CA3164550A1 - Image information processing method for use in q&a system, device and electronic equipment - Google Patents
Image information processing method for use in q&a system, device and electronic equipment Download PDFInfo
- Publication number
- CA3164550A1 CA3164550A1 CA3164550A CA3164550A CA3164550A1 CA 3164550 A1 CA3164550 A1 CA 3164550A1 CA 3164550 A CA3164550 A CA 3164550A CA 3164550 A CA3164550 A CA 3164550A CA 3164550 A1 CA3164550 A1 CA 3164550A1
- Authority
- CA
- Canada
- Prior art keywords
- preset
- text data
- classification
- target text
- target
- 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
- 230000010365 information processing Effects 0.000 title claims abstract description 22
- 238000003672 processing method Methods 0.000 title claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000001514 detection method Methods 0.000 claims description 16
- 230000015654 memory Effects 0.000 claims description 12
- 102100032202 Cornulin Human genes 0.000 claims description 9
- 101000920981 Homo sapiens Cornulin Proteins 0.000 claims description 9
- 230000008030 elimination Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 230000004044 response Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000037430 deletion Effects 0.000 description 3
- 238000012217 deletion Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000006403 short-term memory Effects 0.000 description 3
- 230000002457 bidirectional effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/34—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present application discloses an image information processing method for use in a questioning and answering (hereinafter referred to as "Q&A") system, and corresponding device and electronic equipment, of which the method comprises: receiving a consultation request sent by a user, wherein the consultation request includes an image to be processed; recognizing target text data contained in the image to be processed according to a preset recognizing rule; determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds; and obtaining an answering statement to which the target classification corresponds from an answering statement library and returning the answering statement to the user.
Description
IMAGE INFORMATION PROCESSING METHOD FOR USE IN Q&A SYSTEM, DEVICE AND ELECTRONIC EQUIPMENT
BACKGROUND OF THE INVENTION
Technical Field [0001] The present invention relates to the field of information processing technology, and more particularly to an image information processing method for use in a Q&A
system, and corresponding device and electronic equipment.
Description of Related Art
BACKGROUND OF THE INVENTION
Technical Field [0001] The present invention relates to the field of information processing technology, and more particularly to an image information processing method for use in a Q&A
system, and corresponding device and electronic equipment.
Description of Related Art
[0002] In the traditional service industry, as a labor-intensive post, human customer service is a highly intensive and highly repetitive job over the entire time period.
Accordingly, in order to reduce manpower cost and enhance efficiency, more and more enterprises have introduced the automatic Q&A system enabling automatic response with corresponding answering statements to questions raised by users, alleviating the pressure of human customer service to a certain degree, and enhancing accuracy, standardization, and stability of enterprise services.
Accordingly, in order to reduce manpower cost and enhance efficiency, more and more enterprises have introduced the automatic Q&A system enabling automatic response with corresponding answering statements to questions raised by users, alleviating the pressure of human customer service to a certain degree, and enhancing accuracy, standardization, and stability of enterprise services.
[0003] However, it is usual for users to input such non-text information as pictures to the automatic Q&A system, if such common information carriers cannot be recognized, many inconveniences would be brought to the use by users. Therefore, there is an urgent need to propose an information processing method capable of making response to image information input by a user, so as to address the above technical problems that have long been pending in the state of the art.
Date Recue/Date Received 2022-06-21 SUMMARY OF THE INVENTION
Date Recue/Date Received 2022-06-21 SUMMARY OF THE INVENTION
[0004] To deal with prior-art deficiencies, a main objective of the present invention it is to provide an image information processing method for use in a Q&A system, and corresponding device and electronic equipment, so as to solve the aforementioned technical problems prevalent in the state of the art.
[0005] To achieve the above objective, according to one aspect, the present invention provides an image information processing method for use in a Q&A system, the method comprises:
[0006] receiving a consultation request sent by a user, wherein the consultation request includes an image to be processed;
[0007] recognizing target text data contained in the image to be processed according to a preset recognizing rule;
[0008] determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds; and
[0009] obtaining an answering statement to which the target classification corresponds from an answering statement library and returning the answering statement to the user.
[0010] In some embodiments, the step of determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds includes:
[0011] generating an edit distance between the target text data and the preset keyword according to the preprocessed target text data and the preset keyword to which each preset classification corresponds;
[0012] generating a weighted edit distance between the target text data and each preset keyword according to the edit distance between the target text data and the preset keyword and a preset weight to which the preset keyword corresponds;
Date Recue/Date Received 2022-06-21
Date Recue/Date Received 2022-06-21
[0013] determining a weight distance between the target text data and each preset classification according to the weighted edit distance between the target text data and each preset keyword and the preset keyword to which each preset classification corresponds; and
[0014] determining the preset classification with the smallest weight distance to the target text data as a target classification.
[0015] In some embodiments, the preset classifications include other types, and the method comprises:
[0016] determining that the preset classification to which the target text data corresponds is the other type when the weight distance between the target text data and each preset classification is greater than a preset threshold.
[0017] In some embodiments, the target text data includes at least two text information samples, and, before the step of determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds, the method further comprises:
[0018] eliminating from the target text data any text information sample whose text length is smaller than a preset length threshold, and generating the preprocessed target text data.
[0019] In some embodiments, the step of generating an edit distance between the target text data and the preset keyword according to the preprocessed target text data and the preset keyword to which each preset classification corresponds includes:
[0020] generating an edit distance between each text information sample and the preset keyword according to a preset edit distance algorithm;
[0021] eliminating from all edit distances any edit distance that exceeds a preset distance threshold; and
[0022] generating an edit distance between the target text data and the preset keyword according to the edit distances after elimination.
