CN112308678A - Price information processing method, device, equipment and medium based on image recognition - Google Patents
Price information processing method, device, equipment and medium based on image recognition Download PDFInfo
- Publication number
- CN112308678A CN112308678A CN202011246846.5A CN202011246846A CN112308678A CN 112308678 A CN112308678 A CN 112308678A CN 202011246846 A CN202011246846 A CN 202011246846A CN 112308678 A CN112308678 A CN 112308678A
- Authority
- CN
- China
- Prior art keywords
- information
- price
- candidate text
- text information
- candidate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0611—Request for offers or quotes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
- G06Q30/0643—Graphical representation of items or shoppers
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the disclosure discloses a price information processing method, device, equipment and medium based on image recognition. One embodiment of the method comprises: extracting text information from the article display image as text identification information to obtain a text identification information set; screening out text identification information meeting a first preset condition group from the text identification information set to serve as candidate text information; generating first candidate text information, a second candidate text information set and third candidate text information in response to determining that candidate text information including any price identification keyword information in a preset price identification keyword information set exists in the candidate text information set; generating a first set of distance values and a second set of distance values; candidate price information is generated based on the second set of candidate text information, the first set of distance values, and the second set of distance values. This embodiment improves the accuracy of the generated price information.
Description
Technical Field
Embodiments of the present disclosure relate to the field of computer technologies, and in particular, to a price information processing method, apparatus, device, and medium based on image recognition.
Background
Price information processing is a technology for acquiring price information by a certain technical means. Currently, a common method is to crawl price information displayed in a page through a specific crawler program.
However, when price information processing is performed in the above manner, there are often technical problems as follows:
firstly, the webpage structures of different shopping platforms are often different, so that different crawler programs need to be developed to crawl price information displayed in the webpage; moreover, when the webpage structure changes, the crawler program fails, so that the development and maintenance cost of the crawler program is high; in addition, the price in the page is only the current price of the item, and for scenes such as the pre-sale of a new item, the price information in the pre-sale cannot be obtained in advance, so that the generated and displayed price information is not accurate enough.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Some embodiments of the present disclosure propose price information processing methods, apparatuses, devices, and media based on image recognition to solve one or more of the technical problems mentioned in the background section above.
In a first aspect, some embodiments of the present disclosure provide a price information processing method based on image recognition, the method including: extracting text information from the article display image as text identification information to obtain a text identification information set; and screening out the text identification information meeting a first preset condition group from the text identification information set to serve as candidate text information, and obtaining a candidate text information set. And in response to determining that candidate text information including any price identification keyword information in a preset price identification keyword information set exists in the candidate text information set, generating a first candidate text information, a second candidate text information set and third candidate text information based on the candidate text information set, the price identification keyword information set and a preset price-related identifier information set. Generating a first set of distance values and a second set of distance values based on the first candidate text information, the second set of candidate text information and the third candidate text information. And generating candidate price information based on the second candidate text information set, the first distance value set and the second distance value set.
Optionally, generating a first candidate text information set, a second candidate text information set, and a third candidate text information based on the candidate text information set, the price identification keyword information set, and a preset price related identifier information set, includes: and screening candidate text information containing any price identification keyword in the price identification keyword information set in the text content information from the candidate text information set to serve as first candidate text information.
Optionally, generating a first candidate text information set, a second candidate text information set, and a third candidate text information based on the candidate text information set, the price identification keyword information set, and a preset price related identifier information set, includes: and screening candidate text information containing numerical values in the text content information from the candidate text information set to serve as second candidate text information, and obtaining a second candidate text information set.
Optionally, generating a first candidate text information set, a second candidate text information set, and a third candidate text information based on the candidate text information set, the price identification keyword information set, and a preset price related identifier information set, includes: and screening candidate text information containing any price-related identifier information in the price-related identifier information set in the text content information from the candidate text information set to serve as third candidate text information.
Optionally, generating a first distance value set and a second distance value set based on the first candidate text information, the second candidate text information set, and the third candidate text information, includes the following steps: determining a distance value between a center coordinate value of the identification box included in the first candidate text information and a center coordinate value of the identification box included in each second candidate text information in the second candidate text information set as a first distance value, so as to obtain a first distance value set; and determining a distance value between the center coordinate value of the identification frame included in the third candidate text information and the center coordinate value of the identification frame included in each second candidate text information in the second candidate text information set as a second distance value, so as to obtain a second distance value set.
Optionally, generating candidate price information based on the second candidate text information set, the first distance value set, and the second distance value set, includes the following steps: screening second candidate text information of which the corresponding first distance value meets a second preset condition from the second candidate text information set to serve as first candidate price information, and obtaining a first candidate price information set; and screening out first candidate price information of which the corresponding second distance value meets a third preset condition from the first candidate price information set as candidate price information.
