CN110334702B

CN110334702B - Data transmission method and device based on configuration platform and computer equipment

Info

Publication number: CN110334702B
Application number: CN201910463920.XA
Authority: CN
Inventors: 唐奥强
Original assignee: OneConnect Financial Technology Co Ltd Shanghai
Current assignee: OneConnect Financial Technology Co Ltd Shanghai
Priority date: 2019-05-30
Filing date: 2019-05-30
Publication date: 2023-04-18
Anticipated expiration: 2039-05-30
Also published as: CN110334702A; WO2020238556A1

Abstract

The application discloses a data transmission method, a device, computer equipment and a storage medium based on a configuration platform, wherein the method comprises the following steps: receiving a character recognition application sent by an uploading terminal; judging whether the designated picture is similar to a pre-stored picture or not by using a preset picture similarity judging method; if the designated picture is not similar to a pre-stored picture, sending the designated picture to a designated text recognition terminal, wherein the designated text recognition terminal is used for recognizing the text content in the designated picture as a picture text; receiving the picture text sent by the appointed text recognition terminal, and calculating the similarity value of the picture text and the prestored text by using a preset text similarity calculation method; and if the similarity value is not greater than a preset similarity threshold value, sending the picture text to the text display terminal. Therefore, the extra network overhead caused by repeated sending of the text information corresponding to the repeated pictures is reduced.

Description

Data transmission method and device based on configuration platform and computer equipment

Technical Field

The present application relates to the field of computers, and in particular, to a data transmission method and apparatus based on a configuration platform, a computer device, and a storage medium.

Background

Recognizing characters in pictures is a technology commonly used in current production and life. In the traditional character recognition method, an uploading terminal directly uploads a picture including characters to a recognition terminal, the recognition terminal recognizes the picture to obtain recognized characters, and the recognition terminal sends the recognized characters to the uploading terminal. The traditional method needs repeated identification on repeated pictures, which wastes computation power; and the identification characters cannot be sent to the third-party terminal in real time, and if the identification characters are to be sent to the third-party terminal, the identification characters need to be further sent to the third-party terminal by the uploading terminal, so that one step of information sending process is added, resources are wasted, and the identification characters cannot be displayed in real time and at the same time.

Disclosure of Invention

The application mainly aims to provide a data transmission method, a data transmission device, computer equipment and a storage medium based on a configuration platform, and aims to reduce the additional network overhead caused by repeated sending of text information corresponding to repeated pictures.

In order to achieve the above object, the present application provides a data transmission method based on a configuration platform, including the following steps:

receiving a character recognition application sent by an uploading terminal, wherein the character recognition application designates a character display terminal and carries a designated picture;

judging whether the designated picture is similar to a pre-stored picture or not by using a preset picture similarity judging method;

if the designated picture is not similar to a pre-stored picture, sending the designated picture to a designated text recognition terminal, wherein the designated text recognition terminal is used for recognizing the text content in the designated picture as a picture text;

receiving the picture character text sent by the appointed text recognition terminal, calculating a similarity value between the picture character text and a prestored character by using a preset text similarity calculation method, and judging whether the similarity value is greater than a preset similarity threshold value, wherein the prestored character refers to a character obtained by performing character recognition on the prestored picture;

and if the similarity value is not greater than a preset similarity threshold value, sending the picture character text to the character display terminal.

The application provides a data transmission device based on configuration platform includes:

the character recognition application receiving unit is used for receiving a character recognition application sent by the uploading terminal, wherein the character recognition application designates a character display terminal and carries a designated picture;

the image similarity judging unit is used for judging whether the designated image is similar to a pre-stored image or not by utilizing a preset image similarity judging method;

the designated picture sending unit is used for sending the designated picture to a designated text recognition terminal if the designated picture is not similar to a pre-stored picture, and the designated text recognition terminal is used for recognizing the text content in the designated picture as a picture text;

a picture text receiving unit, configured to receive the picture text sent by the specified text recognition terminal, calculate a similarity value between the picture text and a pre-stored text by using a preset text similarity calculation method, and determine whether the similarity value is greater than a preset similarity threshold, where the pre-stored text refers to a text obtained by performing text recognition on the pre-stored picture;

and the picture text sending unit is used for sending the picture text to the text display terminal if the similarity value is not greater than a preset similarity threshold value.

The present application provides a computer device comprising a memory storing a computer program and a processor implementing the steps of any of the above methods when the processor executes the computer program.

The present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method of any of the above.

The data transmission method, the data transmission device, the computer equipment and the storage medium based on the configuration platform receive a character recognition application sent by an uploading terminal; judging whether the specified picture is similar to a prestored picture or not; if the designated picture is not similar to a pre-stored picture, sending the designated picture to a designated text recognition terminal, wherein the designated text recognition terminal is used for recognizing the text content in the designated picture as a picture text; receiving the picture text sent by the appointed text recognition terminal, and calculating the similarity value of the picture text and a prestored text; and if the similarity value is not greater than a preset similarity threshold value, sending the picture text to the text display terminal. Therefore, the extra network overhead caused by repeated sending of the character information corresponding to the repeated pictures is reduced, and the real-time display and recognition of the characters are realized.

Drawings

Fig. 1 is a schematic flowchart of a data transmission method based on a configuration platform according to an embodiment of the present application;

fig. 2 is a schematic block diagram of a configuration platform-based data transmission apparatus according to an embodiment of the present application;

fig. 3 is a schematic block diagram of a structure of a computer device according to an embodiment of the present application.

The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.

Referring to fig. 1, an embodiment of the present application provides a data transmission method based on a configuration platform, including the following steps:

s1, receiving a character recognition application sent by an uploading terminal, wherein the character recognition application designates a character display terminal and carries a designated picture;

s2, judging whether the designated picture is similar to a pre-stored picture or not by using a preset picture similarity judging method;

s3, if the specified picture is not similar to a pre-stored picture, sending the specified picture to a specified text recognition terminal, wherein the specified text recognition terminal is used for recognizing the text content in the specified picture as a picture text;

s4, receiving the picture text sent by the appointed text recognition terminal, calculating a similarity value between the picture text and a pre-stored character by using a preset text similarity calculation method, and judging whether the similarity value is greater than a preset similarity threshold value, wherein the pre-stored character refers to a character obtained by performing character recognition on the pre-stored picture;

and S5, if the similarity value is not greater than a preset similarity threshold value, sending the picture text to the text display terminal.

Recognizing characters in pictures is a technology commonly used in current production and life. In a traditional character recognition method, an uploading terminal directly uploads a picture including characters to a recognition terminal, the recognition terminal recognizes the picture to obtain recognized characters, and the recognition terminal sends the recognized characters to the uploading terminal. The traditional method needs repeated identification on repeated pictures, which wastes computation power; and the identification characters cannot be sent to the third-party terminal in real time, and if the identification characters are to be sent to the third-party terminal, the identification characters need to be further sent to the third-party terminal by the uploading terminal, so that one step of information sending process is added, resources are wasted, and the identification characters cannot be displayed in real time and at the same time. According to the method and the device, the data transmission process is controlled by using the configuration platform, the similarity calculation is performed twice, so that the appointed picture is ensured to be a new picture, and the picture text recognized from the appointed picture is sent to the appointed text display terminal, so that the technical effects of saving calculation power, saving a flow and displaying recognized texts in real time are achieved.