Date Recue/Date Received 2022-06-21
Date Recue/Date Received 2022-06-21
[0023] In some embodiments, the preset recognizing rule includes a preset text detection algorithm and a preset text recognition algorithm, and the step of recognizing target text data contained in the image to be processed according to a preset recognizing rule includes:
[0024] employing the preset text detection algorithm to recognize a text region contained in the image to be processed;
[0025] employing the preset text recognition algorithm to recognize the text information samples contained in the text region; and
[0026] determining the target text data contained in the image to be recognized according to the text information samples contained in the text region.
[0027] In some embodiments, the step of employing the preset text detection algorithm to recognize a text region contained in the image to be processed includes:
[0028] employing a CTPN text detection algorithm to recognize a text region contained in the image to be processed; and
[0029] the step of employing the preset text recognition algorithm to recognize the text information samples contained in the text region includes:
[0030] employing a CRNN+CTC neural network model to recognize the text information samples contained in the text region.
[0031] In some embodiments, the preset keyword to which each preset classification corresponds is prestored in a keyword library stored in a preset document, the answering statement library is prestored in the preset document, and the method comprises:
[0032] receiving a rule updating request; and
[0033] updating the preset document according to categories to be updated and/or answering statements to be updated as included in the rule updating request.
[0034] According to the second aspect, the present application provides an image information Date Recue/Date Received 2022-06-21 processing device for use in a Q&A system, the device comprises:
[0035] a receiving module, for receiving a consultation request sent by a user, wherein the consultation request includes an image to be processed;
[0036] a recognizing module, for recognizing target text data contained in the image to be processed according to a preset recognizing rule;
[0037] a judging module, for determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds; and
[0038] an answering module, for obtaining an answering statement to which the target classification corresponds from an answering statement library and returning the answering statement to the user.
[0039] According to the third aspect, the present application provides an electronic equipment that comprises:
[0040] one or more processor(s); and
[0041] a memory, associated with the one or more processor(s) and storing a program instruction that executes the following operations when it is read and executed by the one or more processor(s):
[0042] receiving a consultation request sent by a user, wherein the consultation request includes an image to be processed;
[0043] recognizing target text data contained in the image to be processed according to a preset recognizing rule;
[0044] determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds; and
[0045] obtaining an answering statement to which the target classification corresponds from an answering statement library and returning the answering statement to the user.
Date Recue/Date Received 2022-06-21
Date Recue/Date Received 2022-06-21
[0046] The present invention achieves the following advantageous effects.
[0047] The present application provides an image information processing method for use in a Q&A system, and the method comprises receiving a consultation request sent by a user, wherein the consultation request includes an image to be processed;
recognizing target text data contained in the image to be processed according to a preset recognizing rule;
determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds; and obtaining an answering statement to which the target classification corresponds from an answering statement library and returning the answering statement to the user. By recognizing text information contained in the image, and by determining a preset classification to which the image corresponds according to an edit distance between the text information and a keyword, it is made possible to return an answering statement of the corresponding preset classification to a user, whereby is realized automatic response to image information input by the user, are enhanced user convenience and efficiency, and is enhanced accuracy of the answer to the user.
recognizing target text data contained in the image to be processed according to a preset recognizing rule;
determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds; and obtaining an answering statement to which the target classification corresponds from an answering statement library and returning the answering statement to the user. By recognizing text information contained in the image, and by determining a preset classification to which the image corresponds according to an edit distance between the text information and a keyword, it is made possible to return an answering statement of the corresponding preset classification to a user, whereby is realized automatic response to image information input by the user, are enhanced user convenience and efficiency, and is enhanced accuracy of the answer to the user.
[0048] As further disclosed by the present application, the preset keyword to which each preset classification corresponds is prestored in a keyword library stored in a preset document, the answering statement library is prestored in the preset document, and the method comprises: receiving a rule updating request; and updating the preset document according to keywords to be updated and/or answering statements to be updated as included in the rule updating request. When it is required to change response or keywords due to change in activity or sales promotion, the answering statement library or the keyword library in the preset document can be directly updated, and the Q&A system can reload the corresponding preset document under hot start, whereby convenience and timeliness in changing the rules of the answering statement library or the keyword library are enhanced.
Date Recue/Date Received 2022-06-21
Date Recue/Date Received 2022-06-21
[0049] It is not necessary for all products of the present invention to possess all the above effects.
BRIEF DESCRIPTION OF THE DRAWINGS
BRIEF DESCRIPTION OF THE DRAWINGS
[0050] In order to more clearly describe the technical solutions in the embodiments of the present invention, drawings required for the illustration of the embodiments will be briefly introduced below. Apparently, the drawings described below are merely directed to some embodiments of the present invention, and it is possible for persons ordinarily skilled in the art to acquire other drawings without spending creative effort in the process based on these drawings.
[0051] Fig. 1 is a flowchart illustrating answering provided by the embodiments of the present application;
[0052] Fig. 2 is a view schematically illustrating a text region provided by the embodiments of the present application;
[0053] Fig. 3 is a flowchart illustrating the method provided by the embodiments of the present application
[0054] Fig. 4 is a view illustrating the structure of the device provided by the embodiments of the present application; and
[0055] Fig. 5 is a view illustrating the structure of the electronic equipment provided by the embodiments of the present application.
DETAILED DESCRIPTION OF THE INVENTION
DETAILED DESCRIPTION OF THE INVENTION
[0056] In order to make more lucid and clear the objectives, technical solutions and advantages of the present invention, the technical solutions in the embodiments of the present Date Recue/Date Received 2022-06-21 invention will be clearly and comprehensively described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the embodiments as described are merely partial embodiments, rather than the entire embodiments, of the present invention. All other embodiments obtainable by persons ordinarily skilled in the art based on the embodiments in the present invention without spending any creative effort shall all be covered by the protection scope of the present invention.
