An information processing method and information processing system based on artificial intelligence

Abstract

The present invention provides an information processing method and an information processing system based on artificial intelligence, and the processing method includes the following steps: step S1, collecting picture information of products that need information collection; step S2, presetting an information acquirer for the products that need information collection, and being able to directly obtain the information of the product through the information acquirer; step S3, performing information recognition on the picture information obtained by information collection, and comparing the recognized information with the product information obtained by the preset information acquirer, and adjusting the comparison parameters when the information comparison is incorrect; step S4, applying the comparison parameters obtained based on the proofreading and verification module to the information recognition of the product for recognition. The present invention can adjust the recognition strategy according to the transmission angle of the product transmission process and the distance between the product and the recognition device, improve the accuracy of information processing, and solve the problem that the information recognition of existing products is not intelligent and accurate enough.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to an information processing method and an information processing system based on artificial intelligence. 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] In the existing technology, in the process of identifying the digital information on the transmission product, due to the fluidity of the transmission process, the transmission product cannot be transmitted according to the specified placement position, which leads to recognition deviation when identifying the digital information on the product during the transmission process. The existing technology usually presets a deviation coefficient to compensate for it, but the final recognition accuracy is still not enough, resulting in inaccurate information recognition of some products. Summary of the invention

[0004] In view of the shortcomings of the prior art, the purpose of the present invention is to provide an information processing method and information processing system based on artificial intelligence, which can adjust the recognition strategy according to the transmission angle of the product transmission process and the distance between the product and the recognition device, improve the accuracy of information processing, and solve the problem that the information recognition of existing products is not intelligent and accurate enough.

[0005] In order to achieve the above object, the present invention is implemented by the following technical solution: an information processing method based on artificial intelligence, the processing method comprising the following steps:

[0006] Step S1, collecting picture information of products that need information collection;

[0007] Step S2, presetting an information acquirer for the product for which information needs to be collected, and directly acquiring the information of the product through the information acquirer;

[0008] Step S3, performing information recognition on the image information obtained by the information collection, and comparing the recognized information with the product information obtained by the preset information acquisition device, and adjusting the comparison parameters when the information comparison is incorrect;

[0009] Step S4, applying the comparison parameters obtained based on the proofreading and verification module to the product information identification for identification.

[0010] Furthermore, the step S1 further comprises: obtaining a contour line of a side surface of the product having information and setting it as an information contour line, and then obtaining an angle between the contour line and a product transmission direction and setting it as a product angle;

[0011] Obtaining the distance between the product information contour line and the product information acquisition unit and setting it as the information distance;

[0012] Then obtain the image information of the side of the product with information and the product information of the information acquirer.

[0013] Furthermore, the step S3 further includes: substituting the information distance of the product into the distance calibration formula to obtain a distance conversion ratio, and performing corresponding comparison scaling on the acquired image information according to the distance conversion ratio;

[0014] The obtained image information of several products is sorted from small to large according to the product angle of the product, and then the digital information on the image is horizontally scaled and converted according to a preset first conversion coefficient, and the digital information on the image is recognized after the conversion, and then the recognition results of the products are compared with the product information of the preset information acquisition device in the sorting order;

[0015] When an error occurs in the comparison result, the first conversion coefficient and the angle of the product with the error are substituted into the coefficient compensation formula to obtain the second conversion coefficient, and then the product with the comparison error is continued to be compared according to the second conversion coefficient. When a comparison error occurs again, the current conversion coefficient and the angle of the product with the error are continued to be substituted into the coefficient compensation formula to obtain the conversion coefficient for the next stage, until all products with all angles are successfully compared.

[0016] Furthermore, the step S4 further includes: classifying the products according to their product angles according to the product angles when a comparison error occurs each time, and obtaining a conversion coefficient obtained in each classification interval;

[0017] Then, according to the conversion coefficient in each classification interval, the digital information in the image information of the products in the interval is horizontally scaled and converted, and then the converted information is digitally recognized.