Optionally, the method further comprises: and in response to determining that candidate text information including any price-related keyword information in a preset price-related keyword information set exists in the candidate text information set, generating fourth candidate text information based on the candidate text information set and the price-related keyword information set.
Optionally, generating a fourth candidate text message based on the candidate text message set and the price-related keyword message set includes: and screening candidate text information of which the text content information comprises any price-related keyword information in the price-related keyword information set from the candidate text information set to serve as fourth candidate text information.
Optionally, generating a fourth candidate text message based on the candidate text message set and the price-related keyword message set, further includes: and determining a distance value between the center coordinate value of the identification box included in the fourth candidate text information and the center coordinate value of the identification box included in each second candidate text information in the second candidate text information set as a third distance value, so as to obtain a third distance value set.
Optionally, generating a fourth candidate text message based on the candidate text message set and the price-related keyword message set, further includes: and screening out second candidate text information of which the corresponding third distance value meets a fourth preset condition from the second candidate text information set to serve as price related text information.
Optionally, generating a fourth candidate text message based on the candidate text message set and the price-related keyword message set, further includes: and determining the candidate price information as the price information to be presented in response to the fact that the difference value between the candidate price information and the page price information is determined to be within a preset range.
Optionally, generating a fourth candidate text message based on the candidate text message set and the price-related keyword message set, further includes: and generating presentation price information based on the price information to be presented and the price related text information.
In a second aspect, some embodiments of the present disclosure provide an image recognition-based price information processing apparatus, including: the extraction unit is configured to extract text information from the article display image as text identification information, and a text identification information set is obtained; the screening unit is configured to screen out text identification information meeting a first preset condition group from the text identification information set to serve as candidate text information, and a candidate text information set is obtained; a first generating unit configured to generate a first candidate text information, a second candidate text information and a third candidate text information based on the candidate text information set, the price identification keyword information set and a preset price-related identifier information set in response to determining that there is candidate text information including any price identification keyword information in a preset price identification keyword information set in the candidate text information set; a second generating unit configured to generate a first distance value set and a second distance value set based on the first candidate text information, the second candidate text information set, and the third candidate text information; a third generating unit configured to generate candidate price information based on the second candidate text information set, the first distance value set, and the second distance value set.
Optionally, the first generating unit is further configured to: and screening candidate text information containing any price identification keyword in the price identification keyword information set in the text content information from the candidate text information set to serve as first candidate text information.
Optionally, the first generating unit is further configured to: and screening candidate text information containing numerical values in the text content information from the candidate text information set to serve as second candidate text information, and obtaining a second candidate text information set.
Optionally, the first generating unit is further configured to: and screening candidate text information containing any price-related identifier information in the price-related identifier information set in the text content information from the candidate text information set to serve as third candidate text information.
Optionally, the second generating unit is further configured to: determining a distance value between a center coordinate value of the identification box included in the first candidate text information and a center coordinate value of the identification box included in each second candidate text information in the second candidate text information set as a first distance value, so as to obtain a first distance value set; and determining a distance value between the center coordinate value of the identification frame included in the third candidate text information and the center coordinate value of the identification frame included in each second candidate text information in the second candidate text information set as a second distance value, so as to obtain a second distance value set.
Optionally, the third generating unit is further configured to: screening second candidate text information of which the corresponding first distance value meets a second preset condition from the second candidate text information set to serve as first candidate price information, and obtaining a first candidate price information set; and screening out first candidate price information of which the corresponding second distance value meets a third preset condition from the first candidate price information set as candidate price information.
Optionally, the apparatus further comprises: and in response to determining that candidate text information including any price-related keyword information in a preset price-related keyword information set exists in the candidate text information set, generating fourth candidate text information based on the candidate text information set and the price-related keyword information set.
Optionally, the apparatus is further configured to: and screening candidate text information of which the text content information comprises any price-related keyword information in the price-related keyword information set from the candidate text information set to serve as fourth candidate text information.
Optionally, the apparatus further comprises: and determining a distance value between the center coordinate value of the identification box included in the fourth candidate text information and the center coordinate value of the identification box included in each second candidate text information in the second candidate text information set as a third distance value, so as to obtain a third distance value set.
Optionally, the apparatus further comprises: and screening out second candidate text information of which the corresponding third distance value meets a fourth preset condition from the second candidate text information set to serve as price related text information.
Optionally, the apparatus further comprises: and determining the candidate price information as the price information to be presented in response to the fact that the difference value between the candidate price information and the page price information is determined to be within a preset range.
Optionally, the apparatus further comprises: and generating presentation price information based on the price information to be presented and the price related text information.
In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method described in any of the implementations of the first aspect.
In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium on which a computer program is stored, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect.
