Terminal access method and system based on stroke order, OCR and artificial intelligence

Abstract

The present invention provides a terminal access method and system based on stroke order, OCR and artificial intelligence, wherein the method comprises: obtaining an access request of a first terminal; parsing the access request, obtaining stroke order information input by a user and / or identification information recognized by OCR received by the first terminal; inputting the stroke order information and / or identification information into a pre-established verification model to verify the access request of the first terminal; when the verification passes, accepting the access of the first terminal, otherwise, rejecting the access of the first terminal. The terminal access method based on stroke order, OCR and artificial intelligence of the present invention verifies the access request based on the stroke order information and / or identification information input by the user when the terminal accesses the request, and grants access when the access request is valid, effectively avoiding the waste of network resources caused by the user accidentally clicking on an APP or website, and the big data platform can determine the identity of the terminal accesser based on the stroke order information and / or identification information, effectively protecting the privacy of the terminal holder.

Description

Technical Field

[0001] The present invention relates to the technical field of terminal access, and in particular to a terminal access method and system based on stroke order, OCR and artificial intelligence. Background Art

[0002] At present, during the operation of the big data platform, it is inevitable that there will be many terminal requests for access. The existing terminals that access the big data platform are websites, APPs, etc. The terminal access to the big data platform is only a verification between the terminal and the big data platform, such as the verification between the terminal identification number and the big data platform address. That is, when the user opens the APP or website, the terminal access to the big data platform is completed. It is inevitable that users will mistakenly click on the APP or website to access, which will cause a waste of network resources on the big data platform. In addition, the big data platform does not verify which user uses the terminal access, and cannot effectively protect the privacy of the terminal holder. Summary of the invention

[0003] One of the purposes of the present invention is to provide a terminal access method based on stroke order, OCR and artificial intelligence. When a terminal access request is made, the access request is verified based on the stroke order information and / or identification information input by the user. When the access request is valid, access is allowed, thereby effectively avoiding the waste of network resources caused by the user accidentally clicking on an APP or website, etc., and the big data platform can determine the identity of the terminal accessor based on the stroke order information and / or identification information, thereby effectively protecting the privacy of the terminal holder.

[0004] An embodiment of the present invention provides a terminal access method based on stroke order, OCR and artificial intelligence, including:

[0005] Obtaining an access request from a first terminal;

[0006] Parsing the access request, obtaining the stroke order information input by the user and / or the identification information recognized by OCR received by the first terminal;

[0007] Inputting the stroke order information and / or identification information into a pre-established verification model to verify the access request of the first terminal;

[0008] When the verification is successful, the access of the first terminal is accepted; otherwise, the access of the first terminal is rejected.

[0009] Preferably, the terminal access method based on stroke order, OCR and artificial intelligence also includes:

[0010] obtaining first parameter information of the first terminal,

[0011] Determine the access module to be called based on the first parameter information;

[0012] Accepting access of the first terminal through the access module;

[0013] The first parameter information includes: a terminal type, a type and model of an external device connected to the terminal, and models of various components of the terminal, or one or more combinations thereof.

[0014] Preferably, the terminal access method based on stroke order, OCR and artificial intelligence also includes:

[0015] obtaining the location information of the first terminal,

[0016] Obtaining access restriction conditions in an area where a first location corresponding to the positioning information is located;

[0017] Acquire second parameter information of all connected second terminals in the area where the current first location is located;

[0018] Acquire third parameter information of the first terminal;

[0019] Based on the second parameter information, the third parameter information and the restriction condition, determining whether to allow the first terminal to access the area where the first location is located;

[0020] When access by the first terminal is allowed within the area where the first location is located, accepting access by the first terminal;

[0021] When not allowed, obtain the restriction conditions and access status of the area adjacent to the area where the first location is located, determine the area accessible to the first terminal based on the access status and restriction conditions of the adjacent area, and send the area accessible to the first terminal to the first terminal.

[0022] Preferably, inputting the stroke order information and / or the identification information into a pre-established verification model to verify the access request of the first terminal includes:

[0023] Extracting characteristic values ​​of the stroke order information and / or the identification information, substituting the characteristic values ​​into a pre-established neural network model, obtaining a verification factor, querying a preset verification table, and when the verification factor exists in the verification table, the access request of the first terminal is verified to be successful;

[0024] or,

[0025] Constructing a verification vector based on the stroke order information and / or the identification information, matching the verification vector with a standard vector in a pre-established verification library, and when the matching degree between the verification vector and the standard vector is greater than a preset matching value, the access request of the first terminal is verified to be successful;

[0026] The matching degree calculation formula between the verification vector and the standard vector is as follows:

[0027]

[0028] Among them, Pq is the matching degree between the verification vector and the qth standard vector in the verification library; n is the dimension of the verification vector and the standard vector; a i,q is the data value of the ith dimension of the qth standard vector; b i is the data value of the i-th dimension of the verification vector;

[0029] The stroke order information includes: a stroke type, an order between stroke types, and parameter information of each stroke, or one or more combinations thereof;

[0030] The parameter information of each stroke includes: the position relationship parameters between the starting point, the end point, and a preset number of sampling points between the starting point and the end point of each stroke, and / or the handwriting force parameters of the starting point, the end point, and a preset number of sampling points between the starting point and the end point of each stroke;

[0031] The identification information includes: one or a combination of text, graphics, and symbols.