[0018] An information processing system based on artificial intelligence information processing, the information processing system comprises an information collection module, a proofreading and approval module and an application processing module, the information collection module is used to collect picture information that needs to be collected;

[0019] The calibration and verification module includes an information preset unit and a verification unit. The preset unit is used to preset an information acquirer for a product that needs to collect information, and the information of the product can be directly obtained through the information acquirer; the verification unit is used to perform information recognition on the image information obtained by the information collection, and compare the recognized information with the product information obtained by the preset information acquirer, and adjust the comparison parameters when the information comparison is incorrect;

[0020] The application processing module is used to apply the comparison parameters obtained by the proofreading and verification module to the information identification of the product for identification.

[0021] Further, the information collection module includes a product status collection unit and a product information collection unit; the product status collection unit is configured with a product status collection strategy, and the product status collection strategy includes: obtaining a contour line of a side surface of the product with information and setting it as an information contour line, and then obtaining an angle between the contour line and a product transmission direction and setting it as a product angle;

[0022] Then, the distance between the product information contour line and the product information collection unit is obtained and set as the information distance;

[0023] The product information acquisition unit is used to obtain the image information of a side of the product with information and the product information of the information acquirer.

[0024] Furthermore, the checking unit is configured with a checking strategy, which includes: substituting the information distance of the product into the distance calibration formula to obtain a distance conversion ratio, and performing corresponding comparison scaling on the acquired image information according to the distance conversion ratio;

[0025] The obtained image information of several products is sorted from small to large according to the product angle of the product, and then the digital information on the image is horizontally scaled and converted according to a preset first conversion coefficient, and the digital information on the image is recognized after the conversion, and then the recognition results of the products are compared with the product information of the preset information acquisition device in the sorting order;

[0026] When an error occurs in the comparison result, the first conversion coefficient and the angle of the product with the error are substituted into the coefficient compensation formula to obtain the second conversion coefficient, and then the product with the comparison error is continued to be compared according to the second conversion coefficient. When a comparison error occurs again, the current conversion coefficient and the angle of the product with the error are continued to be substituted into the coefficient compensation formula to obtain the conversion coefficient for the next stage, until all products with all angles are successfully compared.

[0027] Further, the distance calibration formula is configured as:; wherein Hb is the distance conversion ratio, h is the information distance of the product, k is the distance conversion coefficient, and the coefficient compensation formula is configured as:; wherein K is the conversion coefficient, i represents the number of the conversion coefficient obtained next time, i-1 represents the number of the previous conversion coefficient, α is the product angle, and b1 is the conversion ratio corresponding to the angle.

[0028] Further, the application processing module includes a classification processing unit and an application unit, the classification processing unit is configured with a classification processing strategy, and the classification processing strategy includes: classifying the products according to their product angles according to the product angles when a comparison error occurs each time, and obtaining the conversion coefficients obtained in each classification interval;

[0029] The application unit is configured with an application strategy, which includes: performing horizontal scaling conversion on digital information in the image information of products in each classification interval according to a conversion coefficient in the interval, and then performing digital recognition on the converted information.

[0030] The beneficial effects of the present invention are as follows: the present invention first collects picture information of products that need information collection; then presets an information acquirer for the products that need information collection, and can directly obtain the information of the product through the information acquirer; then information recognition is performed on the picture information obtained by the information collection, and the recognized information is compared with the product information obtained by the preset information acquirer, and the comparison parameters are adjusted when the information comparison is incorrect; finally, the comparison parameters obtained based on the proofreading and approval module are applied to the information recognition of the product for identification. This process obtains the comparison parameters corresponding to products in different transmission states by pre-identifying multiple groups of products, thereby improving the accuracy of information recognition in subsequent actual applications of products. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0032] Figure 1 It is a system principle block diagram of the present invention;

[0033] Figure 2 A top view of the product transmission process of the present invention;

[0034] Figure 3 The present invention is a flow chart of the method.