The above embodiments of the present disclosure have the following advantages: the accuracy of price information generated by the image recognition-based price information processing method of some embodiments of the present disclosure is improved. Specifically, the inventors found that the reason for the generated price information being not accurate enough is that: price information crawled by a crawler program is often inconsistent with the actual price in scenes such as new product pre-sale. Based on this, the price information processing method based on image recognition of some embodiments of the present disclosure is realized by acquiring a text recognition information set in an article display image. And then screening out the text identification information meeting the preset conditions according to the preset conditions. In practical situations, the display position of the price information is generally closer to the display position of the price identification keyword information or the price related identifier information, and the distance is used for filtering to obtain the price information of the articles in a corresponding scene of pre-selling new articles and the like. In a scene of pre-selling a new product and the like, price information corresponding to the product is often updated in the product display image in advance, but is not updated in the display page synchronously. Therefore, the method determines the price information of the article through the text identification information set in the article display image, and can well represent the price corresponding to the article in scenes such as the pre-sale of a new article. Thus, the accuracy of the generated price information is improved.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and elements are not necessarily drawn to scale.
FIG. 1 is a schematic diagram of one application scenario of a price information processing method based on image recognition, according to some embodiments of the present disclosure;
FIG. 2 is a flow diagram of some embodiments of a price information processing method based on image recognition according to the present disclosure;
FIG. 3 is a set of textual recognition information in some embodiments of a price information processing method based on image recognition according to the present disclosure;
FIG. 4 is a flow diagram of further embodiments of a price information processing method based on image recognition according to the present disclosure;
FIG. 5 is a schematic block diagram of some embodiments of an image recognition based price information processing apparatus according to the present disclosure;
FIG. 6 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 is a schematic diagram of an application scenario of a price information processing method based on image recognition according to some embodiments of the present disclosure.
In the application scenario of fig. 1, first, the computing device 101 may extract text information from the item display image 102 as text identification information, resulting in a set of text identification information 103. Then, the computing device 101 may screen out the text recognition information satisfying the first preset condition group from the text recognition information set 103 as candidate text information, resulting in a candidate text information set 104. Next, the computing device 101 may generate a first candidate text information 107, a second candidate text information 108, and a third candidate text information 109 based on the candidate text information set 104, the price identification keyword information set 105, and a preset price-related identifier information set 106 in response to determining that there is a candidate text information including any one of the preset price identification keyword information sets 105 in the candidate text information set 104. The computing device 101 may then generate a first set of distance values 110 and a second set of distance values 111 based on the first candidate text information 107, the second set of candidate text information 108, and the third candidate text information 109. Finally, the computing device 101 may generate candidate price information 112 based on the second set of candidate text information 108, the first set of distance values 110, and the second set of distance values 111.
The computing device 101 may be hardware or software. When the computing device is hardware, it may be implemented as a distributed cluster composed of multiple servers or terminal devices, or may be implemented as a single server or a single terminal device. When the computing device is embodied as software, it may be installed in the hardware devices enumerated above. It may be implemented, for example, as multiple software or software modules to provide distributed services, or as a single software or software module. And is not particularly limited herein.
It should be understood that the number of computing devices in FIG. 1 is merely illustrative. There may be any number of computing devices, as implementation needs dictate.
With continued reference to fig. 2, a flow diagram 200 of some embodiments of a price information processing method based on image recognition according to the present disclosure is shown. The price information processing method based on image recognition comprises the following steps:
In some embodiments, the execution subject of the price information processing method based on image Recognition (for example, the computing device 101 shown in fig. 1) may extract the characters from the item display image by using An OCR (Optical Character Recognition) technique, An EAST (Scene Character detection) algorithm, a CNN (Convolutional Neural Networks) model, or the like.
In some embodiments, the execution subject may filter out the text recognition information satisfying the first preset condition group from the text recognition information set 301 as candidate text information, to obtain a candidate text information set. Wherein, the first preset condition set may include, but is not limited to, at least one of the following: corresponding to text recognition informationThe area of the mark frame is more than or equal to 1cm2And the central coordinate value of the identification box corresponding to the text identification information is a positive number. The identification box can be used for framing the text information in the display picture. The center coordinate value of the mark frame is a coordinate value in the image coordinate system. The image coordinate system may be a coordinate system established with an upper left corner of the image as an origin, a line parallel to a wide side of the image as a horizontal axis, and a line parallel to a long side of the image as a vertical axis.
In some embodiments, the executing body generates the first candidate text information, the second candidate text information and the third candidate text information based on the candidate text information set, the price identification keyword information set and the preset price-related identifier information set in response to determining that there is candidate text information including any price identification keyword information in the preset price identification keyword information set in the candidate text information set. Wherein the price identification keyword information set may include, but is not limited to, at least one of the following: "hand price", "store-celebration price", "new-person price", "opening-to-learn price", "preferential price", "activity price", "ticket back price", "overtime price", "first-order price", "surprise price", "wild price", "time-limited price". The set of price related identifier information may include, but is not limited to, at least one of: "element", "this", "$". May include the steps of:
firstly, screening candidate text information containing any price identification keyword in the price representation keyword information set from the candidate text information set through a BF (Brute Force) algorithm to serve as first candidate text information.