[0032] Preferably, the first terminal performs the following operations:

[0033] receiving a joint access preparation instruction input by a user;

[0034] Outputting a plurality of preset joint access templates for joint access;

[0035] Calling the joint access template selected by the user;

[0036] Sending a joint access query to at least one second terminal that complies with a first rule of the joint access template based on the joint access template;

[0037] receiving feedback from the second terminal regarding the inquiry;

[0038] When the feedback meets the second rule of the joint access template and / or reaches the start time preset in the joint access template, outputting a joint access start query;

[0039] Receiving a confirmation instruction from the user regarding the start of the joint access inquiry;

[0040] Receive handwriting input from the user;

[0041] Analyze handwriting to obtain stroke order information and recognition information;

[0042] Generate an access request based on the stroke order information and the identification information;

[0043] The first rule includes: a distance from the first terminal is less than a preset first distance value, a terminal of a preset type is within a preset space, and a distance from the first terminal is equal to a preset second distance value, or one or more combinations thereof;

[0044] The second rule includes: the number of second terminals that provide feedback is greater than a preset number value and / or the ratio of the number of second terminals that provide feedback of agreement to the number of second terminals that receive the inquiry is greater than a preset first ratio.

[0045] The present invention also provides a terminal access system based on stroke order, OCR and artificial intelligence, comprising:

[0046] A receiving module, used to obtain an access request from a first terminal;

[0047] A parsing module, used to parse the access request and obtain the stroke order information input by the user and / or the identification information recognized by OCR received by the first terminal;

[0048] The verification module is used to input the stroke order information and / or identification information into a pre-established verification model to verify the access request of the first terminal; when the verification is passed, the access of the first terminal is accepted, otherwise, the access of the first terminal is rejected.

[0049] Preferably, the terminal access system based on stroke order, OCR and artificial intelligence also includes:

[0050] A first parameter acquisition module is used to acquire first parameter information of a first terminal.

[0051] A calling module, configured to determine an access module to be called based on the first parameter information; and accept access of the first terminal through the access module;

[0052] The first parameter information includes: a terminal type, a type and model of an external device connected to the terminal, and models of various components of the terminal, or one or more combinations thereof.

[0053] Preferably, the terminal access system based on stroke order, OCR and artificial intelligence also includes:

[0054] A positioning module, used to obtain the positioning information of the first terminal,

[0055] A first condition acquisition module, used to acquire access restriction conditions permitted in an area where a first location corresponding to the positioning information is located;

[0056] A second parameter acquisition module, used to acquire second parameter information of all connected second terminals in the area where the current first location is located;

[0057] A third parameter acquisition module, used to acquire third parameter information of the first terminal;

[0058] A judgment module is used to judge whether the first terminal is allowed to access the area where the first location is located based on the second parameter information, the third parameter information and the restriction conditions; when the first terminal is allowed to access the area where the first location is located, accept the access of the first terminal; when not allowed, obtain the restriction conditions and access status of the area adjacent to the area where the first location is located, determine the area accessible to the first terminal based on the access status and restriction conditions of the adjacent area, and send the area accessible to the first terminal to the first terminal.

[0059] Preferably, the verification module performs the following operations:

[0060] Extracting characteristic values ​​of the stroke order information and / or the identification information, substituting the characteristic values ​​into a pre-established neural network model, obtaining a verification factor, querying a preset verification table, and when the verification factor exists in the verification table, the access request of the first terminal is verified to be successful;

[0061] or,

[0062] Constructing a verification vector based on the stroke order information and / or the identification information, matching the verification vector with a standard vector in a pre-established verification library, and when the matching degree between the verification vector and the standard vector is greater than a preset matching value, the access request of the first terminal is verified to be successful;

[0063] The matching degree calculation formula between the verification vector and the standard vector is as follows:

[0064]

[0065] Among them, P q is the matching degree between the verification vector and the qth standard vector in the verification library; n is the dimension of the verification vector and the standard vector; a i,q is the data value of the ith dimension of the qth standard vector; b i is the data value of the i-th dimension of the verification vector;

[0066] The stroke order information includes: a stroke type, an order between stroke types, and parameter information of each stroke, or one or more combinations thereof;

[0067] The parameter information of each stroke includes: the position relationship parameters between the starting point, the end point, and a preset number of sampling points between the starting point and the end point of each stroke, and / or the handwriting force parameters of the starting point, the end point, and a preset number of sampling points between the starting point and the end point of each stroke;

[0068] The identification information includes: one or a combination of text, graphics, and symbols.

[0069] Preferably, the first terminal performs the following operations:

[0070] receiving a joint access preparation instruction input by a user;

[0071] Outputting a plurality of preset joint access templates for joint access;

[0072] Calling the joint access template selected by the user;

[0073] Sending a joint access query to at least one second terminal that complies with a first rule of the joint access template based on the joint access template;

[0074] receiving feedback from the second terminal regarding the inquiry;

[0075] When the feedback meets the second rule of the joint access template and / or reaches the start time preset in the joint access template, outputting a joint access start query;

[0076] Receiving a confirmation instruction from the user regarding the start of the joint access inquiry;

[0077] Receive handwriting input from the user;

[0078] Analyze handwriting to obtain stroke order information and recognition information;

[0079] Generate an access request based on the stroke order information and the identification information;

[0080] The first rule includes: a distance from the first terminal is less than a preset first distance value, a terminal of a preset type is within a preset space, and a distance from the first terminal is equal to a preset second distance value, or one or more combinations thereof;

[0081] The second rule includes: the number of second terminals that provide feedback is greater than a preset number value and / or the ratio of the number of second terminals that provide feedback of agreement to the number of second terminals that receive the inquiry is greater than a preset first ratio.