[0035] In the figure: 10, product; 20, transmission device; 30, identification device. DETAILED DESCRIPTION

[0036] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0037] See also Figure 1 and Figure 2 , an information processing system based on artificial intelligence information processing, the information processing system includes an information acquisition module, a proofreading and approval module and an application processing module, the information acquisition module is used to collect image information that needs to be collected; the information acquisition module includes a product status acquisition unit and a product information acquisition unit; the product status acquisition unit is configured with a product status acquisition strategy, the product status acquisition strategy includes: acquiring the contour line of a side surface of a product 10 with information and setting it as the information contour line, and then acquiring the angle between the contour line and the transmission direction of the product 10 and setting it as the product angle; when there is a certain transmission angle between the product 10 and the transmission direction of the transmission device 20, the digital information in the image of the product 10 acquired at this time will be scaled to a certain extent, and at this time, a certain scaling ratio is required to restore the digital information to a certain extent, so as to improve the accuracy of the final recognition.

[0038] Then, the distance between the information contour line of the product 10 and the product information acquisition unit is obtained and set as the information distance; wherein the product status acquisition unit is arranged directly above the product 10, and is used to obtain the status image between the product 10 and the product information acquisition unit from the top. The product 10 is transmitted by the transmission device 20 during the transmission process.

[0039] The product information acquisition unit is used to acquire the image information of the side of the product 10 with information and the product information of the information acquirer. The information acquisition unit uses the recognition device 30 to acquire the image information of the product 10.

[0040] The calibration and verification module includes an information preset unit and a verification unit. The preset unit is used to preset an information acquirer for a product that needs to collect information, and the information of the product 10 can be directly obtained through the information acquirer; the verification unit is used to identify the image information obtained by the information acquisition, and compare the identified information with the product information obtained by the preset information acquirer, and adjust the comparison parameters when the information comparison is incorrect;

[0041] The verification unit is configured with a verification strategy, which includes: substituting the information distance of the product 10 into the distance calibration formula to obtain the distance conversion ratio, and scaling the acquired image information for corresponding comparison according to the distance conversion ratio; different distances between the product 10 and the recognition device 30 have a certain proportion of difference in the digital information in the final image information, so scaling the final product 10 image information according to the information distance of the product 10 can improve the accuracy of the final recognition.

[0042] The acquired image information of the plurality of products 10 is sorted from small to large according to the product angle of the product 10, and then the digital information on the image is horizontally scaled and converted according to a preset first conversion coefficient, and the digital information on the image is recognized after the conversion, and then the recognition results of the products 10 are sequentially compared with the product information of the preset information acquisition device according to the sorting order;

[0043] When an error occurs in the comparison result, the first conversion coefficient and the product angle of the product 10 with the error are substituted into the coefficient compensation formula to obtain the second conversion coefficient, and then the product 10 with the comparison error is continued to be compared according to the second conversion coefficient. When a comparison error occurs again, the current conversion coefficient and the product angle of the product 10 with the error are continued to be substituted into the coefficient compensation formula to obtain the conversion coefficient of the next stage, until all products 10 with different angles are successfully compared. Among them, each time a comparison error occurs, it means that the current product angle has reached the level that needs to be classified into the next level, and at this time, the conversion coefficient needs to be changed again to improve the final recognition accuracy.

[0044] The distance calibration formula is configured as follows:; wherein Hb is the distance conversion ratio, h is the information distance of product 10, k is the distance conversion coefficient, and the value of k is between 0.5 and 1. The coefficient compensation formula is configured as follows:; wherein K is the conversion coefficient, i represents the number of the conversion coefficient obtained next time, i-1 represents the number of the conversion coefficient obtained last time, α is the product angle, and b1 is the conversion ratio corresponding to the angle, wherein the value of b1 is greater than 1.

[0045] The application processing module is used to apply the comparison parameters obtained by the proofreading and verifying module to the information identification of the product 10 for identification.