[0057] Precisely as recited in the Description of Related Art, the prior-art automatic Q&A system cannot recognize pictures input by users, so it is difficult to correspondingly respond to the pictures. To solve this technical problem, the present application provides an image information processing method for use in a Q&A system enabling extraction of text information contained in a picture, classification of the picture according to the text information, and return of a correspondingly classified answering statement to the user, so that is realized automatic reply to picture information.
[0058] Embodiment 1
[0059] Specifically, as shown in Fig. 1, a process of applying the image information processing method for use in a Q&A system as disclosed by this embodiment of the present application to respond to an image sent from a user includes the following.
[0060] S10 - receiving a consultation request sent by a user, wherein the consultation request includes an image to be processed.
[0061] Specifically, in addition to pictures, the consultation information can further include such information as text information and speech data. The image to be processed can be a screenshot of a mobile terminal or any other image.
Date Recue/Date Received 2022-06-21
Date Recue/Date Received 2022-06-21
[0062] S20 - employing a CTPN text detection algorithm to recognize a text region contained in the image to be processed.
[0063] The CTPN text detection algorithm can recognize text regions contained in the image to be processed. As shown in Fig. 2, the text region indicates a region of a text frame that contains words in the picture.
[0064] CTPN is a word recognizing network model. To enhance recognition speed, the present application employs ShuffleNet v2 to serve as the network structure of a convolutional neural network model (CNN) contained in CTPN that extracts features.
ShuffleNet can greatly reduce the computational amount of the model at the same time of maintaining accuracy, and its basic unit is improved over a residual unit.
ShuffleNet can greatly reduce the computational amount of the model at the same time of maintaining accuracy, and its basic unit is improved over a residual unit.
[0065] S30 ¨ employing a CRNN+CTC text recognition algorithm to recognize text information samples contained in each text region.
[0066] The CRNN+CTC text recognition algorithm includes a CRNN network model and a CTC
algorithm. the CRNN network model includes a convolutional neural network model (CNN) and a bidirectional long short-term memory network model (LSTM), of which the long short-term memory network model (LSTM) here is a variant of the RNN
model.
Preferably, it is possible to use a dense convolutional network model (DenseNet) to serve as the convolutional neural network model (CNN).
algorithm. the CRNN network model includes a convolutional neural network model (CNN) and a bidirectional long short-term memory network model (LSTM), of which the long short-term memory network model (LSTM) here is a variant of the RNN
model.
Preferably, it is possible to use a dense convolutional network model (DenseNet) to serve as the convolutional neural network model (CNN).
[0067] The process of employing the text recognition algorithm for recognition includes:
extracting an image convolution feature of the image to be processed through the convolutional neural network CNN model; extracting a sequence feature of the image convolution feature through the bidirectional long short-term memory network LSTM
model; and employing the CTC algorithm to transform to the final recognition result according to the extracted sequence feature and through such operations as duplicate Date Recue/Date Received 2022-06-21 removal and integration, etc. The CTC algorithm is a type of loss function capable of solving the problem in which characters cannot be aligned.
extracting an image convolution feature of the image to be processed through the convolutional neural network CNN model; extracting a sequence feature of the image convolution feature through the bidirectional long short-term memory network LSTM
model; and employing the CTC algorithm to transform to the final recognition result according to the extracted sequence feature and through such operations as duplicate Date Recue/Date Received 2022-06-21 removal and integration, etc. The CTC algorithm is a type of loss function capable of solving the problem in which characters cannot be aligned.
[0068] Based on the above algorithms, an embodiment of the present application provides an end-to-end text recognition algorithm in which character cutting is not required. Based on the CRNN+CTC algorithm, it is possible in the embodiments of the present application to recognize each text region, and to obtain a text list, namely target text data, which contains plural text information samples.
[0069] S40 ¨ preprocessing the target text data, and eliminating therefrom any text information sample whose text length is smaller than a preset threshold.
[0070] By eliminating any text information sample whose text length is smaller than a preset threshold, it is possible to enhance the subsequent efficiency in calculating the edit distance, and to reduce the interference to the accuracy of subsequent classification by noise data in the target text data.
[0071] S50 ¨ generating a weight distance between any text information sample retained after preprocessing and each preset classification.
[0072] Specifically, the above process of generating the weight distance includes the following.
[0073] S51 - generating an edit distance between the text information sample and each preset keyword of each preset classification according to a preset edit distance algorithm.
[0074] It is possible to determine the preset keyword to which each preset classification corresponds based on the keyword library stored in the preset document.
[0075] Preset classifications can be classified in advance according to such classifying rules as Date Recue/Date Received 2022-06-21 business requirement. The business personnel can collect screenshots received by the Q&A system in advance, then determine preset classifications to which these screenshots respectively correspond, thereafter screen out representative texts appearing for many times in the screenshots under the same preset classifications to serve as the preset keywords to which the preset classifications correspond, and sort to obtain the corresponding keyword library according to the preset classifications and the preset keywords and store the corresponding keyword library in the preset document.
[0076] Based on the above classifying rule, the automatic Q&A system can realize automatic response to screenshots cut out by users. When it is judged that pictures sent by target users of the automatic Q&A system are not screenshots under most scenarios, it is also possible for the business personnel to collect pictures of corresponding categories and to classify corresponding preset classifications and keywords according to the pictures.