[0082] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0083] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0085] Figure 1 Schematic diagram of a terminal access method based on stroke order, OCR and artificial intelligence in an embodiment of the present invention;

[0086] Figure 2 Schematic diagram of another terminal access method based on stroke order, OCR and artificial intelligence in an embodiment of the present invention;

[0087] Figure 3 The figure is a schematic diagram of a terminal access system based on stroke order, OCR and artificial intelligence in an embodiment of the present invention. DETAILED DESCRIPTION

[0088] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0089] The embodiment of the present invention provides a terminal access method based on stroke order, OCR and artificial intelligence, such as Figure 1 As shown, including:

[0090] Step S1: obtaining an access request from a first terminal;

[0091] Step S2: parsing the access request, obtaining the stroke order information input by the user and / or the identification information recognized by OCR received by the first terminal;

[0092] Step S3: inputting the stroke order information and / or identification information into a pre-established verification model to verify the access request of the first terminal; when the verification is passed, accepting the access of the first terminal, otherwise, rejecting the access of the first terminal.

[0093] The working principle and beneficial effects of the above technical solution are:

[0094] When a user uses the first terminal to access the cloud platform, he needs to input handwriting for access verification through a touch screen or an electronic pen, and the first terminal analyzes the handwriting to obtain stroke order information and / or identification information; the identification information is the text, graphics, characters, etc. recognized by the first terminal based on OCR (Optical Character Recognition) recognition technology; when the first terminal sends an access request to the cloud platform, the stroke order information and / or identification information is embedded in it and sent synchronously, and when the cloud platform receives the access request of the first terminal, the validity of the access request is verified based on the stroke order information and identification information in the access request; when the verification is passed, the access of the first terminal is allowed, and when the verification is not passed, it means that the access request is invalid, and the access of the first terminal is rejected, so as to eliminate invalid access requests. For example, the standard used by the cloud platform for verification can be the standard set by the cloud platform, such as the Chinese name and icon of the cloud platform, etc.; it can also be the verification pattern, graphics, text, etc. set by the user when registering. When the pattern set by the user when registering is used, the registered account of the user can be logged in at the first terminal synchronously, so as to complete the terminal access and account login in one step, simplify the user's operation, and improve the user's experience.

[0095] The terminal access method based on stroke order, OCR and artificial intelligence of the present invention verifies the access request based on the stroke order information and / or identification information input by the user when the terminal access request is made. When the access request is valid, access is allowed, thereby effectively avoiding the waste of network resources caused by the user accidentally clicking on an APP or website, etc., and the big data platform can determine the identity of the terminal accessor based on the stroke order information and / or identification information, thereby effectively protecting the privacy of the terminal holder.

[0096] In one embodiment, Figure 2 As shown, the terminal access method based on stroke order, OCR and artificial intelligence also includes:

[0097] Step S11: Acquire first parameter information of the first terminal,

[0098] Step S12: determining the access module to be called based on the first parameter information;

[0099] Step S13: accepting access from the first terminal through the access module;

[0100] The first parameter information includes: a terminal type, a type and model of an external device connected to the terminal, and models of various components of the terminal, or one or more combinations thereof.

[0101] The working principle and beneficial effects of the above technical solution are:

[0102] After access is granted, it is necessary to call the appropriate access module for the terminal according to the type of terminal and the functions it has, so that the cloud platform provides various users with multiple terminals to access the portal website and personalized service portal. The terminal devices support PC, mobile phones and other mobile devices, tablet computers (electronic schoolbags) and electronic whiteboards, etc. In addition, when the same type of terminal accesses the cloud platform, when it is connected to a device with a writing board, the access module corresponding to the writing board is called, thereby realizing the rationalization of the access module and avoiding the waste of resources caused by loading redundant access functions.

[0103] In one embodiment, the terminal access method based on stroke order, OCR and artificial intelligence further includes:

[0104] obtaining the location information of the first terminal,

[0105] Obtaining access restriction conditions in an area where a first location corresponding to the positioning information is located;

[0106] Acquire second parameter information of all connected second terminals in the area where the current first location is located;

[0107] Acquire third parameter information of the first terminal;

[0108] Based on the second parameter information, the third parameter information and the restriction condition, determining whether to allow the first terminal to access the area where the first location is located;

[0109] When access by the first terminal is allowed within the area where the first location is located, accepting access by the first terminal;

[0110] When not allowed, obtain the restriction conditions and access status of the area adjacent to the area where the first location is located, determine the area accessible to the first terminal based on the access status and restriction conditions of the adjacent area, and send the area accessible to the first terminal to the first terminal.

[0111] The working principle and beneficial effects of the above technical solution are:

[0112] Before allowing the first terminal to access and before the first terminal formally accesses, the cloud platform can also determine the impact of the first terminal on other terminals that have already accessed when accessing the area where it is located based on the positioning information of the first terminal. When there is an impact, the access situation and access restrictions of the adjacent area are determined, and the best accessible area for the first terminal is determined, and the user is reminded to access the corresponding area; wherein, the division of the area is divided by the cloud platform according to the distribution of access points (such as base stations); the restriction condition can be the network transmission speed, etc., and the second parameter information and the third parameter information can be the network transmission speed requirements of the terminal, etc. Through the division of the area and the judgment of the impact on the access of the first terminal during access, the operation of the terminals that have already accessed in the area is guaranteed. In addition, the best access area is provided for the first terminal to be accessed, the operating environment after the first terminal is accessed is guaranteed, and the user's access experience is improved.

[0113] In one embodiment, obtaining restriction conditions and access conditions of an area adjacent to an area where the first location is located, and determining an area accessible to the first terminal based on the access conditions and restriction conditions of the adjacent area, includes:

[0114] Get the current access status of adjacent areas.