As described in the step S1, a text recognition application sent by an uploading terminal is received, the text recognition application designates a text display terminal, and the text recognition application carries a designated picture. The execution main body of the application is a configuration platform, the configuration platform is used for controlling a data transmission process among an uploading terminal, an identification terminal and a character display terminal, and is preferably a configuration platform based on a big data technology, for example, a big data engine spark is adopted, a big database HBase is adopted, and the like, so that the configuration platform can store and process a large amount of data from a large number of users. The uploading terminal can be any terminal, such as a terminal with a scanning function, a terminal with a photographing function, and the like, and is preferably a terminal capable of acquiring an image to obtain a specified picture. The appointed picture is a picture with characters.

As described in the step S2, a preset image similarity determination method is used to determine whether the designated image is similar to a pre-stored image. The preset image similarity judging method comprises the following steps: sequentially comparing the appointed picture with corresponding pixel points in a prestored picture, if the ratio of the number of the same pixel points in the number of all the pixel points is greater than a preset threshold value, judging that the appointed picture is similar to the prestored picture, namely indicating that the appointed picture is prestored in a configuration platform and is a repeated picture, and because the prestored picture adopts a character recognition technology to recognize a character text, the identification does not need to be carried out again; if the ratio of the number of the same pixel points in all the pixel point numbers is not larger than a preset threshold value, judging that the appointed picture is not similar to a pre-stored picture, indicating that the appointed picture is a new picture, and identifying by adopting a character identification technology, so that identification is needed.

As described in the step S3, if the specified picture is not similar to a pre-stored picture, the specified picture is sent to a specified text recognition terminal, and the specified text recognition terminal is configured to recognize the text content in the specified picture as a picture text. If the specified picture is not similar to the pre-stored picture, the specified picture has the character recognition requirement, and therefore the specified picture is sent to a specified text recognition terminal. According to the method and the device, the designated text recognition terminal and the configuration platform are separated, so that the character recognition function is independently split and recognized by the designated text recognition terminal, the recognition terminal of the corresponding character recognition algorithm can be used for recognizing according to a specific picture, hierarchical management is achieved, resources are saved (only simple pictures are recognized by the simple algorithm), and error tracking is facilitated. The technology for recognizing the text content in the designated picture as the picture text can adopt the existing mature Recognition technology, such as an OCR technology (the OCR technology is an Optical Character Recognition (Optical Character Recognition), which is a computer input technology that can be used for converting image information into image information, and is not described herein again.

As described in step S4, the picture text sent by the designated text recognition terminal is received, a preset text similarity calculation method is used to calculate a similarity value between the picture text and a pre-stored text, and it is determined whether the similarity value is greater than a preset similarity threshold, where the pre-stored text refers to a text obtained by performing text recognition on the pre-stored picture. The method for calculating the similarity between the picture text and the pre-stored text by using the preset text similarity calculation method can be any method, for example: and adopting a WMD algorithm (word mover's distance), a cosine similarity based algorithm, a simhash algorithm, a word frequency vector algorithm and the like to obtain the similarity value between the picture text and the prestored text. The similarity threshold may be any value, such as 100%, and further, in order to avoid misjudgment, the similarity threshold may be set to be less than 100%, such as greater than or equal to 80%.

As described in step S5 above, if the similarity value is not greater than the preset similarity threshold, the picture text is sent to the text display terminal. The similarity value is used for judging whether the picture text is the same as the pre-stored text, namely judging whether the specified picture is the same as the pre-stored picture. If the similarity value is not greater than the preset similarity threshold value, the designated picture is a new picture, so that the picture character text identified by the designated picture is not stored in the character display terminal, and the picture character text is sent to the character display terminal so as to display the identified characters in real time and at the same time. Furthermore, if the similarity value is greater than a preset similarity threshold value, the designated picture is a repeated picture, so that the picture text recognized by the designated picture is stored by the text display terminal, the picture text is not required to be sent, the text display terminal only needs to be informed of the storage position of the picture text, and the text display terminal directly calls local storage data, so that the network overhead is saved.

In an embodiment, the step S2 of determining whether the designated picture is similar to a pre-stored picture by using a preset picture similarity determination method includes:

s201, performing graying processing on the designated picture and the prestored picture respectively to obtain a first grayscale picture and a second grayscale picture;

s202, calculating the average value Am of the gray values of all the pixel points in the mth column or the mth row of the gray picture, and calculating the average value B of the gray values of all the pixel points in the gray picture;

s203, according to the formula:

calculating a global variance ^ of the mth column or row of the grayscale picture>

Wherein N is the total number of columns or rows in the grayscale picture;

s204, according to a formula:

obtaining the difference between the total variances of the m-th column or the m-th row of the two gray-scale pictures>

Wherein +>

For the global variance of the mth column or row of the first gray picture, < >>

The total variance of the m column or m row of the second gray-scale picture;

s205, judgment

Whether the variance is smaller than a preset variance error threshold value;

s206, if

And if the difference is smaller than a preset variance error threshold value, judging that the designated picture is similar to a pre-stored picture.

As described above, whether the designated picture is similar to the pre-stored picture or not is determined by using a preset picture similarity determination method. Where graying refers to expressing a color as a grayscale color, e.g. in the RGB model, e.g. asIf R = G = B, the color represents a gray scale color, wherein the value of R = G = B is called a gray scale value, so that each pixel of the gray scale image only needs one byte to store the gray scale value (also called an intensity value and a brightness value), thereby reducing the storage capacity. The gray scale range is, for example, 0 to 255 (when the values of R, G, and B are all 0 to 255, it will naturally change with the change of the value ranges of R, G, and B). The method of using the graying processing may be any method, for example, a component method, a maximum value method, an average value method, a weighted average method, or the like. The gray value range is only 256, so that the calculated amount can be greatly reduced by comparing the pictures on the basis. And calculating the average value Am of the gray values of all the pixel points in the mth column or the mth row of the gray picture, and calculating the average value B of the gray values of all the pixel points in the gray picture. The process of calculating the average value Am of the gray values of all the pixel points in the mth column or the mth row of the gray picture comprises the following steps: collecting gray values of all pixel points of an mth column or an mth row of the gray picture, adding the gray values of all pixel points of the mth column or the mth row, and dividing the sum of the gray values obtained through the addition by the number of all pixel points of the mth column or the mth row to obtain an average value Am of the gray values of all pixel points of the mth column or the mth row of the gray picture. The process of calculating the average value B of the gray values of all the pixel points in the gray picture comprises the following steps: and calculating the sum of the gray values of all the pixel points in the gray picture, and dividing the sum of the gray values by the number of the pixel points to obtain the average value B of the gray values of all the pixel points in the gray picture. According to the formula:

Where N is the total number of columns or rows in the grayscale picture. In the application, the average value Am of the gray values of the pixel points of the mth column or the mth row of the gray picture and the gray are measured by adopting the total varianceThe difference between the average values B of the gray values of all the pixels in the picture.

