponding to the announcement information includes:

[0070] S210: Acquire a text image corresponding to the announcement information based on preset screenshot setting information through crawler technology.

[0071] Specifically, it is understandable that the text image corresponding to the target website fault announcement information can be automatically crawled by crawler technology. Screenshot setting information can be preset to set the form, range and granularity of crawler crawling to obtain the required text image. Among them, crawler technology is a conventional technical means in this field and will not be repeated here.

[0072] Among them, in one or more embodiments, the announcement information of the target website appears in the form of a title, and whether the announcement information is fault announcement information can be determined by detecting the announcement information in the form of a title. If so, the lower-level link corresponding to the announcement information is accessed through crawler technology, and the specific content of the fault announcement information is intercepted on the announcement information web page to which the lower-level link of the announcement information jumps to obtain a text image.

[0073] In an optional embodiment, if Figure 5 As shown, the step S300 of identifying text information in the text image and forming warning information based on the text information includes:

[0074] S310: Process the text image to obtain local features and global features.

[0075] S320: Recognize the local features and the global features through OCR technology to obtain text information.

[0076] S330: generating warning information according to the text information and the current time.

[0077] Specifically, in order to improve the accuracy of text information recognition in text images, the text images can be preprocessed first, which may include noise removal, image enhancement, grayscale and binarization. Then, by converting the image preprocessed information into feature data that can be processed by the computer, local features and global features are extracted by segmenting the intervals between characters in the information, with the goal of providing each feature to OCR for separate recognition. Finally, the OCR recognition engine is used to match and recognize the extracted features, including text information such as bank name, announcement content, business type and Beijing time.

[0078] Among them, when forming the early warning information, since some fault announcement information is a forecast of future faults, when forming the early warning information, on the one hand, it is necessary to give an early warning of the fault of the financial institution, and on the other hand, it is necessary to consider the current time to determine whether the fault has occurred. Therefore, the early warning information can be formed according to the text information and the current time, and the current time can be considered to give an early warning of the fault of the financial institution, avoiding useless fault warnings to users and improving user experience.

[0079] In an optional implementation manner, the warning information includes the current fault status. The step S300 of sending the warning information to the user terminal includes:

[0080] S340: If the current fault status is effective, the warning information is sent to the user terminal.

[0081] Specifically, a warning text can be formed based on the recognized text information, and the current fault status can be determined based on the effective time of the financial institution fault. Whether to send a warning message to the user terminal is determined based on whether the current fault status is effective, so as to optimize the financial institution warning method. For example, in a specific example, the format of the warning message can be shown in Table 1. In the "status" column, the recognized "time" is compared with the current time: if the current time is within the "time", the fault status is effective; if the current time is less than the "time", the status is invalid; if the current time is greater than the "time", the status is to be effective. It is assumed that the current time is 6:15 on April 15th.

[0082] Table 1

[0083]

[0084]

[0085] The present application is further explained below through a specific example. In this specific example, an employee of a financial institution entered the subway station from Line 8A on April 16 at 5:23, and exited the station at Metro Station B at 6:19 by scanning the subway QR code of an online payment platform. At 10:57, the employee returned to Metro Station B and prepared to scan the QR code to enter the station. At this time, the mobile phone prompted that there was an unpaid record of 6 yuan for the ride, and it must be paid first before scanning the code to enter the station. The employee was in a hurry to take the ride, so he paid 6 yuan first (payment time 10:58), and then scanned the QR code to enter the station. After exiting Metro Station A, the employee raised two questions. One was why he failed to pay successfully when he exited Metro Station B normally in the morning, and the other was why he paid 6 yuan instead of 5 yuan. Because the customer also purchased a subway U-hui ticket, he enjoys a 30% discount, with a maximum discount of 1 yuan. The employee consulted the customer service of the mobile network payment platform. After multiple searches, the customer service found that the reason for the failure of the outbound payment was that the "card issuer refused the transaction" and that the fare discount was not available because the payment was delayed. However, the customer service said that they did not know the specific reason for the rejection and asked the customer to contact the card issuer. At this time, the employee realized that it might be related to the upgrade of the bank system this morning, because the payment card was bound to the bank card. Then he checked the bank's announcement information. The bank issued a system upgrade notice on the afternoon of April 14, "System upgrade and maintenance from 4:00 to 8:30 on April 16. During this period, our online banking, telephone banking, mobile banking, bank-enterprise interconnection, counters, self-service equipment and other related systems will be suspended..." Therefore, there are problems in the prior art: the customer service post of the network payment platform did not know that the bank had a system upgrade on that day, and did not know the specific reason why the card issuer refused the transaction. Second, because it was during the upgrade period, the card issuer refused to pay, but after the system upgrade was completed and normal service was provided to the outside world, since it was not due to personal reasons of the passenger, the delayed payment should still enjoy the fee discount, that is, it should not be deducted 6 yuan, but 5 yuan. Third, whether the online payment platform APP has an announcement on the homepage that XXX financial institution has a system upgrade on that day, which may cause delayed payment or inability to pay.

[0086] The financial institution fault warning method of the present application first collects website information keywords such as system upgrades or network failures of the issuing bank and URL sets of each commercial bank website, such as URLs of all bank websites and URLs of other corporate, social and other websites, as well as keywords. Keywords can be system upgrades, suspension of services, communication failures, etc. Keywords: about, respect, customer, bank, our bank, system, communication, failure, upgrade, maintenance, commissioning, shutdown, suspension, service, Beijing, time, year, month, day, personal online banking, personal mobile banking, corporate online banking, corporate mobile banking, telephone banking, bank-enterprise interconnection, counter, self-service equipment, business outlets, inconvenience, question, call, please understand and hereby announce, etc.

[0087] Store the collected target website URL sets and search keywords. Set rules include the announcement information containing keywords such as about, respect, customer, bank, our bank, system, communication, failure, upgrade, maintenance, shutdown, suspension, service, Beijing, time, year, month, day, personal online banking, personal mobile banking, corporate online banking, corporate mobile banking, telephone banking, bank-enterprise interconnection, counter, self-service equipment, business outlets, inconvenience, question, call, please understand, and hereby announce. According to the importance of the target website and the accuracy of the announcement information, the official website URLs of the internal systems of major card issuing banks are stored as the first category of information, and the URLs of major social networking sites are stored as the second category of information.

[0088] According to the importance of the search keywords, the precise hit rate is improved, and the weights of each keyword group are distinguished and sorted from small to large according to the weight, as shown in Table 2.

[0089] Table 2

[0090] Serial number Keywords Weight 1 about 1 2 Respect 1 3 client 1 4 Personal Internet Banking 2 5 Personal Mobile Banking 2 6 bank 2 7 system 2 8 communication 3 9 Fault 3 10 upgrade 3 11 maintain 3 12 Downtime 3 13 pause 3 14 Serve 3 ... ... ...

[0091] In order to improve crawling efficiency, for the first-class information collected in the first step, the commercial bank website announcement information is set to be crawled once every day at 20:00. This kind of information is proactively announced in advance by the commercial bank and is predictable. For the second-class information, the announcement information on the social networking sites outside the bank is crawled once a day for 24 hours on all the mainstream social networking sites collected in the first step. This kind of information is sudden and unpredictable.

[0092] Search using keywords on the websites of commercial banks and mainstream social websites, retrieve the announcements published on various network platforms, and search the announcements published based on keywords. If at least one of the following information is found, such as about, respect, customer, bank, our bank, system, communication, failure, upgrade, maintenance, commissioning, shutdown, suspension, service, Beijing, time, year, month, day, personal online banking, personal mobile banking, corporate online banking, corporate mobile banking, telephone banking, bank-enterprise interconnection, counter, self-service equipment, business outlets, inconvenience, question, call, sorry, and hereby announce, add the weights and compare with the assumed preset value of 5. If it is greater than or equal to the preset value, the target is hit. For example, if personal online banking is hit with 2 points and shutdown is hit with 3 points, the hit announcement information will be included in the next step of processing.