[0115] Obtain the moving time from the first position to the adjacent area;

[0116] Get the historical access status trend chart of adjacent areas;

[0117] Determine, based on the current access situation, the third parameter information, the moving time, and the historical access situation trend chart, a second access situation of the adjacent area after the user moves to the adjacent area for access;

[0118] Based on the difference between the moving time, the restriction condition and the second access situation, the recommendation degree of the adjacent area is determined. The calculation formula is as follows:

[0119]

[0120] Where D is the recommendation degree, T is the moving time; C k is the value of the kth parameter of the constraint or the second access case, β k is the preset weight corresponding to the value of the kth parameter of the restriction condition or the second access situation; α is the preset weight corresponding to the movement time; and m is the number of parameters in the restriction condition or the second access situation.

[0121] The working principle and beneficial effects of the above technical solution are:

[0122] The recommendation degree of the adjacent area is calculated by the time it takes for the user to move to the adjacent area and the remaining margin of the restriction condition after moving to the adjacent area. Among them, the shorter the time it takes for the user to move to the adjacent area, the higher the recommendation degree and the larger the margin, which means that the possibility that the user can access the adjacent area after moving to the adjacent area is higher. The adjacent area with the highest recommendation degree is recommended to the user to provide the best access area for the user.

[0123] In one embodiment, inputting the stroke order information and / or the identification information into a pre-established verification model to verify the access request of the first terminal includes:

[0124] Extracting characteristic values ​​of the stroke order information and / or the identification information, substituting the characteristic values ​​into a pre-established neural network model, obtaining a verification factor, querying a preset verification table, and when the verification factor exists in the verification table, the access request of the first terminal is verified to be successful;

[0125] or,

[0126] Constructing a verification vector based on the stroke order information and / or the identification information, matching the verification vector with a standard vector in a pre-established verification library, and when the matching degree between the verification vector and the standard vector is greater than a preset matching value, the access request of the first terminal is verified to be successful;

[0127] The matching degree calculation formula between the verification vector and the standard vector is as follows:

[0128]

[0129] Among them, P q is the matching degree between the verification vector and the qth standard vector in the verification library; n is the dimension of the verification vector and the standard vector; a i,q is the data value of the ith dimension of the qth standard vector; b i is the data value of the i-th dimension of the verification vector;

[0130] The stroke order information includes: a stroke type, an order between stroke types, and parameter information of each stroke, or one or more combinations thereof;

[0131] The parameter information of each stroke includes: the position relationship parameters between the starting point, the end point, and a preset number of sampling points between the starting point and the end point of each stroke, and / or the handwriting force parameters of the starting point, the end point, and a preset number of sampling points between the starting point and the end point of each stroke;

[0132] The identification information includes: one or a combination of text, graphics, and symbols.

[0133] The working principle and beneficial effects of the above technical solution are:

[0134] This embodiment provides two solutions for verifying access requests. Solution 1: Use a pre-trained neural network model to extract the characteristic values ​​of stroke order information and / or identification information and input them into it to obtain a verification factor, and determine the final verification result based on the verification factor. Solution 2: Use a pre-established verification library to construct a verification vector based on stroke order information and / or identification information, match the verification vector with the standard vector in the verification library, and verify through the matching result. Furthermore, the stroke order information and identification information are combined to improve the verification accuracy, that is, when writing text, it is also possible not to follow the standard, and to use the stroke order as a verification point according to user customization, thereby improving the granularity of verification and realizing user-defined operability. In addition, taking into account the handwriting strength parameters between strokes, the recognition of the same stroke of the same word written by different people is realized, and the recognition of people based on the stroke order information and identification information scheme is improved.

[0135] In one embodiment, the first terminal performs the following operations:

[0136] receiving a joint access preparation instruction input by a user;

[0137] Outputting a plurality of preset joint access templates for joint access;

[0138] Calling the joint access template selected by the user;

[0139] Sending a joint access query to at least one second terminal that complies with a first rule of the joint access template based on the joint access template;

[0140] receiving feedback from the second terminal regarding the inquiry;

[0141] When the feedback meets the second rule of the joint access template and / or reaches the start time preset in the joint access template, outputting a joint access start query;

[0142] Receiving a confirmation instruction from the user regarding the start of the joint access inquiry;

[0143] Receive handwriting input from the user;

[0144] Analyze handwriting to obtain stroke order information and recognition information;

[0145] Generate an access request based on the stroke order information and the identification information;

[0146] The first rule includes: a distance from the first terminal is less than a preset first distance value, a terminal of a preset type is within a preset space, and a distance from the first terminal is equal to a preset second distance value, or one or more combinations thereof;

[0147] The second rule includes: the number of second terminals that provide feedback is greater than a preset number value and / or the ratio of the number of second terminals that provide feedback of agreement to the number of second terminals that receive the inquiry is greater than a preset first ratio.

[0148] The working principle and beneficial effects of the above technical solution are:

[0149] When there are multiple terminals that need to access the cloud platform in the same area or at the same time, a joint access operation mode can be used to improve the efficiency of cloud platform access; for example: a class needs to access the cloud platform for a mock exam. The teacher can use the first terminal to send a joint access inquiry to the second terminal used by the students. When the first terminal receives feedback from all the students' second terminals, the teacher uses the first terminal to access the cloud platform. After access, the cloud platform sends the mock exam paper to the second terminal, and can change the exam question number or question value according to different locations.