[0077] S52 - generating a weighted edit distance between the text information sample and each preset keyword of each preset classification according to the edit distance between the text information sample and each preset keyword of each classification and a preset weight to which each preset keyword corresponds under the corresponding preset classification.
[0078] Before the weighted edit distance is generated, it is possible to eliminate any edit distance that exceeds a preset distance threshold from all edit distances to which all preset keywords under the preset classification correspond based on the edit distance between the text information sample and each preset keyword of the preset classification.
[0079] Specifically, after any edit distance that exceeds the preset distance threshold has been eliminated, the weighted edit distance between the text information sample and the preset keyword can be expressed as:
[0080] weighted edit distance = preset weight * edit distance.
Date Recue/Date Received 2022-06-21
Date Recue/Date Received 2022-06-21
[0081] S53 ¨ determining a weight distance between the text information sample and each preset classification according to the weighted edit distance between the text information sample and each preset keyword of each preset classification.
[0082] Specifically, taking for example a certain preset classification that includes three preset keywords, namely keyword 1, keyword 2, and keyword 3, the weight distance between the text information sample and the preset classification can be expressed as:
[0083] weight distance = weighted edit distance between text information sample and keyword 1 + weighted edit distance between text information sample and keyword 2 +
weighted edit distance between text information sample and keyword 3.
weighted edit distance between text information sample and keyword 3.
[0084] S54 - determining the preset classification with the smallest weight distance to the target text data as a target classification.
[0085] Specifically, when weight distances of the target text data to all preset classifications are all greater than the corresponding preset threshold, it can be determined that the target text data pertains to any other type in the preset classifications, i.e., it is impossible to determine the business requirement to which the corresponding image to be processed corresponds. When the preset classifications and the preset keywords are stipulated according to screenshots, images attributed to other types may be pictures other than screenshots.
[0086] The images determined as other types can be stored in a preset database, so as to facilitate the business personnel to periodically enquire and to set up corresponding preset categories and preset keywords, so that the effect in responding to users' questions is enhanced.
[0087] S55 ¨ obtaining an answering statement to which the target category corresponds from Date Recue/Date Received 2022-06-21 an answering statement library and returning the answering statement to the user.
[0088] Specifically, the answering statement library can be prestored in the preset document, in which are stored answering statements to which each preset category corresponds.
[0089] Due to business adjustment, it may be usually required for the business personnel to update the answering statement library and the keyword library, and the updating process includes the following.
[0090] S60 ¨ receiving an updating request sent by the business personnel.
[0091] The updating request can include categories to be updated and/or answering statements to be updated. The categories to be updated can include addition, deletion, and modification of keywords of a certain preset category, or addition and deletion of the certain preset category. The answering statements to be updated can include addition of answering statements to which a certain preset category corresponds, deletion of answering statements to which a certain preset category corresponds, and modification of answering statements to which a certain preset category corresponds.
[0092] S61 - updating the preset document according to the categories to be updated and/or answering statements to be updated as included in the rule updating request.
[0093] The Q&A system can reload the corresponding preset document under hot start, whereby convenience and timeliness in changing the rules of the answering statement library and the keyword library are enhanced.
[0094] Embodiment 2
[0095] Corresponding to the above embodiment, the present application provides an image Date Recue/Date Received 2022-06-21 information processing method for use in a Q&A system, as shown in Fig. 3, the method comprises the following steps.
[0096] 3100 - receiving a consultation request sent by a user, wherein the consultation request includes an image to be processed.
[0097] 3200 - recognizing target text data contained in the image to be processed according to a preset recognizing rule.
[0098] Preferably, the preset recognizing rule includes a preset text detection algorithm and a preset text recognition algorithm, and the step of recognizing target text data contained in the image to be processed according to a preset recognizing rule includes:
[0099] 3211 - employing the preset text detection algorithm to recognize a text region contained in the image to be processed;
[0100] 3212 - employing the preset text recognition algorithm to recognize the text information samples contained in the text region; and
[0101] 3213 - determining the target text data contained in the image to be recognized according to the text information samples contained in the text region.
[0102] Preferably, the step of employing the preset text detection algorithm to recognize a text region contained in the image to be processed includes:
[0103] 3214 - employing a CTPN text detection algorithm to recognize a text region contained in the image to be processed; and
[0104] the step of employing the preset text recognition algorithm to recognize the text information samples contained in the text region includes:
[0105] 3215 - employing a CRNN+CTC neural network model to recognize the text information samples contained in the text region.
[0106] 3300 - determining a preset classification to which the target text data corresponds as a Date Recue/Date Received 2022-06-21 target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds.
[0107] Preferably, the step of determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds includes:
[0108] 3311 - generating an edit distance between the target text data and the preset keyword according to the preprocessed target text data and the preset keyword to which each preset classification corresponds;
[0109] 3312 - generating a weighted edit distance between the target text data and each preset keyword according to the edit distance between the target text data and the preset keyword and a preset weight to which the preset keyword corresponds;
[0110] 3313 - determining a weight distance between the target text data and each preset classification according to the weighted edit distance between the target text data and each preset keyword and the preset keyword to which each preset classification corresponds; and
[0111] 3314 - determining the preset classification with the smallest weight distance to the target text data as a target classification.
[0112] Preferably, the preset classifications include other types, and the method comprises:
[0113] 3315 - determining that the preset classification to which the target text data corresponds is the other type when the weight distance between the target text data and each preset classification is greater than a preset threshold.
[0114] Preferably, the target text data includes at least two text information samples, and, before the step of determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds, the method Date Recue/Date Received 2022-06-21 further comprises:
[0115] 3316 - eliminating from the target text data any text information sample whose text length is smaller than a preset length threshold, and generating the preprocessed target text data.