[0093] According to the acquired text image, the warning information is formed and automatically pushed to the user terminal. The format of the text image can be:

[0094] The system will be upgraded and maintained from 4:00 to 8:30 on April 16, 2023. During this period, our online banking, telephone banking, mobile banking, bank-enterprise interconnection, counters, self-service equipment and other related systems will be suspended. We apologize for the inconvenience.

[0095] Announcement

[0096] China XX Bank Co., Ltd.

[0097] April 14, 2023

[0098] In order to improve the accuracy of text recognition, the acquired image is preprocessed, including noise removal, image enhancement, grayscale, binarization, etc. The text information after image preprocessing is converted into feature data that can be processed by the computer, and the local features and global features are extracted by segmenting the intervals between characters in the second text information, with the purpose of providing each feature to OCR for separate recognition. The extracted features are matched and recognized using the OCR recognition engine, including the bank name "China XX Bank Co., Ltd.", the announcement content "System upgrade and maintenance from 4:00 to 8:30 on April 16, 2023, during which our online banking, telephone banking, mobile banking, bank-enterprise interconnection, counter, self-service equipment and other related systems will be suspended. We apologize for the inconvenience", business type "online banking, telephone banking, mobile banking, bank-enterprise interconnection, counter, self-service equipment", Beijing time "April 16, 2023 4:00 to 8:30" and other text information. According to the text recognition results, an early warning report is automatically generated and sent to the customer service post, the format of which is shown in Table 1 below. In the "status" column, the identified "time" is compared with the current time: if the current time is within the "time", the status is effective; if the current time is less than the "time", the status is expired; if the current time is greater than the "time", the status is pending. The format of the warning information can be shown in Table 3 (assuming the current time is 6:19 on April 16).

[0099] Table 3

[0100]

[0101] This application uses web crawler technology to proactively, quickly and comprehensively search for announcement information that affects services, and to warn of faults to control the transaction process, thereby avoiding the time-consuming and laborious problem of manually querying information, thereby improving customer experience. Through OCR text recognition technology, situations in which faults affect transactions are directly presented to improve customer service and reduce customer complaints. When a card-issuing bank suspends services due to system upgrades or network failures and is unable to enjoy deduction discounts, the financial institution's terminal application can proactively identify and promptly take measures such as giving customers discounts or delaying transactions to control transactions at the user's terminal, reducing a large number of customer complaints or inquiries and improving customer satisfaction.

[0102] Based on the same principle, the present application also discloses a failure warning device for a financial institution. Figure 6As shown, in this embodiment, the device includes a fault detection module 11, an image acquisition module 12 and a fault warning module 13.

[0103] The fault detection module 11 is used to detect the announcement information of the target website based on the link of the target website to determine whether the announcement information is fault announcement information.

[0104] The image acquisition module 12 is used to acquire the text image corresponding to the announcement information.

[0105] The fault warning module 13 is used to identify the text information in the text image and form warning information based on the text information, and send the warning information to the user terminal so that the user terminal controls the transaction of the user terminal based on the warning information.

[0106] In an optional embodiment, the target website includes an official website and a social networking website. The fault detection module 11 is used to detect the announcement information of the official website based on the link of the official website through a first detection rule; and detect the announcement information of the social networking website based on the link of the social networking website through a second detection rule.

[0107] In an optional embodiment, the fault detection module 11 is used to access the target website based on the link of the target website; detect the target keyword existing in the preset keywords in the announcement information of the target website; and determine whether the announcement information is fault announcement information based on the target keyword.

[0108] In an optional implementation, the fault detection module 11 is used to determine a total weight based on each of the target keywords and the corresponding preset weights; if the total weight is greater than a preset weight standard value, the announcement information is a fault announcement information.