According to the formula:

Wherein it is present>

The total variance of the m-th column or m-th row of the second gray picture. The difference in global variance->

The difference of the gray values of the m-th column or the m-th row of the two gray pictures is reflected. When/is>

A smaller value, for example 0, indicates->

Is equal or approximately equal to +>

The gray value of the mth column or row of the first gray picture can be regarded as the same or approximately the same gray value of the mth column or row of the second gray picture (approximate judgment is performed to save calculation power, and the accuracy of the judgment is high because the overall variances of the two different pictures are generally unequal), otherwise, the gray value of the mth column or row of the first gray picture is regarded as the same gray value of the mth column or row of the second gray picture.

Judgment of

Whether it is less than a preset variance error threshold. Wherein->

Is returned as->

Maximum value of (2). If/or>

And if the difference is smaller than a preset variance error threshold value, judging that the specified picture is similar to a pre-stored picture. Therefore, approximate judgment (because all gray values of the gray pictures converted from two different pictures are generally unequal, and all gray values of the gray pictures converted from the same picture are generally equal) is utilized, and whether the specified picture is similar to the prestored picture or not is judged on the premise of consuming less computing resources.

s201, sequentially comparing corresponding pixel points in the designated picture and a pre-stored picture, and counting the number of the same pixel points;

s202, according to a formula: calculating the same pixel point ratio = the number of the same pixel points/the number of all pixel points in the designated picture;

s203, judging whether the ratio of the same pixel points is greater than a preset ratio threshold value;

and S204, if the ratio of the same pixel points is greater than a preset ratio threshold, judging that the designated picture is similar to a pre-stored picture.

As described above, whether the designated picture is similar to the pre-stored picture or not is determined by using a preset picture similarity determination method. In order to accurately judge whether the designated picture is similar to the pre-stored picture, the embodiment adopts a mode of successively comparing pixel points for judgment. If the two pictures are the same, the number of the same pixel points should be the majority, that is, the ratio of the same pixel points is close to 1. Accordingly, according to the formula: and calculating the same pixel point ratio = the number of the same pixel points/the number of all pixel points in the appointed picture, and if the same pixel point ratio is greater than a preset ratio threshold, judging that the appointed picture is similar to a prestored picture.

In one embodiment, after the step S2 of determining whether the specified picture is similar to a pre-stored picture by using a preset picture similarity determination method, the method includes:

s21, if the designated picture is similar to a pre-stored picture, acquiring all characters corresponding to the uploading terminal, and acquiring a character text corresponding to the pre-stored picture according to the corresponding relation between a preset picture and the pre-stored character text;

s22, searching the text corresponding to the pre-stored picture in all the characters corresponding to the uploading terminal, so as to obtain the position information of the text corresponding to the pre-stored picture in all the characters corresponding to the uploading terminal;

and S23, sending the position information to the character display terminal.

As described above, the position information is transmitted to the text display terminal. If the designated picture is similar to the pre-stored picture, the position information of the text corresponding to the pre-stored picture in all the characters corresponding to the uploading terminal is only required to be sent to the character display terminal, the character display terminal can call all the characters corresponding to the uploading terminal from the local storage through the position information, and the character content corresponding to the designated picture is obtained according to the position information. In order to meet the requirement of big data processing, further, a Kafka message queue can be used for transmitting the position information, that is, the position information is put into a preset Kafka message queue to be consumed by the character display terminal. Kafka, among others, is a high-throughput, distributed publish-subscribe message queue that can handle all the action flow data in a consumer-sized web site.

In one embodiment, the step S3 of sending the specified picture to a specified text recognition terminal if the specified picture is not similar to a pre-stored picture, where the specified text recognition terminal is configured to recognize text contents in the specified picture as a picture text, includes:

s301, if the designated picture is not similar to a pre-stored picture, recognizing a preset region in the picture character text picture by using a preset preliminary character recognition technology to obtain a preliminary recognition character, wherein the area of the preset region is smaller than that of the designated picture;

s302, acquiring a character text corresponding to a pre-stored picture according to a corresponding relation between the pre-stored picture and the pre-stored character text;

s303, comparing the preliminary identification characters with the character texts corresponding to the pre-stored pictures, so as to judge whether the character texts corresponding to the pre-stored pictures contain the preliminary identification characters;

s304, if the character text corresponding to the pre-stored picture does not contain the preliminary identification characters, the designated picture is sent to a designated text identification terminal, and the designated text identification terminal is used for identifying the character content in the designated picture as the picture character text.

As described above, it is achieved that whether the pictures are the same or not is further determined on the premise that a small amount of calculation is ensured. In this embodiment, in order to prevent the misjudgment that may occur in the foregoing image judgment, a preliminary character recognition technology is adopted in this embodiment to further determine whether the designated image is similar to the pre-stored image. The preliminary word recognition technique may be any word recognition technique, such as an OCR recognition technique. The area of the predetermined region is smaller than the area of the designated picture, for example, the predetermined region is an edge region of the designated picture. Because the camera needs to be moved when pictures are scanned, for example, the camera is translated rightwards, the left edge area is different from the text corresponding to the pre-stored picture, and therefore whether the appointed picture is similar to the pre-stored picture can be judged only by identifying the left edge area. Therefore, on the premise of consuming only a small amount of calculation power, the embodiment can further determine whether the specified picture is similar to a pre-stored picture, and when the text corresponding to the pre-stored picture does not include the preliminary identification text (i.e., the specified picture is not similar to the pre-stored picture), the specified picture is sent to a specified text identification terminal, and the specified text identification terminal is used for identifying the text content in the specified picture as the picture text.

In one embodiment, the step S4 of receiving the picture text sent by the specified text recognition terminal, calculating a similarity value between the picture text and a pre-stored text by using a preset text similarity calculation method, and determining whether the similarity value is greater than a preset similarity threshold, where the pre-stored text refers to a text obtained by performing text recognition on the pre-stored picture, includes:

s401, receiving the picture character text sent by the specified text recognition terminal;

s402, adopting a formula:

calculating the similarity value of the picture character text and pre-stored characters, wherein the pre-stored characters refer to characters obtained by performing character recognition on the pre-stored pictures; wherein similarity is a similarity value, A is a word frequency vector of the picture character text, B is a word frequency vector of the prestored characters, ai is the frequency of the ith word of the picture character text, and Bi is the frequency of the ith word of the prestored characters;

and S403, judging whether the similarity value is larger than a preset similarity threshold value.

As described above, the similarity value of the picture text and the pre-stored text is calculated, and whether the similarity value is larger than a preset similarity threshold value or not is judged. The word frequency vector is a multidimensional vector formed by using the frequency (frequency) of each word in the text content as a dimensional numerical value of the vector. I.e., a = (A1, A2, …, an), where An is the word frequency of the last word (n words in total). The similarity calculation method is obtained by calculating according to the cosine similarity of the text contents of the two nodes so as to reflect the similarity between the text contents of the two nodes. When the similarity value is closer to 1, the more similar is indicated; closer to 0 indicates less similarity. And judging whether the similarity value is larger than a preset similarity threshold value or not. Wherein the similarity threshold is preferably 100%.

In one embodiment, after step S4 of receiving the picture text sent by the specified text recognition terminal, calculating a similarity value between the picture text and a pre-stored text by using a preset text similarity calculation method, and determining whether the similarity value is greater than a preset similarity threshold, where the pre-stored text refers to a text obtained by performing text recognition on the pre-stored picture, the method includes:

s41, if the similarity value is larger than a preset similarity threshold value, acquiring all characters corresponding to the uploading terminal;

s42, acquiring position information of the prestored characters in all characters corresponding to the uploading terminal;

and S43, sending the position information to the character display terminal.

As described above, the position information is transmitted to the text display terminal. If the similarity value is larger than the preset similarity threshold value, the designated picture is similar to a pre-stored picture (the picture character text is similar to the pre-stored characters), therefore, only the position information of the pre-stored characters in all the characters corresponding to the uploading terminal is needed to be sent to the character display terminal, the character display terminal can call all the characters corresponding to the uploading terminal from the local storage through the position information, and the character content corresponding to the designated picture is obtained according to the position information. In order to meet the requirement of big data processing, furthermore, a Kafka message queue can be adopted to transmit the position information, that is, the position information is put into a preset Kafka message queue to be consumed by the character display terminal. Kafka, among others, is a high-throughput, distributed publish-subscribe message queue that can handle all the action flow data in a consumer-sized web site.

In an embodiment, before the step S5 of sending the picture text to the text display terminal if the similarity value is not greater than a preset similarity threshold, the method includes:

s41, acquiring a flow value sent to the character display terminal within a preset time;

s42, judging whether the flow value is larger than a preset flow threshold value or not;

and S43, if the flow value is larger than a preset flow threshold, obtaining the similarity threshold in a mode of reducing a numerical value of a preset standard threshold.

As described above, setting the similarity threshold is achieved. In order to further reduce the pressure of a configuration platform, the method comprises the steps of obtaining a flow value sent to the character display terminal within preset time; judging whether the flow value is larger than a preset flow threshold value or not; if the flow value is larger than the preset flow threshold, the similarity threshold is obtained by reducing the numerical value of the preset standard threshold, and the numerical value is reduced on the basis of the standard threshold so as to reduce the number of times of sending the text to the text display terminal and further reduce the pressure of configuring the platform.

The data transmission method based on the configuration platform receives a character recognition application sent by an uploading terminal; judging whether the specified picture is similar to a prestored picture or not; if the designated picture is not similar to a pre-stored picture, sending the designated picture to a designated text recognition terminal, wherein the designated text recognition terminal is used for recognizing the text content in the designated picture as a picture text; receiving the picture text sent by the appointed text recognition terminal, and calculating the similarity value of the picture text and a prestored text; and if the similarity value is not greater than a preset similarity threshold value, sending the picture text to the text display terminal. Therefore, the extra network overhead caused by repeated sending of the text information corresponding to the repeated pictures is reduced, and the real-time display and recognition of the text are realized.

Referring to fig. 2, an embodiment of the present application provides a data transmission apparatus based on a configuration platform, including:

a text recognition application receiving unit 10, configured to receive a text recognition application sent by an uploading terminal, where the text recognition application specifies a text display terminal and the text recognition application carries a specified picture;

the picture similarity judging unit 20 is configured to judge whether the specified picture is similar to a pre-stored picture by using a preset picture similarity judging method;

a designated picture sending unit 30, configured to send the designated picture to a designated text recognition terminal if the designated picture is not similar to a pre-stored picture, where the designated text recognition terminal is configured to recognize text contents in the designated picture as a picture text;

a picture text receiving unit 40, configured to receive the picture text sent by the specified text recognition terminal, calculate a similarity value between the picture text and a pre-stored text by using a preset text similarity calculation method, and determine whether the similarity value is greater than a preset similarity threshold, where the pre-stored text refers to a text obtained by performing text recognition on the pre-stored picture;

and the picture text sending unit 50 is configured to send the picture text to the text display terminal if the similarity value is not greater than a preset similarity threshold.

Recognizing characters in pictures is a technology commonly used in current production and life. In the traditional character recognition method, an uploading terminal directly uploads a picture including characters to a recognition terminal, the recognition terminal recognizes the picture to obtain recognized characters, and the recognition terminal sends the recognized characters to the uploading terminal. The traditional method needs repeated identification on repeated pictures, which wastes computation power; and the identification characters cannot be sent to the third-party terminal in real time, and if the identification characters are to be sent to the third-party terminal, the identification characters need to be further sent to the third-party terminal by the uploading terminal, so that one step of information sending process is added, resources are wasted, and the identification characters cannot be displayed in real time and at the same time. According to the method and the device, the data transmission process is controlled by using the configuration platform, the similarity calculation is performed twice, so that the appointed picture is ensured to be a new picture, and the picture text recognized from the appointed picture is sent to the appointed text display terminal, so that the technical effects of saving calculation power, saving a flow and displaying recognized texts in real time are achieved.

As described in the foregoing unit 10, a text recognition application sent by an uploading terminal is received, the text recognition application specifies a text display terminal, and the text recognition application carries a specified picture. The execution main body of the application is a configuration platform, the configuration platform is used for controlling the data transmission process among an uploading terminal, an identification terminal and a character display terminal, and is preferably a configuration platform based on a big data technology, for example, a big data engine spark is adopted, a big database HBase is adopted, and the like, so that the configuration platform can store and process a large amount of data from a large number of users. The uploading terminal can be any terminal, such as a terminal with a scanning function, a terminal with a photographing function, and the like, and is preferably a terminal capable of acquiring an image to obtain a specified picture. Wherein, the appointed picture is a picture with characters.

As described in the foregoing unit 20, a preset picture similarity determination method is used to determine whether the specified picture is similar to a pre-stored picture. The preset image similarity judging method comprises the following steps: sequentially comparing the designated picture with corresponding pixel points in a prestored picture, if the ratio of the number of the same pixel points in all the pixel point numbers is greater than a preset threshold value, judging that the designated picture is similar to the prestored picture, namely, indicating that the designated picture is prestored in a configuration platform and is a repeated picture, and because the prestored picture adopts a character recognition technology to recognize a character text, the identification is not needed to be performed again; if the ratio of the number of the same pixel points in all the pixel point numbers is not larger than a preset threshold value, judging that the appointed picture is not similar to a pre-stored picture, indicating that the appointed picture is a new picture, and identifying by adopting a character identification technology, so that identification is needed.

As described in the foregoing unit 30, if the specified picture is not similar to a pre-stored picture, the specified picture is sent to a specified text recognition terminal, and the specified text recognition terminal is configured to recognize text contents in the specified picture as a picture text. And if the specified picture is not similar to the pre-stored picture, the specified picture has the requirement of character recognition, and therefore the specified picture is sent to a specified text recognition terminal. According to the method and the device, the designated text recognition terminal and the configuration platform are separated, so that the character recognition function is independently split and recognized by the designated text recognition terminal, the recognition terminal of the corresponding character recognition algorithm can be used for recognizing according to a specific picture, hierarchical management is achieved, resources are saved (only simple pictures are recognized by the simple algorithm), and error tracking is facilitated. The technology for recognizing the text content in the designated picture as the picture text can adopt the existing mature Recognition technology, such as an OCR technology (the OCR technology is an Optical Character Recognition (Optical Character Recognition), which is a computer input technology that can be used for converting image information into image information, and is not described herein again.

As described in the above unit 40, the picture text sent by the specified text recognition terminal is received, a preset text similarity calculation method is used to calculate a similarity value between the picture text and a pre-stored text, and it is determined whether the similarity value is greater than a preset similarity threshold, where the pre-stored text refers to a text obtained by performing text recognition on the pre-stored picture. The method for calculating the similarity between the picture text and the pre-stored text by using the preset text similarity calculation method can be any method, for example: and adopting a WMD algorithm (word mover's distance), a cosine similarity based algorithm, a simhash algorithm, a word frequency vector algorithm and the like to obtain the similarity value between the picture text and the prestored text. The similarity threshold may be any value, such as 100%, and further, in order to avoid misjudgment, the similarity threshold may be set to be less than 100%, such as greater than or equal to 80%.

As described in the above-mentioned unit 50, if the similarity value is not greater than the preset similarity threshold, the picture text is sent to the text display terminal. And the similarity value is used for judging whether the picture character text is the same as the pre-stored character, namely judging whether the designated picture is the same as the pre-stored picture. If the similarity value is not greater than the preset similarity threshold value, the designated picture is a new picture, so that the picture character text identified by the designated picture is not stored in the character display terminal, and the picture character text is sent to the character display terminal so as to display the identified characters in real time and at the same time. Furthermore, if the similarity value is greater than a preset similarity threshold value, the designated picture is a repeated picture, so that the picture text recognized by the designated picture is stored by the text display terminal, the picture text is not required to be sent, the text display terminal only needs to be informed of the storage position of the picture text, and the text display terminal directly calls local storage data, so that the network overhead is saved.

In one embodiment, the picture similarity determining unit 20 includes:

the graying processing subunit is used for respectively carrying out graying processing on the designated picture and the prestored picture to obtain a first grayscale picture and a second grayscale picture;

the gray value average operator unit is used for calculating the average value Am of the gray values of all the pixel points of the mth column or the mth row of the gray picture and calculating the average value B of the gray values of all the pixel points in the gray picture;

a global variance obtaining subunit, configured to:

calculating a global variance { (m-th row } or m-th column of the grayscale picture>

Wherein N is the total number of columns or rows in the grayscale picture;

a difference between the overall variances obtaining subunit, configured to:

Wherein it is present>

For the overall variance in column m or row m of the first gray picture, based on the mean variance of the column m or row m>

The total variance of the m column or m row of the second gray-scale picture;

a variance error threshold judgment subunit for judging

Whether the variance is smaller than a preset variance error threshold value;

a picture similarity determination subunit for determining if

And if the difference is smaller than a preset variance error threshold value, judging that the specified picture is similar to a pre-stored picture.

As described above, whether the designated picture is similar to the pre-stored picture or not is determined by using a preset picture similarity determination method. In the RGB model, for example, if R = G = B, the color represents a gray color, where the value of R = G = B is called a gray value, and therefore, each pixel of the gray image only needs one byte to store the gray value (also called an intensity value, a brightness value), thereby reducing the storage amount. The gray scale range is, for example, 0 to 255 (when the values of R, G, and B are all 0 to 255, it will naturally change with the change of the value ranges of R, G, and B). The method using the graying treatment may be any method, such as a component method, a maximum value method, an average methodValue methods, weighted average methods, etc. The value range of the gray values is only 256, so that the calculation amount can be greatly reduced by comparing the images on the basis. And calculating the average value Am of the gray values of all the pixel points in the mth column or the mth row of the gray picture, and calculating the average value B of the gray values of all the pixel points in the gray picture. The process of calculating the average value Am of the gray values of all the pixel points in the mth column or the mth row of the gray picture comprises the following steps: collecting gray values of all pixel points of an mth column or an mth row of the gray picture, adding the gray values of all pixel points of the mth column or the mth row, and dividing the sum of the gray values obtained through the addition by the number of all pixel points of the mth column or the mth row to obtain an average value Am of the gray values of all pixel points of the mth column or the mth row of the gray picture. The process of calculating the average value B of the gray values of all the pixel points in the gray picture comprises the following steps: and calculating the sum of the gray values of all the pixel points in the gray picture, and dividing the sum of the gray values by the number of the pixel points to obtain the average value B of the gray values of all the pixel points in the gray picture. According to the formula:

Where N is the total number of columns or rows in the grayscale picture. In the application, the difference between the average Am of the gray values of the pixel points in the mth column or the mth row of the gray picture and the average B of the gray values of all the pixel points in the gray picture is measured by adopting the overall variance.

According to the formula:

Wherein it is present>

The difference of the gray values of the m-th column or the m-th row of the two gray pictures is reflected. When +>

Smaller, for example 0, indicates->

Equal or approximately equal to +>

Judgment of

Whether it is less than a preset variance error threshold. Wherein->

Is the returned value of->

Maximum value of (2). If/or>

And if the difference is smaller than a preset variance error threshold value, judging that the designated picture is similar to a pre-stored picture. Therefore, approximate judgment (because all gray values of the gray level pictures converted from two different pictures are generally unequal, and all gray values of the gray level pictures converted from the same picture are generally equal) is utilized, and whether the specified picture is similar to a prestored picture or not is judged on the premise of consuming less computing resources.

In one embodiment, the picture similarity determining unit 20 includes:

the same pixel point counting subunit is used for sequentially comparing the corresponding pixel points in the appointed picture and a prestored picture and counting the number of the same pixel points;

the same pixel point proportion calculation subunit is used for calculating the proportion of the same pixel point according to a formula: calculating the same pixel point ratio = the number of the same pixel points/the number of all pixel points in the designated picture;

a ratio threshold judging subunit, configured to judge whether the ratio of the same pixel point is greater than a preset ratio threshold;

and the similarity judgment subunit is used for judging that the designated picture is similar to a pre-stored picture if the same pixel point proportion is greater than a preset proportion threshold value.

As described above, whether the specified picture is similar to the pre-stored picture or not is determined by using a preset picture similarity determination method. In order to accurately judge whether the designated picture is similar to the pre-stored picture, the embodiment adopts a mode of successively comparing pixel points for judgment. If the two pictures are the same, the number of the same pixel points should be the majority, that is, the ratio of the same pixel points is close to 1. Accordingly, according to the formula: and calculating the same pixel point ratio = the number of the same pixel points/the number of all pixel points in the appointed picture, and if the same pixel point ratio is greater than a preset ratio threshold, judging that the appointed picture is similar to a prestored picture.

In one embodiment, the apparatus comprises:

the all-character acquisition unit is used for acquiring all characters corresponding to the uploading terminal if the specified picture is similar to a pre-stored picture, and acquiring a character text corresponding to the pre-stored picture according to the corresponding relation between a preset picture and the pre-stored character text;

the position information acquisition unit is used for searching the character texts corresponding to the pre-stored pictures in all the characters corresponding to the uploading terminal so as to acquire the position information of the character texts corresponding to the pre-stored pictures in all the characters corresponding to the uploading terminal;

and the position information sending unit is used for sending the position information to the character display terminal.

As described above, the position information is transmitted to the text display terminal. If the appointed picture is similar to the pre-stored picture, the position information of the text corresponding to the pre-stored picture in all the characters corresponding to the uploading terminal is only needed to be sent to the character display terminal, the character display terminal can call all the characters corresponding to the uploading terminal from the local storage through the position information, and the character content corresponding to the appointed picture is obtained according to the position information. In order to meet the requirement of big data processing, further, a Kafka message queue can be used for transmitting the position information, that is, the position information is put into a preset Kafka message queue to be consumed by the character display terminal. Kafka, among others, is a high-throughput, distributed publish-subscribe message queue that can handle all the action flow data in a consumer-sized web site.

In one embodiment, the designated picture sending unit 30 includes:

a preliminary identification character acquisition subunit, configured to, if the specified picture is not similar to a pre-stored picture, identify a predetermined region in the picture character text picture by using a preset preliminary character identification technology to obtain a preliminary identification character, where an area of the predetermined region is smaller than an area of the specified picture;

the character text acquisition subunit is used for acquiring a character text corresponding to a pre-stored picture according to the corresponding relation between the pre-stored picture and the pre-stored character text;

a preliminary identification character judgment subunit, configured to compare the preliminary identification character with a character text corresponding to the pre-stored picture, so as to judge whether the character text corresponding to the pre-stored picture includes the preliminary identification character;

and the appointed picture sending subunit is used for sending the appointed picture to an appointed text recognition terminal if the character text corresponding to the pre-stored picture does not contain the preliminary recognition characters, and the appointed text recognition terminal is used for recognizing the character content in the appointed picture as the picture character text.

As described above, it is achieved that whether the pictures are the same or not is further determined on the premise that a small amount of calculation is ensured. In this embodiment, in order to prevent the misjudgment that may occur in the foregoing image judgment, the preliminary character recognition technology is adopted in this embodiment to further determine whether the designated image is similar to the pre-stored image. The preliminary word recognition technique may be any word recognition technique, such as an OCR recognition technique. The area of the predetermined region is smaller than the area of the designated picture, for example, the predetermined region is an edge region of the designated picture. Because the camera needs to be moved when pictures are scanned, for example, the camera is translated rightwards, the left edge area is different from the text corresponding to the pre-stored picture, and therefore whether the appointed picture is similar to the pre-stored picture can be judged only by identifying the left edge area. Therefore, on the premise of consuming only a small amount of calculation power, the embodiment can further determine whether the specified picture is similar to a pre-stored picture, and when the text corresponding to the pre-stored picture does not include the preliminary identification text (i.e., the specified picture is not similar to the pre-stored picture), the specified picture is sent to a specified text identification terminal, and the specified text identification terminal is used for identifying the text content in the specified picture as the picture text.

In one embodiment, the photo text receiving unit 40 includes:

the picture character text receiving subunit is used for receiving the picture character text sent by the specified text recognition terminal;

a similarity value calculating subunit configured to adopt the formula:

calculating the similarity value of the picture character text and prestored characters, wherein the prestored characters refer to characters obtained by performing character recognition on the prestored picture; wherein similarity is a similarity value, A is a word frequency vector of the picture character text, B is a word frequency vector of the prestored characters, ai is the frequency of the ith word of the picture character text, and Bi is the frequency of the ith word of the prestored characters;

and the similarity threshold judging subunit is used for judging whether the similarity value is greater than a preset similarity threshold.

As described above, the similarity value of the picture text and the pre-stored text is calculated, and whether the similarity value is larger than a preset similarity threshold value or not is judged. The word frequency vector is a multidimensional vector formed by using the frequency (frequency) of each word in the text content as a dimensional numerical value of the vector. I.e., a = (A1, A2, …, an), where An is the word frequency of the last word (n words in total). The similarity calculation method is obtained by calculating the cosine similarity of the text contents of the two nodes so as to reflect the similarity between the text contents of the two nodes. When the similarity value is closer to 1, it indicates more similarity; closer to 0, indicating less similarity. And judging whether the similarity value is greater than a preset similarity threshold value or not. Wherein the similarity threshold is preferably 100%.

In one embodiment, the apparatus comprises:

the all-character acquisition unit is used for acquiring all characters corresponding to the uploading terminal if the similarity value is greater than a preset similarity threshold value;

the position information acquisition unit is used for acquiring the position information of the prestored characters in all characters corresponding to the uploading terminal;

As described above, the position information is transmitted to the text display terminal. If the similarity value is larger than the preset similarity threshold value, the designated picture is similar to a pre-stored picture (the picture character text is similar to the pre-stored characters), therefore, only the position information of the pre-stored characters in all the characters corresponding to the uploading terminal is needed to be sent to the character display terminal, the character display terminal can call all the characters corresponding to the uploading terminal from the local storage through the position information, and the character content corresponding to the designated picture is obtained according to the position information. In order to meet the requirement of big data processing, further, a Kafka message queue can be used for transmitting the position information, that is, the position information is put into a preset Kafka message queue to be consumed by the character display terminal. Kafka, among others, is a high-throughput, distributed publish-subscribe message queue that can handle all the action flow data in a consumer-sized web site.

In one embodiment, the apparatus comprises:

the flow value acquisition unit is used for acquiring a flow value sent to the character display terminal within a preset time;

the flow threshold judging unit is used for judging whether the flow value is larger than a preset flow threshold or not;

and the similarity threshold acquisition unit is used for acquiring the similarity threshold by reducing the numerical value of a preset standard threshold if the flow value is greater than the preset flow threshold.

The data transmission device based on the configuration platform receives a character recognition application sent by an uploading terminal; judging whether the specified picture is similar to a prestored picture or not; if the designated picture is not similar to a pre-stored picture, sending the designated picture to a designated text recognition terminal, wherein the designated text recognition terminal is used for recognizing the text content in the designated picture as a picture text; receiving the picture character text sent by the appointed text recognition terminal, and calculating the similarity value of the picture character text and a prestored character; and if the similarity value is not greater than a preset similarity threshold value, sending the picture text to the text display terminal. Therefore, the extra network overhead caused by repeated sending of the character information corresponding to the repeated pictures is reduced, and the real-time display and recognition of the characters are realized.

Referring to fig. 3, an embodiment of the present invention further provides a computer device, where the computer device may be a server, and an internal structure of the computer device may be as shown in the figure. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used for storing data used by the data transmission method based on the configuration platform. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of data transfer based on a configuration platform.

The processor executes the data transmission method based on the configuration platform, and the method comprises the following steps of: receiving a character recognition application sent by an uploading terminal, wherein the character recognition application designates a character display terminal and carries a designated picture; judging whether the designated picture is similar to a pre-stored picture or not by using a preset picture similarity judging method; if the specified picture is not similar to a pre-stored picture, sending the specified picture to a specified text recognition terminal, wherein the specified text recognition terminal is used for recognizing the text content in the specified picture as a picture text; receiving the picture character text sent by the appointed text recognition terminal, calculating a similarity value between the picture character text and a prestored character by using a preset text similarity calculation method, and judging whether the similarity value is greater than a preset similarity threshold value, wherein the prestored character refers to a character obtained by performing character recognition on the prestored picture; and if the similarity value is not greater than a preset similarity threshold value, sending the picture text to the text display terminal.

In one embodiment, the step of determining whether the designated picture is similar to a pre-stored picture by using a preset picture similarity determination method includes: carrying out graying processing on the designated picture and the prestored picture respectively to obtain a first grayscale picture and a second grayscale picture; calculating the average value Am of the gray values of all the pixel points in the mth column or the mth row of the gray picture, and calculating the average value B of the gray values of all the pixel points in the gray picture; according to the formula:

Wherein N is the total number of columns or rows in the grayscale picture; according to the formula>

Obtaining the m-th columns or m-th rows of the two gray level picturesIs greater than or equal to>

Wherein +>

The total variance of the m column or m row of the second gray-scale picture; judgment->

Whether the variance is smaller than a preset variance error threshold value; if/or>

In one embodiment, the step of determining whether the designated picture is similar to a pre-stored picture by using a preset picture similarity determination method includes: sequentially comparing the designated picture with corresponding pixel points in a prestored picture, and counting the number of the same pixel points; according to the formula: calculating the same pixel point ratio = the number of the same pixel points/the number of all pixel points in the designated picture; judging whether the ratio of the same pixel points is greater than a preset ratio threshold value or not; and if the same pixel point occupation ratio is larger than a preset occupation ratio threshold value, judging that the appointed picture is similar to a pre-stored picture.

In one embodiment, after the step of determining whether the designated picture is similar to a pre-stored picture by using a preset picture similarity determination method, the method includes: if the designated picture is similar to a pre-stored picture, acquiring all characters corresponding to the uploading terminal, and acquiring a character text corresponding to the pre-stored picture according to the corresponding relation between a preset picture and the pre-stored character text; searching the text corresponding to the pre-stored picture in all the characters corresponding to the uploading terminal, so as to obtain the position information of the text corresponding to the pre-stored picture in all the characters corresponding to the uploading terminal; and sending the position information to the character display terminal.

In one embodiment, if the specified picture is not similar to a pre-stored picture, the step of sending the specified picture to a specified text recognition terminal, where the specified text recognition terminal is configured to recognize text contents in the specified picture as a picture text includes: if the designated picture is not similar to a pre-stored picture, recognizing a preset region in the picture character text picture by using a preset preliminary character recognition technology to obtain a preliminary recognition character, wherein the area of the preset region is smaller than that of the designated picture; acquiring a character text corresponding to a pre-stored picture according to the corresponding relation between the pre-stored picture and the pre-stored character text; comparing the preliminary identification characters with the character texts corresponding to the pre-stored pictures so as to judge whether the character texts corresponding to the pre-stored pictures contain the preliminary identification characters; and if the character text corresponding to the pre-stored picture does not contain the preliminary identification characters, sending the specified picture to a specified text identification terminal, wherein the specified text identification terminal is used for identifying the character content in the specified picture as the picture character text.

In one embodiment, the receiving the picture text sent by the specified text recognition terminal, and calculating a similarity value between the picture text and a pre-stored text by using a preset text similarity calculation method, and determining whether the similarity value is greater than a preset similarity threshold, where the pre-stored text refers to a text obtained by performing text recognition on the pre-stored picture, and the step includes: receiving the picture text sent by the specified text recognition terminal; the formula is adopted:

calculating the similarity value of the picture character text and prestored characters, wherein the prestored characters refer to the characters obtained by carrying out text processing on the prestored pictureCharacters obtained by character recognition; wherein similarity is a similarity value, A is a word frequency vector of the picture character text, B is a word frequency vector of the prestored characters, ai is the frequency of the ith word of the picture character text, and Bi is the frequency of the ith word of the prestored characters; and judging whether the similarity value is larger than a preset similarity threshold value.

In one embodiment, the receiving the picture text sent by the specified text recognition terminal, calculating a similarity value between the picture text and a pre-stored text by using a preset text similarity calculation method, and determining whether the similarity value is greater than a preset similarity threshold, where the pre-stored text refers to a text obtained by performing text recognition on the pre-stored picture, and the method includes: if the similarity value is larger than a preset similarity threshold value, acquiring all characters corresponding to the uploading terminal; acquiring position information of the prestored characters in all characters corresponding to the uploading terminal; and sending the position information to the character display terminal.

In one embodiment, before the step of sending the picture text to the text display terminal if the similarity value is not greater than a preset similarity threshold value, the method includes: acquiring a flow value sent to the character display terminal within a preset time; judging whether the flow value is larger than a preset flow threshold value or not; and if the flow value is larger than a preset flow threshold, obtaining the similarity threshold by reducing the numerical value of a preset standard threshold.

It will be understood by those skilled in the art that the structures shown in the drawings are only block diagrams of some of the structures associated with the embodiments of the present application and do not constitute a limitation on the computer apparatus to which the embodiments of the present application may be applied.

The computer equipment receives a character recognition application sent by an uploading terminal; judging whether the specified picture is similar to a prestored picture or not; if the designated picture is not similar to a pre-stored picture, sending the designated picture to a designated text recognition terminal, wherein the designated text recognition terminal is used for recognizing the text content in the designated picture as a picture text; receiving the picture character text sent by the appointed text recognition terminal, and calculating the similarity value of the picture character text and a prestored character; and if the similarity value is not greater than a preset similarity threshold value, sending the picture character text to the character display terminal. Therefore, the extra network overhead caused by repeated sending of the character information corresponding to the repeated pictures is reduced, and the real-time display and recognition of the characters are realized.

An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for data transmission based on a configuration platform is implemented, including the following steps: receiving a character recognition application sent by an uploading terminal, wherein the character recognition application designates a character display terminal and carries a designated picture; judging whether the designated picture is similar to a pre-stored picture or not by using a preset picture similarity judging method; if the specified picture is not similar to a pre-stored picture, sending the specified picture to a specified text recognition terminal, wherein the specified text recognition terminal is used for recognizing the text content in the specified picture as a picture text; receiving the picture text sent by the appointed text recognition terminal, calculating a similarity value between the picture text and a pre-stored text by using a preset text similarity calculation method, and judging whether the similarity value is greater than a preset similarity threshold value, wherein the pre-stored text refers to a text obtained by performing text recognition on the pre-stored picture; and if the similarity value is not greater than a preset similarity threshold value, sending the picture text to the text display terminal.

In one embodiment, the step of determining whether the specified picture is similar to a pre-stored picture by using a preset picture similarity determination method includes: carrying out graying processing on the designated picture and the prestored picture respectively to obtain a first grayscale picture and a second grayscale picture; calculating the average value Am of the gray values of all the pixel points of the mth column or the mth row of the gray picture, and calculating the gray pictureAverage value B of gray values of all the pixels in the image; according to the formula:

Wherein it is present>

In one embodiment, the step of determining whether the designated picture is similar to a pre-stored picture by using a preset picture similarity determination method includes: sequentially comparing the corresponding pixel points in the appointed picture and the pre-stored picture, and counting the number of the same pixel points; according to the formula: calculating the same pixel point occupation ratio = the number of the same pixel points/the number of all the pixel points in the designated picture; judging whether the ratio of the same pixel points is greater than a preset ratio threshold value or not; and if the same pixel point occupation ratio is larger than a preset occupation ratio threshold value, judging that the appointed picture is similar to a pre-stored picture.

In one embodiment, if the specified picture is not similar to a pre-stored picture, the step of sending the specified picture to a specified text recognition terminal, where the specified text recognition terminal is configured to recognize text contents in the specified picture as a picture text includes: if the designated picture is not similar to a pre-stored picture, recognizing a preset region in the picture character text picture by using a preset preliminary character recognition technology to obtain a preliminary recognition character, wherein the area of the preset region is smaller than that of the designated picture; acquiring a character text corresponding to a pre-stored picture according to the corresponding relation between the pre-stored picture and the pre-stored character text; comparing the preliminary identification characters with character texts corresponding to the pre-stored pictures so as to judge whether the character texts corresponding to the pre-stored pictures contain the preliminary identification characters; and if the character text corresponding to the pre-stored picture does not contain the preliminary identification characters, sending the specified picture to a specified text identification terminal, wherein the specified text identification terminal is used for identifying the character content in the specified picture as the picture character text.

In one embodiment, the receiving is sent by the specified text recognition terminalCalculating a similarity value between the picture character text and a prestored character by using a preset text similarity calculation method, and judging whether the similarity value is greater than a preset similarity threshold value, wherein the prestored character refers to a character obtained by performing character recognition on the prestored picture, and the method comprises the following steps of: receiving the picture text sent by the appointed text recognition terminal; the formula is adopted:

calculating the similarity value of the picture character text and prestored characters, wherein the prestored characters refer to characters obtained by performing character recognition on the prestored picture; wherein similarity is a similarity value, A is a word frequency vector of the picture character text, B is a word frequency vector of the prestored characters, ai is the frequency of the ith word of the picture character text, and Bi is the frequency of the ith word of the prestored characters; and judging whether the similarity value is larger than a preset similarity threshold value.

The computer-readable storage medium receives a character recognition application sent by an uploading terminal; judging whether the specified picture is similar to a prestored picture or not; if the designated picture is not similar to a pre-stored picture, sending the designated picture to a designated text recognition terminal, wherein the designated text recognition terminal is used for recognizing the text content in the designated picture as a picture text; receiving the picture character text sent by the appointed text recognition terminal, and calculating the similarity value of the picture character text and a prestored character; and if the similarity value is not greater than a preset similarity threshold value, sending the picture character text to the character display terminal. Therefore, the extra network overhead caused by repeated sending of the text information corresponding to the repeated pictures is reduced, and the real-time display and recognition of the text are realized.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRDRAM), enhanced SDRAM (ESDRAM), synchronous Link (Synchlink) DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct bused dynamic RAM (DRDRAM), and bused dynamic RAM (RDRAM).

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, apparatus, article, or method that comprises the element.

The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.

Claims

1. A data transmission method based on a configuration platform is characterized by comprising the following steps:

judging whether the designated picture is similar to a pre-stored picture or not by using a preset picture similarity judgment method;

if the similarity value is not greater than a preset similarity threshold value, the picture character text is sent to the character display terminal;

the step of judging whether the specified picture is similar to a pre-stored picture by using a preset picture similarity judging method comprises the following steps:

performing graying processing on the designated picture and the prestored picture respectively to obtain a first grayscale picture and a second grayscale picture;

calculating the average value Am of the gray values of all the pixel points in the mth column or the mth row of the gray picture, and calculating the average value B of the gray values of all the pixel points in the gray picture;

according to the formula:

Wherein N is the total number of columns or rows in the grayscale picture;

according to the formula:

Wherein it is present>

The total variance of the mth column or the mth row of the second gray-scale picture;

judgment of

Whether the variance is smaller than a preset variance error threshold value;

if it is

2. The data transmission method based on the configuration platform according to claim 1, wherein the step of determining whether the designated picture is similar to a pre-stored picture by using a preset picture similarity determination method comprises:

sequentially comparing the designated picture with corresponding pixel points in a prestored picture, and counting the number of the same pixel points;

according to the formula: calculating the same pixel point ratio = the number of the same pixel points/the number of all pixel points in the designated picture;

judging whether the ratio of the same pixel points is greater than a preset ratio threshold value or not;

and if the occupation ratio of the same pixel point is greater than a preset occupation ratio threshold value, judging that the designated picture is similar to a pre-stored picture.

3. The data transmission method based on the configuration platform according to claim 1, wherein the step of determining whether the designated picture is similar to a pre-stored picture by using a preset picture similarity determination method comprises:

if the designated picture is similar to a pre-stored picture, acquiring all characters corresponding to the uploading terminal, and acquiring a character text corresponding to the pre-stored picture according to the corresponding relation between a preset picture and the pre-stored character text;

searching the text corresponding to the pre-stored picture in all the characters corresponding to the uploading terminal, so as to obtain the position information of the text corresponding to the pre-stored picture in all the characters corresponding to the uploading terminal;

and sending the position information to the character display terminal.

4. The configuration platform based data transmission method according to claim 1, wherein if the designated picture is not similar to a pre-stored picture, the designated picture is sent to a designated text recognition terminal, and the designated text recognition terminal is configured to recognize text contents in the designated picture as a picture text, including:

if the designated picture is not similar to a pre-stored picture, identifying a preset region in the picture text picture by using a preset preliminary character identification technology to obtain preliminary identification characters, wherein the area of the preset region is smaller than that of the designated picture;

acquiring a character text corresponding to a pre-stored picture according to the corresponding relation between the pre-stored picture and the pre-stored character text;

comparing the preliminary identification characters with the character texts corresponding to the pre-stored pictures so as to judge whether the character texts corresponding to the pre-stored pictures contain the preliminary identification characters;

and if the character text corresponding to the pre-stored picture does not contain the preliminary identification characters, sending the specified picture to a specified text identification terminal, wherein the specified text identification terminal is used for identifying the character content in the specified picture as the picture character text.

5. The data transmission method based on the configuration platform according to claim 1, wherein the step of receiving the picture text sent by the designated text recognition terminal, calculating a similarity value between the picture text and a pre-stored text by using a preset text similarity calculation method, and determining whether the similarity value is greater than a preset similarity threshold, wherein the pre-stored text refers to a text obtained by performing text recognition on the pre-stored picture, includes:

receiving the picture text sent by the appointed text recognition terminal;

the formula is adopted:

and judging whether the similarity value is larger than a preset similarity threshold value or not.

6. The data transmission method based on the configuration platform according to claim 1, wherein before the step of sending the picture text to the text display terminal if the similarity value is not greater than a preset similarity threshold value, the method includes:

acquiring a flow value sent to the character display terminal within a preset time;

judging whether the flow value is larger than a preset flow threshold value or not;

and if the flow value is larger than a preset flow threshold, obtaining the similarity threshold by reducing a numerical value of a preset standard threshold.

7. A data transmission device based on a configuration platform, comprising:

the image similarity judging unit is used for judging whether the specified image is similar to a pre-stored image by utilizing a preset image similarity judging method;

the designated picture sending unit is used for sending the designated picture to a designated text recognition terminal if the designated picture is not similar to a pre-stored picture, and the designated text recognition terminal is used for recognizing the character content in the designated picture as a picture character text;

the picture text sending unit is used for sending the picture text to the text display terminal if the similarity value is not greater than a preset similarity threshold value;

the gray value average operator unit is used for calculating the average value Am of the gray values of all the pixel points in the mth column or the mth row of the gray picture and calculating the average value B of the gray values of all the pixel points in the gray picture;

an overall variance obtaining subunit, configured to:

Wherein N is the total number of columns or rows in the grayscale picture;

a difference between the overall variances obtaining subunit, configured to:

Wherein it is present>

The total variance of the m column or m row of the second gray-scale picture;

a variance error threshold judgment subunit for judging

Whether the variance is smaller than a preset variance error threshold value;

a picture similarity determination subunit for determining if

8. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.