[0116] Preferably, the step of generating an edit distance between the target text data and the preset keyword according to the preprocessed target text data and the preset keyword to which each preset classification corresponds includes:
[0117] 3318 - generating an edit distance between each text information sample and the preset keyword according to a preset edit distance algorithm;
[0118] 3319 - eliminating from all edit distances any edit distance that exceeds a preset distance threshold; and
[0119] 3320 - generating an edit distance between the target text data and the preset keyword according to the edit distances after elimination.
[0120] 3400 - obtaining an answering statement to which the target classification corresponds from an answering statement library and returning the answering statement to the user.
[0121] Preferably, the preset keyword to which each preset classification corresponds is prestored in a keyword library stored in a preset document, the answering statement library is prestored in the preset document, and the method comprises:
[0122] 3500 - receiving a rule updating request; and
[0123] 3510 - updating the preset document according to categories to be updated and/or answering statements to be updated as included in the rule updating request.
[0124] Embodiment 3
[0125] Corresponding to Embodiment 1 and Embodiment 2, as shown in Fig. 4, the present application provides an image information processing device for use in a Q&A
system, the device comprises:
Date Recue/Date Received 2022-06-21
system, the device comprises:
Date Recue/Date Received 2022-06-21
[0126] a receiving module 410, for receiving a consultation request sent by a user, wherein the consultation request includes an image to be processed;
[0127] a recognizing module 420, for recognizing target text data contained in the image to be processed according to a preset recognizing rule;
[0128] a judging module 430, for determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds; and
[0129] an answering module 440, for obtaining an answering statement to which the target classification corresponds from an answering statement library and returning the answering statement to the user.
[0130] Preferably, the judging module 430 can be further employed for generating an edit distance between the target text data and the preset keyword according to the preprocessed target text data and the preset keyword to which each preset classification corresponds; generating a weighted edit distance between the target text data and each preset keyword according to the edit distance between the target text data and the preset keyword and a preset weight to which the preset keyword corresponds;
determining a weight distance between the target text data and each preset classification according to the weighted edit distance between the target text data and each preset keyword and the preset keyword to which each preset classification corresponds; and determining the preset classification with the smallest weight distance to the target text data as a target classification.
determining a weight distance between the target text data and each preset classification according to the weighted edit distance between the target text data and each preset keyword and the preset keyword to which each preset classification corresponds; and determining the preset classification with the smallest weight distance to the target text data as a target classification.
[0131] Preferably, the preset classifications include other types, and the judging module 430 can be further employed for determining that the preset classification to which the target text data corresponds is the other type when the weight distance between the target text data and each preset classification is greater than a preset threshold.
Date Recue/Date Received 2022-06-21
Date Recue/Date Received 2022-06-21
[0132] Preferably, the target text data includes at least two text information samples, and the judging module 430 can be further employed for eliminating from the target text data any text information sample whose text length is smaller than a preset length threshold, and generating the preprocessed target text data.
[0133] Preferably, the judging module 430 can be further employed for generating an edit distance between each text information sample and the preset keyword according to a preset edit distance algorithm; eliminating from all edit distances any edit distance that exceeds a preset distance threshold; and generating an edit distance between the target text data and the preset keyword according to the edit distances after elimination.
[0134] Preferably, the recognizing module 420 can be further employed for employing the preset text detection algorithm to recognize a text region contained in the image to be processed;
employing the preset text recognition algorithm to recognize the text information samples contained in the text region; and determining the target text data contained in the image to be recognized according to the text information samples contained in the text region.
employing the preset text recognition algorithm to recognize the text information samples contained in the text region; and determining the target text data contained in the image to be recognized according to the text information samples contained in the text region.
[0135] Preferably, the recognizing module 420 can be further used for employing a CTPN text detection algorithm to recognize a text region contained in the image to be processed; and employing a CRNN+CTC neural network model to recognize the text information samples contained in the text region.
[0136] Preferably, the receiving module 410 can be further employed for receiving a rule updating request; and the device further comprises an updating module for updating the preset document according to categories to be updated and/or answering statements to be updated as included in the rule updating request.
[0137] Embodiment 4 Date Recue/Date Received 2022-06-21
[0138] Corresponding to all the foregoing embodiments, this embodiment of the present application provides an electronic equipment that comprises:
[0139] one or more processor(s); and a memory, associated with the one or more processor(s) and storing a program instruction that executes the following operations when it is read and executed by the one or more processor(s):
[0140] receiving a consultation request sent by a user, wherein the consultation request includes an image to be processed;
[0141] recognizing target text data contained in the image to be processed according to a preset recognizing rule;
[0142] determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds; and
[0143] obtaining an answering statement to which the target classification corresponds from an answering statement library and returning the answering statement to the user.
[0144] Fig. 5 exemplarily illustrates the framework of the electronic equipment that can specifically include a processor 1510, a video display adapter 1511, a magnetic disk driver 1512, an input/output interface 1513, a network interface 1514, and a memory 1520.
The processor 1510, the video display adapter 1511, the magnetic disk driver 1512, the input/output interface 1513, the network interface 1514, and the memory 1520 can be communicably connected with one another via a communication bus 1530.
The processor 1510, the video display adapter 1511, the magnetic disk driver 1512, the input/output interface 1513, the network interface 1514, and the memory 1520 can be communicably connected with one another via a communication bus 1530.
[0145] The processor 1510 can be embodied as a general CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuit(s) for executing relevant program(s) to realize the technical solutions provided by the present application.
[0146] The memory 1520 can be embodied in such a form as an ROM (Read Only Memory), an RAM (Random Access Memory), a static storage device, or a dynamic storage device.