[0109] In an optional implementation, the image acquisition module 12 is used to acquire the text image corresponding to the announcement information based on preset screenshot setting information through crawler technology.

[0110] In an optional embodiment, the fault warning module 13 is used to process the text image to obtain local features and global features; identify the local features and the global features through OCR technology to obtain text information; and form warning information based on the text information and the current time.

[0111] In an optional implementation manner, the warning information includes a current fault state. The fault warning module 13 is configured to send the warning information to the user terminal if the current fault state is effective.

[0112] Since the principle of solving the problem by the device is similar to that of the above method, the implementation of the device can refer to the implementation of the method and will not be repeated here.

[0113] An embodiment of the present application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the computer program.

[0114] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0115] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer programs to produce the systems, devices, modules or units described in the above embodiments, which can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer device, and specifically, the computer device can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0116] In a typical example, the computer device specifically includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method executed by the client as described above is implemented; or, when the processor executes the program, the method executed by the server as described above is implemented.

[0117] Reference below Figure 7 , which shows a schematic diagram of the structure of a computer device 600 suitable for implementing an embodiment of the present application.

[0118] like Figure 7 As shown, the computer device 600 includes a central processing unit (CPU) 601, which can perform various appropriate operations and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0119] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal feedback device (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed as needed as the storage section 608.

[0120] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program tangibly contained on a machine-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 609, and / or installed from a removable medium 611.

[0121] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0122] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0123] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0124] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0125] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0126] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0127] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0128] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0129] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0130] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for early warning of failures in financial institutions, characterized in that: include: Detecting the announcement information of the target website based on the link of the target website to determine whether the announcement information is fault announcement information; If so, obtaining a text image corresponding to the announcement information; The text information in the text image is identified and warning information is formed based on the text information, and the warning information is sent to the user terminal so that the user terminal controls the transaction of the user terminal based on the warning information.

2. The financial institution failure early warning method according to claim 1, characterized in that: The target websites include official websites and social networking websites; The detecting of the announcement information of the target website based on the link of the target website includes: Detecting announcement information of the official website based on the link of the official website through a first detection rule; The announcement information of the social networking site is detected based on the link of the social networking site through the second detection rule.

3. The financial institution failure early warning method according to claim 1, characterized in that: The step of detecting keywords of the announcement information of the target website based on the link of the target website to determine whether the announcement information is fault announcement information comprises: Accessing the target website based on the link of the target website; Detecting target keywords in the announcement information of the target website that are present in preset keywords; Based on the target keyword, it is determined whether the announcement information is fault announcement information.

4. The financial institution failure early warning method according to claim 3, characterized in that: The determining whether the announcement information is fault announcement information based on the target keyword includes: Determine a total weight based on each of the target keywords and the corresponding preset weights; If the total weight is greater than the preset weight standard value, the announcement information is fault announcement information.

5. The financial institution failure early warning method according to claim 1, characterized in that: The obtaining of the text image corresponding to the announcement information comprises: The text image corresponding to the announcement information is obtained based on preset screenshot setting information through crawler technology.

6. The financial institution failure early warning method according to claim 1, characterized in that: The identifying text information in the text image and forming warning information based on the text information includes: Processing the text image to obtain local features and global features; Recognize the local features and the global features through OCR technology to obtain text information; A warning message is generated according to the text message and the current time.

7. The financial institution failure early warning method according to claim 6, characterized in that: The warning information includes the current fault status; The sending of the warning information to the user terminal comprises: If the current fault status is effective, the warning information is sent to the user terminal.

8. A failure warning device for a financial institution, characterized in that: include: A fault detection module, used to detect the announcement information of the target website based on the link of the target website to determine whether the announcement information is fault announcement information; An image acquisition module, used for acquiring a text image corresponding to the announcement information; The fault warning module is used to identify the text information in the text image and form warning information based on the text information, and send the warning information to the user terminal so that the user terminal controls the transaction of the user terminal based on the warning information.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images