Disclosure of Invention
The invention aims to provide an automatic approval method, device, equipment and medium based on a picture processing interface, so as to improve the efficiency, accuracy, reliability and the like of automatic approval according to the contents of a form.
The above purpose is achieved by the following technical scheme:
according to one aspect of the invention, the invention provides an automatic approval method based on a picture processing interface, which comprises the following steps:
acquiring an identity document photo uploaded by a filling user;
invoking a picture processing interface which is pre-established with connection to carry out information identification and tampering identification processing on the identity document photo, and giving a picture processing result score; according to the historical success rate of the picture processing interface, determining that the final result depends on the specific gravity Weight of the picture processing interface, wherein Weight is more than or equal to 0 and less than or equal to 1; calculating to obtain the final score of the form according to the score of the picture processing result and the proportion of the final result depending on a picture processing interface;
and judging whether the final score is higher than a preset threshold value, and if so, entering an automatic approval process. Optionally, the picture processing interface which is connected in advance is called to carry out information identification and tamper identification processing on the identity document photo, and a picture processing result score is given; determining that the final result depends on the Weight of the picture processing interface according to the historical success rate of the picture processing interface, wherein the Weight is more than or equal to 0 and less than or equal to 1; according to the score of the picture processing result and the proportion of the final result depending on the picture processing interface, the step of calculating the final score of the form comprises the following steps:
Calling a big data PS detection interface to identify information on the identity document photo and carrying out falsification identification to obtain image pixel level characteristics, obtaining falsification conditions of pictures and characters according to the image pixel level characteristics, and giving scores of the big data PS detection interface according to the falsification conditions of the pictures and the characters;
determining the proportion of the final result depending on the big data PS detection interface according to the historical success rate of the big data PS detection interface;
multiplying the specific gravity of the final result depending on the big data PS detection interface by the big data PS detection interface score to obtain a third mode detection score, and taking the third mode detection score as the final score of the filling form.
Optionally, the picture processing interface which is connected in advance is called to carry out information identification and tamper identification processing on the identity document photo, and a picture processing result score is given; determining that the final result depends on the Weight of the picture processing interface according to the historical success rate of the picture processing interface, wherein the Weight is more than or equal to 0 and less than or equal to 1; according to the score of the picture processing result and the proportion of the final result depending on the picture processing interface, the step of calculating the final score of the form comprises the following steps:
Calling an OCR picture recognition interface to carry out OCR picture recognition on the information on the identity document photo, judging the accuracy of uploading the identity document photo according to the image recognition characteristics, and giving an OCR picture recognition score;
calling a big data PS detection interface to identify information on the identity document photo, performing tampering identification, and giving a score of the big data PS detection interface;
determining the final result depending on the specific gravity of the big data PS detection interface according to the historical success rate of the big data PS detection interface, and calculating the difference between the specific gravity and 1, wherein the difference is a non-negative number;
multiplying the specific gravity by the big data PS detection interface score to obtain a third mode detection score; multiplying the difference value with the OCR picture recognition score to obtain a second mode detection score;
and calculating to obtain a final score of the form according to the third mode detection score and the second mode detection score.
Further, the calculation formula of the final score of the form is:
S＝(S2 *(1-Weight)+S3 *Weight)/2；
wherein S is the final score of the form, S2 For OCR picture recognition score, S3 For the big data PS detection interface score, weight is the proportion of the final result dependent big data PS detection interface.
Optionally, the automatic approval method based on the picture processing interface further includes: performing face recognition calculation on the form filling user to obtain a face recognition score, namely a first mode detection score; and then calculating to obtain the final score of the form according to the score of the picture processing result, the proportion of the final result depending on the picture processing interface and the first mode detection score.
Further, the step of calculating the final score of the form according to the score of the picture processing result, the specific gravity of the final result depending on the picture processing interface, and the first mode detection score includes:
calling an OCR picture processing interface to carry out OCR picture recognition on the information on the identity document picture, judging the accuracy of uploading the identity document picture according to the image recognition characteristics, and giving an OCR picture recognition score;
calling a big data PS detection interface to identify information on the identity document photo, performing tampering identification, and giving a score of the big data PS detection interface;
determining the final result depending on the specific gravity of the big data PS detection interface according to the historical success rate of the big data PS detection interface, and calculating the difference between the specific gravity and 1, wherein the difference is a non-negative number;
Multiplying the difference value with the OCR picture recognition score to obtain a second mode detection score; multiplying the specific gravity by the big data PS detection interface score to obtain a third mode detection score;
according to the first mode detection score, the second mode detection score and the third mode detection score, calculating to obtain a final score of the form, wherein a calculation formula is as follows:
S＝(S1 +S2 *(1-Weight)+S3 *Weight)/2；
wherein S is the final score of the form, S1 For face recognition score, S2 For OCR picture recognition score, S3 For the big data PS detection interface score, weight is the proportion of the final result dependent big data PS detection interface.
Optionally, after the step of determining whether the final score is higher than a preset threshold, if yes, entering an automatic approval process, the method further includes: and updating the proportion of the final result dependent picture processing interface in real time according to the success rate of the automatic approval result.
According to another aspect of the present invention, an automatic approval device based on a picture processing interface is provided, the access device includes:
the acquisition unit is used for acquiring the identity document photo uploaded by the form filling user;
the computing unit is used for calling a picture processing interface which is pre-established to perform information identification and tamper identification processing on the identity document photo and giving a picture processing result score; according to the historical success rate of the picture processing interface, determining that the final result depends on the specific gravity Weight of the picture processing interface, wherein Weight is more than or equal to 0 and less than or equal to 1; then, according to the score of the picture processing result and the proportion of the final result depending on a picture processing interface, calculating to obtain the final score of the form;
And the judging unit is used for judging whether the final score is higher than a preset threshold value, and if so, entering an automatic approval process.
Optionally, the access device further includes: and the face recognition unit is used for carrying out face recognition on the form filling user and calculating to obtain a face recognition score, namely a first mode detection score.
Further, the calculating unit is further configured to calculate a final score of the form according to the score of the picture processing result, the specific gravity of the final result dependent on the picture processing interface, and the first mode detection score.
According to still another aspect of the present invention, there is provided an electronic apparatus including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform steps in the picture processing interface based automatic approval method.
According to still another aspect of the present invention, there is further provided a computer readable storage medium having a computer program stored therein, the computer program when executed by a processor implementing each step in the automatic approval method based on a picture processing interface.
The beneficial effects are that: the invention discloses an automatic approval method, device, equipment and medium based on a picture processing interface, and relates to the technical field of artificial intelligence. According to the invention, the picture processing result score is obtained by calling the picture processing interface which is pre-established and connected to carry out identification and tampering identification processing based on technologies such as image detection/biological identification and the like, the final score of the form filling is obtained by calculating the picture processing result score and the historical result of automatic approval depending on the specific gravity of the picture processing interface, and then whether the automatic approval process is entered is judged according to the final score and the preset threshold value, so that the accuracy of automatic approval is improved, the reliability of automatic approval according to the final score of the online appointment form filling content is improved, the approval efficiency of banks is improved, and the labor cost of manual approval of personnel at banking sites for appointment form filling information is reduced.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention:
fig. 1 schematically shows a flow chart of an automatic approval method based on a picture processing interface according to an exemplary embodiment of the present invention. As shown in fig. 1, the automatic approval method based on the image processing interface provided by the invention includes:
and step S100, acquiring the identity document photo uploaded by the form filling user. The identity card photo can be a front-back photo of an identity card, a passport and the like.