Date Recue/Date Received 2022-06-21 The memory 1520 can store an operating system 1521 for controlling the running of an electronic equipment 1500, and a basic input/output system (BIOS) 1522 for controlling lower-level operations of the electronic equipment 1500. In addition, the memory 1520 can also store a web browser 1523, a data storage administration system 1524, and an icon font processing system 1525, etc. The icon font processing system 1525 can be an application program that specifically realizes the aforementioned various step operations in the embodiments of the present application. To sum it up, when the technical solutions provided by the present application are to be realized via software or firmware, the relevant program codes are stored in the memory 1520, and invoked and executed by the processor 1510. The input/output interface 1513 is employed to connect with an input/output module to realize input and output of information. The input/output module can be equipped in the device as a component part (not shown in the drawings), and can also be externally connected with the device to provide corresponding functions. The input means can include a keyboard, a mouse, a touch screen, a microphone, and various sensors etc., and the output means can include a display screen, a loudspeaker, a vibrator, an indicator light etc.
Date Recue/Date Received 2022-06-21 The memory 1520 can store an operating system 1521 for controlling the running of an electronic equipment 1500, and a basic input/output system (BIOS) 1522 for controlling lower-level operations of the electronic equipment 1500. In addition, the memory 1520 can also store a web browser 1523, a data storage administration system 1524, and an icon font processing system 1525, etc. The icon font processing system 1525 can be an application program that specifically realizes the aforementioned various step operations in the embodiments of the present application. To sum it up, when the technical solutions provided by the present application are to be realized via software or firmware, the relevant program codes are stored in the memory 1520, and invoked and executed by the processor 1510. The input/output interface 1513 is employed to connect with an input/output module to realize input and output of information. The input/output module can be equipped in the device as a component part (not shown in the drawings), and can also be externally connected with the device to provide corresponding functions. The input means can include a keyboard, a mouse, a touch screen, a microphone, and various sensors etc., and the output means can include a display screen, a loudspeaker, a vibrator, an indicator light etc.
[0147] The network interface 1514 is employed to connect to a communication module (not shown in the drawings) to realize intercommunication between the current device and other devices. The communication module can realize communication in a wired mode (via USB, network cable, for example) or in a wireless mode (via mobile network, WIFI, Bluetooth, etc.).
[0148] The bus 1530 includes a passageway transmitting information between various component parts of the device (such as the processor 1510, the video display adapter 1511, the magnetic disk driver 1512, the input/output interface 1513, the network interface 1514, and the memory 1520).
[0149] Additionally, the electronic equipment 1500 may further obtain information of specific Date Recue/Date Received 2022-06-21 collection conditions from a virtual resource object collection condition information database 1541 for judgment on conditions, and so on.
[0150] As should be noted, although merely the processor 1510, the video display adapter 1511, the magnetic disk driver 1512, the input/output interface 1513, the network interface 1514, the memory 1520, and the bus 1530 are illustrated for the aforementioned equipment, the equipment may further include other component parts prerequisite for realizing normal running during specific implementation. In addition, as can be understood by persons skilled in the art, the aforementioned equipment may as well only include component parts necessary for realizing the solutions of the present application, without including the entire component parts as illustrated.
[0151] As can be known through the description to the aforementioned embodiments, it is clearly learnt by person skilled in the art that the present application can be realized through software plus a general hardware platform. Based on such understanding, the technical solutions of the present application, or the contributions made thereby over the state of the art, can be essentially embodied in the form of a software product, and such a computer software product can be stored in a storage medium, such as an ROM/RAM, a magnetic disk, an optical disk etc., and includes plural instructions enabling a computer equipment (such as a personal computer, a cloud server, or a network device etc.) to execute the methods described in various embodiments or some sections of the embodiments of the present application.
[0152] The various embodiments are progressively described in the Description, identical or similar sections among the various embodiments can be inferred from one another, and each embodiment stresses what is different from other embodiments.
Particularly, with respect to the system or system embodiment, since it is essentially similar to the method embodiment, its description is relatively simple, and the relevant sections thereof can be inferred from the corresponding sections of the method embodiment. The system or Date Recue/Date Received 2022-06-21 system embodiment as described above is merely exemplary in nature, units therein described as separate parts can be or may not be physically separate, parts displayed as units can be or may not be physical units, that is to say, they can be located in a single site, or distributed over a plurality of network units. It is possible to select partial modules or the entire modules to realize the objectives of the embodied solutions based on practical requirements. It is understandable and implementable by persons ordinarily skilled in the art without spending creative effort in the process. What the above describes is merely directed to preferred embodiments of the present invention, and is not meant to restrict the present invention. Any modification, equivalent substitution, and improvement makeable within the spirit and scope of the present invention shall all be covered by the protection scope of the present invention.
Date Recue/Date Received 2022-06-21
Particularly, with respect to the system or system embodiment, since it is essentially similar to the method embodiment, its description is relatively simple, and the relevant sections thereof can be inferred from the corresponding sections of the method embodiment. The system or Date Recue/Date Received 2022-06-21 system embodiment as described above is merely exemplary in nature, units therein described as separate parts can be or may not be physically separate, parts displayed as units can be or may not be physical units, that is to say, they can be located in a single site, or distributed over a plurality of network units. It is possible to select partial modules or the entire modules to realize the objectives of the embodied solutions based on practical requirements. It is understandable and implementable by persons ordinarily skilled in the art without spending creative effort in the process. What the above describes is merely directed to preferred embodiments of the present invention, and is not meant to restrict the present invention. Any modification, equivalent substitution, and improvement makeable within the spirit and scope of the present invention shall all be covered by the protection scope of the present invention.