[0150] In one embodiment, the first terminal performs the following operations:

[0151] receiving a joint access preparation instruction input by a user;

[0152] Acquiring location information of the first terminal;

[0153] Determining whether the position corresponding to the positioning information is located at a preset second position;

[0154] When located at the second position, outputting a plurality of preset joint access templates for joint access;

[0155] Calling the joint access template selected by the user;

[0156] Sending a joint access query to at least one second terminal that complies with a first rule of the joint access template based on the joint access template;

[0157] receiving feedback from the second terminal regarding the inquiry;

[0158] When the feedback meets the second rule of the joint access template and / or reaches the start time preset in the joint access template, outputting a joint access start query;

[0159] Receiving a confirmation instruction from the user regarding the start of the joint access inquiry;

[0160] Receive handwriting input from the user;

[0161] Analyze handwriting to obtain stroke order information and recognition information;

[0162] Generate an access request based on the stroke order information and the identification information;

[0163] The first rule is that the position corresponding to the positioning information of the second terminal is a preset third position;

[0164] The second rule is that all the second terminals being inquired provide feedback and the feedback is agreement.

[0165] The working principle and beneficial effects of the above technical solution are:

[0166] The main application scenario of this embodiment is that the teacher initiates joint access for the exam at the preset second position (lectern). The teacher can initiate joint access only when the first terminal is in position, ensuring the cloud platform's judgment of the joint access scenario; the position corresponding to the location information of the second terminal in the first rule is the preset third position (for example: the student's desk position); ensuring that the terminal receiving the joint access inquiry is the student's terminal. The second terminal of the student who needs to take the exam is jointly connected to the cloud platform through the teacher's first terminal, improving access efficiency and improving the multimedia of education.

[0167] The present invention also provides a terminal access system based on stroke order, OCR and artificial intelligence, such as Figure 3 As shown, including:

[0168] Receiving module 1, used to obtain an access request from a first terminal;

[0169] Parsing module 2, used to parse the access request and obtain the stroke order information input by the user and / or the identification information recognized by OCR received by the first terminal;

[0170] Verification module 3 is used to input stroke order information and / or identification information into a pre-established verification model to verify the access request of the first terminal; when the verification is passed, the access of the first terminal is accepted, otherwise, the access of the first terminal is rejected.

[0171] The working principle and beneficial effects of the above technical solution are:

[0172] When a user uses the first terminal to access the cloud platform, he needs to input handwriting for access verification through a touch screen or an electronic pen, and the first terminal analyzes the handwriting to obtain stroke order information and / or identification information; the identification information is the text, graphics, characters, etc. recognized by the first terminal based on OCR (Optical Character Recognition) recognition technology; when the first terminal sends an access request to the cloud platform, the stroke order information and / or identification information is embedded in it and sent synchronously, and when the cloud platform receives the access request of the first terminal, the validity of the access request is verified based on the stroke order information and identification information in the access request; when the verification is passed, the access of the first terminal is allowed, and when the verification is not passed, it means that the access request is invalid, and the access of the first terminal is rejected, so as to eliminate invalid access requests. For example, the standard used by the cloud platform for verification can be the standard set by the cloud platform, such as the Chinese name and icon of the cloud platform, etc.; it can also be the verification pattern, graphics, text, etc. set by the user when registering. When the pattern set by the user when registering is used, the registered account of the user can be logged in at the first terminal synchronously, so as to complete the terminal access and account login in one step, simplify the user's operation, and improve the user's experience.

[0173] The terminal access system based on stroke order, OCR and artificial intelligence of the present invention verifies the access request based on the stroke order information and / or identification information input by the user when the terminal access request is made. When the access request is valid, access is allowed, thereby effectively avoiding the waste of network resources caused by the user accidentally clicking on an APP or website, etc., and the big data platform can determine the identity of the terminal accessor based on the stroke order information and / or identification information, thereby effectively protecting the privacy of the terminal holder.

[0174] In one embodiment, the terminal access system based on stroke order, OCR and artificial intelligence further includes:

[0175] A first parameter acquisition module is used to acquire first parameter information of a first terminal.

[0176] A calling module, configured to determine an access module to be called based on the first parameter information; and accept access of the first terminal through the access module;

[0177] The first parameter information includes: a terminal type, a type and model of an external device connected to the terminal, and models of various components of the terminal, or one or more combinations thereof.

[0178] The working principle and beneficial effects of the above technical solution are:

[0179] After access is granted, it is necessary to call the appropriate access module for the terminal according to the type of terminal and the functions it has, so that the cloud platform provides various users with multiple terminals to access the portal website and personalized service portal. The terminal devices support PC, mobile phones and other mobile devices, tablet computers (electronic schoolbags) and electronic whiteboards, etc. In addition, when the same type of terminal accesses the cloud platform, when it is connected to a device with a writing board, the access module corresponding to the writing board is called, thereby realizing the rationalization of the access module and avoiding the waste of resources caused by loading redundant access functions.

[0180] In one embodiment, the terminal access system based on stroke order, OCR and artificial intelligence further includes:

[0181] A positioning module, used to obtain the positioning information of the first terminal,

[0182] A first condition acquisition module, used to acquire access restriction conditions permitted in an area where a first location corresponding to the positioning information is located;

[0183] A second parameter acquisition module, used to acquire second parameter information of all connected second terminals in the area where the current first location is located;

[0184] A third parameter acquisition module, used to acquire third parameter information of the first terminal;

[0185] A judgment module is used to judge whether the first terminal is allowed to access the area where the first location is located based on the second parameter information, the third parameter information and the restriction conditions; when the first terminal is allowed to access the area where the first location is located, accept the access of the first terminal; when not allowed, obtain the restriction conditions and access status of the area adjacent to the area where the first location is located, determine the area accessible to the first terminal based on the access status and restriction conditions of the adjacent area, and send the area accessible to the first terminal to the first terminal.