[0046] The application processing module includes a classification processing unit and an application unit. The classification processing unit is configured with a classification processing strategy. The classification processing strategy includes: classifying the product 10 according to its product angle based on the product angle each time a comparison error occurs, and obtaining the conversion coefficient obtained in each classification interval; through continuous verification by the verification unit, the product 10 can be divided according to its angle, and the corresponding conversion coefficient can be directly used in actual application after division, thereby improving the accuracy of product 10 recognition and improving the intelligence of information recognition of different products 10.

[0047] The application unit is configured with an application strategy, which includes: performing horizontal scaling conversion on the digital information in the image information of the product 10 in each classification interval according to the conversion coefficient in the interval, and then performing digital recognition on the converted information. Under normal circumstances, when there is an angle between the product 10 and the transmission direction of the transmission device 20, the image information corresponding to the product 10 can be corrected by simply performing horizontal scaling.

[0048] See also Figure 3 , the information processing method of the information processing system comprises the following steps:

[0049] Step S1, collect image information of the product 10 that needs to be collected; obtain the contour line of the side of the product 10 with information and set it as the information contour line, then obtain the angle between the contour line and the product transmission direction and set it as the product angle; obtain the distance between the information contour line of the product 10 and the product information collection unit and set it as the information distance; then obtain the image information of the side of the product 10 with information and the product information of the information acquirer.

[0050] Step S2, presetting an information acquirer for the product for which information collection is required, and directly acquiring the information of the product 10 through the information acquirer.

[0051] Step S3, performing information recognition on the image information obtained by the information collection, and comparing the recognized information with the product information obtained by the preset information acquisition device, and adjusting the comparison parameters when the information comparison is incorrect;

[0052] Substitute the information distance of the product 10 into the distance calibration formula to obtain the distance conversion ratio, and perform corresponding comparison scaling on the acquired image information according to the distance conversion ratio;

[0053] The acquired image information of the plurality of products 10 is sorted from small to large according to the product angle of the product 10, and then the digital information on the image is horizontally scaled and converted according to a preset first conversion coefficient, and the digital information on the image is recognized after the conversion, and then the recognition results of the products 10 are sequentially compared with the product information of the preset information acquisition device according to the sorting order;

[0054] When an error occurs in the comparison result, the first conversion coefficient and the product angle of the product 10 with the error are substituted into the coefficient compensation formula to obtain the second conversion coefficient, and then the product 10 with the comparison error is continued to be compared according to the second conversion coefficient. When a comparison error occurs again, the current conversion coefficient and the product angle of the product 10 with the error are continued to be substituted into the coefficient compensation formula to obtain the conversion coefficient of the next stage, until all products 10 with all angles are successfully compared.

[0055] Step S4, applying the comparison parameters obtained based on the proofreading and verification module to the information identification of the product 10 for identification; classifying the product 10 according to its product angle based on the product angle when each comparison error occurs, and obtaining the conversion coefficient obtained in each classification interval; then performing horizontal scaling conversion on the digital information in the image information of the product 10 in each classification interval based on the conversion coefficient in the interval, and then performing digital identification on the converted information.