Date Recue/Date Received 2022-06-21
Claims (10)
1. An image information processing method for use in a Q&A system, characterized in that the method comprises:
receiving a consultation request sent by a user, wherein the consultation request includes an image to be processed;
recognizing target text data contained in the image to be processed according to a preset recognizing rule;
determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds; and obtaining an answering statement to which the target classification corresponds from an answering statement library and returning the answering statement to the user.
receiving a consultation request sent by a user, wherein the consultation request includes an image to be processed;
recognizing target text data contained in the image to be processed according to a preset recognizing rule;
determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds; and obtaining an answering statement to which the target classification corresponds from an answering statement library and returning the answering statement to the user.
2. The image information processing method for use in a Q&A system according to Claim 1, characterized in that the step of determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds includes:
generating an edit distance between the target text data and the preset keyword according to the preprocessed target text data and the preset keyword to which each preset classification corresponds;
generating a weighted edit distance between the target text data and each preset keyword according to the edit distance between the target text data and the preset keyword and a preset weight to which the preset keyword corresponds;
determining a weight distance between the target text data and each preset classification according to the weighted edit distance between the target text data and each preset keyword and the preset keyword to which each preset classification corresponds; and Date Recue/Date Received 2022-06-21 determining the preset classification with the smallest weight distance to the target text data as a target classification.
generating an edit distance between the target text data and the preset keyword according to the preprocessed target text data and the preset keyword to which each preset classification corresponds;
generating a weighted edit distance between the target text data and each preset keyword according to the edit distance between the target text data and the preset keyword and a preset weight to which the preset keyword corresponds;
determining a weight distance between the target text data and each preset classification according to the weighted edit distance between the target text data and each preset keyword and the preset keyword to which each preset classification corresponds; and Date Recue/Date Received 2022-06-21 determining the preset classification with the smallest weight distance to the target text data as a target classification.
3. The image information processing method for use in a Q&A system according to Claim 2, characterized in that the preset classifications include other types, and the method comprises:
determining that the preset classification to which the target text data corresponds is the other type when the weight distance between the target text data and each preset classification is greater than a preset threshold.
determining that the preset classification to which the target text data corresponds is the other type when the weight distance between the target text data and each preset classification is greater than a preset threshold.
4. The image information processing method for use in a Q&A system according to Claim 2, characterized in that the target text data includes at least two text information samples, and before the step of determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds, the method further comprises:
eliminating from the target text data any text information sample whose text length is smaller than a preset length threshold, and generating the preprocessed target text data.
eliminating from the target text data any text information sample whose text length is smaller than a preset length threshold, and generating the preprocessed target text data.
5. The image information processing method for use in a Q&A system according to Claim 4, characterized in that the step of generating an edit distance between the target text data and the preset keyword according to the preprocessed target text data and the preset keyword to which each preset classification corresponds includes:
generating an edit distance between each text information sample and the preset keyword according to a preset edit distance algorithm;
eliminating from all edit distances any edit distance that exceeds a preset distance threshold; and generating an edit distance between the target text data and the preset keyword according to the edit distances after elimination.
generating an edit distance between each text information sample and the preset keyword according to a preset edit distance algorithm;
eliminating from all edit distances any edit distance that exceeds a preset distance threshold; and generating an edit distance between the target text data and the preset keyword according to the edit distances after elimination.
6. The image information processing method for use in a Q&A system according to Claim 4, characterized in that the preset recognizing rule includes a preset text detection algorithm and a Date Recue/Date Received 2022-06-21 preset text recognition algorithm, and that the step of recognizing target text data contained in the image to be processed according to a preset recognizing rule includes:
employing the preset text detection algorithm to recognize a text region contained in the image to be processed;
employing the preset text recognition algorithm to recognize the text information samples contained in the text region; and determining the target text data contained in the image to be recognized according to the text information samples contained in the text region.
employing the preset text detection algorithm to recognize a text region contained in the image to be processed;
employing the preset text recognition algorithm to recognize the text information samples contained in the text region; and determining the target text data contained in the image to be recognized according to the text information samples contained in the text region.
7. The image information processing method for use in a Q&A system according to Claim 6, characterized in that the step of employing the preset text detection algorithm to recognize a text region contained in the image to be processed includes:
employing a CTPN text detection algorithm to recognize a text region contained in the image to be processed; and that the step of employing the preset text recognition algorithm to recognize the text information samples contained in the text region includes:
employing a CRNN+CTC neural network model to recognize the text information samples contained in the text region.
employing a CTPN text detection algorithm to recognize a text region contained in the image to be processed; and that the step of employing the preset text recognition algorithm to recognize the text information samples contained in the text region includes:
employing a CRNN+CTC neural network model to recognize the text information samples contained in the text region.
8. The image information processing method for use in a Q&A system according to anyone of Claims 1 to 7, characterized in that the preset keyword to which each preset classification corresponds is prestored in a keyword library stored in a preset document, that the answering statement library is prestored in the preset document, and the method comprises:
receiving a rule updating request; and updating the preset document according to categories to be updated and/or answering statements to be updated as included in the rule updating request.
receiving a rule updating request; and updating the preset document according to categories to be updated and/or answering statements to be updated as included in the rule updating request.
9. An image information processing device for use in a Q&A system, characterized in that the device comprises:
Date Recue/Date Received 2022-06-21 a receiving module, for receiving a consultation request sent by a user, wherein the consultation request includes an image to be processed;
a recognizing module, for recognizing target text data contained in the image to be processed according to a preset recognizing rule;
a judging module, for determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds; and an answering module, for obtaining an answering statement to which the target classification corresponds from an answering statement library and returning the answering statement to the user.