And secondly, screening candidate text information containing text numerical values from the candidate text information set through a Boyer-Moore character string search algorithm to obtain a second candidate text information set.
And thirdly, screening candidate text information containing any price related identifier information in the price related identifier information set from the candidate text information set through a Sunday algorithm to serve as third candidate text information.
In some embodiments, the executing body generating the first distance value set and the second distance value set based on the first candidate text information, the second candidate text information set, and the third candidate text information may include:
first, a distance value between a coordinate value of an upper left corner of an identification box corresponding to the first candidate text information and a coordinate value of an upper left corner of an identification box corresponding to each second candidate text information in the second candidate text information set is determined through a two-point distance formula to generate a first distance value, and a first distance value set is obtained. Wherein the distance value may be a euclidean distance or the like.
And secondly, determining a distance value between the coordinate value of the upper left corner of the identification box corresponding to the third candidate text information and the coordinate value of the upper left corner of the identification box corresponding to each second candidate text information in the second candidate text information set through a two-point distance formula to generate a second distance value, so as to obtain a second distance value set.
In some embodiments, the execution subject generates candidate price information based on the second set of candidate text information, the first set of distance values, and the second set of distance values. The second candidate text information whose corresponding first distance value and second distance value are respectively the maximum values of the first distance value set and the second distance value set may be screened from the second candidate text information set as candidate price information.
The above embodiments of the present disclosure have the following advantages: the accuracy of price information generated by the image recognition-based price information processing method of some embodiments of the present disclosure is improved. Specifically, the inventors found that the reason for the generated price information being not accurate enough is that: price information crawled by a crawler program is often inconsistent with the actual price in scenes such as new product pre-sale. Based on this, the price information processing method based on image recognition of some embodiments of the present disclosure is realized by acquiring a text recognition information set in an article display image. And then screening out the text identification information meeting the preset conditions according to the preset conditions. In practical situations, the display position of the price information is generally closer to the display position of the price identification keyword information or the price related identifier information, and the distance is used for filtering to obtain the price information of the articles in a corresponding scene of pre-selling new articles and the like. In a scene of pre-selling a new product and the like, price information corresponding to the product is often updated in the product display image in advance, but is not updated in the display page synchronously. Therefore, the method determines the price information of the article through the text identification information set in the article display image, and can well represent the price corresponding to the article in scenes such as the pre-sale of a new article. Thus, the accuracy of the generated price information is improved.
With further reference to FIG. 4, a flow 400 of further embodiments of a price information processing method based on image recognition is shown. The flow 400 of the price information processing method based on image recognition comprises the following steps:
In some embodiments, the execution subject may recognize and extract text information from the article display image through an RNN (Recurrent Neural Network) model or an LSTM (Long Short-Term Memory) model to generate a text recognition information set. Wherein, the text information may include but is not limited to at least one of the following: text content information, text confidence value, identification box size information. The above-mentioned identification box size information may include, but is not limited to, at least one of the following: the coordinate value of the center of the identification frame, the length value of the identification frame and the width value of the identification frame.
As an example, the above text recognition information set may be [ [ six grades of gale, 0.29652, (80, 80), 40, 45], [ penta-leaf gale, energy efficient, 0.99917, (240, 80), 100, 45] ].
In some embodiments, the execution subject may filter out, from the text recognition information set, text recognition information that satisfies a first preset condition group as candidate text information, to obtain a candidate text information set. Wherein, the first preset condition set may include, but is not limited to, at least one of the following: the text confidence value included in the text recognition information is greater than or equal to the preset confidence value, the length value of the identification frame included in the text recognition information is greater than or equal to the preset length value of the identification frame, and the width value of the identification frame is greater than or equal to the preset width value of the identification frame.
As an example, the preset confidence value may be 0.1. The preset logo box length value may be 15 (pixels). The preset flag frame width value may be 15 (pixels).
In some embodiments, the execution subject may filter out candidate text information, which includes any price identification keyword in the price identification keyword information set, in the text content information from the candidate text information set as the first candidate text information. Wherein, the price identification keyword information may include, but is not limited to, at least one of the following items: "new price", "collocation price", "experience price", "genuine price", "up-new price", "cost price", "brand price", "respect price".
As an example, the execution main body may screen candidate text information, which includes any price identification keyword in the price identification keyword information set, from the candidate text information set through a KMP (Knuth-Morris-Pratt, pattern matching) algorithm as first candidate text information.
In some embodiments, the execution subject may screen out candidate text information, which includes any price identification keyword in the price identification keyword information set, in the text content information from the candidate text information set as the first candidate text information in various ways.
As an example, the executing body may screen candidate text information, which includes any price identification keyword in the price identification keyword information set, in the text content information from the candidate text information set through a Rabin-Karp algorithm as the first candidate text information.