[0186] The working principle and beneficial effects of the above technical solution are:

[0187] Before allowing the first terminal to access and before the first terminal formally accesses, the cloud platform can also determine the impact of the first terminal on other terminals that have already accessed when accessing the area where it is located based on the positioning information of the first terminal. When there is an impact, the access situation and access restrictions of the adjacent area are determined, and the best accessible area for the first terminal is determined, and the user is reminded to access the corresponding area; wherein, the division of the area is divided by the cloud platform according to the distribution of access points (such as base stations); the restriction condition can be the network transmission speed, etc., and the second parameter information and the third parameter information can be the network transmission speed requirements of the terminal, etc. Through the division of the area and the judgment of the impact on the access of the first terminal during access, the operation of the terminals that have already accessed in the area is guaranteed. In addition, the best access area is provided for the first terminal to be accessed, the operating environment after the first terminal is accessed is guaranteed, and the user's access experience is improved.

[0188] In one embodiment, obtaining restriction conditions and access conditions of an area adjacent to an area where the first location is located, and determining an area accessible to the first terminal based on the access conditions and restriction conditions of the adjacent area, includes:

[0189] Get the current access status of adjacent areas.

[0190] Obtain the moving time from the first position to the adjacent area;

[0191] Get the historical access status trend chart of adjacent areas;

[0192] Determine, based on the current access situation, the third parameter information, the moving time, and the historical access situation trend chart, a second access situation of the adjacent area after the user moves to the adjacent area for access;

[0193] Based on the difference between the moving time, the restriction condition and the second access situation, the recommendation degree of the adjacent area is determined. The calculation formula is as follows:

[0194]

[0195] Where D is the recommendation degree, T is the moving time; C k is the value of the kth parameter of the constraint or the second access case, β k is the preset weight corresponding to the value of the kth parameter of the restriction condition or the second access situation; α is the preset weight corresponding to the movement time; and m is the number of parameters in the restriction condition or the second access situation.

[0196] The working principle and beneficial effects of the above technical solution are:

[0197] The recommendation degree of the adjacent area is calculated by the time it takes for the user to move to the adjacent area and the remaining margin of the restriction condition after moving to the adjacent area. Among them, the shorter the time it takes for the user to move to the adjacent area, the higher the recommendation degree and the larger the margin, which means that the possibility that the user can access the adjacent area after moving to the adjacent area is higher. The adjacent area with the highest recommendation degree is recommended to the user to provide the best access area for the user.

[0198] In one embodiment, the verification module performs the following operations:

[0199] Extracting characteristic values ​​of the stroke order information and / or the identification information, substituting the characteristic values ​​into a pre-established neural network model, obtaining a verification factor, querying a preset verification table, and when the verification factor exists in the verification table, the access request of the first terminal is verified to be successful;

[0200] or,

[0201] Constructing a verification vector based on the stroke order information and / or the identification information, matching the verification vector with a standard vector in a pre-established verification library, and when the matching degree between the verification vector and the standard vector is greater than a preset matching value, the access request of the first terminal is verified to be successful;

[0202] The matching degree calculation formula between the verification vector and the standard vector is as follows:

[0203]

[0204] Among them, P q is the matching degree between the verification vector and the qth standard vector in the verification library; n is the dimension of the verification vector and the standard vector; a i,q is the data value of the ith dimension of the qth standard vector; b i is the data value of the i-th dimension of the verification vector;

[0205] The stroke order information includes: a stroke type, an order between stroke types, and parameter information of each stroke, or one or more combinations thereof;

[0206] The parameter information of each stroke includes: the position relationship parameters between the starting point, the end point, and a preset number of sampling points between the starting point and the end point of each stroke, and / or the handwriting force parameters of the starting point, the end point, and a preset number of sampling points between the starting point and the end point of each stroke;

[0207] The identification information includes: one or a combination of text, graphics, and symbols.

[0208] The working principle and beneficial effects of the above technical solution are:

[0209] This embodiment provides two solutions for verifying access requests. Solution 1: Use a pre-trained neural network model to extract the characteristic values ​​of stroke order information and / or identification information and input them into it to obtain a verification factor, and determine the final verification result based on the verification factor. Solution 2: Use a pre-established verification library to construct a verification vector based on stroke order information and / or identification information, match the verification vector with the standard vector in the verification library, and verify through the matching result. Furthermore, the stroke order information and identification information are combined to improve the verification accuracy, that is, when writing text, it is also possible not to follow the standard, and to use the stroke order as a verification point according to user customization, thereby improving the granularity of verification and realizing user-defined operability. In addition, taking into account the handwriting strength parameters between strokes, the recognition of the same stroke of the same word written by different people is realized, and the recognition of people based on the stroke order information and identification information scheme is improved.

[0210] In one embodiment, the first terminal performs the following operations:

[0211] receiving a joint access preparation instruction input by a user;

[0212] Outputting a plurality of preset joint access templates for joint access;

[0213] Calling the joint access template selected by the user;

[0214] Sending a joint access query to at least one second terminal that complies with a first rule of the joint access template based on the joint access template;

[0215] receiving feedback from the second terminal regarding the inquiry;

[0216] When the feedback meets the second rule of the joint access template and / or reaches the start time preset in the joint access template, outputting a joint access start query;

[0217] Receiving a confirmation instruction from the user regarding the start of the joint access inquiry;

[0218] Receive handwriting input from the user;

[0219] Analyze handwriting to obtain stroke order information and recognition information;

[0220] Generate an access request based on the stroke order information and the identification information;

[0221] The first rule includes: a distance from the first terminal is less than a preset first distance value, a terminal of a preset type is within a preset space, and a distance from the first terminal is equal to a preset second distance value, or one or more combinations thereof;

[0222] The second rule includes: the number of second terminals that provide feedback is greater than a preset number value and / or the ratio of the number of second terminals that provide feedback of agreement to the number of second terminals that receive the inquiry is greater than a preset first ratio.