Step S200, invoking a picture processing interface which is pre-established and connected to perform picture information identification and tamper identification processing on the identity document photo, and giving a picture processing result score; according to the historical success rate of the picture processing interface, determining that the final result depends on the specific gravity Weight of the picture processing interface, wherein Weight is more than or equal to 0 and less than or equal to 1; and calculating to obtain the final score of the form according to the score of the picture processing result and the proportion of the final result depending on the picture processing interface. The picture processing interface which is pre-established with connection can be a picture processing interface such as a big data PS detection interface, an OCR picture recognition interface and the like; the picture processing result scores are calculated in percentage. The historical success rate of the picture processing interface is determined according to the number ratio of identity document photos which are not required to be re-uploaded when the online service is handled on line after the online form filling user uploads the identity document photos, wherein the larger the number ratio of the identity document photos which are not required to be re-uploaded is, the larger the specific gravity of the final result depending on the picture processing interface is, and the closer to 1 is. Further, the bank can change the Weight in real time according to the success rate of the subsequent picture processing interface judgment.
And step S300, judging whether the final score is higher than a preset threshold value, and if so, entering an automatic approval process.
According to the invention, the final result of automatic approval is calculated according to the historical success rate of the picture processing interface and depends on the specific gravity of the picture processing interface, then the final score of the form filling is calculated according to the specific gravity and the score of the picture processing result obtained by calling the picture processing interface based on the image detection technology, and finally the final score is compared with the preset threshold value, so that the flow of automatic approval according to the form filling content in the online reservation process is realized, the approval efficiency of banks is improved, the labor cost of manual approval of bank website personnel is saved, the reliability of automatic approval according to the form filling content in the online reservation process is improved, and the accuracy of automatic approval is improved.
Because the big data PS detection interface has a certain failure probability, the invention calculates the specific gravity of the final result depending on the big data PS detection interface according to the historical processing success rate so as to improve the reliability judgment of the identity document information.
In an alternative embodiment, in step S200, specifically, as shown in fig. 2, the method includes the following steps:
step S211, calling a big data PS detection interface to identify and tamper the information on the identity document photo to obtain image pixel level characteristics, and obtaining tamper conditions of the picture and the text according to the image pixel level characteristics; according to the tampering condition of the pictures and the characters, giving out big data PS detection Interface score, i.e. tamper identification score S3 . The information on the identity document photo mainly comprises image information and text information, and the text information can comprise: name, birth year, date, home address, certificate validity period, identity number such as identity card number, etc. The embodiment of the invention adopts a picture identification system to finish the falsification identification of the information, namely judging whether picture information such as personal head portraits and text information such as home addresses on identity document photos are considered falsified or not. In the step of giving the tamper identification score according to the tamper condition, tamper detection is taken as an example for the identity card photo, the input data are picture data comprising a portrait plane and picture data comprising a certification authority plane, and the tamper condition mainly outputs three conditions of tamper, no tamper and failure. In the tampering identification process, whether the picture or the text is considered tampered or not is identified according to the pixel level. The tamper authentication process is a function of a big data PS detection interface that returns a result of successful or failed picture identification and details of the identification, for example, the details are as follows:
when the result is 'negative' (not tampered), the details are always 'no'.
When 'result' is 'positive' (tampered), the 'details' is an array containing one or more of the following:
- 'text_sampled' (text tampered)
Photo_sampled' (picture with tampering)
When ' result ' is ' failed, ' details ' is an array containing one of the following:
- 'failed_to_find' (no identification card found)
Specifically, the step of giving a tamper authentication score, that is, a big data PS probe interface score, may include the following according to the tamper condition:
if there is tampering: the characters or pictures are tampered, and the score of the big data PS detection interface is-50; the characters and the pictures are tampered, and the score of the big data PS detection interface is-100;
if no tampering exists: the characters and the pictures are not tampered, and the score of the big data PS detection interface is 100;
if failure occurs: the identity document photo is not identified, and the big data PS detection interface score is 0.
And S212, determining the proportion of the final result depending on the big data PS detection interface according to the historical success rate of the big data PS detection interface. Because the big data PS detection interface has a certain failure probability, the success rate of the big data PS detection interface can influence the score ratio of the big data PS detection interface, if the accumulated identity document photos uploaded by a user are more successful in the picture authentication system, namely the number of the identity document photos which are not required to be uploaded again is more when the user transacts business at a counter after uploading the identity document photos, the final result depends on the big data PS detection interface to be more specific, wherein the final result refers to the success rate of the whole automatic approval process.