In some embodiments, the executing entity may screen candidate text information, which includes any price-related identifier information in the price-related identifier information set, in the text content information from the candidate text information set as the third candidate text information through any algorithm mentioned in step 202, step 403, step 404, and 404. Wherein the set of price related identifier information may comprise at least one of: "element", "$", "#".
In some embodiments, the executing entity may determine, by a two-point distance formula, a distance value between a center coordinate value of the identification box included in the first candidate text information and a center coordinate value of the identification box included in each second candidate text information in the second candidate text information set to generate a first distance value, so as to obtain the first distance value set.
In some embodiments, the executing entity may determine, by a two-point distance formula, a distance value between a center coordinate value of the identification box included in the third candidate text information and a center coordinate value of the identification box included in each second candidate text information in the second candidate text information set to generate a second distance value, so as to obtain the second distance value set.
And 408, screening second candidate text information of which the corresponding first distance value meets a second preset condition from the second candidate text information set to serve as first candidate price information to obtain a first candidate price information set.
In some embodiments, the executing entity may screen out, from the second candidate text information set, second candidate text information whose corresponding first distance value satisfies a second preset condition as the first candidate price information, to obtain the first candidate price information set. The second preset condition may be that the first distance value is less than or equal to a mean value of each first distance value in the first distance value set.
In some embodiments, the executing entity may screen out, from the first candidate price information set, first candidate price information whose corresponding second distance value satisfies a third preset condition as candidate price information. The third preset condition may be that the second distance value is equal to a smallest second distance value in the second distance value set.
Optionally, the executing body may generate a fourth candidate text message based on the candidate text message set and the price related keyword message set in response to determining that the candidate text message set includes candidate text messages including any price related keyword message in the preset price related keyword message set. Wherein the set of price related keyword information may include at least one of: "coupon", "fold", "decrease", "full".
Optionally, the executing body may determine, as a third distance value, a distance value between a center coordinate value of the identification box included in the fourth candidate text information and a center coordinate value of the identification box included in each second candidate text information in the second candidate text information set, so as to obtain the third distance value set. The distance value between the coordinate value of the center of the logo box included in the fourth candidate text information and the coordinate value of the center of the logo box included in each second candidate text information in the second candidate text information set can be determined through a distance formula between two points.
Optionally, the executing body may screen, from the second candidate text information set, second candidate text information whose corresponding third distance value meets a fourth preset condition as price-related text information. The fourth preset condition may be that the third distance value is the same as the minimum value of the third distance values.
Optionally, the executing body may determine the candidate price information as the price information to be presented in response to determining that a difference between the candidate price information and the page price information is within a preset range. Wherein the preset range may be [0, 100 ]. The page price information can be obtained by crawling from a display page of the corresponding article through a crawler program.
Optionally, the execution main body may generate presentation price information based on the price information to be presented and the price-related text information.
As an example, the price information to be presented may be "399 yuan", and the price-related text information may be "300 yuan to 40 yuan full". Thus, the generated presentation price information may be "359 dollars".
As yet another example, the price information to be presented may be "99 yuan", and the price-related text information may be "200 yuan to 40 yuan full". Thus, the generated presentation price information may be "99-yuan".
The above embodiments of the present disclosure have the following advantages: text recognition information with a low text confidence value can be understood as text information recognition with insufficient precision. Meanwhile, the fact that the length value and the width value of the identification frame are small can be understood that the area occupied by the text information inside the identification frame is small, in practical situations, the text information is generally punctuation marks and the like, and the influence on the generation of subsequent price information is small, so that the acquired text recognition information is primarily screened through the first preset condition group, and the text recognition information with the text confidence value, the length value and the width value not meeting the conditions is filtered. The consumption of computing resources is reduced. In addition, since the text recognition information set recognized from the article display image includes the price identification keyword, the text recognition information of any one of the numerical value or the price-related identifier information has a large influence on the final price generation. Therefore, the first candidate text information, the second candidate text information set and the third candidate text information are obtained through condition screening. Therefore, information with small influence on the final price generation is further filtered, and the consumption of computing resources is reduced. Then, in an actual case, in the article display image, a numerical value in the vicinity of the text identification information containing the price identification keyword information and the text identification information containing the price-related identifier information tends to be price information. Based on this, further filtering is performed by distance, thereby generating candidate price information. This approach compares to using a crawler to crawl price information in a page as price information. The price information recognition and generation under the scenes of new product pre-sale and the like can be better adapted. Thus, the accuracy of the generated price information is improved.
With further reference to fig. 5, as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a price information processing apparatus based on image recognition, which correspond to those of the method embodiments shown in fig. 2, and which may be applied in particular in various electronic devices.