[0223] The working principle and beneficial effects of the above technical solution are:

[0224] When there are multiple terminals that need to access the cloud platform in the same area or at the same time, a joint access operation mode can be used to improve the efficiency of cloud platform access; for example: a class needs to access the cloud platform for a mock exam. The teacher can use the first terminal to send a joint access inquiry to the second terminal used by the students. When the first terminal receives feedback from all the students' second terminals, the teacher uses the first terminal to access the cloud platform. After access, the cloud platform sends the mock exam paper to the second terminal, and can change the exam question number or question value according to different locations.

[0225] In one embodiment, the first terminal performs the following operations:

[0226] receiving a joint access preparation instruction input by a user;

[0227] Acquiring location information of the first terminal;

[0228] Determining whether the position corresponding to the positioning information is located at a preset second position;

[0229] When located at the second position, outputting a plurality of preset joint access templates for joint access;

[0230] Calling the joint access template selected by the user;

[0231] Sending a joint access query to at least one second terminal that complies with a first rule of the joint access template based on the joint access template;

[0232] receiving feedback from the second terminal regarding the inquiry;

[0233] When the feedback meets the second rule of the joint access template and / or reaches the start time preset in the joint access template, outputting a joint access start query;

[0234] Receiving a confirmation instruction from the user regarding the start of the joint access inquiry;

[0235] Receive handwriting input from the user;

[0236] Analyze handwriting to obtain stroke order information and recognition information;

[0237] Generate an access request based on the stroke order information and the identification information;

[0238] The first rule is that the position corresponding to the positioning information of the second terminal is a preset third position;

[0239] The second rule is that all the second terminals being inquired provide feedback and the feedback is agreement.

[0240] The working principle and beneficial effects of the above technical solution are:

[0241] The main application scenario of this embodiment is that the teacher initiates joint access for the exam at the preset second position (lectern). The teacher can initiate joint access only when the first terminal is in position, ensuring the cloud platform's judgment of the joint access scenario; the position corresponding to the location information of the second terminal in the first rule is the preset third position (for example: the student's desk position); ensuring that the terminal receiving the joint access inquiry is the student's terminal. The second terminal of the student who needs to take the exam is jointly connected to the cloud platform through the teacher's first terminal, improving access efficiency and improving the multimedia of education.

[0242] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A terminal access method based on stroke order, OCR and artificial intelligence, characterized in that: include: Obtaining an access request from a first terminal; Parsing the access request, obtaining the stroke order information input by the user and / or the identification information recognized by OCR received by the first terminal; Inputting the stroke order information and / or the identification information into a pre-established verification model to verify the access request of the first terminal; When the verification is successful, accepting access by the first terminal; otherwise, rejecting access by the first terminal; The step of inputting the stroke order information and / or the identification information into a pre-established verification model to verify the access request of the first terminal includes: Extracting feature values ​​of the stroke order information and / or the identification information, substituting the feature values ​​into a pre-established neural network model to obtain a verification factor, querying a preset verification table, and when the verification factor exists in the verification table, the access request of the first terminal is verified to be successful; or, Constructing a verification vector based on the stroke order information and / or the identification information, matching the verification vector with a standard vector in a pre-established verification library, and when the matching degree between the verification vector and the standard vector is greater than a preset matching value, the access request of the first terminal is verified to be successful; The matching degree calculation formula between the verification vector and the standard vector is as follows: Among them, P q is the matching degree between the verification vector and the qth standard vector in the verification library; n is the dimension of the verification vector and the standard vector; a i,q is the data value of the ith dimension of the qth standard vector; b i is the i-th dimension data value of the verification vector.

2. The terminal access method based on stroke order, OCR and artificial intelligence as claimed in claim 1, characterized in that: Also includes: acquiring first parameter information of the first terminal, Determining the access module to be called based on the first parameter information; Accepting access of the first terminal through the access module; The first parameter information includes: a terminal type, a type and model of an external device connected to the terminal, and models of various components of the terminal, or one or more combinations thereof.

3. The terminal access method based on stroke order, OCR and artificial intelligence as claimed in claim 1, characterized in that: Also includes: obtaining the location information of the first terminal, Obtaining access restriction conditions for an area where a first location corresponding to the positioning information is located; Acquire second parameter information of all connected second terminals in the area where the first location is currently located; Acquire third parameter information of the first terminal; Based on the second parameter information, the third parameter information and the restriction condition, determining whether to allow the first terminal to access the area where the first location is located; When access by the first terminal is allowed within the area where the first location is located, accepting access by the first terminal; When it is not allowed, obtaining restriction conditions and access conditions of an area adjacent to the area where the first location is located, determining an area accessible to the first terminal based on the access conditions and restriction conditions of the adjacent area, and sending the area accessible to the first terminal to the first terminal; The second parameter information is the network transmission speed requirement of the second terminal, and the third parameter information is the network transmission speed requirement of the first terminal; The limiting condition is the network transmission speed.

4. The terminal access method based on stroke order, OCR and artificial intelligence as claimed in claim 1, characterized in that: The stroke order information includes: a stroke type, an order between stroke types, and parameter information of each stroke, or one or more combinations thereof; The parameter information of each stroke includes: a position relationship parameter between a starting point, an end point, and a preset number of sampling points between the starting point and the end point of each stroke, and / or a handwriting force parameter of a starting point, an end point, and a preset number of sampling points between the starting point and the end point of each stroke; The identification information includes: one or a combination of text, graphics, and symbols.