Date Recue/Date Received 2022-06-21 a receiving module, for receiving a consultation request sent by a user, wherein the consultation request includes an image to be processed;
a recognizing module, for recognizing target text data contained in the image to be processed according to a preset recognizing rule;
a judging module, for determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds; and an answering module, for obtaining an answering statement to which the target classification corresponds from an answering statement library and returning the answering statement to the user.
10. An electronic equipment, characterized in that the electronic equipment comprises:
one or more processor(s); and a memory, associated with the one or more processor(s) and storing a program instruction that executes the following operations when it is read and executed by the one or more processor(s):
receiving a consultation request sent by a user, wherein the consultation request includes an image to be processed;
recognizing target text data contained in the image to be processed according to a preset recognizing rule;
determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds; and obtaining an answering statement to which the target classification corresponds from an answering statement library and returning the answering statement to the user.
Date Recue/Date Received 2022-06-21
one or more processor(s); and a memory, associated with the one or more processor(s) and storing a program instruction that executes the following operations when it is read and executed by the one or more processor(s):
receiving a consultation request sent by a user, wherein the consultation request includes an image to be processed;
recognizing target text data contained in the image to be processed according to a preset recognizing rule;
determining a preset classification to which the target text data corresponds as a target classification according to an edit distance between the preprocessed target text data and a preset keyword to which each preset classification corresponds; and obtaining an answering statement to which the target classification corresponds from an answering statement library and returning the answering statement to the user.
Date Recue/Date Received 2022-06-21
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110687218.9A CN113342954A (en) | 2021-06-21 | 2021-06-21 | Image information processing method and device applied to question-answering system and electronic equipment |
| CN202110687218.9 | 2021-06-21 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CA3164550A1 true CA3164550A1 (en) | 2022-12-21 |
Family
ID=77478284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CA3164550A Pending CA3164550A1 (en) | 2021-06-21 | 2022-06-21 | Image information processing method for use in q&a system, device and electronic equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113342954A (en) |
| CA (1) | CA3164550A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116205749A (en) * | 2023-05-06 | 2023-06-02 | 深圳市秦保科技有限公司 | Electronic policy information data management method, device, equipment and readable storage medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113821602B (en) * | 2021-09-29 | 2024-05-24 | 平安银行股份有限公司 | Automatic answering method, device, equipment and medium based on image-text chat record |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108345692B (en) * | 2018-03-16 | 2020-07-31 | 北京京东尚科信息技术有限公司 | Automatic question answering method and system |
| CN111191445B (en) * | 2018-11-15 | 2024-04-19 | 京东科技控股股份有限公司 | Advertisement text classification method and device |
| CN110851576A (en) * | 2019-10-16 | 2020-02-28 | 迈达斯智能(深圳)有限公司 | Question and answer processing method, device, equipment and readable medium |
| CN111680142A (en) * | 2020-05-29 | 2020-09-18 | 平安普惠企业管理有限公司 | Automatic answering method and device based on text recognition and computer equipment |
| CN112612877A (en) * | 2020-12-16 | 2021-04-06 | 平安普惠企业管理有限公司 | Multi-type message intelligent reply method, device, computer equipment and storage medium |
-
2021
- 2021-06-21 CN CN202110687218.9A patent/CN113342954A/en not_active Withdrawn
-
2022
- 2022-06-21 CA CA3164550A patent/CA3164550A1/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116205749A (en) * | 2023-05-06 | 2023-06-02 | 深圳市秦保科技有限公司 | Electronic policy information data management method, device, equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113342954A (en) | 2021-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9300672B2 (en) | Managing user access to query results | |
| CA3164550A1 (en) | Image information processing method for use in q&a system, device and electronic equipment | |
| US9218568B2 (en) | Disambiguating data using contextual and historical information | |
| CN108491866B (en) | Pornographic picture identification method, electronic device and readable storage medium | |
| CN112579909A (en) | Object recommendation method and device, computer equipment and medium | |
| CA3166079C (en) | A processing method, device and electronic device for a question-and-answer statement | |
| US20180005022A1 (en) | Method and device for obtaining similar face images and face image information | |
| CA3144405A1 (en) | Text information recognizing method, extracting method, devices and system | |
| CN111143555A (en) | Big data-based customer portrait generation method, device, equipment and storage medium | |
| US10762089B2 (en) | Open ended question identification for investigations | |
| CN114494935A (en) | Video information processing method and device, electronic equipment and medium | |
| CN114186040A (en) | Operation method of intelligent robot customer service | |
| CN113888760B (en) | Method, device, equipment and medium for monitoring violation information based on software application | |
| CN113596011B (en) | Flow identification method and device, computing device and medium | |
| CN113032251B (en) | Method, device and storage medium for determining service quality of application program | |
| CN115759100A (en) | Data processing method, device, equipment and medium | |
| CN114547252A (en) | Text recognition method and device, electronic equipment and medium | |
| US20220129913A1 (en) | Control point compliance prediction based on regulation in multi-media | |
| CN113449506A (en) | Data detection method, device and equipment and readable storage medium | |
| CN113779559A (en) | Method, apparatus, electronic device, and medium for identifying cheating websites | |
| CN113343133A (en) | Display page generation method, related device and computer program product | |
| US20230289227A1 (en) | Multi-Computer System for Forecasting Data Surges | |
| US11874881B2 (en) | Business documents presentation device, business documents presentation method and business documents presentation program | |
| US10891813B2 (en) | Cognitive vetting system for unsolicited residential visitors | |
| US20230162722A1 (en) | Techniques for model training |