As shown in fig. 5, the price information processing apparatus 500 based on image recognition of some embodiments includes: an extraction unit 501, a screening unit 502, a first generation unit 503, a second generation unit 504, and a third generation unit 505. The extracting unit 501 is configured to extract text information from the article display image as text identification information, resulting in a text identification information set. The screening unit 502 is configured to screen out text recognition information satisfying a first preset condition group from the text recognition information set as candidate text information, resulting in a candidate text information set. A first generating unit 503 configured to generate a first candidate text information, a second candidate text information and a third candidate text information based on the candidate text information set, the price identification keyword information set and a preset price-related identifier information set in response to determining that there is candidate text information including any price identification keyword information in a preset price identification keyword information set in the candidate text information set. A second generating unit 504 configured to generate a first distance value set and a second distance value set based on the first candidate text information, the second candidate text information set, and the third candidate text information. A third generating unit 505 configured to generate candidate price information based on the second candidate text information set, the first distance value set, and the second distance value set.
In an optional implementation of some embodiments, the first generating unit 503 is further configured to: and screening candidate text information containing any price identification keyword in the price identification keyword information set in the text content information from the candidate text information set to serve as first candidate text information.
In an optional implementation of some embodiments, the first generating unit 503 is further configured to: and screening candidate text information containing numerical values in the text content information from the candidate text information set to serve as second candidate text information, and obtaining a second candidate text information set.
In an optional implementation of some embodiments, the first generating unit 503 is further configured to: and screening candidate text information containing any price-related identifier information in the price-related identifier information set in the text content information from the candidate text information set to serve as third candidate text information.
In an optional implementation of some embodiments, the second generating unit 504 is further configured to: determining a distance value between a center coordinate value of the identification box included in the first candidate text information and a center coordinate value of the identification box included in each second candidate text information in the second candidate text information set as a first distance value, so as to obtain a first distance value set; and determining a distance value between the center coordinate value of the identification frame included in the third candidate text information and the center coordinate value of the identification frame included in each second candidate text information in the second candidate text information set as a second distance value, so as to obtain a second distance value set.
In an optional implementation of some embodiments, the third generating unit 505 is further configured to: screening second candidate text information of which the corresponding first distance value meets a second preset condition from the second candidate text information set to serve as first candidate price information, and obtaining a first candidate price information set; and screening out first candidate price information of which the corresponding second distance value meets a third preset condition from the first candidate price information set as candidate price information.
In an optional implementation of some embodiments, the apparatus 500 further comprises: a fourth generating unit configured to generate fourth candidate text information based on the candidate text information set and the price-related keyword information set in response to determining that there is candidate text information including any price-related keyword information in a preset price-related keyword information set in the candidate text information set.
In an optional implementation of some embodiments, the fourth generating unit is further configured to: and screening candidate text information of which the text content information comprises any price-related keyword information in the price-related keyword information set from the candidate text information set to serve as fourth candidate text information.
In an optional implementation of some embodiments, the apparatus further comprises: and determining a distance value between the center coordinate value of the identification box included in the fourth candidate text information and the center coordinate value of the identification box included in each second candidate text information in the second candidate text information set as a third distance value, so as to obtain a third distance value set.
In an optional implementation of some embodiments, the apparatus further comprises: and determining the candidate price information as the price information to be presented in response to the fact that the difference value between the candidate price information and the page price information is determined to be within a preset range.
In an optional implementation of some embodiments, the apparatus further comprises: and generating presentation price information based on the price information to be presented and the price related text information.
It will be understood that the elements described in the apparatus 500 correspond to various steps in the method described with reference to fig. 2. Meanwhile, full-minus information is possibly included in the display picture corresponding to the article. First, the full minus keyword is recognized by the fourth generation unit. Then, a full-minus value is determined through regular filtering and distance calculation. Therefore, final price information is obtained, and the accuracy of price information generation is improved.
Referring now to FIG. 6, a block diagram of an electronic device (such as computing device 101 shown in FIG. 1)600 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 6, electronic device 600 may include a processing means (e.g., central processing unit, graphics processor, etc.) 601 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data necessary for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 6 illustrates an electronic device 600 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 6 may represent one device or may represent multiple devices as desired.
In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. The computer program, when executed by the processing device 601, performs the above-described functions defined in the methods of some embodiments of the present disclosure.
It should be noted that the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: and extracting text information from the article display image as text identification information to obtain a text identification information set. And screening out the text identification information meeting a first preset condition group from the text identification information set to serve as candidate text information, and obtaining a candidate text information set. And in response to determining that candidate text information including any price identification keyword information in a preset price identification keyword information set exists in the candidate text information set, generating a first candidate text information, a second candidate text information set and third candidate text information based on the candidate text information set, the price identification keyword information set and a preset price-related identifier information set. Generating a first set of distance values and a second set of distance values based on the first candidate text information, the second set of candidate text information and the third candidate text information. And generating candidate price information based on the second candidate text information set, the first distance value set and the second distance value set.
Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in some embodiments of the present disclosure may be implemented by software, and may also be implemented by hardware. The described units may also be provided in a processor, and may be described as: a processor includes a collation extraction unit, a filtering unit, a first generation unit, a second generation unit, and a third generation unit. The names of the units do not form a limitation on the units themselves in some cases, for example, the filtering unit may also be described as a unit that filters out text recognition information satisfying a first preset condition group from the text recognition information set as candidate text information to obtain a candidate text information set.
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.
Claims (17)
1. A price information processing method based on image recognition comprises the following steps:
extracting text information from the article display image as text identification information to obtain a text identification information set;
screening out text identification information meeting a first preset condition group from the text identification information set to serve as candidate text information, and obtaining a candidate text information set;
in response to determining that candidate text information including any price identification keyword information in a preset price identification keyword information set exists in the candidate text information set, generating first candidate text information, a second candidate text information set and third candidate text information based on the candidate text information set, the price identification keyword information set and a preset price-related identifier information set;
generating a first set of distance values and a second set of distance values based on the first candidate text information, the second set of candidate text information, and the third candidate text information;
generating candidate price information based on the second set of candidate text information, the first set of distance values, and the second set of distance values.
2. The method of claim 1, wherein the method further comprises:
and in response to determining that candidate text information comprising any price-related keyword information in a preset price-related keyword information set exists in the candidate text information set, generating fourth candidate text information based on the candidate text information set and the price-related keyword information set.
3. The method of claim 2, wherein the text recognition information comprises: text content information, text confidence numerical values, and identification box size information; the identification frame size information includes: the coordinate value of the center of the identification frame, the length value of the identification frame and the width value of the identification frame.
4. The method of claim 3, wherein the first set of preset conditions comprises at least one of:
text confidence coefficient values included in the text identification information are greater than or equal to preset confidence coefficient values; the text recognition information includes an identification frame length value greater than or equal to a preset identification frame length value and an identification frame width value greater than or equal to a preset identification frame width value.
5. The method of claim 3, wherein generating first, second and third candidate text information based on the set of candidate text information, the set of price identifying keyword information and a preset set of price-related identifier information comprises:
and screening candidate text information containing any price identification keyword in the price identification keyword information set in text content information from the candidate text information set to serve as first candidate text information.
6. The method of claim 3, wherein generating first, second and third candidate text information based on the set of candidate text information, the set of price identifying keyword information and a preset set of price-related identifier information comprises:
and screening candidate text information containing numerical values in the text content information from the candidate text information set to serve as second candidate text information, and obtaining a second candidate text information set.
7. The method of claim 3, wherein generating first, second and third candidate text information based on the set of candidate text information, the set of price identifying keyword information and a preset set of price-related identifier information comprises:
and screening candidate text information containing any price related identifier information in the price related identifier information set in the text content information from the candidate text information set to serve as third candidate text information.
8. The method of claim 3, wherein said generating a first set of distance values and a second set of distance values based on the first candidate text information, the second set of candidate text information, and the third candidate text information comprises:
determining a distance value between a center coordinate value of the identification box included in the first candidate text information and a center coordinate value of the identification box included in each second candidate text information in the second candidate text information set as a first distance value, so as to obtain a first distance value set;
and determining a distance value between the center coordinate value of the identification box included in the third candidate text information and the center coordinate value of the identification box included in each second candidate text information in the second candidate text information set as a second distance value, so as to obtain a second distance value set.
9. The method of claim 3, wherein said generating candidate price information based on the second set of candidate text information, the first set of distance values, and the second set of distance values comprises:
screening second candidate text information of which the corresponding first distance value meets a second preset condition from the second candidate text information set to serve as first candidate price information, and obtaining a first candidate price information set;
and screening out first candidate price information of which the corresponding second distance value meets a third preset condition from the first candidate price information set as candidate price information.
10. The method of claim 9, wherein generating a fourth candidate textual information based on the set of candidate textual information and the set of price-related keyword information comprises:
and screening candidate text information of which the text content information comprises any price related keyword information in the price related keyword information set from the candidate text information set to serve as fourth candidate text information.
11. The method of claim 10, wherein the method further comprises:
and determining a distance value between the center coordinate value of the identification box included in the fourth candidate text information and the center coordinate value of the identification box included in each second candidate text information in the second candidate text information set as a third distance value, so as to obtain a third distance value set.
12. The method of claim 11, wherein the method further comprises:
and screening out second candidate text information of which the corresponding third distance value meets a fourth preset condition from the second candidate text information set as price related text information.
13. The method of claim 12, wherein the method further comprises:
and in response to determining that the difference value between the candidate price information and the page price information is within a preset range, determining the candidate price information as price information to be presented.
14. The method of claim 13, wherein the method further comprises:
and generating presentation price information based on the price information to be presented and the price related text information.
