Big data artificial intelligence information processing system and method thereof

Abstract

The invention belongs to the technical field of information processing, and particularly relates to a big data artificial intelligence information processing system and method, and the system comprises an image collection module which is used for collecting a product image; the first character analysis module is used for analyzing characters in the product image acquired by the image acquisition module; the second character analysis module is used for analyzing the characters which cannot be recognized in a character structure comparison mode when the first character analysis module cannot completely recognize the characters on the product; and the input module is used for inputting the characters analyzed by the first character analysis module so as to input the product information. According to the invention, the first character analysis module used for analyzing the characters in the product image acquired by the image acquisition module is arranged, so that when the placement angle of the product changes, the information on the product can still be identified, and the identification accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and specifically to a big data artificial intelligence information processing system and method thereof. Background Art

[0002] Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robots, language recognition, image recognition, natural language processing, and expert systems. Since the birth of artificial intelligence, the theory and technology of artificial intelligence have become increasingly mature, and the application field has continued to expand. It can be imagined that the technological products brought by artificial intelligence in the future will be the "container" of human wisdom. Artificial intelligence can simulate the information process of human consciousness and thinking. Information processing is the process of removing the false and retaining the true, removing the coarse and retaining the fine, from the surface to the inside, and from this to that of the collected information. It is an activity process that produces secondary information with high value content and convenient for users to use based on the original information. Using artificial intelligence to process information can improve the efficiency of the information processing process.

[0003] At present, in the process of product transportation, artificial intelligence technology is usually used to identify the information on the product. However, when the product is placed at a different angle during transportation, it is difficult to identify the information on the product because the text on the product is tilted. If it is recognized, there may be errors in recognition. Therefore, the existing artificial intelligence recognition technology has the problem of inaccurate recognition. Therefore, a big data artificial intelligence information processing system and method are invented. Summary of the invention

[0004] To solve the above technical problems, according to one aspect of the present invention, the present invention provides the following technical solutions:

[0005] A big data artificial intelligence information processing system, comprising:

[0006] An image acquisition module, used for acquiring product images;

[0007] A first text analysis module, used to analyze the text in the product image captured by the image acquisition module;

[0008] The second text analysis module is used to analyze the unrecognizable text by using a text structure comparison method when the first text analysis module cannot completely recognize the text on the product;

[0009] An input module, used to input the text analyzed by the first text analysis module to input product information;

[0010] A notification module, used to notify personnel when the first text analysis module and the second text analysis module fail to fully recognize the text on the product;

[0011] The sound playback module is used to enable personnel to read the text on the product after notifying them;

[0012] The sound analysis module is used to analyze and convert the sound played by the sound playing module so as to obtain information on the product and place it in the input module.

[0013] As a preferred solution of the big data artificial intelligence information processing system described in the present invention, the first text analysis module includes:

[0014] The text angle analysis module is used to analyze the text display angle in the product image acquired by the image acquisition module, so as to analyze the angle at which the text on the product is photographed in the image;

[0015] A database for storing display images of various texts at various angles;

[0016] The retrieval module is used to retrieve the corresponding folder in the database according to the text angle analyzed by the text angle analysis module.

[0017] As a preferred solution of the big data artificial intelligence information processing system described in the present invention, the first text analysis module also includes:

[0018] A comparison module, used to compare the text angles analyzed by the text angle analysis module with the folders retrieved by the retrieval module;

[0019] The first judgment module is used to judge whether the text angle analyzed by the comparison module is similar in the database. If so, the text will be obtained.

[0020] As a preferred solution of the big data artificial intelligence information processing system described in the present invention, the first text analysis module also includes:

[0021] A recording module, used for recording the data judged by the first judging module. If a word is obtained, the obtained word will be recorded. Otherwise, if no word is obtained, a symbol will be used for recording.

[0022] The second judgment module is used to connect the obtained texts to determine whether they are fluent when all the texts are obtained. If they are fluent, they will be uploaded to the input module.

[0023] As a preferred solution of the big data artificial intelligence information processing system described in the present invention, there are several folders in the database, each folder corresponds to an angle, and each file contains a text image of the corresponding angle.

[0024] As a preferred solution of the big data artificial intelligence information processing system described in the present invention, the second text analysis module includes:

[0025] A text acquisition module is used to extract the text that is not recognized in the recording module and the text located before and after the text;

[0026] A word storage module is used to store various words;

[0027] The text comparison module is used to compare the text information extracted by the text acquisition module with various words stored in the word storage module to compare words that are similar to the text extracted by the text acquisition module.

[0028] As a preferred solution of the big data artificial intelligence information processing system described in the present invention, the second text analysis module also includes:

[0029] A first text structure module is used to extract the text angle structure analyzed by the text angle analysis module;

[0030] The second text structure module is used to extract the word structure compared by the text comparison module;

[0031] The structure comparison module is used to compare the text structure extracted by the first text structure module with the word structure extracted by the second text structure module to compare the area of ​​the overlapping part.

[0032] As a preferred solution of the big data artificial intelligence information processing system described in the present invention, the second text analysis module also includes:

[0033] A sorting module, used to sort the words compared by the text comparison module according to the overlap area compared by the structure comparison module;

[0034] The transmission module is used to transmit the words sorted by the sorting module to the recording module in order from high to low, and after being judged by the second judgment module, if it is fluent, it will be uploaded to the input module, otherwise, the corresponding words will be deleted by the deletion module.

[0035] A method for big data artificial intelligence information processing includes the following specific steps:

[0036] Step 1: Collect product images through the image acquisition module;

[0037] Step 2: Analyze the text display angle in the product image collected by the image collection module through the text angle analysis module to analyze the angle at which the text on the product is photographed in the image. Then, the corresponding folder will be retrieved in the database according to the text angle analyzed by the text angle analysis module through the retrieval module. After the retrieval, the text angle analyzed by the text angle analysis module will be compared with the folder retrieved by the retrieval module through the comparison module. After the comparison, the first judgment module will be used to judge whether the text angle analyzed by the comparison module is similar in the database. If there is a similarity, the text will be obtained. Then, the data judged by the first judgment module will be recorded through the recording module. If the text is obtained, the obtained text will be recorded. On the contrary, if the text is not obtained, it will be recorded using symbols. When all the text is obtained, the obtained text will be connected through the second judgment module to judge whether it is smooth. If it is smooth, it will be uploaded to the input module;

[0038] Step 3: The text that is not recognized in the recording module and the text located before and after the text are extracted by the text acquisition module. After the extraction, the text angle structure analyzed by the text angle analysis module will be extracted by the first text structure module. At the same time, the text information extracted by the text acquisition module will be compared with various words stored in the word storage module by the text comparison module to compare words that are similar to the text extracted by the text acquisition module. Then, the word structure compared by the text comparison module will be extracted by the second text structure module. After the extraction, the text structure extracted by the first text structure module and the word structure extracted by the second text structure module will be compared by the structure comparison module to compare the area of ​​the overlapping part. After the comparison, the words compared by the text comparison module will be sorted by the sorting module according to the overlapping area compared by the structure comparison module. After the sorting, the words sorted by the sorting module will be transmitted to the recording module in a descending order by the transmission module, and judged by the second judgment module. If they are smooth, they will be uploaded to the input module. Otherwise, the corresponding words will be deleted by the deletion module.

[0039] Compared with existing technologies:

[0040] By setting up a first text analysis module for analyzing the text in the product image captured by the image acquisition module, it is possible to identify the information on the product when the placement angle of the product changes, thereby improving the recognition accuracy; in addition, by setting up a second text analysis module, it is possible to use a text structure comparison method to analyze the unrecognizable text when the first text analysis module cannot completely identify the text on the product, thereby further improving the recognition accuracy of the product information. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of the process of the present invention;

[0042] Figure 2 This is a schematic diagram of the database framework of the present invention. DETAILED DESCRIPTION

[0043] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0044] The present invention provides a big data artificial intelligence information processing system, please refer to Figure 1-Figure 2 ;

[0045] The system comprises: an image acquisition module for acquiring product images; a first text analysis module for analyzing text in the product images acquired by the image acquisition module; a second text analysis module for analyzing the text that cannot be recognized by using a text structure comparison method when the first text analysis module cannot fully recognize the text on the product; an input module for inputting the text analyzed by the first text analysis module to realize the input of product information; a notification module for notifying personnel when the first text analysis module and the second text analysis module cannot fully recognize the text on the product; a sound playback module for enabling the personnel to read the text on the product aloud after notifying the personnel; and a sound analysis module for analyzing and converting the sound played by the sound playback module to obtain information on the product and place it in the input module.

[0046] The first text analysis module includes: a text angle analysis module, which is used to analyze the text display angle in the product image collected by the image collection module to analyze the angle at which the text on the product is photographed in the image; a database, which is used to store the display images of various texts at various angles; a retrieval module, which is used to retrieve the corresponding folder in the database according to the text angle analyzed by the text angle analysis module; a comparison module, which is used to compare the text angle analyzed by the text angle analysis module in the folder retrieved by the retrieval module; a first judgment module, which is used to judge whether the text angle analyzed by the comparison module is similar in the database, and if so, the text will be obtained; a recording module, which is used to record the data judged by the first judgment module, and if the text is obtained, the obtained text will be recorded, otherwise, if the text is not obtained, it will be recorded using symbols; a second judgment module, which is used to connect the obtained text when all the text is obtained to judge whether it is smooth, and if it is smooth, it will be uploaded to the input module.

[0047] The database is provided with several folders, each folder corresponds to an angle, and each file contains a text image of the corresponding angle.

[0048] The second text analysis module includes: a text acquisition module, which is used to extract the text that is not recognized in the recording module and the text located before and after the text; a word storage module, which is used to store various words; a text comparison module, which is used to compare the text information extracted by the text acquisition module with the various words stored in the word storage module, so as to compare the words that are similar to the text extracted by the text acquisition module; a first text structure module, which is used to extract the text angle structure analyzed by the text angle analysis module; a second text structure module, which is used to extract the word structure compared by the text comparison module; a structure comparison module, which is used to compare the text structure extracted by the first text structure module with the word structure extracted by the second text structure module, so as to compare the area of ​​the overlapping part; a sorting module, which is used to sort the words compared by the text comparison module according to the overlapping area compared by the structure comparison module; a transmission module, which is used to transmit the words sorted by the sorting module to the recording module in order from high to low, and judged by the second judgment module, if they are smooth, they will be uploaded to the input module, otherwise, the corresponding words will be deleted by using the deletion module.

[0049] A method for big data artificial intelligence information processing includes the following specific steps:

[0050] Step 1: Collect product images through the image acquisition module;

[0051] Step 2: Analyze the text display angle in the product image collected by the image collection module through the text angle analysis module to analyze the angle at which the text on the product is photographed in the image. Then, the corresponding folder will be retrieved in the database according to the text angle analyzed by the text angle analysis module through the retrieval module. After the retrieval, the text angle analyzed by the text angle analysis module will be compared with the folder retrieved by the retrieval module through the comparison module. After the comparison, the first judgment module will be used to judge whether the text angle analyzed by the comparison module is similar in the database. If there is a similarity, the text will be obtained. Then, the data judged by the first judgment module will be recorded through the recording module. If the text is obtained, the obtained text will be recorded. On the contrary, if the text is not obtained, it will be recorded using symbols. When all the text is obtained, the obtained text will be connected through the second judgment module to judge whether it is smooth. If it is smooth, it will be uploaded to the input module;

[0052] Step 3: extract the unrecognized text and the text located before and after the text in the recording module through the text acquisition module. After extraction, the text angle structure analyzed by the text angle analysis module will be extracted through the first text structure module. At the same time, the text information extracted by the text acquisition module will be compared with various words stored in the word storage module through the text comparison module to compare the words that are similar to the text extracted by the text acquisition module. Then, the word structure compared by the text comparison module will be extracted through the second text structure module. After extraction, the text structure extracted by the first text structure module and the word structure extracted by the second text structure module will be compared through the structure comparison module to compare the area of ​​the overlapping part. After comparison, the words compared by the text comparison module will be sorted according to the overlapping area compared by the structure comparison module through the sorting module. After sorting, the words sorted by the sorting module will be transmitted to the recording module in a descending order through the transmission module, and judged by the second judgment module. If they are smooth, they will be uploaded to the input module. Otherwise, the corresponding words will be deleted by the deletion module.

[0053] Among them, when the first text analysis module and the second text analysis module fail to completely recognize the text on the product, the personnel will be notified through the notification module. After the notification, the personnel will read the text on the product through the sound playback module. After reading, the sound played by the sound playback module will be analyzed and converted by the sound analysis module to obtain the information on the product and place it in the entry module.

[0054] Although the present invention has been described above with reference to the embodiments, various modifications may be made thereto and parts thereof may be replaced by equivalents without departing from the scope of the present invention. In particular, as long as there is no structural conflict, the various features in the embodiments disclosed in the present invention may be used in combination with each other in any manner, and the fact that these combinations are not exhaustively described in this specification is only for the sake of omitting space and saving resources. Therefore, the present invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A big data artificial intelligence information processing system, characterized in that: include: An image acquisition module, used for acquiring product images; A first text analysis module, used to analyze the text in the product image captured by the image acquisition module; The second text analysis module is used to analyze the unrecognizable text by using a text structure comparison method when the first text analysis module cannot completely recognize the text on the product; An input module, used to input the text analyzed by the first text analysis module to input product information; A notification module, used to notify personnel when the first text analysis module and the second text analysis module fail to fully recognize the text on the product; The sound playback module is used to enable personnel to read the text on the product after notifying them; The sound analysis module is used to analyze and convert the sound played by the sound playing module so as to obtain information on the product and place it in the input module.

2. A big data artificial intelligence information processing system according to claim 1, characterized in that: The first text analysis module includes: The text angle analysis module is used to analyze the text display angle in the product image acquired by the image acquisition module, so as to analyze the angle at which the text on the product is photographed in the image; A database for storing display images of various texts at various angles; The retrieval module is used to retrieve the corresponding folder in the database according to the text angle analyzed by the text angle analysis module.

3. A big data artificial intelligence information processing system according to claim 2, characterized in that: The first text analysis module also includes: A comparison module, used to compare the text angles analyzed by the text angle analysis module with the folders retrieved by the retrieval module; The first judgment module is used to judge whether the text angle analyzed by the comparison module is similar in the database. If so, the text will be obtained.

4. A big data artificial intelligence information processing system according to claim 3, characterized in that: The first text analysis module also includes: A recording module, used for recording the data judged by the first judging module. If a word is obtained, the obtained word will be recorded. Otherwise, if no word is obtained, a symbol will be used for recording. The second judgment module is used to connect the obtained texts to determine whether they are fluent when all the texts are obtained. If they are fluent, they will be uploaded to the input module.

5. A big data artificial intelligence information processing system according to claim 4, characterized in that: The database is provided with a plurality of folders, each folder corresponds to an angle, and each file contains a text image at the corresponding angle.

6. A big data artificial intelligence information processing system according to claim 4, characterized in that: The second text analysis module includes: A text acquisition module is used to extract the text that is not recognized in the recording module and the text located before and after the text; A word storage module is used to store various words; The text comparison module is used to compare the text information extracted by the text acquisition module with various words stored in the word storage module to compare words that are similar to the text extracted by the text acquisition module.

7. A big data artificial intelligence information processing system according to claim 6, characterized in that: The second text analysis module also includes: A first text structure module is used to extract the text angle structure analyzed by the text angle analysis module; The second text structure module is used to extract the word structure compared by the text comparison module; The structure comparison module is used to compare the text structure extracted by the first text structure module with the word structure extracted by the second text structure module to compare the area of ​​the overlapping part.

8. A big data artificial intelligence information processing system according to claim 7, characterized in that: The second text analysis module also includes: A sorting module, used to sort the words compared by the text comparison module according to the overlap area compared by the structure comparison module; The transmission module is used to transmit the words sorted by the sorting module to the recording module in order from high to low, and after being judged by the second judgment module, if it is fluent, it will be uploaded to the input module, otherwise, the corresponding words will be deleted by the deletion module.

9. A method for big data artificial intelligence information processing, characterized in that: The specific steps are as follows: Step 1: Collect product images through the image acquisition module; Step 2: Analyze the text display angle in the product image collected by the image collection module through the text angle analysis module to analyze the angle at which the text on the product is photographed in the image. Then, the corresponding folder will be retrieved in the database according to the text angle analyzed by the text angle analysis module through the retrieval module. After the retrieval, the text angle analyzed by the text angle analysis module will be compared with the folder retrieved by the retrieval module through the comparison module. After the comparison, the first judgment module will be used to judge whether the text angle analyzed by the comparison module is similar in the database. If there is a similarity, the text will be obtained. Then, the data judged by the first judgment module will be recorded through the recording module. If the text is obtained, the obtained text will be recorded. On the contrary, if the text is not obtained, it will be recorded using symbols. When all the text is obtained, the obtained text will be connected through the second judgment module to judge whether it is smooth. If it is smooth, it will be uploaded to the input module; Step 3: The text that is not recognized in the recording module and the text located before and after the text are extracted by the text acquisition module. After the extraction, the text angle structure analyzed by the text angle analysis module will be extracted by the first text structure module. At the same time, the text information extracted by the text acquisition module will be compared with various words stored in the word storage module by the text comparison module to compare words that are similar to the text extracted by the text acquisition module. Then, the word structure compared by the text comparison module will be extracted by the second text structure module. After the extraction, the text structure extracted by the first text structure module and the word structure extracted by the second text structure module will be compared by the structure comparison module to compare the area of ​​the overlapping part. After the comparison, the words compared by the text comparison module will be sorted by the sorting module according to the overlapping area compared by the structure comparison module. After the sorting, the words sorted by the sorting module will be transmitted to the recording module in a descending order by the transmission module, and judged by the second judgment module. If they are smooth, they will be uploaded to the input module. Otherwise, the corresponding words will be deleted by the deletion module.

Images