S213, multiplying the specific gravity of the final result depending on the big data PS detection interface by the picture PS identification score to obtain a third mode detection score; and calculating a final score of the form according to the third mode detection score, for example, the third mode detection score can be used as the final score of the form. Further, the third pattern detection score may be directly used as the final score of the form in this embodiment. Of course, in order to further ensure accuracy, reliability, etc. of various information of the form-filling user, the third pattern detection score may be combined with results obtained through other processing techniques such as biological recognition-based living body detection, face recognition, and processing such as OCR image recognition in image detection, etc., so as to calculate a final score of the form-filling.
In an optional embodiment, in step S200, in the step of performing a picture processing on the information on the identity document photo and giving a score of a result of the picture processing, the picture processing may further include an OCR image recognition process. Specifically, in step S200, as shown in fig. 3, the following steps may be included:
Step S221, calling OCR picture processing interface to perform OCR picture recognition on the information on the identity document photo, and according to the image recognition characteristicsJudging the accuracy of uploading the identity document photo and giving out an OCR picture recognition score S2 . The OCR picture recognition is mainly used for recognizing the front and back photos of the uploaded identity document, and the comprehensive score of the picture can be given through percentage calculation mainly through the characteristics shown in the following table 1, such as a target area, an image rotation angle, brightness, a brightness value, ambiguity, an ambiguity value, whether unfilled corners, whether light spots, a light spot area duty ratio and the like, and the score is returned by an interface.
TABLE 1 Picture identification characteristics and corresponding scores
| obj area | Target area | string | Upper left and lower right angular coordinates of the target |
| rotation | Image rotation angle | string | Four angles: 0,90, 180, 270 |
| light | Brightness of light | string | 0 is abnormal, 1 is normal |
| lightValue | Brightness value | string | The value range is as follows: 0-1 |
| blur | Ambiguity degree | string | 0 is abnormal, 1 is normal |
| blurValue | Ambiguity values | string | The value range is as follows: greater than 0 |
| lack corner | Whether or not the corner is unfilled | string | 0 is abnormal, 1 is normal |
| is flare | Whether or not to light spot | string | 0 is abnormal, 1 is normal |
| flare ratio | Duty cycle of spot area | string | The value range is as follows: 0-1 |
Step S222, identifying and falsifying the information on the identity document photo through the big data PS detection interface, and giving a big data PS detection interface score.
Step S223, determining that the final result depends on the specific gravity of the big data PS detection interface according to the historical success rate of the big data PS detection interface, and calculating the difference between the specific gravity and 1, wherein the difference is a non-negative number; i.e., (1-weight).
Step S224, multiplying the difference value with the OCR picture recognition score to obtain a second mode detection score; and multiplying the specific gravity by the big data PS detection interface score to obtain a third mode detection score.
And step S225, calculating a final score of the form filling by adopting an effective score algorithm according to the third mode detection score and the second mode detection score.
In this embodiment of the present invention, the proportion of the OCR picture recognition score in the final score is inversely proportional to the proportion of the big data PS detection interface. Specifically, if the number of accumulated identity document photos uploaded by a user is larger in the picture authentication system, the specific gravity of the final result depending on the big data PS detection interface is adjusted and increased, and the OCR picture recognition score S is reduced2 The proportion of the final score is increased to increase the total score passing rate, reduce the subsequent repeated uploading process steps of the identity document photo, and realize the improvement of approval efficiency during business handling.
Illustratively, the calculation formula of the final score of the form may be:
S＝(S2 *(1-Weight)+S3 *Weight)/2；
wherein S is the final score, S2 For OCR picture recognition score, S3 For the big data PS detection interface score, weight is the proportion of the final result dependent big data PS detection interface.
In an alternative embodiment, the automatic approval method may further include: and carrying out face recognition on the form filling user. The face recognition part is a configurable module, and in a preferred embodiment, the automatic approval method includes a face recognition part, and the face recognition can be, for example, living body detection, such as detection according to limb motion, head motion, face motion, gesture recognition, voice recognition, and the like. Specifically, as shown in fig. 4, calculating the final score of the form after the face recognition of the form filling user may include the following steps:
step S400, face recognition is carried out on the form filling user, and a face recognition score, namely a first mode detection score, is obtained through calculation;
step S230, calculating a final score of the form by using an effective score algorithm according to the first mode detection score, the second mode detection score and the third mode detection score.
The automatic approval method based on the picture processing interface specifically comprises the following steps:
Acquiring an identity document photo uploaded by a filling user;
performing face recognition on the form filling user, and calculating to obtain a face recognition score, namely a first mode detection score;
determining the final result depending on the specific gravity of the big data PS detection interface according to the historical success rate of the big data PS detection interface, and calculating the difference between the specific gravity and 1, wherein the difference is a non-negative number;
tampering identification is carried out on information on the identity document photo through the big data PS detection interface, and the score of the big data PS detection interface is given; multiplying the specific gravity by the big data PS detection interface score to obtain a third mode detection score;
performing OCR picture recognition on the information on the identity document photo, judging the accuracy of uploading the identity document photo, and giving an OCR picture recognition score; multiplying the difference value with the OCR picture recognition score to obtain a second mode detection score;
and calculating to obtain a final score of the form by adopting an effective score algorithm according to the first mode detection score, the second mode detection score and the third mode detection score, wherein the calculation formula of the effective score algorithm can be as follows:
S＝(S1 +S2 *(1-Weight)+S3 *Weight)/2；
wherein S is the final score, S1 For face recognition score, S2 For OCR picture recognition score, S3 For the big data PS detection interface score, weight is the proportion of the final result dependent big data PS detection interface.
According to the preferred embodiment of the invention, three mode detection scores are adopted, a final score is obtained according to a calculation formula, and whether the automatic approval process is entered is judged by comparing the final score with a preset threshold value. The face recognition score, namely the first mode detection score, can reflect the reliability of the living body score; the OCR picture recognition score, namely the second mode detection score, can reflect the accuracy of uploading the identity document photo; the big data PS detection interface score, i.e. the third mode detection score, may reflect the reliability of the identity document. According to the preferred embodiment of the application, the authenticity and the validity of the user form filling content and the reliability of automatic approval according to the authenticity and the validity are verified through the combined detection of the three different modes of dynamic, static and dynamic; the accuracy of automatic approval is improved; the method omits a plurality of unnecessary links when the form filling user goes to the bank line to transact business, and greatly improves the approval efficiency of the whole bank.
In the embodiment of the invention, the face recognition can be finished by one or more of a background algorithm model, a silence detection data model, a video living body algorithm model and the like in a face recognition system.
In the embodiment of the invention, the identification of the human face is mainly preferably carried out by adopting an identification video mode for living body detection. For example, the face recognition score may be a live shot score. For example, whether the current shooting is living shooting or not may be determined according to the degree of change of the background light of the screen of the shooting device and the accuracy of the corresponding action made by the filling user according to the prompt of the shooting device, and a face recognition score may be given. The photographing device is, for example, a mobile phone or the like. The face recognition score in this embodiment of the present invention is mainly used to reflect the reliability that the photographic subject is a living body.
Optionally, the face recognition score may also be a composite score, for example, including the following steps: comparing and analyzing the face recognition result of the form filling user with the characteristics of various types of the turnup photos in the background algorithm model database through a background algorithm model to obtain scores belonging to the turnup characteristics; judging whether the photographed picture in face recognition is a directly photographed portrait or not through the silence detection data model, and giving a portrait photographed picture score; judging whether the current shooting is living shooting or not according to the change degree of the background light of the screen of the shooting equipment and the accuracy of corresponding actions made by a filling user according to the prompt of the shooting equipment through a video living body algorithm model, and giving a living body shooting score; and integrating the score belonging to the turnup characteristic, the score of the portrait shot photo and the score of the living body shot to obtain the face recognition score.
In the above embodiment of the present invention, the face recognition score, that is, the first mode detection score, may reflect the reliability of the living body score; the OCR picture recognition score or the second mode detection score may represent the accuracy of uploading identity document photos. The big data PS detection interface score or the third pattern detection score may reflect the authenticity of the identity document. The embodiment of the invention ensures the authenticity, the effectiveness and the reliability of the user form filling content through the combined detection of the three different modes of dynamic, static and dynamic; the accuracy of automatic approval is improved; the method omits a plurality of unnecessary links when the form filling user goes to the bank line to transact business, and greatly improves the approval efficiency of the whole bank.
In the present invention, in step S300, it is determined whether the final score is higher than a preset threshold, if yes, an automatic approval process is entered. The preset threshold can be set according to actual conditions, for example, the preset threshold can be set to 60 minutes, and if the final score exceeds 60 minutes, the real and effective form filling is judged, so that the automatic approval service can be rapidly completed.
In an optional embodiment, step S300, after determining that the final score is higher than the preset threshold and enters the step of the automatic approval process, further includes: and updating the proportion of the final result dependent picture processing interface in real time according to the success rate of the automatic approval result so as to enable the calculation of the subsequent final score to be more accurate. According to the embodiment of the invention, the specific gravity is adjusted in real time, so that the reliability of the final score is further improved, and the accuracy of automatic approval is further improved.
Fig. 5 schematically shows a structure of an automatic approval apparatus based on a picture processing interface according to an embodiment of the present invention. As shown in fig. 5, an automatic approval device based on a picture processing interface provided in the present application includes: an acquisition unit 100, a calculation unit 200, and a judgment unit 300.
The obtaining unit 100 is configured to perform a step of obtaining an identity document photo uploaded by a filling order user.
The computing unit 200 is configured to perform picture processing on the identity document photo, and give a score of a picture processing result; according to the historical success rate of the picture processing interface, determining that the final result depends on the specific gravity Weight of the picture processing interface, wherein Weight is more than or equal to 0 and less than or equal to 1; and then calculating to obtain the final score of the form according to the score of the picture processing result and the proportion of the final result depending on the picture processing interface.
The judging unit 300 is configured to execute the step of judging whether the final score is higher than a preset threshold, and if yes, entering an automatic approval process.
In an alternative embodiment, the apparatus may further include: and the face recognition unit is used for carrying out face recognition on the form filling user and calculating to obtain a face recognition score, namely a first mode detection score.
In an alternative embodiment, the computing unit 200 may include a picture processing module, a specific gravity determining module, a final score computing module, and the like.
The picture processing module is used for executing picture processing on the identity document photo and giving a picture processing score. The picture processing module is used for executing the steps of tamper identification of information on the identity document photo through the big data PS detection interface, obtaining tamper conditions, and giving scores of the big data PS detection interface according to the tamper conditions. The image processing module is used for performing OCR image recognition on the information on the identity document photo, judging the accuracy of uploading the identity document photo and giving an OCR image recognition score.
The specific gravity determining module is used for executing the step of determining that the final result depends on the specific gravity of the big data PS detection interface according to the historical success rate of the big data PS detection interface.
The final score calculation module is used for executing the step of calculating and obtaining a form filling final score according to the picture processing result score and the proportion of the final result depending on a picture processing interface; and the step of calculating the final score of the form according to the picture processing result score, the final result depending on the proportion of the picture processing interface and the first mode detection score.
Illustratively, in the step of performing calculation of the final score of the form according to the picture processing result score and the final result depending on the specific gravity of the picture processing interface, and the first mode detection score, the calculation formula may be:
S＝(S1 +S2 *(1-Weight)+S3 *Weight)/2；
wherein S is the final score of the form, S1 For face recognition score, S2 For OCR picture recognition score, S3 For the big data PS detection interface score, weight is the proportion of the final result dependent big data PS detection interface.
The face recognition score, i.e., the first mode detection score in this embodiment of the present invention, may reflect the reliability of the living body score; the OCR picture recognition score, or the second mode detection score, may represent the accuracy of uploading identity document photos. The big data PS detection interface score or the third pattern detection score may reflect the authenticity of the identity document. The embodiment of the invention ensures the authenticity, the effectiveness and the reliability of the user form filling content through the combined detection of the three different modes of dynamic, static and dynamic; the accuracy of automatic approval is improved; the method omits a plurality of unnecessary links when the form filling user goes to the bank line to transact business, and greatly improves the approval efficiency of the whole bank.