[0056] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An information processing method based on artificial intelligence, characterized in that: The processing method comprises the following steps: Step S1, collecting picture information of products that need information collection; Step S2, presetting an information acquirer for the product for which information needs to be collected, and directly acquiring the information of the product through the information acquirer; Step S3, performing information recognition on the image information obtained by the information collection, and comparing the recognized information with the product information obtained by the preset information acquisition device, and adjusting the comparison parameters when the information comparison is incorrect; Step S4, applying the comparison parameters obtained by the proofreading and verification module to the product information identification for identification; The step S1 further includes: obtaining a contour line of a side surface of the product with information and setting it as an information contour line, and then obtaining an angle between the contour line and a product transmission direction and setting it as a product angle; Obtaining the distance between the product information contour line and the product information acquisition unit and setting it as the information distance; Then obtain the image information of the side of the product with information and the product information of the information acquirer; The step S3 further includes: substituting the information distance of the product into the distance calibration formula to obtain a distance conversion ratio, and performing corresponding comparison scaling on the acquired image information according to the distance conversion ratio; The obtained image information of several products is sorted from small to large according to the product angle of the product, and then the digital information on the image is horizontally scaled and converted according to a preset first conversion coefficient, and the digital information on the image is recognized after the conversion, and then the recognition results of the products are compared with the product information of the preset information acquisition device in the sorting order; When an error occurs in the comparison result, the first conversion coefficient and the angle of the product with the error are substituted into the coefficient compensation formula to obtain the second conversion coefficient, and then the product with the comparison error is continued to be compared according to the second conversion coefficient. When a comparison error occurs again, the current conversion coefficient and the angle of the product with the error are continued to be substituted into the coefficient compensation formula to obtain the conversion coefficient for the next stage, until all products with all angles are successfully compared.

2. The information processing method based on artificial intelligence according to claim 1, characterized in that: The step S4 further includes: classifying the products according to their product angles according to each product angle when a comparison error occurs, and obtaining a conversion coefficient obtained in each classification interval; Then, according to the conversion coefficient in each classification interval, the digital information in the image information of the products in the interval is horizontally scaled and converted, and then the converted information is digitally recognized.

3. An information processing system based on artificial intelligence, the system implementing an information processing method based on artificial intelligence as claimed in any one of claims 1-2, characterized in that: The information processing system includes an information acquisition module, a calibration and verification module, and an application processing module. The information acquisition module is used to collect the image information that needs to be collected; The calibration and verification module includes an information preset unit and a verification unit. The information preset unit is used to preset an information acquirer for a product that needs to collect information, and the information of the product can be directly obtained through the information acquirer; the verification unit is used to perform information recognition on the image information obtained by the information collection, and compare the recognized information with the product information obtained by the preset information acquirer, and adjust the comparison parameters when the information comparison is incorrect; The application processing module is used to apply the comparison parameters obtained by the proofreading and verification module to the information identification of the product for identification; The information collection module includes a product status collection unit and a product information collection unit; The product status acquisition unit is configured with a product status acquisition strategy, which includes: acquiring a contour line of a side surface of the product with information and setting it as an information contour line, and then acquiring an angle between the contour line and a product transmission direction and setting it as a product angle; Then, the distance between the product information contour line and the product information collection unit is obtained and set as the information distance; The product information acquisition unit is used to obtain the image information of the side of the product with information and the product information of the information acquirer; The checking unit is configured with a checking strategy, which includes: substituting the information distance of the product into the distance calibration formula to obtain the distance conversion ratio, and performing corresponding comparison scaling on the acquired image information according to the distance conversion ratio; The obtained image information of several products is sorted from small to large according to the product angle of the product, and then the digital information on the image is horizontally scaled and converted according to a preset first conversion coefficient, and the digital information on the image is recognized after the conversion, and then the recognition results of the products are compared with the product information of the preset information acquisition device in the sorting order; When an error occurs in the comparison result, the first conversion coefficient and the angle of the product with the error are substituted into the coefficient compensation formula to obtain the second conversion coefficient, and then the product with the comparison error is continued to be compared according to the second conversion coefficient. When a comparison error occurs again, the current conversion coefficient and the angle of the product with the error are continued to be substituted into the coefficient compensation formula to obtain the conversion coefficient for the next stage, until all products with all angles are successfully compared.

4. The information processing system according to claim 3, characterized in that: The application processing module includes a classification processing unit and an application unit. The classification processing unit is configured with a classification processing strategy. The classification processing strategy includes: classifying the products according to their product angles according to the product angles when a comparison error occurs each time, and obtaining the conversion coefficients obtained in each classification interval; The application unit is configured with an application strategy, which includes: performing horizontal scaling conversion on digital information in the image information of products in each classification interval according to a conversion coefficient in the interval, and then performing digital recognition on the converted information.

Images