5. The terminal access method based on stroke order, OCR and artificial intelligence as claimed in claim 1, characterized in that: The first terminal performs the following operations: receiving a joint access preparation instruction input by a user; Outputting a plurality of preset joint access templates for joint access; calling the joint access template selected by the user; Sending a joint access query to at least one second terminal that complies with a first rule of the joint access template based on the joint access template; receiving feedback from the second terminal regarding the inquiry; When the feedback meets the second rule of the joint access template and / or reaches the start time preset in the joint access template, outputting a joint access start query; receiving a confirmation instruction from the user to start the joint access inquiry; receiving handwriting input by the user; Analyze the handwriting to obtain the stroke order information and the identification information; generating the access request based on the stroke order information and the identification information; The first rule includes: a distance from the first terminal less than a preset first distance value, a terminal of a preset type within a preset space, and a distance from the first terminal equal to a preset second distance value, or one or more combinations thereof; The second rule includes: the number of the second terminals that are fed back is greater than a preset number value and / or the ratio of the number of the second terminals that are fed back as agreed to the number of the second terminals that receive the inquiry is greater than a preset first ratio.

6. A terminal access system based on stroke order, OCR and artificial intelligence, characterized in that: include: A receiving module, used to obtain an access request from a first terminal; A parsing module, used to parse the access request and obtain the stroke order information input by the user and / or the identification information recognized by OCR received by the first terminal; a verification module, configured to input the stroke order information and / or the identification information into a pre-established verification model to verify the access request of the first terminal; when the verification is passed, accept the access of the first terminal; otherwise, reject the access of the first terminal; The verification module performs the following operations: Extracting feature values ​​of the stroke order information and / or the identification information, substituting the feature values ​​into a pre-established neural network model to obtain a verification factor, querying a preset verification table, and when the verification factor exists in the verification table, the access request of the first terminal is verified to be successful; or, Constructing a verification vector based on the stroke order information and / or the identification information, matching the verification vector with a standard vector in a pre-established verification library, and when the matching degree between the verification vector and the standard vector is greater than a preset matching value, the access request of the first terminal is verified to be successful; The matching degree calculation formula between the verification vector and the standard vector is as follows: Among them, P q is the matching degree between the verification vector and the qth standard vector in the verification library; n is the dimension of the verification vector and the standard vector; a i,q is the data value of the ith dimension of the qth standard vector; b i is the i-th dimension data value of the verification vector.

7. The terminal access system based on stroke order, OCR and artificial intelligence as claimed in claim 6, characterized in that: Also includes: A first parameter acquisition module is used to acquire first parameter information of the first terminal. A calling module, used to determine an access module to be called based on the first parameter information; Accepting access of the first terminal through the access module; The first parameter information includes: a terminal type, a type and model of an external device connected to the terminal, and models of various components of the terminal, or one or more combinations thereof.

8. The terminal access system based on stroke order, OCR and artificial intelligence as claimed in claim 6, characterized in that: Also includes: a positioning module, configured to obtain the positioning information of the first terminal, A first condition acquisition module, used to acquire a restriction condition for allowing access within an area where a first position corresponding to the positioning information is located; A second parameter acquisition module is used to acquire second parameter information of all connected second terminals in the area where the first location is currently located; A third parameter acquisition module, used to acquire third parameter information of the first terminal; A judgment module, configured to judge whether the first terminal is allowed to access the area where the first location is located based on the second parameter information, the third parameter information and the restriction condition; When the first terminal is allowed to access the area where the first location is located, accepting the access of the first terminal; when not allowed, obtaining the restriction conditions and access status of the area adjacent to the area where the first location is located, determining the area accessible to the first terminal based on the access status and the restriction conditions of the adjacent area, and sending the area accessible to the first terminal to the first terminal; The second parameter information is the network transmission speed requirement of the second terminal, and the third parameter information is the network transmission speed requirement of the first terminal; The limiting condition is the network transmission speed.

9. The terminal access system based on stroke order, OCR and artificial intelligence as claimed in claim 6, characterized in that: The stroke order information includes: a stroke type, an order between stroke types, and parameter information of each stroke, or one or more combinations thereof; The parameter information of each stroke includes: a position relationship parameter between a starting point, an end point, and a preset number of sampling points between the starting point and the end point of each stroke, and / or a handwriting force parameter of a starting point, an end point, and a preset number of sampling points between the starting point and the end point of each stroke; The identification information includes: one or a combination of text, graphics, and symbols.

10. The terminal access system based on stroke order, OCR and artificial intelligence as claimed in claim 6, characterized in that: The first terminal performs the following operations: receiving a joint access preparation instruction input by a user; Outputting a plurality of preset joint access templates for joint access; calling the joint access template selected by the user; Sending a joint access query to at least one second terminal that complies with a first rule of the joint access template based on the joint access template; receiving feedback from the second terminal regarding the inquiry; When the feedback meets the second rule of the joint access template and / or reaches the start time preset in the joint access template, outputting a joint access start query; receiving a confirmation instruction from the user to start the joint access inquiry; receiving handwriting input by the user; Analyze the handwriting to obtain the stroke order information and the identification information; generating the access request based on the stroke order information and the identification information; The first rule includes: a distance from the first terminal less than a preset first distance value, a terminal of a preset type within a preset space, and a distance from the first terminal equal to a preset second distance value, or one or more combinations thereof; The second rule includes: the number of the second terminals that are fed back is greater than a preset number value and / or the ratio of the number of the second terminals that are fed back as agreed to the number of the second terminals that receive the inquiry is greater than a preset first ratio.

Images