Fig. 6 schematically shows the structure of the electronic device of the present invention. As shown in fig. 6, the electronic device 1 may include: memory 11, processor 10, a bus, and a computer program stored in memory 11 and executable on said processor 10, such as an automated approval program 12. The processor 10, when executing the computer program, implements the steps of the automatic approval method based on a picture processing interface of the present invention. For example, the method is realized to acquire the identity document photo uploaded by the filling order user; performing picture processing on the identity document photo, and giving a score of a picture processing result; according to the historical success rate of the picture processing interface, determining that the final result depends on the specific gravity Weight of the picture processing interface, wherein Weight is more than or equal to 0 and less than or equal to 1; calculating to obtain the final score of the form according to the score of the picture processing result and the proportion of the final result depending on a picture processing interface; and judging whether the final score is higher than a preset threshold value, if so, entering the steps of automatic approval process and the like.
The memory 11 includes at least one type of readable storage medium including flash memory, a removable hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory may in some embodiments be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. The memory 11 may in other embodiments also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only for storing application software installed in the electronic device 1 and various types of data, such as codes of the automatic approval program 12, but also for temporarily storing data that has been output or is to be output.
The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device 1, connects respective components of the entire electronic device 1 using various interfaces and lines, executes or executes programs or modules stored in the memory 11, and invokes data stored in the memory 11 to perform various functions of the electronic device 1 and process data.
The bus may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.
It will be appreciated by a person skilled in the art that the electronic device 1 with the above-described components is not limiting of the electronic device 1, and may comprise fewer or more components, or may be combined with certain components, or may be arranged in different components. For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to each component, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.
Further, the electronic device 1 may also comprise a network interface, optionally the network interface may comprise a wired interface and/or a wireless interface (e.g. WI-FI interface, bluetooth interface, etc.), typically used for establishing a communication connection between the electronic device 1 and other electronic devices.
Optionally, the electronic device 1 may further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The automatic approval program 12 stored in the memory 11 of the electronic device 1 is a combination of instructions which, when run in the processor 10, may implement the steps of the method or may implement the functions of the units and/or modules, such as: the method comprises the steps of obtaining an identity document photo uploaded by a filling order user; performing picture processing on the identity document photo, and giving a score of a picture processing result; according to the historical success rate of the picture processing interface, determining that the final result depends on the specific gravity Weight of the picture processing interface, wherein Weight is more than or equal to 0 and less than or equal to 1; calculating to obtain the final score of the form according to the score of the picture processing result and the proportion of the final result depending on a picture processing interface; and judging whether the final score is higher than a preset threshold value, if so, entering the steps of automatic approval process and the like.
In the present invention, the modules/units integrated in the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as a stand alone product. The computer readable storage medium may be any tangible medium containing or storing a program or instructions thereon, where the computer program is stored to be executed by the processor 10, where the functions of each step in the automatic approval method based on a picture processing interface or each unit/module in the system according to the present invention are implemented by hardware related to the stored program instructions. For example, the method is realized to acquire the identity document photo uploaded by the filling order user; performing picture processing on the identity document photo, and giving a score of a picture processing result; according to the historical success rate of the picture processing interface, determining that the final result depends on the specific gravity Weight of the picture processing interface, wherein Weight is more than or equal to 0 and less than or equal to 1; calculating to obtain the final score of the form according to the score of the picture processing result and the proportion of the final result depending on a picture processing interface; and judging whether the final score is higher than a preset threshold value, if so, entering the steps of automatic approval process and the like. The computer readable medium may include, for example: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and device may be implemented in other manners. The system embodiments described above are merely illustrative, e.g., the division of the modules is merely a logical functional division, and other manners of division are possible in actual practice.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or modules recited in the apparatus claims can also be implemented by means of one unit or module in software or hardware. The terms second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.