15. A price information processing apparatus comprising:
the extraction unit is configured to extract text information from the article display image as text identification information, and a text identification information set is obtained;
the screening unit is configured to screen out text identification information meeting a first preset condition group from the text identification information set to serve as candidate text information, and a candidate text information set is obtained;
a first generating unit configured to generate a first candidate text information, a second candidate text information and a third candidate text information based on the candidate text information set, the price identification keyword information set and a preset price-related identifier information set in response to determining that there is candidate text information including any price identification keyword information in a preset price identification keyword information set in the candidate text information set;
a second generating unit configured to generate a first set of distance values and a second set of distance values based on the first candidate text information, the second set of candidate text information, and the third candidate text information;
a third generating unit configured to generate candidate price information based on the second set of candidate text information, the first set of distance values, and the second set of distance values.
16. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-14.
17. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1-14.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011246846.5A CN112308678A (en) | 2020-11-10 | 2020-11-10 | Price information processing method, device, equipment and medium based on image recognition |
| PCT/CN2021/125399 WO2022100401A1 (en) | 2020-11-10 | 2021-10-21 | Image recognition-based price information processing method and apparatus, device, and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011246846.5A CN112308678A (en) | 2020-11-10 | 2020-11-10 | Price information processing method, device, equipment and medium based on image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112308678A true CN112308678A (en) | 2021-02-02 |
Family
ID=74326652
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011246846.5A Pending CN112308678A (en) | 2020-11-10 | 2020-11-10 | Price information processing method, device, equipment and medium based on image recognition |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112308678A (en) |
| WO (1) | WO2022100401A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022100401A1 (en) * | 2020-11-10 | 2022-05-19 | 北京沃东天骏信息技术有限公司 | Image recognition-based price information processing method and apparatus, device, and medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140244392A1 (en) * | 2013-02-27 | 2014-08-28 | Xue Si Xing Digital Marketing Co., Ltd. | Graphical Recognition Inventory Management and Marketing System |
| CN105912642A (en) * | 2016-04-08 | 2016-08-31 | 世纪禾光科技发展（北京）有限公司 | Product price data acquisition method and system |
| CN110610166B (en) * | 2019-09-18 | 2022-06-07 | 北京猎户星空科技有限公司 | Text region detection model training method and device, electronic equipment and storage medium |
| CN112308678A (en) * | 2020-11-10 | 2021-02-02 | 北京沃东天骏信息技术有限公司 | Price information processing method, device, equipment and medium based on image recognition |
-
2020
- 2020-11-10 CN CN202011246846.5A patent/CN112308678A/en active Pending
-
2021
- 2021-10-21 WO PCT/CN2021/125399 patent/WO2022100401A1/en active Application Filing
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022100401A1 (en) * | 2020-11-10 | 2022-05-19 | 北京沃东天骏信息技术有限公司 | Image recognition-based price information processing method and apparatus, device, and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022100401A1 (en) | 2022-05-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109934142B (en) | Method and apparatus for generating feature vectors of video | |
| CN111160410B (en) | Object detection method and device | |
| CN113723158A (en) | Text structured recognition method and device, electronic equipment and computer readable medium | |
| CN113420757B (en) | Text auditing method and device, electronic equipment and computer readable medium | |
| CN114092948B (en) | Bill identification method, device, equipment and storage medium | |
| CN114153959A (en) | Key value matching method and device, readable medium and electronic equipment | |
| CN112308678A (en) | Price information processing method, device, equipment and medium based on image recognition | |
| CN111597107A (en) | Information output method and device and electronic equipment | |
| CN110852242A (en) | Watermark identification method, device, equipment and storage medium based on multi-scale network | |
| CN113807056B (en) | Document name sequence error correction method, device and equipment | |
| CN110659540A (en) | Traffic light detection method and device | |
| CN113255812A (en) | Video frame detection method and device and electronic equipment | |
| CN113393288A (en) | Order processing information generation method, device, equipment and computer readable medium | |
| CN113971810A (en) | Document generation method, device, platform, electronic equipment and storage medium | |
| CN114463768A (en) | Form recognition method and device, readable medium and electronic equipment | |
| CN110334763B (en) | Model data file generation method, model data file generation device, model data file identification device, model data file generation apparatus, model data file identification apparatus, and model data file identification medium | |
| CN112035581A (en) | Model-based task processing method, device, equipment and medium | |
| CN112669000A (en) | Government affair item processing method and device, electronic equipment and storage medium | |
| CN113191257A (en) | Order of strokes detection method and device and electronic equipment | |
| CN113742564A (en) | Target resource pushing method and device | |
| CN111382365A (en) | Method and apparatus for outputting information | |
| CN111932323B (en) | Article information interface display method, device, equipment and computer readable medium | |
| CN114492413B (en) | Text proofreading method and device and electronic equipment | |
| CN114926830B (en) | Screen image recognition method, apparatus, device and computer readable medium | |
| CN117172220B (en) | Text similarity information generation method, device, equipment and computer readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |